{"meta":{"query_hash":"9d470e2ffb3e","filters":{"topic":"Adaptive Dynamic Programming Control"},"cohort_total":117,"direct_labels_cover":0,"predictions_cover":117,"exported":117,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/9d470e2ffb3e","api":"https://metacan.xera.ac/api/v1/cohort?topic=Adaptive+Dynamic+Programming+Control"},"results":[{"id":"W1526607063","doi":"10.1007/978-3-540-72432-2_81","title":"Generalized Reinforcement Learning Fuzzy Control with Vague States","year":2007,"lang":"en","type":"book-chapter","venue":"Advances in soft computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Fuzzy logic; Control theory (sociology); Computer science; Vagueness; Controller (irrigation); Fuzzy control system; Binary number; Control engineering; Artificial intelligence; Control (management); Mathematics; Engineering","score_opus":0.010652102777369513,"score_gpt":0.2566872670682516,"score_spread":0.24603516429088212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526607063","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000030804258,0.0062632635,0.9185673,0.000071850314,0.00036888162,0.0006316408,0.0000013020825,0.00046570261,0.07359926],"genre_scores_gemma":[0.38073775,0.0011841173,0.55983335,0.0017063498,0.0008422778,0.000035083056,0.00011585915,0.00030062097,0.055244572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99640757,0.00006383145,0.00080430385,0.0010644795,0.00073647784,0.0009233381],"domain_scores_gemma":[0.997302,0.0007334698,0.0008929802,0.00066978205,0.00025038823,0.00015136579],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009471794,0.00066760974,0.00087501795,0.00030588973,0.00028160834,0.0001743511,0.0012256429,0.00022598905,0.000015434476],"category_scores_gemma":[0.000060913553,0.00064170914,0.0001479863,0.00014119233,0.0002235124,0.0005496017,0.00042463274,0.0010702133,0.00005096314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058070316,0.000010930293,0.0002742746,0.00004092129,0.00007373597,0.00019811971,0.00045663115,0.4662795,0.0000036942558,0.13073681,0.000010050913,0.40185726],"study_design_scores_gemma":[0.0029709344,0.00040947951,0.000031297175,0.0007773919,0.000035843444,0.000045746718,0.00003308511,0.8239111,0.0000032962128,0.019627592,0.15111665,0.0010376101],"about_ca_topic_score_codex":0.00004597008,"about_ca_topic_score_gemma":0.00013974552,"teacher_disagreement_score":0.40081966,"about_ca_system_score_codex":0.00029298928,"about_ca_system_score_gemma":0.00013950332,"threshold_uncertainty_score":0.9996034},"labels":[],"label_agreement":null},{"id":"W1873139171","doi":"10.1109/ccece.2000.849537","title":"A modified actor-critic reinforcement learning algorithm","year":2002,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Backpropagation; Inverted pendulum; Artificial neural network; Bellman equation; Function (biology); Function approximation; Artificial intelligence; Fuzzy logic; Algorithm; Mathematics; Mathematical optimization; Nonlinear system","score_opus":0.01959364087753272,"score_gpt":0.22708790000562337,"score_spread":0.20749425912809066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1873139171","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016255089,0.000075199794,0.978272,0.00061962934,0.00015055107,0.00015891809,1.442405e-7,0.0005192202,0.020041738],"genre_scores_gemma":[0.8744354,0.0000069141533,0.11279722,0.0003583977,0.000045249206,0.00002641509,0.0000011360743,0.000008618325,0.012320642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873555,0.000048875114,0.00019398674,0.0003226894,0.00029750384,0.0004013836],"domain_scores_gemma":[0.9992914,0.00008126002,0.000050717146,0.00039353975,0.00007167557,0.00011141717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016406651,0.0001376913,0.00013931982,0.00008335372,0.00013611942,0.00016526724,0.0006409397,0.000044928634,0.00012260418],"category_scores_gemma":[0.00006329962,0.00012503604,0.00006793965,0.00022106008,0.000035574754,0.00041000737,0.00021492131,0.00019071464,0.00030291767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011180755,0.000050606337,0.000028560216,0.00000438612,0.000030763124,0.000032894495,0.0005350682,0.004021794,0.00015590177,0.120294236,0.0004906758,0.874354],"study_design_scores_gemma":[0.0003929663,0.00010578674,0.000038433755,0.0000058312744,0.0000036562285,0.000010453824,0.000021030684,0.9926615,0.000048045058,0.0005693585,0.0059792465,0.0001637401],"about_ca_topic_score_codex":0.00003510169,"about_ca_topic_score_gemma":0.0000014062841,"teacher_disagreement_score":0.98863965,"about_ca_system_score_codex":0.00007627976,"about_ca_system_score_gemma":0.000011563739,"threshold_uncertainty_score":0.50988215},"labels":[],"label_agreement":null},{"id":"W2003323955","doi":"10.1109/ijcnn.2007.4370928","title":"Pitch Control of an Aircraft with Aggregated Reinforcement Learning Algorithms","year":2007,"lang":"en","type":"article","venue":"IEEE International Conference on Neural Networks/IEEE ... International Conference on Neural Networks","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Cerebellar model articulation controller; Controller (irrigation); Aerodynamics; Control theory (sociology); Control system; Pitch control; Control engineering; Control (management); Adaptive control; Artificial intelligence; Engineering","score_opus":0.037093143854737345,"score_gpt":0.29929420971262816,"score_spread":0.2622010658578908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003323955","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045853212,0.000038301463,0.9374736,0.00288023,0.0066224025,0.001064992,0.000028117114,0.00056310405,0.005476073],"genre_scores_gemma":[0.99297357,0.000103895145,0.0021741518,0.0019624173,0.001440199,0.00012343528,0.0002013204,0.000096690914,0.0009243154],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919214,0.00043481222,0.0017408418,0.0018484831,0.0025568858,0.0014975505],"domain_scores_gemma":[0.9934531,0.00073911663,0.0016243733,0.0010877313,0.0024609398,0.00063477596],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012276707,0.0011567506,0.0009923468,0.0007525877,0.00036260157,0.0008672376,0.004663384,0.00045388893,0.00025384396],"category_scores_gemma":[0.00012718386,0.0010331136,0.00037970554,0.00072912517,0.0005143328,0.0017076933,0.00027460812,0.0022608005,0.000029367173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002161627,0.000379807,0.0006843339,0.0000072797925,0.00042758146,0.00035575047,0.0001465454,0.81807894,0.00076013926,0.075723164,0.00011164014,0.101163216],"study_design_scores_gemma":[0.0036912083,0.0027781327,0.0008437037,0.0003288839,0.000046990255,0.0001453911,0.00011358072,0.9897355,0.0004163169,0.00066241284,0.00021558852,0.0010222798],"about_ca_topic_score_codex":0.00017758884,"about_ca_topic_score_gemma":0.00021659888,"teacher_disagreement_score":0.94712037,"about_ca_system_score_codex":0.0004505501,"about_ca_system_score_gemma":0.00019689937,"threshold_uncertainty_score":0.9992119},"labels":[],"label_agreement":null},{"id":"W2016840647","doi":"10.1162/neco_a_00277","title":"Adaptive Optimal Control Without Weight Transport","year":2012,"lang":"en","type":"article","venue":"Neural Computation","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Toronto","funders":"Canadian Institutes of Health Research","keywords":"Computer science; Optimal control; Adaptive control; Control (management); Mathematics; Control theory (sociology); Mathematical optimization; Artificial intelligence","score_opus":0.014906962990867497,"score_gpt":0.24952887589965603,"score_spread":0.23462191290878853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016840647","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.074249275,0.00013326664,0.9234692,0.00042159916,0.0006071218,0.00036468412,0.000003486871,0.00037398192,0.00037739222],"genre_scores_gemma":[0.92734617,6.6983995e-7,0.07195076,0.0003940019,0.0002032338,0.000031075295,0.000008875194,0.00001552586,0.000049677248],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998443,0.00013002506,0.00026238212,0.00032248438,0.0003479831,0.0004941119],"domain_scores_gemma":[0.9992124,0.000117895295,0.00014225031,0.00022134227,0.00013141995,0.00017473735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026747206,0.00020321934,0.0002288214,0.00009592845,0.00013210351,0.000052733252,0.00040893702,0.00006635468,0.0000044711264],"category_scores_gemma":[0.0000154542,0.00018763659,0.00010089624,0.00024434464,0.000057716657,0.0012152462,0.000040743234,0.00019576686,0.00006123575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044878616,0.0007086013,0.09208392,0.00003039823,0.0002822217,0.000067826266,0.0050836103,0.10805878,0.0021420843,0.11143458,0.00043225204,0.67922693],"study_design_scores_gemma":[0.0011383308,0.00017037209,0.04832997,0.0000059443505,0.000022479577,0.00003219089,0.000014866166,0.9493071,0.00006466937,0.00034985034,0.0003453405,0.00021890446],"about_ca_topic_score_codex":0.000016449512,"about_ca_topic_score_gemma":0.0000023977718,"teacher_disagreement_score":0.8530969,"about_ca_system_score_codex":0.00007109426,"about_ca_system_score_gemma":0.00003422112,"threshold_uncertainty_score":0.7651598},"labels":[],"label_agreement":null},{"id":"W2023678709","doi":"10.1002/oca.993","title":"2‐DOF nonlinear ℋ<sub>∞</sub> certainty‐equivalent filters (CEFs)","year":2011,"lang":"en","type":"article","venue":"Optimal Control Applications and Methods","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Control theory (sociology); Nonlinear system; Filter (signal processing); Mathematics; Impulse response; Linear filter; Impulse (physics); Class (philosophy); Degrees of freedom (physics and chemistry); Mathematical analysis; Applied mathematics; Computer science; Physics; Classical mechanics","score_opus":0.02331007977431794,"score_gpt":0.30127617060313466,"score_spread":0.27796609082881674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023678709","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016493481,0.0004382813,0.9947145,0.0003702688,0.000086128246,0.0009824974,0.000019622217,0.00023991722,0.0014994597],"genre_scores_gemma":[0.2124523,0.000044029908,0.78620076,0.0003757056,0.00007338054,0.00077097595,0.000005578873,0.0000199334,0.00005733019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979922,0.0002718579,0.00038018698,0.00069299986,0.00017902243,0.0004836937],"domain_scores_gemma":[0.99817634,0.00034023056,0.00018768117,0.00085206254,0.00018357801,0.00026010326],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011075974,0.00026778455,0.0003647936,0.00013384725,0.00025509446,0.000117277465,0.0007976715,0.0001103331,0.0000087360195],"category_scores_gemma":[0.00006420222,0.00024759836,0.0001388725,0.00032093862,0.00017639426,0.00029786874,0.00023538756,0.00022629206,0.000032605458],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048524853,0.00013942241,0.000052574273,0.000010774178,0.00008324031,0.0000037912284,0.00027041478,0.0000790717,0.019229302,0.064103015,0.00002940315,0.9159505],"study_design_scores_gemma":[0.0031077575,0.00049704686,0.002386561,0.000020447747,0.00017407324,0.00006329082,0.00011700792,0.92674816,0.011270766,0.0064278273,0.048331928,0.0008551519],"about_ca_topic_score_codex":0.000027866809,"about_ca_topic_score_gemma":0.000003486552,"teacher_disagreement_score":0.92666906,"about_ca_system_score_codex":0.00004846942,"about_ca_system_score_gemma":0.000068973604,"threshold_uncertainty_score":0.9999976},"labels":[],"label_agreement":null},{"id":"W2032378315","doi":"10.1109/tcyb.2014.2311578","title":"A Clustering-Based Graph Laplacian Framework for Value Function Approximation in Reinforcement Learning","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Cluster analysis; Graph; Laplace operator; Reinforcement; Laplacian matrix; Computer science; Mathematics; Theoretical computer science; Artificial intelligence; Psychology; Mathematical analysis; Social psychology","score_opus":0.012196086102425497,"score_gpt":0.23833626966938337,"score_spread":0.22614018356695786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2032378315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000622586,0.0000064181536,0.99741703,0.000315964,0.0006072083,0.0006190858,0.0000011849351,0.00023739388,0.00017311104],"genre_scores_gemma":[0.81176,0.0000020228422,0.18754533,0.00030298787,0.000031151067,0.00022239353,0.0000035879568,0.000018794268,0.00011370231],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857503,0.0001169003,0.00031929644,0.00038347242,0.0002681226,0.00033719998],"domain_scores_gemma":[0.9989289,0.0004024737,0.00012953923,0.00038373444,0.00008021521,0.00007513063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045883885,0.0001892844,0.00018095653,0.00028542697,0.0001804345,0.00011052705,0.00031100167,0.00014917142,0.000004250354],"category_scores_gemma":[0.0000416848,0.0002070248,0.000102263584,0.00040413445,0.000039863782,0.00017337831,0.0000027053045,0.00037783725,0.000014879518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007460607,0.00007952553,0.000011361663,0.000022239146,0.00001430939,3.3464227e-7,0.00021038775,0.87954086,0.000100297846,0.02200549,0.0000028481143,0.09793777],"study_design_scores_gemma":[0.0010468691,0.00080742396,0.00010721425,0.00007554243,0.000021502681,9.767749e-7,0.00001796893,0.9878755,0.0005674595,0.008573116,0.0006969709,0.00020943083],"about_ca_topic_score_codex":0.000029776213,"about_ca_topic_score_gemma":0.00012106436,"teacher_disagreement_score":0.81113744,"about_ca_system_score_codex":0.00014100707,"about_ca_system_score_gemma":0.000039781906,"threshold_uncertainty_score":0.84422266},"labels":[],"label_agreement":null},{"id":"W2039416092","doi":"10.1002/cjce.5450790127","title":"Bang‐Bang solution of nonlinear time‐optimal control problems using a semi‐exhaustivesearch","year":2001,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bang–bang control; Convergence (economics); Optimal control; Nonlinear system; Mathematics; Control (management); Mathematical optimization; Control theory (sociology); Nonlinear programming; Applied mathematics; Computer science; Economics; Physics","score_opus":0.012513258134855447,"score_gpt":0.2155197025225859,"score_spread":0.20300644438773044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039416092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24522994,0.00039769808,0.75332385,0.0007200669,0.00011050788,0.00015879658,0.000004725464,0.000020490415,0.000033934546],"genre_scores_gemma":[0.9750153,0.0000010070111,0.02473997,0.000032130614,0.00017365043,0.0000019126423,6.1380865e-7,0.000015841519,0.000019607212],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986526,0.000034387784,0.00038116385,0.00013002011,0.0003131658,0.0004887053],"domain_scores_gemma":[0.99876875,0.00014708417,0.00018248214,0.00022511306,0.00030853192,0.00036803947],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007344142,0.00014065855,0.00027458902,0.00020801646,0.00007089668,0.00007480699,0.00084401376,0.00007931422,0.000009017777],"category_scores_gemma":[0.00026370987,0.00011465342,0.00012745423,0.00039467207,0.00010792966,0.00026680567,0.00004361757,0.00045693756,0.0000031554284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003661502,0.00003166404,0.00029836636,0.000038189402,0.00021605793,0.00015489315,0.0007146815,0.3870845,0.60451734,0.0010331037,0.000059179212,0.0058154156],"study_design_scores_gemma":[0.00053987605,0.0000550734,0.000056650835,0.00011193038,0.000024341258,0.00035348933,0.0000040764317,0.9939484,0.0044355,0.00005085951,0.00030314844,0.00011665368],"about_ca_topic_score_codex":0.00069492235,"about_ca_topic_score_gemma":0.000036910806,"teacher_disagreement_score":0.7297853,"about_ca_system_score_codex":0.0003559046,"about_ca_system_score_gemma":0.00059750554,"threshold_uncertainty_score":0.4675431},"labels":[],"label_agreement":null},{"id":"W2066268309","doi":"10.2316/journal.206.2011.1.206-3412","title":"DISCRETE-TIME OPTIMAL CONTROL OF NONHOLONOMIC MOBILE ROBOT FORMATIONS USING LINEARLY PARAMETERIZED NEURAL NETWORKS","year":2011,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Control theory (sociology); Artificial neural network; Parameterized complexity; Controller (irrigation); Computer science; Optimal control; Discrete time and continuous time; Mobile robot; Lyapunov stability; Nonlinear system; Nonholonomic system; Kinematics; Lyapunov function; Dynamic programming; Stability (learning theory); Robot; Mathematics; Mathematical optimization; Control (management); Artificial intelligence; Algorithm","score_opus":0.015170453927309292,"score_gpt":0.25193749398421583,"score_spread":0.23676704005690655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066268309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14310566,0.00007963707,0.85616636,0.00008811694,0.00041294622,0.00011657813,0.00000465964,0.000018641911,0.0000074164886],"genre_scores_gemma":[0.74157584,0.00000957829,0.2583068,0.000031164764,0.00006380944,0.0000019842485,0.0000027457463,0.0000053499407,0.0000027372644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988653,0.00006052367,0.00059747003,0.000101772755,0.00024593217,0.00012899245],"domain_scores_gemma":[0.99847436,0.00010276315,0.0008228576,0.000113716145,0.0004247676,0.00006155556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031570482,0.000106355896,0.00022614088,0.00018514284,0.000045766727,0.00012053809,0.0004967137,0.00005113507,0.000005429902],"category_scores_gemma":[0.000038673268,0.000094354844,0.000100927486,0.00007197717,0.00006009338,0.00095635984,0.00006750112,0.00012449406,0.0000011106653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000699835,0.00009394934,0.00047741362,0.000003076132,0.00015905517,0.000010530822,0.0005620754,0.97103775,0.0014329888,0.0018128195,0.0000024906558,0.024337871],"study_design_scores_gemma":[0.0010518365,0.0002951854,0.0025986189,0.00003069416,0.000031617175,0.00011351714,0.000020494117,0.9954609,0.00007664567,0.00022700471,0.0000083690065,0.00008507249],"about_ca_topic_score_codex":0.000010699203,"about_ca_topic_score_gemma":4.499597e-7,"teacher_disagreement_score":0.5984702,"about_ca_system_score_codex":0.000053414995,"about_ca_system_score_gemma":0.00004276177,"threshold_uncertainty_score":0.3847679},"labels":[],"label_agreement":null},{"id":"W2083748997","doi":"10.1007/s11768-011-0170-8","title":"Asymptotic tracking by a reinforcement learning-based adaptive critic controller","year":2011,"lang":"en","type":"article","venue":"Journal of Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Control theory (sociology); Controller (irrigation); Reinforcement learning; Artificial neural network; Tracking error; Computer science; Feed forward; Bounded function; Adaptive control; Nonlinear system; Lyapunov function; Lyapunov stability; Mathematics; Artificial intelligence; Control engineering; Engineering; Control (management)","score_opus":0.01146694965448446,"score_gpt":0.2295948023311984,"score_spread":0.21812785267671392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2083748997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00045087744,0.00085839373,0.99705577,0.00029003774,0.000038338287,0.0004277687,0.0000019647275,0.000044217966,0.0008326611],"genre_scores_gemma":[0.9949584,0.000011306021,0.0040690065,0.0006401126,0.00006920567,0.00010072408,5.595607e-7,0.000010895379,0.00013980702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984888,0.00033957133,0.0004946895,0.00019560747,0.00022827138,0.00025305993],"domain_scores_gemma":[0.9978818,0.0008721536,0.00051198434,0.000203934,0.0003658444,0.0001642803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015683031,0.00016169062,0.00033117938,0.00012225048,0.00021851934,0.00008629113,0.0005196423,0.00005931792,0.000015220074],"category_scores_gemma":[0.00017555163,0.00013436649,0.0001408559,0.00014896262,0.00014614897,0.00037642237,0.000030368024,0.0003203056,0.000007416056],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071907707,0.0002303964,0.00013741685,0.000009042871,0.00024350446,0.000009064615,0.00054843124,0.0027159776,0.001108054,0.93143845,0.000052998443,0.06278762],"study_design_scores_gemma":[0.02129278,0.003657979,0.00169918,0.00018422764,0.00069647125,0.00021489261,0.00070393813,0.62696576,0.0010375476,0.32032055,0.022245461,0.0009812412],"about_ca_topic_score_codex":0.0000023185976,"about_ca_topic_score_gemma":3.7385206e-7,"teacher_disagreement_score":0.9945075,"about_ca_system_score_codex":0.000044547654,"about_ca_system_score_gemma":0.00008662419,"threshold_uncertainty_score":0.54793066},"labels":[],"label_agreement":null},{"id":"W2110469502","doi":"10.1016/j.automatica.2013.03.004","title":"Pareto optimality in infinite horizon linear quadratic differential games","year":2013,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Mathematics; Pareto principle; Mathematical optimization; Optimal control; Transversality; Quadratic equation; Scalar (mathematics); Minification; Pareto optimal; Applied mathematics; Multi-objective optimization","score_opus":0.009988373953563707,"score_gpt":0.2409104974390513,"score_spread":0.2309221234854876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110469502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37869385,0.00003409657,0.61845094,0.0010422675,0.00017163162,0.00047751528,0.0000011835839,0.00041658588,0.000711949],"genre_scores_gemma":[0.9071442,0.0000023162645,0.09246229,0.00011301812,0.000038663657,0.00014641184,0.0000031942368,0.000011336523,0.00007858854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982748,0.00016343266,0.00043190576,0.00037724382,0.0003034566,0.00044913468],"domain_scores_gemma":[0.9987228,0.00026293474,0.000119927136,0.0007023371,0.0000736748,0.00011835957],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021519928,0.00019656087,0.00030590358,0.00012655476,0.00005919811,0.00022531245,0.0008327547,0.000082629136,0.00006485546],"category_scores_gemma":[0.00021140436,0.00017136006,0.000074042226,0.0003393056,0.000082005026,0.0005853847,0.0002850438,0.0001966507,0.0005220434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016784861,0.0009584652,0.012830916,0.0001930606,0.00016574321,0.000089941896,0.0043411115,0.00052835676,0.0021014458,0.18775196,0.00088311924,0.7901391],"study_design_scores_gemma":[0.0004141154,0.00014171304,0.056410104,0.000036430927,0.0000061673795,0.000002817615,0.000027347782,0.9356006,0.000052552205,0.0069679054,0.00013555936,0.0002047098],"about_ca_topic_score_codex":0.00019626897,"about_ca_topic_score_gemma":0.00003001162,"teacher_disagreement_score":0.93507224,"about_ca_system_score_codex":0.0000659126,"about_ca_system_score_gemma":0.0000652949,"threshold_uncertainty_score":0.6987861},"labels":[],"label_agreement":null},{"id":"W2180467047","doi":"10.1007/s10462-015-9447-5","title":"Exponential moving average based multiagent reinforcement learning algorithms","year":2015,"lang":"en","type":"article","venue":"Artificial Intelligence Review","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Nash equilibrium; Computer science; Reinforcement learning; Algorithm; Convergence (economics); Q-learning; Weighted Majority Algorithm; Mathematical optimization; Artificial intelligence; Mathematics; Wake-sleep algorithm; Unsupervised learning; Generalization error","score_opus":0.0888835926429212,"score_gpt":0.3256896554819136,"score_spread":0.2368060628389924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2180467047","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006333844,0.010151593,0.98661745,0.0011724874,0.00056282524,0.00073059596,4.4829943e-7,0.00029023577,0.00041103593],"genre_scores_gemma":[0.8897086,0.0027875572,0.10452237,0.0021546858,0.0002536546,0.00022915327,0.000019720732,0.000038608883,0.000285653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702716,0.000306409,0.00081048126,0.00060171384,0.0006847344,0.00056947925],"domain_scores_gemma":[0.9982266,0.00014980121,0.00029647964,0.00069485,0.00031470475,0.00031755897],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018855579,0.000280401,0.0004180069,0.000107677566,0.0001805709,0.0002012646,0.0010805742,0.0000628207,0.00007196194],"category_scores_gemma":[0.0008410765,0.00026102283,0.0002074195,0.0005713238,0.00007722726,0.0004870576,0.00033694095,0.000321671,0.000792449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066571174,0.00006758144,0.000011049735,0.00012741357,0.000019731398,0.000044918328,0.00025036655,0.028605856,0.00011481164,0.019132188,0.00008666343,0.9515328],"study_design_scores_gemma":[0.00005453851,0.00016747124,0.0000029254984,0.00071240327,0.00002405546,0.00000800097,0.00004233008,0.9756024,0.0017709567,0.0012911636,0.020004546,0.0003192128],"about_ca_topic_score_codex":0.000102224265,"about_ca_topic_score_gemma":0.0000095474625,"teacher_disagreement_score":0.95121354,"about_ca_system_score_codex":0.00020465303,"about_ca_system_score_gemma":0.00022207198,"threshold_uncertainty_score":0.9999856},"labels":[],"label_agreement":null},{"id":"W2199527024","doi":"10.1016/j.ifacol.2015.11.170","title":"On the Relation between the Hybrid Minimum Principle and Hybrid Dynamic Programming: a Linear Quadratic Example","year":2015,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dynamic programming; Hybrid system; Bellman equation; Mathematical optimization; Optimal control; Mathematics; Hamiltonian (control theory); Maximum principle; Quadratic equation; Control theory (sociology); Key (lock); Function (biology); Process (computing); Quadratic programming; Computer science; Control (management)","score_opus":0.03561845750667487,"score_gpt":0.2763211445067575,"score_spread":0.24070268700008263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2199527024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5717051,0.000352284,0.41245905,0.013341161,0.00025053316,0.0013570267,0.00002413258,0.00034258617,0.0001681109],"genre_scores_gemma":[0.84805375,0.0000068125632,0.15064901,0.00056486554,0.00017128141,0.00009980967,0.00004508516,0.000032894615,0.00037650834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740297,0.00031226187,0.00041848555,0.0006721623,0.0006362314,0.0005579214],"domain_scores_gemma":[0.99716794,0.0011065394,0.00026194094,0.001083099,0.00016212693,0.00021832752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014094325,0.00033884798,0.00031623416,0.00008561562,0.00039007646,0.00027513903,0.0011515697,0.00006310197,0.000003579311],"category_scores_gemma":[0.0007363024,0.00020163697,0.00010709932,0.00034108057,0.00025794187,0.0003281816,0.00037515943,0.0004896688,0.000072392395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002869436,0.00096111797,0.010154019,0.00009919753,0.00075428584,0.0002515993,0.011527027,0.0018161318,0.00088392704,0.115787424,0.00017005202,0.85730827],"study_design_scores_gemma":[0.0012437964,0.0007182077,0.006143203,0.000055877736,0.000072200564,0.00005527949,0.00024155213,0.9766934,0.00007527716,0.0054036863,0.00884328,0.0004542543],"about_ca_topic_score_codex":0.000098484656,"about_ca_topic_score_gemma":0.00005444892,"teacher_disagreement_score":0.97487724,"about_ca_system_score_codex":0.00014848402,"about_ca_system_score_gemma":0.0001698974,"threshold_uncertainty_score":0.8222517},"labels":[],"label_agreement":null},{"id":"W2463409156","doi":"10.1016/j.automatica.2018.05.005","title":"Inversion-based output tracking and unknown input reconstruction of square discrete-time linear systems","year":2018,"lang":"en","type":"preprint","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Minimum phase; Control theory (sociology); Inversion (geology); Unit circle; Tracking (education); Observer (physics); Computer science; Filter (signal processing); Mathematics; Phase (matter); Upper and lower bounds; Algorithm; Control (management); Artificial intelligence","score_opus":0.015063547042502439,"score_gpt":0.24443402173483275,"score_spread":0.22937047469233032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2463409156","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08141214,0.00024187673,0.914629,0.0004701374,0.0012100858,0.000981426,0.00003188888,0.0006480352,0.00037541034],"genre_scores_gemma":[0.88433903,0.0000037822736,0.11532154,0.000037001613,0.00012594841,0.00004546276,0.000021045083,0.000026232947,0.000079951584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975769,0.00026301647,0.0006835647,0.00071488647,0.00043795232,0.00032366416],"domain_scores_gemma":[0.9973337,0.00036674115,0.000739857,0.001081625,0.00034538997,0.00013267044],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006244447,0.00034517646,0.00067010697,0.00027366643,0.00011915975,0.00022412848,0.0009144689,0.00034257385,0.000006884989],"category_scores_gemma":[0.00030116245,0.00032149025,0.00014944322,0.00020921616,0.0003258104,0.0002475755,0.0008237511,0.00036982368,0.00003908158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001302551,0.0005560258,0.005919822,0.010155876,0.001851475,0.00009918082,0.006557835,0.019398574,0.0014328804,0.028156707,0.0016038152,0.92413753],"study_design_scores_gemma":[0.00039088418,0.00013463637,0.00045657172,0.0013826722,0.000063172,0.000016114001,0.000023497016,0.9955985,0.000117507574,0.001290383,0.00021336884,0.00031268032],"about_ca_topic_score_codex":0.000082626015,"about_ca_topic_score_gemma":0.0000031301213,"teacher_disagreement_score":0.9761999,"about_ca_system_score_codex":0.00013278748,"about_ca_system_score_gemma":0.00030425223,"threshold_uncertainty_score":0.9999237},"labels":[],"label_agreement":null},{"id":"W2529970964","doi":"10.1109/tac.2016.2616644","title":"Stability Analysis of Discrete-Time Infinite-Horizon Optimal Control With Discounted Cost","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Australian Research Council; Agence Universitaire de la Francophonie; Agence Nationale de la Recherche","keywords":"Controllability; Robustness (evolution); Discounting; Control theory (sociology); Stability (learning theory); Mathematics; Lyapunov function; Mathematical optimization; Discrete time and continuous time; Optimal control; Sequence (biology); Bellman equation; Nonlinear system; Computer science; Applied mathematics; Control (management); Economics","score_opus":0.008061752130508127,"score_gpt":0.23248288229923736,"score_spread":0.22442113016872922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2529970964","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041783694,0.000012686577,0.9545543,0.0011312524,0.00013926283,0.0013764654,0.00042519736,0.00050361693,0.0000734916],"genre_scores_gemma":[0.9912183,0.000001869534,0.008146562,0.00010505939,0.00001374132,0.00037976928,0.0000029820178,0.00002897641,0.00010270623],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657696,0.00040195408,0.00086089614,0.00075618585,0.0007824229,0.0006215675],"domain_scores_gemma":[0.995425,0.0020665808,0.0004625143,0.0014617515,0.00034688783,0.00023730741],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007264479,0.00044400897,0.001145964,0.000601619,0.00018279847,0.00011317833,0.00093412754,0.00012778585,0.00026082096],"category_scores_gemma":[0.000064142536,0.000281864,0.0004973133,0.0015449646,0.00038069303,0.0006906688,0.0000046253285,0.00018101525,0.00006083838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022159931,0.0026119193,0.0012722651,0.0000969093,0.01804241,0.00005742908,0.0012679525,0.08772583,0.045460604,0.0035651203,0.000026181491,0.8376574],"study_design_scores_gemma":[0.0070581567,0.0010784093,0.0021444226,0.000083719264,0.001820734,0.000004994794,0.000030852658,0.9861073,0.0011920329,0.000051345214,0.00003242839,0.00039560278],"about_ca_topic_score_codex":0.00006619543,"about_ca_topic_score_gemma":0.00014802994,"teacher_disagreement_score":0.94943464,"about_ca_system_score_codex":0.00026728518,"about_ca_system_score_gemma":0.00021157962,"threshold_uncertainty_score":0.99996334},"labels":[],"label_agreement":null},{"id":"W2588293788","doi":"10.1007/s40815-016-0284-8","title":"A Residual Gradient Fuzzy Reinforcement Learning Algorithm for Differential Games","year":2017,"lang":"en","type":"article","venue":"International Journal of Fuzzy Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Algorithm; Residual; Computer science; Weighted Majority Algorithm; Convergence (economics); Fuzzy logic; Artificial intelligence; Mathematics; Mathematical optimization; Wake-sleep algorithm; Artificial neural network; Generalization error","score_opus":0.018618079922298057,"score_gpt":0.2851494187181415,"score_spread":0.2665313387958434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588293788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005271317,0.0002130235,0.984767,0.0011027253,0.007536478,0.00028166713,0.0000075764974,0.00003380097,0.0007863859],"genre_scores_gemma":[0.98064864,0.000020654534,0.016367057,0.000031185435,0.0017900084,0.000027688648,0.0000048068136,0.000013925502,0.0010960354],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997686,0.00008414678,0.00071259047,0.00023297087,0.0009955635,0.00028868904],"domain_scores_gemma":[0.99658626,0.00015587434,0.0016098834,0.00036548523,0.0011495339,0.00013297528],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007938656,0.00017336025,0.00031957444,0.0002384487,0.00028266318,0.00119688,0.002704629,0.00006314085,0.0000021237497],"category_scores_gemma":[0.00034737267,0.00014561308,0.00023678184,0.00002946741,0.000068795554,0.00080604525,0.00032427182,0.00024698768,0.0000073125743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028282232,0.000268897,0.0021381336,0.000045865057,0.002197987,0.0004676587,0.0018016497,0.009310816,0.0014739352,0.16318457,0.0031322346,0.8156954],"study_design_scores_gemma":[0.005935461,0.0012496457,0.0045632715,0.00056456815,0.000074532436,0.00083423674,0.0002731917,0.9499681,0.00025907677,0.0042438167,0.03154238,0.0004917098],"about_ca_topic_score_codex":0.00007767003,"about_ca_topic_score_gemma":0.00000418198,"teacher_disagreement_score":0.9753773,"about_ca_system_score_codex":0.00024283244,"about_ca_system_score_gemma":0.00012972868,"threshold_uncertainty_score":0.99983996},"labels":[],"label_agreement":null},{"id":"W2604485348","doi":"10.1155/2017/4575926","title":"Online Adaptive Optimal Control of Vehicle Active Suspension Systems Using Single‐Network Approximate Dynamic Programming","year":2017,"lang":"en","type":"article","venue":"Mathematical Problems in Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Zhejiang University of Technology; Zhejiang University; National Natural Science Foundation of China","keywords":"Control theory (sociology); Sprung mass; Dynamic programming; Active suspension; Optimal control; Lyapunov function; Suspension (topology); Linear-quadratic regulator; Adaptive control; Controller (irrigation); Hamilton–Jacobi–Bellman equation; Parametric statistics; Computer science; Engineering; Mathematics; Mathematical optimization; Control engineering; Control (management); Nonlinear system; Actuator","score_opus":0.022306285279354316,"score_gpt":0.2466972457208165,"score_spread":0.22439096044146217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604485348","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.036321722,0.00018769398,0.9617837,0.000043054704,0.00022227761,0.0011849708,0.00000796023,0.0002021933,0.000046396322],"genre_scores_gemma":[0.7667185,0.0000014906876,0.23313153,0.0000032643534,0.00003993397,0.00005915858,0.0000020794034,0.000038237788,0.000005803321],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740344,0.00007112353,0.0007636352,0.00053061557,0.00042964824,0.0008015621],"domain_scores_gemma":[0.9979028,0.00032906974,0.00052335265,0.00095842883,0.00015513985,0.00013117536],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00081247697,0.0003573595,0.00075942586,0.00015565094,0.00016912993,0.0002615683,0.0011874419,0.00016072334,0.0000011046895],"category_scores_gemma":[0.00039606306,0.00033942307,0.00012392424,0.0002310402,0.00014162829,0.00070985407,0.00048099193,0.00041780467,0.0000024601975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002136464,0.00039194693,0.00008151675,0.00040312237,0.00008501216,0.000032093907,0.0003852491,0.94897056,0.0070239115,0.035162304,3.1725216e-7,0.00744258],"study_design_scores_gemma":[0.0010284985,0.00016602484,0.00017595461,0.0012700991,0.000027853062,0.000030427194,0.00006003203,0.9949433,0.00011994855,0.0018408604,0.000008171196,0.000328817],"about_ca_topic_score_codex":0.000047300964,"about_ca_topic_score_gemma":0.000009932401,"teacher_disagreement_score":0.7303968,"about_ca_system_score_codex":0.0002952849,"about_ca_system_score_gemma":0.000044672106,"threshold_uncertainty_score":0.99990577},"labels":[],"label_agreement":null},{"id":"W2708409974","doi":"10.1016/j.neunet.2017.05.013","title":"Adaptive near-optimal neuro controller for continuous-time nonaffine nonlinear systems with constrained input","year":2017,"lang":"en","type":"article","venue":"Neural Networks","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; Concordia University","funders":"","keywords":"Control theory (sociology); Nonlinear system; Computer science; Controller (irrigation); Artificial intelligence; Control (management); Physics","score_opus":0.01076070531881443,"score_gpt":0.22836813267640643,"score_spread":0.217607427357592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2708409974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008118566,0.00018126075,0.98632497,0.0014953129,0.00084562035,0.0021730845,0.000037564445,0.00042098312,0.0004026469],"genre_scores_gemma":[0.9490756,0.0000024220824,0.048623867,0.00060113403,0.0006933521,0.00024095361,0.00001583301,0.000059612645,0.00068722724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971046,0.00013373775,0.000477908,0.00091719406,0.00037724097,0.0009893627],"domain_scores_gemma":[0.9965848,0.00080633466,0.0006737105,0.0011855437,0.00047835236,0.00027129182],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00043122706,0.00049108395,0.00082481233,0.000057929094,0.0009654347,0.0014934613,0.0019798763,0.00019570312,0.0000040162518],"category_scores_gemma":[0.00023115116,0.00039412914,0.00020815548,0.000118844546,0.00057747634,0.0007647434,0.0003700767,0.00046417877,0.000018845607],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00374033,0.0004066573,0.0017485126,0.000040383307,0.000767753,0.0005702626,0.00026072052,0.67294556,0.00031628163,0.017321229,0.0033081472,0.29857415],"study_design_scores_gemma":[0.0052437275,0.0013535626,0.0005617791,0.00004740639,0.000053085,0.00010024056,0.000010902823,0.98898613,0.0000037512111,0.000024326671,0.0031671827,0.00044789872],"about_ca_topic_score_codex":0.000074775475,"about_ca_topic_score_gemma":0.000019318628,"teacher_disagreement_score":0.940957,"about_ca_system_score_codex":0.000052019033,"about_ca_system_score_gemma":0.00011375508,"threshold_uncertainty_score":0.99985105},"labels":[],"label_agreement":null},{"id":"W2737014169","doi":"10.1016/j.neucom.2017.07.027","title":"Adaptive critics based cooperative control scheme for islanded Microgrids","year":2017,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Deanship of Scientific Research, King Faisal University; King Fahd University of Petroleum and Minerals","keywords":"Computer science; Scheme (mathematics); Synchronization (alternating current); Graph; Adaptive control; Control (management); Function (biology); Distributed generation; Distributed computing; Mathematical optimization; Artificial intelligence; Theoretical computer science; Mathematics; Engineering; Telecommunications","score_opus":0.025456849660838873,"score_gpt":0.28568807393149687,"score_spread":0.260231224270658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737014169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004942614,0.000040155206,0.9907284,0.0019158463,0.00057205383,0.0010150607,0.000018233986,0.0003092341,0.00045843635],"genre_scores_gemma":[0.7727164,3.1779737e-7,0.22550493,0.0014016536,0.00022930976,0.000065957465,0.0000024611675,0.00002508646,0.000053900967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787664,0.00011739976,0.000340357,0.00074733846,0.00024959559,0.0006686386],"domain_scores_gemma":[0.9971902,0.0007781309,0.00033819836,0.0010328606,0.00052135787,0.00013929783],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00047303422,0.00029858557,0.00038332766,0.00008346829,0.0013712432,0.0008673478,0.0019288398,0.00009193087,0.0000014771339],"category_scores_gemma":[0.0007342118,0.000295581,0.00017740138,0.00008716803,0.00017619481,0.0004575353,0.0003351473,0.00028496824,0.00001418047],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006921131,0.001138868,0.009005235,0.00018642309,0.0005501998,0.0004088597,0.0017275468,0.011189812,0.04564162,0.29273897,0.0028534126,0.6338669],"study_design_scores_gemma":[0.0035911542,0.0003740347,0.0017844099,0.000041659307,0.000017522709,0.000009899396,0.000014922446,0.99023867,0.0009988957,0.00059292413,0.002022453,0.00031344732],"about_ca_topic_score_codex":0.000016657865,"about_ca_topic_score_gemma":0.000008226716,"teacher_disagreement_score":0.97904885,"about_ca_system_score_codex":0.00005902752,"about_ca_system_score_gemma":0.00017609406,"threshold_uncertainty_score":0.99994963},"labels":[],"label_agreement":null},{"id":"W2770533010","doi":"10.1504/ijdsss.2017.10008987","title":"Policy iteration and coupled Riccati solutions for dynamic graphical games","year":2017,"lang":"en","type":"article","venue":"International Journal of Digital Signals and Smart Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Computer science; Nash equilibrium; Graph; Convergence (economics); Reinforcement learning; Mathematical optimization; Mathematics; Theoretical computer science; Artificial intelligence","score_opus":0.01823689569409537,"score_gpt":0.29038850178871645,"score_spread":0.2721516060946211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770533010","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.049540885,0.0005404291,0.94280666,0.006011793,0.00072969723,0.00018792065,0.000035830162,0.000014286003,0.00013248391],"genre_scores_gemma":[0.9985179,0.000049826296,0.0010149492,0.00004342644,0.00024118125,0.000010768986,0.0000040062337,0.0000059353515,0.0001120508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989647,0.00002123799,0.00038263696,0.0001534621,0.0003110657,0.00016687314],"domain_scores_gemma":[0.99845153,0.00017275533,0.0005364639,0.00014703418,0.0005924737,0.0000997377],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004021776,0.000104354236,0.00019767457,0.00019083158,0.00024855105,0.002482251,0.0006101739,0.000044614102,2.559403e-7],"category_scores_gemma":[0.0003341471,0.00008498373,0.00008897758,0.000033990746,0.00010392655,0.0015574496,0.00016882345,0.000073752475,6.897074e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016215588,0.00021406052,0.013106301,0.000050461233,0.0008325165,0.00006731033,0.0005300673,0.00035235143,0.0030093584,0.8616264,0.0002684103,0.11978059],"study_design_scores_gemma":[0.0021111874,0.00046035904,0.020763969,0.00022072275,0.000025216186,0.00078616163,0.000089825786,0.9271121,0.00001126056,0.04565728,0.002504897,0.00025699593],"about_ca_topic_score_codex":0.00002971185,"about_ca_topic_score_gemma":0.000007547198,"teacher_disagreement_score":0.948977,"about_ca_system_score_codex":0.000054749835,"about_ca_system_score_gemma":0.00009210728,"threshold_uncertainty_score":0.9985533},"labels":[],"label_agreement":null},{"id":"W2783810978","doi":"10.1109/iris.2017.8250107","title":"Multi-agent reinforcement learning approach based on reduced value function approximations","year":2017,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Bellman equation; Convergence (economics); Computer science; Mathematical optimization; Graph; Function approximation; Artificial neural network; Function (biology); Markov decision process; Artificial intelligence; Mathematics; Theoretical computer science; Markov process","score_opus":0.033509293003429586,"score_gpt":0.2669293575365366,"score_spread":0.23342006453310704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783810978","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047948456,0.0000037733093,0.9793389,0.00073685235,0.0002895971,0.0004961696,2.1071935e-7,0.0003599287,0.01829507],"genre_scores_gemma":[0.69380254,3.2780886e-7,0.30306277,0.0002696084,0.000032746695,0.00010089873,0.000008373823,0.000008812286,0.0027139212],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851954,0.00008049042,0.00022932253,0.00048204584,0.00037471077,0.0003138939],"domain_scores_gemma":[0.998246,0.00004522785,0.00024365199,0.001233906,0.00012925953,0.00010196737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005469957,0.00017292923,0.00014765038,0.000110778165,0.00096908584,0.0005005496,0.0009796222,0.000062544816,0.000010486715],"category_scores_gemma":[0.0003110458,0.00015103708,0.00009523543,0.00008579067,0.000055822657,0.0004828775,0.00022200325,0.00022669467,0.0000845626],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003427613,0.00032245406,0.00018933127,0.000018446899,0.00005141721,0.0000031693114,0.0003116681,0.7554111,0.0017295944,0.15836696,0.00017911539,0.08338247],"study_design_scores_gemma":[0.00094708096,0.00018656609,0.0026670424,0.000012114172,0.0000107095075,9.563381e-7,0.00003365351,0.99471045,0.00013849279,0.00009870841,0.0010149104,0.00017934653],"about_ca_topic_score_codex":0.000055839726,"about_ca_topic_score_gemma":0.0000015131892,"teacher_disagreement_score":0.6933231,"about_ca_system_score_codex":0.00013153268,"about_ca_system_score_gemma":0.00007333457,"threshold_uncertainty_score":0.74535227},"labels":[],"label_agreement":null},{"id":"W2792955766","doi":"10.1109/intellisys.2017.8324243","title":"A comparative study of the optimal control design using evolutionary algorithms: Application on a close-loop system","year":2017,"lang":"en","type":"article","venue":"2017 Intelligent Systems Conference (IntelliSys)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Control theory (sociology); PID controller; Controller (irrigation); Linkage (software); Computer science; Evolutionary algorithm; Full state feedback; Stability (learning theory); Linear system; Optimal control; Control system; Open-loop controller; State (computer science); Control engineering; Algorithm; Control (management); Closed loop; Mathematics; Engineering; Mathematical optimization; Artificial intelligence; Temperature control","score_opus":0.10519427667976203,"score_gpt":0.32579997793991383,"score_spread":0.2206057012601518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792955766","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033019118,0.0002366893,0.9587336,0.00007556987,0.0015558093,0.0055866744,0.00003105303,0.00017873461,0.000582703],"genre_scores_gemma":[0.9947525,0.000005516359,0.004228168,0.0000151120585,0.00016278897,0.0005458934,0.0000021577991,0.000028668073,0.00025914825],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99467415,0.0012263096,0.0011797555,0.0011397363,0.0011453462,0.00063468504],"domain_scores_gemma":[0.9921571,0.00052325526,0.0021171991,0.0037806556,0.0012318019,0.000189994],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015988267,0.00057618413,0.001087458,0.00021289151,0.0011948079,0.0007484054,0.0052657616,0.00020083837,0.0000032039086],"category_scores_gemma":[0.0002249555,0.00043139604,0.00024602545,0.00022283458,0.00043310196,0.0006542196,0.00059272145,0.0004805765,0.00012681751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001301028,0.005445157,0.007564276,0.00067565776,0.0031509802,0.0001413398,0.026298255,0.3455139,0.0069390284,0.5717441,0.00080517266,0.030421112],"study_design_scores_gemma":[0.00090092054,0.0006788958,0.00087168545,0.00058684824,0.00010785349,0.0000646835,0.004877682,0.99047244,0.000729375,0.00011879325,0.00017012982,0.0004207262],"about_ca_topic_score_codex":0.0017490976,"about_ca_topic_score_gemma":0.000044990156,"teacher_disagreement_score":0.9617334,"about_ca_system_score_codex":0.00059310254,"about_ca_system_score_gemma":0.00040058276,"threshold_uncertainty_score":0.9998138},"labels":[],"label_agreement":null},{"id":"W2803623613","doi":"10.1109/tnnls.2018.2832025","title":"Optimal Synchronization Control of Multiagent Systems With Input Saturation via Off-Policy Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":164,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Australian Research Council; Higher Education Discipline Innovation Project; Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Hamilton–Jacobi–Bellman equation; Reinforcement learning; Optimal control; Computer science; Synchronization (alternating current); Controller (irrigation); Control theory (sociology); Mathematical optimization; Artificial neural network; Bellman equation; Control (management); Mathematics; Artificial intelligence","score_opus":0.0066463272838310685,"score_gpt":0.2161807311212928,"score_spread":0.20953440383746172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2803623613","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010906923,0.0003521061,0.9868983,0.00007878843,0.00073921744,0.000765677,8.1804865e-7,0.0002292851,0.000028883276],"genre_scores_gemma":[0.9985393,0.000033567365,0.00058407313,0.000032175765,0.00032340447,0.00008598298,0.000004370433,0.000028759241,0.00036834177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977472,0.000520083,0.0005009798,0.00045003725,0.00038117613,0.00040057025],"domain_scores_gemma":[0.9986014,0.00022621364,0.000448077,0.0002830006,0.00031712704,0.00012418952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048207788,0.00027370837,0.00037715427,0.00022302794,0.00061221904,0.00026467352,0.00023781367,0.00013226648,0.0000018414289],"category_scores_gemma":[0.000016903376,0.00022869269,0.00006568386,0.00048715374,0.00014210885,0.00041119676,0.0000051454203,0.00058162434,0.000003527122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011232662,0.000028004677,0.00011281226,0.00003825957,0.000091101596,0.0000039397887,0.00044112836,0.94548607,0.0001592682,0.00024225796,0.000002728733,0.05328212],"study_design_scores_gemma":[0.0011770504,0.0017832561,0.00008631256,0.00017757645,0.00004179279,0.000065556764,0.00012620197,0.99598753,0.000024711371,3.1321605e-7,0.00030142037,0.00022829155],"about_ca_topic_score_codex":0.0004132715,"about_ca_topic_score_gemma":0.000015171557,"teacher_disagreement_score":0.9876324,"about_ca_system_score_codex":0.00012837138,"about_ca_system_score_gemma":0.00005190011,"threshold_uncertainty_score":0.9325817},"labels":[],"label_agreement":null},{"id":"W2805646502","doi":"10.1109/syscon.2018.8369536","title":"Applying expectation-maximization evaluation on approximate optimal control","year":2018,"lang":"en","type":"article","venue":"2018 Annual IEEE International Systems Conference (SysCon)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Maximization; Iterative learning control; Reinforcement learning; Computer science; Frame (networking); Optimal control; Trajectory; Convergence (economics); Tracking (education); Task (project management); Generator (circuit theory); Artificial intelligence; Mathematical optimization; Expectation–maximization algorithm; Control theory (sociology); Control (management); Mathematics; Power (physics); Engineering; Maximum likelihood","score_opus":0.035015107107010036,"score_gpt":0.3010516916635031,"score_spread":0.26603658455649304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2805646502","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010407767,0.00003366758,0.9747244,0.0006225366,0.0058341664,0.002008953,0.00008081498,0.00034654778,0.0059411298],"genre_scores_gemma":[0.99179745,0.0000032081139,0.0045607435,0.00032406911,0.0011083108,0.0013978606,0.000059112914,0.000029078043,0.00072016777],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960243,0.00037078204,0.00072241924,0.00089570106,0.0014966927,0.00049009116],"domain_scores_gemma":[0.99535334,0.0002480582,0.0006088276,0.000641028,0.00298769,0.00016105425],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012183113,0.00037022316,0.00037427645,0.0003616183,0.00028775554,0.00073032035,0.0015144781,0.0001696041,0.000085635744],"category_scores_gemma":[0.00034734266,0.00035891222,0.00010987633,0.00029701626,0.00018667299,0.0016537565,0.00010584474,0.00021530766,0.0005853369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075790996,0.0009189468,0.002422573,0.00009186354,0.0012697051,0.00005122558,0.010638903,0.064623214,0.011176997,0.6777825,0.009800289,0.22046588],"study_design_scores_gemma":[0.0017019691,0.00034029948,0.0006540826,0.00014641142,0.000026238735,0.000024958525,0.0005138587,0.9914643,0.00024323564,0.0005716122,0.003918059,0.00039498392],"about_ca_topic_score_codex":0.00015793485,"about_ca_topic_score_gemma":0.000028273927,"teacher_disagreement_score":0.9813897,"about_ca_system_score_codex":0.00044106453,"about_ca_system_score_gemma":0.00029514087,"threshold_uncertainty_score":0.9998863},"labels":[],"label_agreement":null},{"id":"W2885245712","doi":"10.1109/tcyb.2018.2859801","title":"Functional Nonlinear Model Predictive Control Based on Adaptive Dynamic Programming","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundamental Research Funds for the Central Universities; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Model predictive control; Control theory (sociology); Optimal control; Robustness (evolution); Nonlinear system; Dynamic programming; Computer science; Mathematical optimization; Artificial neural network; Lyapunov function; Mathematics; Control (management); Artificial intelligence","score_opus":0.014439540201730003,"score_gpt":0.23581651935001469,"score_spread":0.2213769791482847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885245712","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00047547638,0.000010605211,0.9959368,0.00059895666,0.00086916785,0.00083848595,0.00011237368,0.00059712346,0.0005610235],"genre_scores_gemma":[0.8477375,0.0000019799481,0.15074098,0.0007573437,0.000099981546,0.00019735878,0.000005032484,0.000044694563,0.00041513616],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717927,0.00013359543,0.00039357226,0.00086606306,0.000785697,0.0006418314],"domain_scores_gemma":[0.9979177,0.00035835162,0.00016337655,0.00083692523,0.000487749,0.00023588125],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028927886,0.00041893125,0.0003168505,0.00031561998,0.00042354452,0.00013521503,0.0006915094,0.00020403882,0.00002225251],"category_scores_gemma":[0.000019455136,0.00041377352,0.00023576108,0.00052152877,0.0003801333,0.00028146975,0.000005179082,0.0005984151,0.00020236634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059154944,0.0008558883,0.0000070078077,0.000005118742,0.00013701433,0.00001096427,0.00024224241,0.8772695,0.00018693696,0.0018807466,0.00006304107,0.11874998],"study_design_scores_gemma":[0.0022175382,0.0024386903,0.00013584043,0.00004790682,0.000076559176,0.0000074379914,0.000022060389,0.9931522,0.0005256954,0.0007431299,0.000250222,0.00038271368],"about_ca_topic_score_codex":0.00001599659,"about_ca_topic_score_gemma":0.00006917866,"teacher_disagreement_score":0.847262,"about_ca_system_score_codex":0.00036445,"about_ca_system_score_gemma":0.00031231993,"threshold_uncertainty_score":0.99983144},"labels":[],"label_agreement":null},{"id":"W2887000122","doi":"10.1109/civemsa.2018.8439974","title":"Model-Free Value Iteration Solution for Dynamic Graphical Games","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Perceptron; Reinforcement learning; A priori and a posteriori; Graph; Graphical model; Set (abstract data type); Artificial neural network; Artificial intelligence; Theoretical computer science; Mathematical optimization; Mathematics","score_opus":0.014368884697763856,"score_gpt":0.26553231667832555,"score_spread":0.2511634319805617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887000122","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002041511,0.000019843184,0.9919252,0.004576646,0.00025210067,0.0003779851,0.0000040952746,0.00034258954,0.00046002754],"genre_scores_gemma":[0.56011134,6.6567105e-7,0.43906042,0.0003947983,0.00004697085,0.00004785407,0.0000042516454,0.000005822635,0.00032788859],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889517,0.000034211786,0.0001823992,0.00038907613,0.00019446723,0.00030467022],"domain_scores_gemma":[0.9989818,0.000067952344,0.00005915101,0.00061984634,0.00021338463,0.000057897574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030224773,0.00012073512,0.00011580411,0.00010354715,0.00017396554,0.00014800385,0.0007747097,0.00007605111,0.0000019420297],"category_scores_gemma":[0.0000961545,0.00010661484,0.00008832723,0.00019266631,0.0001042147,0.0005317253,0.00019745386,0.00006240857,0.000015761058],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014282949,0.000028554867,0.000016496166,0.0000036809813,0.000012830052,3.3865948e-7,0.00012458161,0.00023141287,0.002011249,0.94653535,0.00073003396,0.050291218],"study_design_scores_gemma":[0.0004222809,0.00017164947,0.00011524137,0.0000043943055,0.0000056339686,0.0000028945333,0.0000018978311,0.8009946,0.00011122803,0.19766787,0.00038658918,0.00011574472],"about_ca_topic_score_codex":0.000012708299,"about_ca_topic_score_gemma":0.00009977996,"teacher_disagreement_score":0.8007632,"about_ca_system_score_codex":0.00007736654,"about_ca_system_score_gemma":0.00006151139,"threshold_uncertainty_score":0.4347627},"labels":[],"label_agreement":null},{"id":"W2887066212","doi":"10.1109/civemsa.2018.8439951","title":"Reinforcement Learning Solution with Costate Approximation for a Flexible Wing Aircraft","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Heuristic; Dynamic programming; Optimal control; Adaptive control; System dynamics; Function (biology); Dynamical systems theory; Dual (grammatical number); Control theory (sociology); Mathematical optimization; Control (management); Artificial intelligence; Mathematics; Algorithm","score_opus":0.015981380659571984,"score_gpt":0.2507460581578228,"score_spread":0.2347646774982508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887066212","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010712027,0.0000061951046,0.99455494,0.0005161525,0.000084890045,0.0005664085,1.4853597e-7,0.0005297364,0.0026703582],"genre_scores_gemma":[0.69043314,4.104631e-7,0.30708918,0.0001380546,0.000051121955,0.000084375286,0.000005442337,0.0000074520203,0.0021907764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990155,0.000024478857,0.00015868462,0.00028430563,0.00019629531,0.00032072436],"domain_scores_gemma":[0.99933356,0.00005225828,0.00010414138,0.0002291762,0.00022991166,0.00005095307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037789307,0.00010690174,0.000101521226,0.00007647436,0.00028321185,0.00013782893,0.0002650181,0.000029078816,0.000004891564],"category_scores_gemma":[0.00004494544,0.00008710006,0.000031653894,0.00020433324,0.000058059733,0.0006228344,0.00008994157,0.00006874323,0.000028959203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032542917,0.000093342955,0.00059578894,0.000070631184,0.00014776833,0.0000031725938,0.004014216,0.040536247,0.010136428,0.4385191,0.00074490294,0.504813],"study_design_scores_gemma":[0.00076000515,0.0007469014,0.0000851544,0.000021238582,0.000006726495,0.0000041027583,0.00004926164,0.98965186,0.0019332691,0.0009378484,0.005668027,0.00013558731],"about_ca_topic_score_codex":0.000034948545,"about_ca_topic_score_gemma":0.00001739167,"teacher_disagreement_score":0.94911563,"about_ca_system_score_codex":0.000099589066,"about_ca_system_score_gemma":0.00005838037,"threshold_uncertainty_score":0.35518375},"labels":[],"label_agreement":null},{"id":"W2897010625","doi":"10.3390/robotics7040066","title":"Model-Free Gradient-Based Adaptive Learning Controller for an Unmanned Flexible Wing Aircraft","year":2018,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ontario Centres of Excellence","keywords":"Optimal control; Control theory (sociology); Controller (irrigation); Reinforcement learning; Computer science; Adaptive control; Mathematical optimization; Heuristic; Dynamic programming; Dynamical systems theory; Aerodynamics; Gradient descent; Artificial neural network; Control engineering; Mathematics; Artificial intelligence; Control (management); Engineering","score_opus":0.042728730709356906,"score_gpt":0.27880226149812287,"score_spread":0.23607353078876597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897010625","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00070515566,0.000041762465,0.9964438,0.0008071029,0.00031737747,0.00067966164,0.000006472188,0.00065385207,0.00034483246],"genre_scores_gemma":[0.5471864,3.085244e-7,0.45186597,0.00035688808,0.000140664,0.000041575968,0.000005653998,0.000028533228,0.00037400864],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776053,0.00011977859,0.00033272261,0.00067563297,0.00034610552,0.0007652442],"domain_scores_gemma":[0.99796396,0.00027327673,0.00019402942,0.0008416136,0.00050856883,0.00021855754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058463955,0.0002904069,0.00036943218,0.00016520426,0.00049484364,0.00020283673,0.0014607665,0.00012593699,0.0000014458983],"category_scores_gemma":[0.0003032313,0.00029014776,0.00016322688,0.0003157354,0.00017907251,0.0005750712,0.0002477738,0.0002446013,0.000024358429],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013629084,0.000111356996,0.000107175176,0.000007921158,0.000053645424,0.000002699462,0.000403503,0.84284675,0.0004703416,0.14167213,0.00019323712,0.013994955],"study_design_scores_gemma":[0.002851745,0.0014711617,0.000049107603,0.00002861095,0.00003843878,0.0000022982488,0.000047657297,0.9785676,0.00022642026,0.015960475,0.00040882832,0.00034768358],"about_ca_topic_score_codex":0.000018373798,"about_ca_topic_score_gemma":0.000050733914,"teacher_disagreement_score":0.54648125,"about_ca_system_score_codex":0.00015011527,"about_ca_system_score_gemma":0.0001835641,"threshold_uncertainty_score":0.99995506},"labels":[],"label_agreement":null},{"id":"W2904050798","doi":"10.1109/iccss.2018.8572428","title":"Adaptive Critic Optimal Fuzzy Control for Quarter-Car Suspension Systems","year":2018,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fuzzy control system; Control theory (sociology); Computer science; Suspension (topology); Fuzzy logic; Adaptive control; Active suspension; Quarter (Canadian coin); Control engineering; Control (management); Engineering; Artificial intelligence; Mathematics; Actuator","score_opus":0.01547698783135517,"score_gpt":0.25287297785473495,"score_spread":0.23739599002337977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904050798","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011692314,0.00009670929,0.99220777,0.0007940232,0.0013155302,0.0012602552,0.00001291683,0.0004476587,0.0026958997],"genre_scores_gemma":[0.904485,4.655008e-7,0.09410152,0.0003858733,0.00039419057,0.00017810432,0.000002637838,0.000018920411,0.00043332617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978874,0.00013315225,0.00035539563,0.000654622,0.0003125497,0.0006569212],"domain_scores_gemma":[0.9978203,0.00047355786,0.00011807843,0.0006879905,0.00072641275,0.0001736711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005750987,0.00024923362,0.00036580418,0.00011506483,0.00025329547,0.0002770347,0.00088373787,0.00010608356,0.0000049663263],"category_scores_gemma":[0.0001194577,0.00021345589,0.0001423161,0.00019769809,0.00017667445,0.0005490132,0.000118405485,0.000103275444,0.00017287904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017389083,0.00011530185,0.000036093876,0.000018893703,0.0001160015,0.000020047724,0.00043709733,0.00022316408,0.0022041076,0.98210496,0.0036010705,0.010949364],"study_design_scores_gemma":[0.0022192344,0.0017648323,0.00012341232,0.00003163565,0.000029537758,0.00003280633,0.00028577342,0.9899498,0.0001284958,0.0022802546,0.0028356991,0.00031851232],"about_ca_topic_score_codex":0.00009587508,"about_ca_topic_score_gemma":0.000028232886,"teacher_disagreement_score":0.98972666,"about_ca_system_score_codex":0.00010525811,"about_ca_system_score_gemma":0.0000925486,"threshold_uncertainty_score":0.8704479},"labels":[],"label_agreement":null},{"id":"W2912067707","doi":"10.1002/acs.2964","title":"Editorial for the Special Issue on Learning‐based Adaptive Control: Theory and Applications","year":2019,"lang":"en","type":"article","venue":"International Journal of Adaptive Control and Signal Processing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Adaptive learning; Adaptive control; Artificial intelligence; Control (management); Machine learning; Data science","score_opus":0.006952249410241171,"score_gpt":0.2509708647991017,"score_spread":0.24401861538886052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912067707","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014888287,0.0007082371,0.99201053,0.0017437219,0.004436215,0.0006289703,0.000016524484,0.000022932472,0.00028399393],"genre_scores_gemma":[0.94036776,0.000011291539,0.0025758666,0.000747532,0.056111004,0.000053457967,0.0000010410885,0.000015466358,0.00011658729],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981623,0.00021222347,0.00041860688,0.0003059122,0.0006694171,0.00023149433],"domain_scores_gemma":[0.9950528,0.002595626,0.0006588812,0.000101593476,0.0014889344,0.000102146776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001544867,0.00021066474,0.0003298773,0.00016709337,0.00025075875,0.00036441354,0.0007295632,0.000086261585,0.000009757852],"category_scores_gemma":[0.00020338644,0.00014478186,0.00014086596,0.0000906351,0.00017798787,0.00053141674,0.000056212793,0.00045792852,0.000004493725],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008093374,0.000161871,0.00021000039,0.000013256624,0.0006361953,0.000010416298,0.0004914478,0.012045374,0.00090691185,0.0985402,0.001011886,0.8778791],"study_design_scores_gemma":[0.013028317,0.0024011119,0.0007698152,0.00017519695,0.00015215224,0.00004545094,0.00044446046,0.83167464,0.000051202933,0.022492588,0.12842752,0.00033754733],"about_ca_topic_score_codex":0.0000034063044,"about_ca_topic_score_gemma":0.0000013717527,"teacher_disagreement_score":0.98943466,"about_ca_system_score_codex":0.00008433314,"about_ca_system_score_gemma":0.00024323414,"threshold_uncertainty_score":0.59040326},"labels":[],"label_agreement":null},{"id":"W2912832158","doi":"10.1109/tcyb.2018.2890046","title":"Optimal Output Regulation of Linear Discrete-Time Systems With Unknown Dynamics Using Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project; Northeastern University; National Natural Science Foundation of China","keywords":"Reinforcement learning; Optimization problem; Optimal control; Mathematical optimization; Control theory (sociology); Computer science; Discrete time and continuous time; Discrete optimization; Noise (video); System dynamics; Control (management); Mathematics; Artificial intelligence","score_opus":0.009236036983152505,"score_gpt":0.22108144031156662,"score_spread":0.21184540332841412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912832158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06811907,0.000014330367,0.930522,0.000032649026,0.00030561042,0.0005023485,0.0000041321605,0.00013608728,0.00036374354],"genre_scores_gemma":[0.94280815,0.0000029042108,0.053388998,0.000009933794,0.00002023783,0.000011203026,0.0000051849456,0.000029257704,0.0037241017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983357,0.000090012916,0.00039243852,0.00037377476,0.00049802056,0.00031004407],"domain_scores_gemma":[0.99878335,0.000111913316,0.0002715271,0.0005453208,0.00021159537,0.00007628662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022069097,0.00022381096,0.00029889747,0.00017465283,0.00012715181,0.000078513716,0.00038803206,0.00010745776,0.000008389435],"category_scores_gemma":[0.0000041871863,0.00020488542,0.000091572554,0.00035182745,0.00007821956,0.0002824537,0.000006892122,0.00029893927,0.00004149703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048869642,0.00004748647,0.000048159294,0.000025853624,0.00007060875,0.0000016021879,0.00026719595,0.99257666,0.0009848162,0.0022009634,6.9521093e-7,0.003727091],"study_design_scores_gemma":[0.00067070423,0.0006743278,0.000059394144,0.00013121466,0.00005210214,0.000016169091,0.000057539466,0.9970777,0.0008823477,0.000009718563,0.00013525554,0.00023353206],"about_ca_topic_score_codex":0.000111443216,"about_ca_topic_score_gemma":0.000010420699,"teacher_disagreement_score":0.877133,"about_ca_system_score_codex":0.0002589643,"about_ca_system_score_gemma":0.00009505002,"threshold_uncertainty_score":0.8354985},"labels":[],"label_agreement":null},{"id":"W2928373814","doi":"10.1109/tcyb.2019.2901268","title":"Granular Prediction and Dynamic Scheduling Based on Adaptive Dynamic Programming for the Blast Furnace Gas System","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Scheduling (production processes); Dynamic priority scheduling; Computer science; Mathematical optimization; Schedule; Mathematics","score_opus":0.007921224045344375,"score_gpt":0.2191847700500824,"score_spread":0.21126354600473804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928373814","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010994954,0.000114958326,0.98447925,0.00054273475,0.0011579703,0.002183032,0.000053263433,0.00043244273,0.00004137969],"genre_scores_gemma":[0.93817264,0.000017342525,0.06116694,0.000087461696,0.000024601313,0.0003317215,0.000003899992,0.0000483804,0.00014699221],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977982,0.000118356766,0.0003695146,0.00071939244,0.00047658052,0.0005179778],"domain_scores_gemma":[0.99792874,0.00078147306,0.00018041539,0.0008015906,0.00018024238,0.00012753964],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004951254,0.00035054708,0.00029094037,0.00021003875,0.00044818784,0.00023081376,0.0006023116,0.00016060965,0.0000019797637],"category_scores_gemma":[0.000011954114,0.000290506,0.00019147983,0.0003839147,0.00013047236,0.00022098944,0.0000066127805,0.00048331878,0.000027180395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002800474,0.0002729067,0.000049937753,0.00012323818,0.00013294275,0.000007026171,0.00051278924,0.664888,0.00069872395,0.0042334753,0.0000030876322,0.3287978],"study_design_scores_gemma":[0.0014839715,0.0011011729,0.00025669773,0.00022612662,0.000115638184,0.000021825914,0.00028083695,0.9956645,0.00019194437,0.00011463765,0.00027420346,0.0002684401],"about_ca_topic_score_codex":0.000026605445,"about_ca_topic_score_gemma":0.0000835295,"teacher_disagreement_score":0.9271777,"about_ca_system_score_codex":0.00037330607,"about_ca_system_score_gemma":0.00009617294,"threshold_uncertainty_score":0.9999547},"labels":[],"label_agreement":null},{"id":"W2951873227","doi":"10.1109/tac.2019.2922953","title":"Distributed GNE Seeking Under Partial-Decision Information Over Networks via a Doubly-Augmented Operator Splitting Approach","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":148,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Monotone polygon; Convergence (economics); Nash equilibrium; Operator (biology); Computation; Strongly monotone; Distributed algorithm","score_opus":0.006590390268237936,"score_gpt":0.22146990101472894,"score_spread":0.214879510746491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951873227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015329388,0.000022404247,0.98075974,0.0002625393,0.0009669216,0.0016983863,0.000024278337,0.0008619356,0.000074425436],"genre_scores_gemma":[0.9790278,0.0000017121191,0.01985493,0.00073832297,0.000039964725,0.0002579949,0.000020062624,0.000025210777,0.000033990316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970745,0.00019620033,0.0008771374,0.0005215736,0.0006753388,0.00065524166],"domain_scores_gemma":[0.9978063,0.0005248147,0.00034418775,0.00094634644,0.00018571263,0.00019265062],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007298517,0.000396166,0.0005265113,0.00026544553,0.0003335553,0.0006574792,0.000735161,0.0001995608,0.00007274446],"category_scores_gemma":[0.000021892989,0.00036024416,0.00024405622,0.0007566151,0.000049390543,0.0021384284,0.000011062606,0.00038770135,0.00020036021],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011118648,0.00030111562,0.000048628124,0.000036004905,0.00024374099,0.000002963665,0.00032984398,0.6588897,0.0006953157,0.0010415592,0.000032124095,0.3382678],"study_design_scores_gemma":[0.0054179025,0.00016106523,0.0006896498,0.00009407811,0.000071815455,0.000017916449,0.00006664491,0.9927353,0.00008741263,0.000117130934,0.000167281,0.00037380226],"about_ca_topic_score_codex":0.00004170291,"about_ca_topic_score_gemma":0.000006181112,"teacher_disagreement_score":0.96369845,"about_ca_system_score_codex":0.00034662592,"about_ca_system_score_gemma":0.00010080004,"threshold_uncertainty_score":0.99988496},"labels":[],"label_agreement":null},{"id":"W2963138810","doi":"10.1016/j.asoc.2019.105629","title":"Neurodynamic programming and tracking control scheme of constrained-input systems via a novel event-triggered PI algorithm","year":2019,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China","keywords":"Computer science; Dynamic programming; Control theory (sociology); Trajectory; Tracking (education); Bounded function; Artificial neural network; Tracking error; Computation; Algorithm; Mathematics; Control (management); Artificial intelligence","score_opus":0.0064897288057627935,"score_gpt":0.21646625536204842,"score_spread":0.20997652655628563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963138810","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08557717,0.00027167876,0.9115156,0.00008377778,0.00037255342,0.0016167966,0.0000057133734,0.00045478254,0.00010195252],"genre_scores_gemma":[0.77367043,9.858244e-7,0.22606644,0.00011811199,0.00006504371,0.000026674968,0.0000048821585,0.000036322315,0.000011138787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966663,0.00008400283,0.0008840149,0.0009963169,0.0005360033,0.0008333243],"domain_scores_gemma":[0.9974406,0.00072742754,0.00073382107,0.0006825059,0.00023846843,0.00017722808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010521957,0.0004356242,0.0008165016,0.00022004735,0.00019967968,0.0003070701,0.0009009858,0.00016096699,9.4105246e-7],"category_scores_gemma":[0.000050266477,0.0004529179,0.00013944441,0.0005291578,0.00018318072,0.0002712612,0.00037606127,0.00043509816,0.0000127921285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004253887,0.00027432412,0.0019286264,0.0002977636,0.0002817414,0.000022082224,0.0010044964,0.007338793,0.06507227,0.06660792,0.0000034799352,0.85712594],"study_design_scores_gemma":[0.0032644337,0.0001488174,0.0005659653,0.00013000378,0.000029240864,0.00008014249,0.00014499425,0.994817,0.000071025104,0.00017225249,0.00014732608,0.00042878493],"about_ca_topic_score_codex":0.000030355755,"about_ca_topic_score_gemma":0.0000014467699,"teacher_disagreement_score":0.9874782,"about_ca_system_score_codex":0.00008438754,"about_ca_system_score_gemma":0.00012710731,"threshold_uncertainty_score":0.9997923},"labels":[],"label_agreement":null},{"id":"W2967441303","doi":"10.1109/rose.2019.8790425","title":"An Online Reinforcement Learning Wing-Tracking Mechanism for Flexible Wing Aircraft","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Wing; Reinforcement learning; Mechanism (biology); Computer science; Aeronautics; Aerospace engineering; Simulation; Artificial intelligence; Engineering; Physics","score_opus":0.025428907904497814,"score_gpt":0.277794600672952,"score_spread":0.25236569276845416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967441303","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026241371,0.000011765849,0.97058976,0.00040455282,0.00038567348,0.0006684582,6.633965e-7,0.00094594364,0.00075183425],"genre_scores_gemma":[0.7494434,0.0000011141224,0.24652834,0.00058528775,0.00008537085,0.000026378626,0.000015284668,0.000021880453,0.003292938],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813783,0.000045647932,0.00031992389,0.0005859048,0.00032988857,0.0005808061],"domain_scores_gemma":[0.99875236,0.00013531104,0.00014413902,0.0006203568,0.0002232685,0.00012454751],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005508497,0.00021181248,0.00024501645,0.0001333838,0.00020557869,0.0002786832,0.0009453956,0.00007909771,0.000025219437],"category_scores_gemma":[0.00008126198,0.00020231449,0.00011301878,0.00020910059,0.000016303644,0.0011350856,0.000222141,0.00022013848,0.000058169542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024411924,0.00010146429,0.0007371738,0.00003766814,0.00006186814,0.0000049586747,0.00076572865,0.0646585,0.04797028,0.7839425,0.000021195414,0.10167423],"study_design_scores_gemma":[0.0008218722,0.0006001007,0.0002031858,0.000037488502,0.0000092735445,0.0000052490077,0.00020246001,0.98840815,0.003154639,0.0048202244,0.0014461556,0.00029122017],"about_ca_topic_score_codex":0.000057207384,"about_ca_topic_score_gemma":0.000015056133,"teacher_disagreement_score":0.9237496,"about_ca_system_score_codex":0.00011050608,"about_ca_system_score_gemma":0.00007929873,"threshold_uncertainty_score":0.82501453},"labels":[],"label_agreement":null},{"id":"W2967515641","doi":"10.1109/rose.2019.8790424","title":"Neurofuzzy Reinforcement Learning Control Schemes for Optimized Dynamical Performance","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control (management); Artificial intelligence","score_opus":0.006745649804198587,"score_gpt":0.2209946881010428,"score_spread":0.21424903829684422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967515641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020682678,0.00002010287,0.9740005,0.0006497081,0.0003059805,0.0010589224,4.3994575e-7,0.00040290388,0.0028787716],"genre_scores_gemma":[0.88148886,0.0000034415882,0.112136945,0.00053305266,0.00003212698,0.00012056137,0.0000049275145,0.000015747313,0.005664344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837,0.00004878241,0.00030413712,0.00047569544,0.0002793217,0.00052209094],"domain_scores_gemma":[0.9988598,0.00027907957,0.00012909244,0.0004855744,0.00014597559,0.00010047831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040720258,0.00019913587,0.00029587475,0.00008464369,0.00012835284,0.00014473479,0.000810895,0.000067040084,0.0000333528],"category_scores_gemma":[0.000102713944,0.000171319,0.0001374546,0.00015056247,0.000036388992,0.0005287509,0.00018603983,0.00021340462,0.0001587722],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006478662,0.00013762443,0.008133989,0.00012024125,0.0002386463,0.000006102074,0.00024056277,0.36645132,0.0043231384,0.42021963,0.00023596898,0.1992449],"study_design_scores_gemma":[0.0040130764,0.00048241182,0.00030566534,0.000011623635,0.00000920901,0.000004408723,0.000009837573,0.98555213,0.00011329828,0.00010353173,0.00917258,0.00022220441],"about_ca_topic_score_codex":0.0000049405235,"about_ca_topic_score_gemma":4.0465457e-7,"teacher_disagreement_score":0.86186355,"about_ca_system_score_codex":0.00007211952,"about_ca_system_score_gemma":0.00006571949,"threshold_uncertainty_score":0.6986186},"labels":[],"label_agreement":null},{"id":"W2967692091","doi":"10.1109/rose.2019.8790432","title":"Model-Free Adaptive Control Approach Using Integral Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Adaptive control; Control (management); Reinforcement; Artificial intelligence; Engineering","score_opus":0.023251655482380784,"score_gpt":0.2321184257896034,"score_spread":0.20886677030722262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967692091","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026141838,0.00003151079,0.97283167,0.000109143715,0.00013395054,0.0006374713,6.370778e-7,0.00036866343,0.023272755],"genre_scores_gemma":[0.6909654,4.516478e-7,0.30634364,0.00024379288,0.00002241855,0.000019209232,0.0000016227882,0.000013569849,0.0023898776],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979759,0.00012068912,0.00030984246,0.00057895767,0.00045310243,0.0005615427],"domain_scores_gemma":[0.9985558,0.00010168322,0.00016099226,0.00089856214,0.00016121981,0.00012174129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061298296,0.00025463713,0.00032433184,0.00013594114,0.00012195056,0.00016203549,0.0014747201,0.000088918096,0.000016858045],"category_scores_gemma":[0.00007606505,0.00021578772,0.00014003734,0.00025355903,0.00005346028,0.0007300015,0.00056511996,0.00039147647,0.000068735004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002824684,0.000025772366,0.00024561698,0.000004194841,0.000050444734,0.0000018378563,0.00025505753,0.6946893,0.0004838618,0.29741323,0.000025563379,0.006776927],"study_design_scores_gemma":[0.001681494,0.0001836106,0.00002819925,0.000012515995,0.000013479539,0.000009463589,0.0001375514,0.99530697,0.000028265262,0.0022124224,0.000106160645,0.00027984328],"about_ca_topic_score_codex":0.00009600831,"about_ca_topic_score_gemma":0.000003224837,"teacher_disagreement_score":0.6883512,"about_ca_system_score_codex":0.00021725573,"about_ca_system_score_gemma":0.00013503317,"threshold_uncertainty_score":0.8799568},"labels":[],"label_agreement":null},{"id":"W2972407345","doi":"10.23919/acc.2019.8814309","title":"Constrained control Lyapunov function construction via approximation of static Hamilton-Jacobi-Bellman equations","year":2019,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Nonlinear system; Mathematics; Lyapunov function; Classification of discontinuities; Optimal control; Bellman equation; Applied mathematics; Viscosity solution; Mathematical optimization; Mathematical analysis","score_opus":0.005842289523805856,"score_gpt":0.20276530716816488,"score_spread":0.19692301764435902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972407345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010872384,0.000020578816,0.9845827,0.0003489415,0.00055000465,0.001040284,0.000007707314,0.00029083615,0.0022865199],"genre_scores_gemma":[0.8941858,9.052977e-7,0.10530488,0.0001762977,0.000022856568,0.00004383499,0.000021710059,0.000010939525,0.00023277347],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982219,0.00013711698,0.00053715054,0.00041813063,0.00039010448,0.00029560688],"domain_scores_gemma":[0.99828374,0.00033239034,0.00039010486,0.00056250964,0.00035317315,0.000078062876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047012814,0.00019314585,0.0003140343,0.00022713603,0.000088742854,0.000072728144,0.00036980017,0.000093847426,0.000070012145],"category_scores_gemma":[0.0000701072,0.00018296971,0.00010432519,0.00044277933,0.00013751876,0.0007689192,0.000044735585,0.00013579673,0.0001366944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064531116,0.00015174376,0.0015749848,0.000060275233,0.00018747324,0.0000010603045,0.0004091346,0.003327219,0.031348735,0.8279816,0.00003450594,0.13485877],"study_design_scores_gemma":[0.0022563296,0.0003060984,0.0010516647,0.000019209174,0.00004566276,0.000011311406,0.00014542708,0.9812273,0.00053432595,0.014066018,0.00013171471,0.00020496789],"about_ca_topic_score_codex":0.00005235165,"about_ca_topic_score_gemma":0.000011351982,"teacher_disagreement_score":0.9779,"about_ca_system_score_codex":0.00008984722,"about_ca_system_score_gemma":0.00012264986,"threshold_uncertainty_score":0.74612886},"labels":[],"label_agreement":null},{"id":"W2974373467","doi":"10.3390/robotics8040082","title":"Online Multi-Objective Model-Independent Adaptive Tracking Mechanism for Dynamical Systems","year":2019,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Reinforcement learning; Dynamical systems theory; Adaptive control; Scalability; Optimal control; Robotics; Iterative learning control; Aerodynamics; Adaptive learning; Tracking error; Control engineering; Artificial intelligence; Control theory (sociology); Control (management); Mathematical optimization; Robot; Mathematics; Engineering","score_opus":0.03195951659220993,"score_gpt":0.2699029278227233,"score_spread":0.23794341123051338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2974373467","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021890656,0.00005425072,0.9945962,0.00019920862,0.0009985924,0.0015669541,0.00004861928,0.0002965759,0.00005053421],"genre_scores_gemma":[0.60198534,0.0000015612865,0.39736134,0.00008175334,0.000050281695,0.00004155523,0.000010672135,0.000027889819,0.00043962355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99776363,0.00007930408,0.00038647337,0.00072969415,0.00043329978,0.0006076122],"domain_scores_gemma":[0.9982097,0.00024735328,0.0002205485,0.0006633897,0.00051378534,0.00014521243],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032033725,0.0002984486,0.00043513635,0.00012425185,0.00011583239,0.00017626748,0.0009796132,0.00019264688,6.1596637e-7],"category_scores_gemma":[0.00008951427,0.0002882839,0.00018041862,0.00018745106,0.000032916774,0.00041693146,0.00028565433,0.00031698617,0.00003548279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016275233,0.0001950707,0.00003215162,0.000017346138,0.000061024293,0.0000054108964,0.00021742728,0.49767506,0.00037298305,0.49939635,0.0000031309305,0.002007762],"study_design_scores_gemma":[0.001361246,0.0002786614,0.000103389066,0.000051596933,0.00003227558,0.000016172355,0.00019344536,0.98979896,0.00005493565,0.0077599334,0.0000058191736,0.00034354208],"about_ca_topic_score_codex":0.00003370939,"about_ca_topic_score_gemma":0.00005048549,"teacher_disagreement_score":0.5997963,"about_ca_system_score_codex":0.00039258768,"about_ca_system_score_gemma":0.0001645455,"threshold_uncertainty_score":0.9999569},"labels":[],"label_agreement":null},{"id":"W2979612126","doi":"10.1049/iet-cta.2018.6163","title":"Online model‐free reinforcement learning for the automatic control of a flexible wing aircraft","year":2019,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Wing; Computer science; Control (management); Control theory (sociology); Control engineering; Fixed wing; Aeronautics; Artificial intelligence; Engineering; Aerospace engineering","score_opus":0.00934140909909165,"score_gpt":0.25029503380541007,"score_spread":0.24095362470631843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979612126","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013162208,0.00047036985,0.99412584,0.0011747264,0.000040090632,0.0024594506,0.000020188223,0.00016696514,0.00022612335],"genre_scores_gemma":[0.9894792,0.0000068800637,0.0076943035,0.0005471357,0.000050062743,0.0013009999,0.0000057278758,0.000013436774,0.0009022546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988028,0.000106649,0.0003404632,0.0003070212,0.0001659003,0.00027719652],"domain_scores_gemma":[0.99664325,0.0021036074,0.0002368386,0.0008151141,0.00014150665,0.0000596632],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011345369,0.00015401255,0.0002707421,0.000057022473,0.00025863093,0.00006635275,0.0008657099,0.00005209126,0.000007599848],"category_scores_gemma":[0.00012708695,0.00011492972,0.00011757681,0.0001485741,0.000110688045,0.00019587102,0.00011103542,0.00015390114,0.0000070166743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053157488,0.000055092132,0.0000616807,0.000022484799,0.00012002474,7.5827664e-8,0.00022243333,0.13660586,0.0011912145,0.808854,0.000009094768,0.0528049],"study_design_scores_gemma":[0.0026358783,0.00011405562,0.0001883701,0.00001800776,0.00008078009,0.0000021535827,0.000109976754,0.9267985,0.000027407308,0.06852565,0.0013801564,0.00011905552],"about_ca_topic_score_codex":0.000004964292,"about_ca_topic_score_gemma":0.0000013270128,"teacher_disagreement_score":0.988163,"about_ca_system_score_codex":0.00002426382,"about_ca_system_score_gemma":0.000065842774,"threshold_uncertainty_score":0.4686698},"labels":[],"label_agreement":null},{"id":"W2980804356","doi":"10.1007/s41315-019-00105-3","title":"Online model-free controller for flexible wing aircraft: a policy iteration-based reinforcement learning approach","year":2019,"lang":"en","type":"article","venue":"International Journal of Intelligent Robotics and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Ontario Centres of Excellence","keywords":"Aerodynamics; Reinforcement learning; Control theory (sociology); Wing; Kinematics; Controller (irrigation); Stability (learning theory); Computer science; Optimal control; Control engineering; Flight dynamics; Nonlinear system; Engineering; Control (management); Artificial intelligence; Mathematical optimization; Aerospace engineering; Mathematics","score_opus":0.019198946474780678,"score_gpt":0.2903157640076766,"score_spread":0.27111681753289596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980804356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002499517,0.00009878005,0.9948555,0.0038771827,0.000102907165,0.000541639,0.000008442974,0.000033193923,0.00023236901],"genre_scores_gemma":[0.6702481,0.000031202617,0.3282704,0.0005647567,0.00025462426,0.000054393546,0.00002639665,0.000011496492,0.00053864456],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986357,0.000019732055,0.00056000566,0.00021172977,0.00039582295,0.00017702265],"domain_scores_gemma":[0.99808586,0.00018994337,0.00044079853,0.00022316391,0.000964172,0.00009606594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003250318,0.00013834368,0.00020874657,0.0003112329,0.00009374969,0.000237989,0.0010159094,0.000049032973,0.0000022110976],"category_scores_gemma":[0.00011587841,0.0001240588,0.00014923072,0.00014836303,0.000033333727,0.00026064206,0.00014389324,0.00019384602,0.0000032040816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024435258,0.00012403757,0.000081998485,0.0000070249994,0.00007997253,2.779127e-7,0.00008149845,0.7159318,0.00029633945,0.26850834,0.000025611429,0.014838678],"study_design_scores_gemma":[0.0010664797,0.00013013039,0.000024652705,0.000034037505,0.000017519778,0.000014221945,0.00003841468,0.98316264,0.0001511128,0.011408062,0.0038360145,0.000116726595],"about_ca_topic_score_codex":0.000007765744,"about_ca_topic_score_gemma":0.0000010347012,"teacher_disagreement_score":0.6699981,"about_ca_system_score_codex":0.00016129209,"about_ca_system_score_gemma":0.00022622471,"threshold_uncertainty_score":0.5058971},"labels":[],"label_agreement":null},{"id":"W2998797223","doi":"10.1016/j.neucom.2020.01.026","title":"Near-optimal neural-network robot control with adaptive gravity compensation","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cerebellar model articulation controller; Control theory (sociology); Computer science; Artificial neural network; Feed forward; Controller (irrigation); Inverted pendulum; Adaptive control; Lyapunov function; Bounded function; Feedforward neural network; Nonlinear system; Artificial intelligence; Control (management); Mathematics; Control engineering; Engineering","score_opus":0.01630035951098792,"score_gpt":0.21536037733356267,"score_spread":0.19906001782257476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998797223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05611816,0.000038030394,0.9387875,0.0033140252,0.00018275947,0.0006490861,0.0000017457606,0.0007663681,0.00014231345],"genre_scores_gemma":[0.8308002,2.4597566e-7,0.16522506,0.0035981517,0.0003263548,0.000014036042,0.0000024724748,0.000028716824,0.000004809199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726,0.00030574304,0.0003691992,0.0008840076,0.00046347585,0.0007176294],"domain_scores_gemma":[0.9983938,0.0004054135,0.0003223288,0.00041474347,0.00018683737,0.0002768835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027269698,0.00033869018,0.00042196398,0.00003360416,0.00047137617,0.00039967799,0.0009905396,0.00006670385,0.00000232814],"category_scores_gemma":[0.00006997266,0.0003102319,0.00010632495,0.00067560974,0.00012264338,0.00044701443,0.00034884582,0.0005336301,0.000038390546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015020967,0.000041105905,0.0039340947,0.000009578539,0.000049773244,0.00013713661,0.0006999903,0.9303216,0.0004534702,0.0056406925,0.00011601511,0.058446355],"study_design_scores_gemma":[0.0014967144,0.0007087033,0.012592213,0.000019178846,0.000017509363,0.000040490533,0.000017215938,0.9841832,0.000022414164,0.000107804844,0.00048237003,0.0003121748],"about_ca_topic_score_codex":0.000021896205,"about_ca_topic_score_gemma":0.000004833363,"teacher_disagreement_score":0.774682,"about_ca_system_score_codex":0.000045669345,"about_ca_system_score_gemma":0.00009143545,"threshold_uncertainty_score":0.999935},"labels":[],"label_agreement":null},{"id":"W3017059342","doi":"10.1049/iet-cta.2019.0397","title":"Integral reinforcement learning solutions for a synchronisation system with constrained policies","year":2020,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Control engineering; Mathematical optimization; Artificial intelligence; Mathematics; Control (management); Engineering","score_opus":0.01138973012840052,"score_gpt":0.22718047211648623,"score_spread":0.2157907419880857,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017059342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018537781,0.000103806335,0.994257,0.0030631546,0.000013170396,0.0013964752,0.000013468032,0.0003481127,0.00061946356],"genre_scores_gemma":[0.99184614,0.0000021748142,0.0057478338,0.00054894836,0.00009932485,0.0016762955,0.000013967019,0.000009130045,0.00005619054],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990322,0.000104577215,0.00019637425,0.00028822053,0.00009909455,0.00027951374],"domain_scores_gemma":[0.99898374,0.00045528595,0.00013169713,0.0001931264,0.00012078275,0.000115361516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000467989,0.00013293147,0.00017690158,0.000038405702,0.00054398197,0.00013018199,0.00026639333,0.00003981703,0.0000014009189],"category_scores_gemma":[0.00006866222,0.00011069788,0.000050504128,0.00016465761,0.00016982859,0.00018104096,0.000051811425,0.00011641925,0.0000058932164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007367753,0.000010766573,0.000018438603,0.00002478616,0.000057402227,2.9455663e-7,0.00050788774,0.006374793,0.00057949265,0.9731149,0.0000091631555,0.019228369],"study_design_scores_gemma":[0.002112427,0.00038298473,0.000058614383,0.0000264098,0.000068076246,0.00001440763,0.0012880833,0.9820299,0.000028985307,0.0073613846,0.0064305533,0.00019815943],"about_ca_topic_score_codex":0.000008269843,"about_ca_topic_score_gemma":0.0000029815567,"teacher_disagreement_score":0.9916608,"about_ca_system_score_codex":0.00005084676,"about_ca_system_score_gemma":0.000079829,"threshold_uncertainty_score":0.45141286},"labels":[],"label_agreement":null},{"id":"W3037738032","doi":"10.3390/robotics9030049","title":"Model-Free Optimized Tracking Control Heuristic","year":2020,"lang":"en","type":"article","venue":"Robotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Overshoot (microwave communication); Computer science; Reinforcement learning; Heuristic; Tracking error; Controller (irrigation); Control theory (sociology); Control engineering; Artificial neural network; Iterative learning control; Tracking (education); Control (management); Engineering; Artificial intelligence","score_opus":0.03380149084032583,"score_gpt":0.23948310234438983,"score_spread":0.205681611504064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037738032","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046151177,0.000119597746,0.98748356,0.011064518,0.00015208694,0.00026463903,0.0000060791276,0.00048208202,0.0003812757],"genre_scores_gemma":[0.55022746,0.000002491097,0.44785762,0.0017846719,0.00006692767,0.000006860172,0.0000011749195,0.000014345281,0.000038479837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984994,0.00006802576,0.00028508835,0.00042498915,0.00031614085,0.0004063702],"domain_scores_gemma":[0.9986575,0.00018388103,0.00011655785,0.00068439875,0.00012614639,0.00023146307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017324765,0.00019074067,0.00031529515,0.000037703732,0.00009982701,0.0001890486,0.0016489174,0.00007088324,0.000002932642],"category_scores_gemma":[0.00053634186,0.00018903542,0.00011451604,0.00024040918,0.000050278497,0.00029447302,0.00030431314,0.0002406093,0.000051609757],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019755365,0.000028295863,0.000038948943,0.0000086001855,0.000031576114,0.000035655088,0.00022718949,0.91223913,0.00013428683,0.07872896,0.000343852,0.008163768],"study_design_scores_gemma":[0.0022269369,0.000074562886,0.00003014318,0.000008010528,0.000029750512,0.000005320093,0.0000056718095,0.9920872,0.0000137851475,0.005192687,0.00011799628,0.00020793322],"about_ca_topic_score_codex":0.0000027198341,"about_ca_topic_score_gemma":0.0000010027145,"teacher_disagreement_score":0.55018127,"about_ca_system_score_codex":0.000048332986,"about_ca_system_score_gemma":0.000092488146,"threshold_uncertainty_score":0.77086407},"labels":[],"label_agreement":null},{"id":"W3083274012","doi":"","title":"Centralized & Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Rate of convergence; State (computer science); Artificial intelligence; Algorithm; Mathematics","score_opus":0.06386126489103415,"score_gpt":0.24174866563835565,"score_spread":0.1778874007473215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083274012","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020960887,0.000055537697,0.9968551,0.00039127955,0.0005083934,0.0012127542,0.0000146234415,0.00064092985,0.00011177629],"genre_scores_gemma":[0.62365985,0.000092457376,0.37518063,0.00012152601,0.0000641792,0.0000117667905,0.0005309411,0.000030198058,0.0003084602],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694014,0.00059143134,0.00037986436,0.0013841644,0.000091852045,0.00061255944],"domain_scores_gemma":[0.99747,0.00040843908,0.0006034057,0.0008468164,0.00039148767,0.0002798051],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007206075,0.00044820845,0.00056213146,0.00017042717,0.0002876111,0.00025436236,0.0018450354,0.0003170878,0.000017310209],"category_scores_gemma":[0.00044471596,0.0005330066,0.0003825855,0.00064112403,0.00008877637,0.00038427184,0.0018438514,0.0006927816,0.000013842319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010222976,0.000027997863,0.00006993089,0.00006696248,0.0001907774,0.000032231714,0.00016347415,0.9251369,0.00005337553,0.070872195,0.000024206838,0.0032596958],"study_design_scores_gemma":[0.0014288047,0.00011983707,0.000039554645,0.000043838896,0.000163897,9.799412e-7,0.000043317366,0.9881786,0.00007260835,0.00761522,0.0017690855,0.0005242376],"about_ca_topic_score_codex":0.000047029156,"about_ca_topic_score_gemma":0.000004314425,"teacher_disagreement_score":0.6234502,"about_ca_system_score_codex":0.00050857425,"about_ca_system_score_gemma":0.00022536117,"threshold_uncertainty_score":0.99971217},"labels":[],"label_agreement":null},{"id":"W3093727384","doi":"10.48550/arxiv.2010.10577","title":"Structured Online Learning-based Control of Continuous-time Nonlinear Systems","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Parameterized complexity; Benchmark (surveying); Optimal control; Bounded function; Nonlinear system; Mathematical optimization; Function (biology); Mathematics; Algorithm; Artificial intelligence","score_opus":0.027668265216133397,"score_gpt":0.17730922188356374,"score_spread":0.14964095666743035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093727384","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056646846,0.00013826697,0.94071263,0.00021100114,0.0004947498,0.0008703814,0.00022209315,0.0005834918,0.00012051872],"genre_scores_gemma":[0.99415183,0.000007900905,0.0048748786,0.000104396655,0.00014017969,0.0000019063611,0.00012485142,0.000043098982,0.0005509765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968293,0.0005108036,0.00050547556,0.0014175385,0.0002325191,0.0005044151],"domain_scores_gemma":[0.99648523,0.00034630054,0.0010281339,0.0012909515,0.00056777586,0.00028159496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030533408,0.0005417358,0.0011422461,0.00028912953,0.000110049295,0.00012794002,0.0028128857,0.0004438805,0.000013571428],"category_scores_gemma":[0.00022981931,0.00061113253,0.00044417803,0.0005599749,0.00023445222,0.00019068569,0.00084348617,0.0011932869,0.000049124603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018604996,0.00017373318,0.002546174,0.00018558548,0.00041412338,0.00039044145,0.000096735195,0.97865725,0.0006937527,0.015799308,0.000038064834,0.00081876817],"study_design_scores_gemma":[0.0023366457,0.000273945,0.0005409446,0.00013706376,0.0001799311,0.0000031892923,0.000042506792,0.9941083,0.000049347782,0.0010583198,0.0007489373,0.00052084494],"about_ca_topic_score_codex":0.00021834475,"about_ca_topic_score_gemma":0.000014489166,"teacher_disagreement_score":0.93750495,"about_ca_system_score_codex":0.00021958444,"about_ca_system_score_gemma":0.0004761648,"threshold_uncertainty_score":0.999634},"labels":[],"label_agreement":null},{"id":"W3111828395","doi":"10.1109/twc.2020.3022705","title":"Centralized and Distributed Deep Reinforcement Learning Methods for Downlink Sum-Rate Optimization","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Wireless Communications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Telecommunications link; Mathematical optimization; Maximization; Convergence (economics); Optimization problem; Transmitter power output; Artificial intelligence; Algorithm; Mathematics","score_opus":0.03467231661912773,"score_gpt":0.3130906819506749,"score_spread":0.2784183653315472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111828395","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054133063,0.00012334295,0.989764,0.008756427,0.00009347905,0.0007561928,0.00001900429,0.00039998555,0.000033474866],"genre_scores_gemma":[0.5523112,0.00029568307,0.4467357,0.00029071217,0.000007183801,0.00026518552,0.000055708057,0.000014473502,0.000024188294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836266,0.0004929765,0.0003808937,0.00035903754,0.000111633904,0.0002927928],"domain_scores_gemma":[0.9976309,0.0008742348,0.00017304618,0.0009335223,0.00020351305,0.00018476897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039628078,0.00019534444,0.0002494083,0.0000861023,0.0008064196,0.00017920633,0.001100736,0.00008792395,0.0000067611377],"category_scores_gemma":[0.000057861143,0.0002087872,0.00011254812,0.0004961216,0.00013120526,0.00038079973,0.000026857959,0.0003751583,0.000004648353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039496965,0.000078249715,0.000004659868,0.000016501534,0.00008126676,2.2686575e-7,0.00083481224,0.8430474,0.00087723386,0.00843057,0.000006993629,0.1465826],"study_design_scores_gemma":[0.0010170254,0.0001543323,0.000011928974,0.00001730823,0.00005309659,0.0000017048342,0.000088859204,0.99508053,0.00079186074,0.00013187026,0.0024432393,0.00020825185],"about_ca_topic_score_codex":0.000021086002,"about_ca_topic_score_gemma":0.000013720215,"teacher_disagreement_score":0.552257,"about_ca_system_score_codex":0.000089437155,"about_ca_system_score_gemma":0.00005825222,"threshold_uncertainty_score":0.8514095},"labels":[],"label_agreement":null},{"id":"W3112168663","doi":"10.1109/smc42975.2020.9283399","title":"Trajectory Tracking of Underactuated Sea Vessels With Uncertain Dynamics: An Integral Reinforcement Learning Approach","year":2020,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Rudder; Trajectory; Underactuation; Reinforcement learning; Control theory (sociology); Computer science; Tracking error; Tracking (education); Gradient descent; Process (computing); Thrust; Artificial intelligence; Robot; Control (management); Engineering; Artificial neural network; Physics","score_opus":0.028883624396327835,"score_gpt":0.24761960009628142,"score_spread":0.2187359756999536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112168663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021251148,0.000015073928,0.9751602,0.0003948731,0.000026780954,0.00032684157,8.7038046e-7,0.0003846626,0.002439568],"genre_scores_gemma":[0.89822465,0.0000010641738,0.10130712,0.0002586761,0.000022923472,0.000016225116,0.000047154015,0.000019268566,0.00010289019],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998212,0.00014701148,0.000337037,0.00052415807,0.00040932064,0.00037049298],"domain_scores_gemma":[0.9989981,0.00008876412,0.00020961222,0.0003437526,0.00017004789,0.0001896951],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003003011,0.0002319225,0.00031641545,0.00008990116,0.0001003733,0.00013011922,0.0008518406,0.00006584372,0.00001492649],"category_scores_gemma":[0.00006333916,0.00018288477,0.00006711143,0.0005125453,0.000096348,0.0007561144,0.000121613804,0.0003897064,0.000005870345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020883279,0.00021574495,0.0033568223,0.00010687157,0.000241597,0.000034226745,0.009548823,0.72333235,0.0014544884,0.11928879,0.000022102431,0.14218938],"study_design_scores_gemma":[0.0006863962,0.0008801451,0.00029898394,0.00002047192,0.000015294503,0.000007891748,0.0015441419,0.9959009,0.00025631598,0.00009792543,0.00005197326,0.0002395079],"about_ca_topic_score_codex":0.0002052925,"about_ca_topic_score_gemma":0.00005068503,"teacher_disagreement_score":0.8769735,"about_ca_system_score_codex":0.00014725114,"about_ca_system_score_gemma":0.00016936281,"threshold_uncertainty_score":0.74578243},"labels":[],"label_agreement":null},{"id":"W3183314948","doi":"10.23919/acc50511.2021.9482670","title":"A Structured Online Learning Approach to Nonlinear Tracking with Unknown Dynamics","year":2021,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science","keywords":"Computer science; Nonlinear system; Benchmark (surveying); Controller (irrigation); Iterative learning control; Control theory (sociology); Reinforcement learning; Optimal control; Online model; System dynamics; Parameterized complexity; Tracking (education); Function (biology); Mathematical optimization; Artificial intelligence; Mathematics; Algorithm; Control (management)","score_opus":0.011084799240474508,"score_gpt":0.23377520321328252,"score_spread":0.222690403972808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183314948","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028693132,0.000033603763,0.9670634,0.0007772808,0.00008656666,0.00020386666,0.000004127166,0.00041797129,0.0027199998],"genre_scores_gemma":[0.41232985,7.347086e-7,0.58569753,0.000316254,0.000051200015,0.000007794619,0.000041733598,0.000017176195,0.0015377585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981836,0.00009054452,0.00022017222,0.0006899064,0.00036599115,0.00044976475],"domain_scores_gemma":[0.99878365,0.000068178495,0.00007628418,0.0005697982,0.00032463577,0.00017748057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016054786,0.00022036773,0.00026529425,0.00009673888,0.00014733277,0.00029500053,0.00071237574,0.00007120449,0.0000054658453],"category_scores_gemma":[0.0001240511,0.00017942452,0.00006407719,0.0008880035,0.000036425194,0.00029487262,0.0003466535,0.00038360155,0.000009018392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003985742,0.0005015272,0.0023777715,0.000033453987,0.00016047906,0.00018426629,0.001494114,0.06680427,0.0010053064,0.22008762,0.000027596923,0.70728374],"study_design_scores_gemma":[0.00050741306,0.0001215541,0.0014372707,0.000017215436,0.00001140072,0.000117579955,0.0002762123,0.99437904,0.00013148406,0.00020010369,0.0025180036,0.00028274805],"about_ca_topic_score_codex":0.000024937837,"about_ca_topic_score_gemma":0.00040434892,"teacher_disagreement_score":0.92757475,"about_ca_system_score_codex":0.00012763993,"about_ca_system_score_gemma":0.00016683954,"threshold_uncertainty_score":0.7316719},"labels":[],"label_agreement":null},{"id":"W3203907149","doi":"10.1139/juvs-2021-0010","title":"Quadrotor motion control using deep reinforcement learning","year":2021,"lang":"en","type":"article","venue":"Journal of Unmanned Vehicle Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Controller (irrigation); Computer science; Control theory (sociology); Artificial neural network; Artificial intelligence; Control (management); Control engineering; Engineering","score_opus":0.01483512746151684,"score_gpt":0.24576967930088872,"score_spread":0.2309345518393719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203907149","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039961908,0.0010133844,0.9572172,0.00029548543,0.0011260511,0.00022841897,2.4700532e-7,0.0000491156,0.00010814957],"genre_scores_gemma":[0.9941618,0.0000075293774,0.005149916,0.00007703849,0.00037068754,0.000005375927,6.361768e-7,0.000015830477,0.0002112171],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974141,0.00046515517,0.0008601488,0.00022845944,0.00066376134,0.0003683381],"domain_scores_gemma":[0.99742335,0.0001489846,0.0010177036,0.00031992295,0.0009169798,0.000173036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012748243,0.00016835607,0.00044159754,0.00016984438,0.00018482014,0.00032583502,0.00052900944,0.00008947674,0.0000048652555],"category_scores_gemma":[0.00026392558,0.00015354287,0.00020900476,0.00034981812,0.000027049673,0.00078625296,0.000095056916,0.00038593504,0.0000131759725],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007853097,0.00011690164,0.003489396,0.00007806715,0.00033466145,0.0006225512,0.00070283446,0.93273276,0.03454915,0.011172804,0.000037132428,0.016085228],"study_design_scores_gemma":[0.0018905747,0.00027184354,0.00043752353,0.00015702497,0.000037050086,0.0005918456,0.00031536596,0.99463695,0.00040219724,0.000090965455,0.0010110368,0.00015760092],"about_ca_topic_score_codex":0.000032299627,"about_ca_topic_score_gemma":0.0000026989042,"teacher_disagreement_score":0.95419985,"about_ca_system_score_codex":0.00032355095,"about_ca_system_score_gemma":0.00019089378,"threshold_uncertainty_score":0.6261297},"labels":[],"label_agreement":null},{"id":"W3215476862","doi":"10.1109/rose52750.2021.9611772","title":"A Data-Driven Model-Reference Adaptive Control Approach Based on Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Universiti Kebangsaan Malaysia","keywords":"Reference model; Reinforcement learning; Computer science; Process (computing); Adaptive control; Control theory (sociology); Backstepping; Lyapunov function; Trajectory; System dynamics; Control (management); Control engineering; Artificial intelligence; Nonlinear system; Engineering","score_opus":0.06948349707183171,"score_gpt":0.2767778434236618,"score_spread":0.20729434635183008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215476862","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000046281744,0.00006345106,0.9801641,0.00047229783,0.00021641914,0.0013211013,0.000055700973,0.0007217579,0.016938856],"genre_scores_gemma":[0.618903,0.0000051634906,0.3784654,0.0009789158,0.000046135512,0.00026041936,0.0006900843,0.000030935138,0.00061997067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99414593,0.00043091457,0.00071966596,0.002665156,0.0012229937,0.0008153411],"domain_scores_gemma":[0.9933246,0.00030844094,0.0005705833,0.004714481,0.00081638165,0.00026553444],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00096288975,0.0007587092,0.0009316031,0.0002648464,0.00018708028,0.0008079718,0.006029829,0.00043059877,0.000023637675],"category_scores_gemma":[0.00036923305,0.0007022551,0.00020070391,0.00033997605,0.00010772596,0.0005131926,0.00591955,0.0022585657,0.000033920718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054992946,0.00015461573,0.000011961082,0.000038772836,0.00016853938,0.000026362959,0.00018535132,0.9598326,0.000014110134,0.029536411,0.0001306367,0.009845611],"study_design_scores_gemma":[0.0013557137,0.00022349552,0.000019369032,0.00014844087,0.00007219231,0.0000026450462,0.00007468905,0.9967347,0.000005358566,0.00027823835,0.0003525016,0.000732671],"about_ca_topic_score_codex":0.00015394099,"about_ca_topic_score_gemma":0.000024385023,"teacher_disagreement_score":0.61885667,"about_ca_system_score_codex":0.00039307948,"about_ca_system_score_gemma":0.0016201928,"threshold_uncertainty_score":0.99954283},"labels":[],"label_agreement":null},{"id":"W4210630976","doi":"10.3390/math10030499","title":"Optimal Reinforcement Learning-Based Control Algorithm for a Class of Nonlinear Macroeconomic Systems","year":2022,"lang":"en","type":"article","venue":"Mathematics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Natural Science Foundation of China; Education Department of Hunan Province","keywords":"Reinforcement learning; Nonlinear system; Control theory (sociology); Controller (irrigation); Optimal control; Computer science; Control (management); Class (philosophy); Mathematical optimization; Control engineering; Artificial intelligence; Mathematics; Engineering","score_opus":0.010665227900336085,"score_gpt":0.2329612270568643,"score_spread":0.22229599915652823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210630976","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011531368,0.000055913548,0.9970668,0.00014677721,0.00023284162,0.0010830058,0.000036242887,0.000119928474,0.000105328625],"genre_scores_gemma":[0.5071912,4.0938002e-7,0.49147943,0.00008534931,0.000040016876,0.00061901857,0.000015825084,0.000024868079,0.00054391765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985685,0.00006722444,0.0005228881,0.00025063485,0.00028066672,0.0003101396],"domain_scores_gemma":[0.99851793,0.00038692114,0.00047495132,0.000448526,0.000113859285,0.000057814283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008267053,0.00015625039,0.00038247852,0.000107383625,0.00018173234,0.000067344154,0.000796493,0.000033304987,0.000011220557],"category_scores_gemma":[0.000060053982,0.0001601715,0.00014944059,0.00012334765,0.00004460838,0.000079301426,0.00015345305,0.00016238309,0.000007348902],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000147536575,0.0001609631,0.000008910304,0.00012270651,0.00008803892,0.0000041602716,0.00042794464,0.9727382,0.00011722924,0.01948236,0.00009314422,0.0067415675],"study_design_scores_gemma":[0.0018353887,0.00056773954,9.997776e-7,0.000015028317,0.000026791678,0.00001016847,0.00021821744,0.99094564,0.00008561191,0.00017689617,0.0059626466,0.00015485146],"about_ca_topic_score_codex":0.000009782207,"about_ca_topic_score_gemma":3.868983e-7,"teacher_disagreement_score":0.506038,"about_ca_system_score_codex":0.00017868659,"about_ca_system_score_gemma":0.0001400996,"threshold_uncertainty_score":0.65316045},"labels":[],"label_agreement":null},{"id":"W4220820327","doi":"10.1177/09596518221080323","title":"Reinforcement learning-based optimal fault-tolerant control for offshore platforms","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Actuator; Control theory (sociology); Fault tolerance; Reinforcement learning; Submarine pipeline; Observer (physics); Controller (irrigation); Engineering; Fault (geology); Control engineering; Computer science; Control (management); Reliability engineering; Artificial intelligence","score_opus":0.0074439450085303106,"score_gpt":0.19331800724330708,"score_spread":0.18587406223477676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220820327","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021003261,0.0004928329,0.97669464,0.00025190745,0.00085578696,0.00064806273,0.000009536965,0.000037017468,0.0000069365874],"genre_scores_gemma":[0.9968598,0.0000052867103,0.0028953906,0.000027959795,0.00009792419,0.00008522107,5.441592e-7,0.000014081084,0.000013788224],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794686,0.00001011056,0.00093925424,0.00017665049,0.0006391969,0.0002879235],"domain_scores_gemma":[0.9982124,0.00015649275,0.00089160004,0.00011211687,0.000509671,0.000117699696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016153683,0.00020644223,0.0006117203,0.00019705833,0.0001614271,0.000048312035,0.0007321623,0.000068824054,9.988776e-7],"category_scores_gemma":[0.00035151726,0.00015532383,0.0002873509,0.00023133309,0.0000419664,0.00033202552,0.000098011114,0.00041776928,6.226905e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019116266,0.000034973436,0.000022611925,0.0001659123,0.00016574412,0.0000012291587,0.000080609905,0.8908588,0.0062557813,0.10190074,0.000015262054,0.00030714576],"study_design_scores_gemma":[0.0043356298,0.0009080412,0.000017650265,0.0002281798,0.000091176604,0.000077628174,0.00014975872,0.9907616,0.0010482301,0.00004612997,0.002183476,0.00015253073],"about_ca_topic_score_codex":0.0000042843217,"about_ca_topic_score_gemma":6.39981e-8,"teacher_disagreement_score":0.97585654,"about_ca_system_score_codex":0.00014180016,"about_ca_system_score_gemma":0.00011398756,"threshold_uncertainty_score":0.63339216},"labels":[],"label_agreement":null},{"id":"W4244440630","doi":"10.1109/cac53003.2021.9727718","title":"Value Iteration-based Zero-sum Neuro-optimal Control of Modular and Reconfigurable Robots via Adaptive Dynamic Programming","year":2021,"lang":"en","type":"article","venue":"2021 China Automation Congress (CAC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"National Natural Science Foundation of China","keywords":"Dynamic programming; Control theory (sociology); Optimal control; Bellman equation; Convergence (economics); Modular design; Artificial neural network; Mathematics; Iterated function; Lyapunov function; Dimension (graph theory); Adaptive control; Mathematical optimization; Computer science; Control (management); Nonlinear system; Artificial intelligence; Mathematical analysis","score_opus":0.005959237061519206,"score_gpt":0.22257855529873455,"score_spread":0.21661931823721534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244440630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026989862,0.0005664946,0.96926045,0.0012867439,0.00062736036,0.0008289249,0.00003094463,0.0002834117,0.00012579231],"genre_scores_gemma":[0.8918385,0.00000782194,0.10753241,0.00019725543,0.000033528107,0.00012598572,0.00006597546,0.000034069864,0.0001644721],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670964,0.00052691804,0.0007436653,0.00092773995,0.0005678283,0.00052419136],"domain_scores_gemma":[0.997295,0.00045689446,0.0005904712,0.00082811946,0.0006492835,0.0001802173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005360337,0.00039979315,0.0006119323,0.00023711017,0.00028055516,0.00046451142,0.0005548146,0.00016848736,0.00003596045],"category_scores_gemma":[0.0003512976,0.00042529637,0.0001795297,0.0006490433,0.0001669416,0.001011507,0.00009791779,0.0003067317,0.000014072462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012471422,0.0005377496,0.0012721221,0.00020485139,0.00040207422,0.00026990293,0.001007988,0.34808302,0.03178703,0.03496368,0.00005945994,0.58128744],"study_design_scores_gemma":[0.0021130291,0.0002305985,0.0046995557,0.00013170196,0.000063742606,0.00004368285,0.000026390697,0.9879007,0.003169654,0.00097329734,0.00026229213,0.00038540363],"about_ca_topic_score_codex":0.000066659486,"about_ca_topic_score_gemma":0.000028868502,"teacher_disagreement_score":0.8648486,"about_ca_system_score_codex":0.00012901243,"about_ca_system_score_gemma":0.00035039498,"threshold_uncertainty_score":0.9998199},"labels":[],"label_agreement":null},{"id":"W4293057750","doi":"10.1109/vtc2022-spring54318.2022.9861023","title":"Energy- and Cost-Efficient Transmission Strategy in Networked UAV Control System with ADP Trajectory Tracking Control","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Research and Development; National Natural Science Foundation of China","keywords":"Computer science; Energy consumption; Benchmark (surveying); Trajectory; Transmission (telecommunications); Real-time computing; Model predictive control; Control (management); Control theory (sociology); Engineering; Artificial intelligence; Telecommunications","score_opus":0.009365597415460381,"score_gpt":0.20902034867646765,"score_spread":0.19965475126100726,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293057750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13055494,0.0026670948,0.86217815,0.0010764713,0.00042356548,0.0017700997,0.000027104288,0.0011324517,0.0001701228],"genre_scores_gemma":[0.9957789,0.00003595251,0.0018259364,0.0002530726,0.000052982403,0.0018815151,0.000006063062,0.00007645527,0.00008911332],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99402153,0.00069169217,0.0009533076,0.0018291296,0.0010322625,0.0014720636],"domain_scores_gemma":[0.99741006,0.0002436769,0.000528117,0.0012753234,0.00026094134,0.0002818763],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014544581,0.000767931,0.0011936591,0.0011001658,0.0008068592,0.00024802086,0.002143243,0.00044785085,0.000029207757],"category_scores_gemma":[0.000028985789,0.00074300676,0.00018749812,0.0018916327,0.0004811355,0.00027895416,0.00035452895,0.0017309444,0.0000043903437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077582465,0.00085339113,0.0073585203,0.00015804965,0.000621845,0.002837503,0.0006021825,0.3543028,0.017865026,0.32483062,0.000055856395,0.2897384],"study_design_scores_gemma":[0.008102933,0.00094529387,0.0018947837,0.00015405566,0.00010494471,0.00027957125,0.0009194009,0.9824686,0.00023214766,0.00035660266,0.0036710931,0.00087056874],"about_ca_topic_score_codex":0.00035739216,"about_ca_topic_score_gemma":0.0003176789,"teacher_disagreement_score":0.86522394,"about_ca_system_score_codex":0.00071005325,"about_ca_system_score_gemma":0.00060924597,"threshold_uncertainty_score":0.9995021},"labels":[],"label_agreement":null},{"id":"W4294690836","doi":"10.23919/acc53348.2022.9867729","title":"Structured Online Learning for Low-Level Control of Quadrotors","year":2022,"lang":"en","type":"article","venue":"2022 American Control Conference (ACC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Controller (irrigation); Reinforcement learning; Artificial neural network; Identifier; Set (abstract data type); Control engineering; Parameterized complexity; Control theory (sociology); Artificial intelligence; Control (management); Engineering; Algorithm","score_opus":0.01740815177442727,"score_gpt":0.2586946933443374,"score_spread":0.24128654156991014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294690836","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.041813202,0.0001457594,0.953084,0.0015895755,0.00049497106,0.0018522468,0.00064568943,0.00028496023,0.000089607005],"genre_scores_gemma":[0.98514676,0.0000055489077,0.012230152,0.0010592338,0.00010901636,0.0009721842,0.00006970654,0.000050145918,0.00035722723],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956869,0.0007108411,0.00083216705,0.0009893809,0.00086852943,0.00091218273],"domain_scores_gemma":[0.995999,0.0010604718,0.0012134571,0.00092720095,0.0005681232,0.00023175923],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008658804,0.00046235192,0.0011806866,0.0003391065,0.00052082003,0.00012902114,0.0024443793,0.000059419774,0.0001662594],"category_scores_gemma":[0.00065626495,0.0004822164,0.0004008086,0.0008611748,0.0004205617,0.00031679904,0.000458703,0.0007921812,0.0000045607153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014110141,0.0006383317,0.009268006,0.00006579001,0.00084662257,0.000043966465,0.0016369359,0.020796545,0.03369725,0.07823071,0.00029683986,0.853068],"study_design_scores_gemma":[0.00744717,0.0022112362,0.00730489,0.000016618762,0.00010510062,0.000018757868,0.0014409128,0.9706376,0.00011290826,0.0017322728,0.008281588,0.0006909463],"about_ca_topic_score_codex":0.00048833183,"about_ca_topic_score_gemma":0.000112247035,"teacher_disagreement_score":0.9498411,"about_ca_system_score_codex":0.00025264348,"about_ca_system_score_gemma":0.00066434534,"threshold_uncertainty_score":0.99976295},"labels":[],"label_agreement":null},{"id":"W4296473542","doi":"10.1109/access.2022.3208058","title":"Regulation With Guaranteed Convergence Rate for Continuous-Time Systems With Completely Unknown Dynamics in the Presence of Disturbance","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Engineering and Physical Sciences Research Council; National Centre for Nuclear Robotics","keywords":"Convergence (economics); Computer science; Rate of convergence; Function (biology); Mathematical optimization; Algorithm; Mathematics","score_opus":0.015457998732045876,"score_gpt":0.2453259712901463,"score_spread":0.22986797255810043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296473542","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1192175,0.000075660304,0.87820876,0.00035465395,0.0002384884,0.00167278,0.000047202222,0.00006050208,0.00012446151],"genre_scores_gemma":[0.997155,7.616772e-7,0.0019018212,0.000094386996,0.000020494661,0.0006038536,0.000013695999,0.000014058639,0.00019590628],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981516,0.0003204645,0.0003274337,0.00043155902,0.0004583341,0.00031063159],"domain_scores_gemma":[0.99805653,0.00060875615,0.0004261632,0.00066809537,0.00021346117,0.000027014134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000891924,0.00016983971,0.00031601472,0.00008331764,0.00020413287,0.00018469269,0.002475784,0.000023745923,0.0000020272312],"category_scores_gemma":[0.000036710597,0.000115729024,0.000037593672,0.0007365471,0.00016827059,0.00054025266,0.00016214333,0.00015985659,8.1248476e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028588076,0.0007860221,0.078396596,0.00047891677,0.00029298227,0.00013026156,0.004920343,0.46922484,0.002285062,0.42898306,0.00095764425,0.010685459],"study_design_scores_gemma":[0.0010590934,0.0004313979,0.007855204,0.000056467376,0.000014190447,0.000024257928,0.00016186268,0.989102,0.00005197754,0.0005197576,0.00054075255,0.00018302907],"about_ca_topic_score_codex":0.0003659159,"about_ca_topic_score_gemma":0.00019983141,"teacher_disagreement_score":0.8779375,"about_ca_system_score_codex":0.0001434661,"about_ca_system_score_gemma":0.00010546525,"threshold_uncertainty_score":0.47192928},"labels":[],"label_agreement":null},{"id":"W4308902993","doi":"10.1016/j.automatica.2022.110685","title":"Model-free optimal control of discrete-time systems with additive and multiplicative noises","year":2022,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Algebraic Riccati equation; Multiplicative function; Reinforcement learning; Optimal control; Discrete time and continuous time; Mathematics; Stochastic control; Mathematical optimization; Convergence (economics); Iterative learning control; Markov decision process; Controller (irrigation); Control theory (sociology); Riccati equation; Computer science; Control (management); Markov process; Artificial intelligence","score_opus":0.005472723485347404,"score_gpt":0.20316843514690344,"score_spread":0.19769571166155603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308902993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01791653,0.00018280487,0.97966236,0.0004390115,0.000027253833,0.00083062926,0.00025809783,0.00025132037,0.00043199555],"genre_scores_gemma":[0.9112527,0.0000010367892,0.088084206,0.00005684419,0.000008509615,0.0004587302,0.000006124767,0.000014972905,0.00011692481],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984453,0.00017205729,0.00027691678,0.00039340102,0.0004322759,0.00028007315],"domain_scores_gemma":[0.99830955,0.00048171647,0.0002714187,0.00072857563,0.000117652955,0.00009109327],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027811524,0.00017858169,0.0003802846,0.00008610889,0.00019292218,0.000063455744,0.0009594376,0.000026397829,0.000009883095],"category_scores_gemma":[0.000095845186,0.00014682078,0.000046494402,0.00022542365,0.00020890962,0.00027416222,0.0006057485,0.00014663982,0.000004906896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006214969,0.00096977095,0.00069945795,0.0002146216,0.0016698645,0.00013779402,0.017429642,0.36134937,0.0038833912,0.5592153,0.0016754074,0.052133847],"study_design_scores_gemma":[0.0015453972,0.0004696646,0.00038797458,0.000024112953,0.00003868133,0.000029990408,0.0002413564,0.9963269,0.000028249853,0.000640495,0.00008667986,0.00018046907],"about_ca_topic_score_codex":0.000030049167,"about_ca_topic_score_gemma":0.0000013447885,"teacher_disagreement_score":0.8933361,"about_ca_system_score_codex":0.00007571077,"about_ca_system_score_gemma":0.000105182655,"threshold_uncertainty_score":0.59871775},"labels":[],"label_agreement":null},{"id":"W4310607898","doi":"10.1002/9781119808602.ch9","title":"An Application to Low‐level Control of Quadrotors","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Position (finance); Control (management); Stability (learning theory); Sequence (biology); Control engineering; Control theory (sociology); Artificial intelligence; Engineering; Machine learning","score_opus":0.007858356877669302,"score_gpt":0.2499228687523096,"score_spread":0.2420645118746403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310607898","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029159312,0.000035634283,0.92311543,0.00016559979,0.00014054983,0.0013941161,0.000053605174,0.0004389669,0.0746532],"genre_scores_gemma":[0.22801806,0.0000034423108,0.31443632,0.0023884685,0.0003447301,0.0026712052,0.000090775255,0.0006070039,0.45144],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985267,0.00008770025,0.00023047585,0.0005576185,0.00036912487,0.00022840376],"domain_scores_gemma":[0.9982686,0.00004432742,0.00023688091,0.0012806264,0.000047761296,0.00012178787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024137918,0.00020134111,0.0003314962,0.00029279524,0.00003186882,0.000032023687,0.0018220263,0.00010371008,0.0007225687],"category_scores_gemma":[0.000019712425,0.00019473127,0.000076902914,0.0003260749,0.000030424457,0.00006815009,0.0001853982,0.00012758806,0.00009604992],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028893648,0.0004875526,0.00042941823,0.00006854816,0.00019919402,0.000007880177,0.00027635455,0.00044779514,0.0013320538,0.3596815,0.079952784,0.557088],"study_design_scores_gemma":[0.0009701354,0.000434348,0.00029077881,0.00002226975,0.000023507888,0.000003028347,0.0000314143,0.19045126,0.00003494815,0.000784345,0.8063632,0.0005907201],"about_ca_topic_score_codex":0.00068101677,"about_ca_topic_score_gemma":0.00019503443,"teacher_disagreement_score":0.72641045,"about_ca_system_score_codex":0.0000848035,"about_ca_system_score_gemma":0.00008614761,"threshold_uncertainty_score":0.79409105},"labels":[],"label_agreement":null},{"id":"W4310607962","doi":"10.1002/9781119808602.ch6","title":"A Structured Online Learning Approach to Nonlinear Tracking with Unknown Dynamics","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Trajectory; Tracking (education); Identification (biology); Nonlinear system; Variety (cybernetics); Process (computing); Online model; Quadratic equation; Control (management); Artificial intelligence; Control theory (sociology); Mathematical optimization; Mathematics","score_opus":0.009120678008927265,"score_gpt":0.2278479429374062,"score_spread":0.21872726492847894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310607962","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000020774376,0.00007808262,0.7871094,0.00016196257,0.00016611123,0.0006932029,0.0000378699,0.0013241018,0.21040851],"genre_scores_gemma":[0.0009970178,0.000002679979,0.60549164,0.00027197495,0.00017813039,0.000057647914,0.00033002108,0.00039127443,0.3922796],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716043,0.00013902257,0.0002704338,0.0011483907,0.00068117754,0.0006005143],"domain_scores_gemma":[0.99842626,0.000051072635,0.00028021078,0.000976778,0.00007182576,0.00019386083],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019899258,0.000525528,0.00056854833,0.0005026082,0.00015617536,0.00023016921,0.0020410167,0.00019689133,0.000301772],"category_scores_gemma":[0.000052461008,0.00043403212,0.000109446926,0.0008942578,0.00005711209,0.00010954146,0.00081714924,0.0010217797,0.000018674527],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081648526,0.0008799771,0.0006843249,0.00019966859,0.000907442,0.00019653224,0.0013674414,0.033703808,0.00001632529,0.15765126,0.018727142,0.78558445],"study_design_scores_gemma":[0.00044045932,0.00021263091,0.00003980166,0.000030410807,0.000024781755,0.00004107608,0.00012463117,0.62679327,3.1556044e-7,0.00003621518,0.37172103,0.0005353869],"about_ca_topic_score_codex":0.00021367815,"about_ca_topic_score_gemma":0.001305876,"teacher_disagreement_score":0.785049,"about_ca_system_score_codex":0.0003360235,"about_ca_system_score_gemma":0.0001652792,"threshold_uncertainty_score":0.9998112},"labels":[],"label_agreement":null},{"id":"W4310613884","doi":"10.1002/9781119808602.ch5","title":"Structured Online Learning‐Based Control of Continuous‐Time Nonlinear Systems","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Benchmark (surveying); Reinforcement learning; Computer science; Nonlinear system; Stability (learning theory); Riccati equation; Optimal control; Identification (biology); Algebraic Riccati equation; Control theory (sociology); Control (management); Algorithm; Differential equation; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning","score_opus":0.004773300130568655,"score_gpt":0.21334127737555086,"score_spread":0.20856797724498222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310613884","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015721867,0.0012887333,0.9269885,0.00018201015,0.0008352033,0.0015589995,0.00047353024,0.001671988,0.06698536],"genre_scores_gemma":[0.020618195,0.00000683243,0.059173647,0.00032455983,0.00043386105,0.00010486187,0.00046831957,0.00060228794,0.9182674],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694484,0.00044066695,0.00057714083,0.00079007377,0.0007607329,0.00048655024],"domain_scores_gemma":[0.99733675,0.000256502,0.00097153394,0.0011572622,0.00014823489,0.00012973187],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036721284,0.00049330085,0.001175499,0.0004651042,0.0000707143,0.000091983246,0.0019961337,0.00029495123,0.0024783956],"category_scores_gemma":[0.00014557646,0.0004430111,0.00027278837,0.0003614001,0.00012294226,0.00006146554,0.00023622243,0.00065265724,0.000063971194],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074354734,0.0047402857,0.0069572306,0.0025545422,0.0094159115,0.0011806074,0.00071984384,0.085080326,0.005350252,0.09230869,0.5835032,0.20744558],"study_design_scores_gemma":[0.0016254942,0.00025202366,0.000021311704,0.000046771413,0.000045964334,0.000006499962,0.000019142222,0.5639686,0.0000034101909,0.000010594175,0.43366784,0.0003323316],"about_ca_topic_score_codex":0.000529763,"about_ca_topic_score_gemma":0.00004570862,"teacher_disagreement_score":0.8678148,"about_ca_system_score_codex":0.000113944414,"about_ca_system_score_gemma":0.00024197296,"threshold_uncertainty_score":0.9998022},"labels":[],"label_agreement":null},{"id":"W4310613925","doi":"10.1002/9781119808602.ch3","title":"Reinforcement Learning","year":2022,"lang":"en","type":"other","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Markov decision process; Dynamic programming; Optimal control; Mathematical proof; Computer science; Bellman equation; Mathematical optimization; Class (philosophy); Stochastic control; Control (management); Field (mathematics); Markov process; Mathematics; Artificial intelligence","score_opus":0.00743149318627673,"score_gpt":0.22072598638547652,"score_spread":0.2132944931991998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310613925","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.2134265e-9,0.00009080883,0.4878463,0.0000752249,0.00014978359,0.00010512513,1.2741205e-7,0.00070773927,0.5110249],"genre_scores_gemma":[0.0002855639,0.00001007013,0.026647387,0.00026370518,0.000064854445,0.000055622073,0.000011833497,0.00012812893,0.9725328],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99900955,0.00004692594,0.00010315217,0.0003261907,0.0002929031,0.00022129377],"domain_scores_gemma":[0.99931335,0.00002189128,0.00012225933,0.00049020414,0.0000082686465,0.00004403405],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012876265,0.00014593784,0.00015081784,0.00016344688,0.000061108454,0.000059698457,0.0009913045,0.000057465317,0.013710256],"category_scores_gemma":[0.00001937704,0.00013739738,0.00006202855,0.00014877801,0.00001563048,0.000040102255,0.0007496803,0.00027887538,0.00036311604],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.2346853e-7,0.000011778064,0.000027335105,0.000008826082,0.0000658531,0.000027477885,0.000056240726,0.0006245389,0.0000015571514,0.25361443,0.6723215,0.07323975],"study_design_scores_gemma":[0.0001208772,0.000052481057,0.000001577555,0.0000050594826,0.0000031738,0.0000025140853,0.000008169451,0.06701202,2.579534e-7,0.00008734972,0.93255025,0.00015629713],"about_ca_topic_score_codex":0.00012365266,"about_ca_topic_score_gemma":0.000015066655,"teacher_disagreement_score":0.46150795,"about_ca_system_score_codex":0.000088695175,"about_ca_system_score_gemma":0.000047371595,"threshold_uncertainty_score":0.9871913},"labels":[],"label_agreement":null},{"id":"W4314946886","doi":"10.1109/cdc51059.2022.9992796","title":"Inverse Optimal Control with Discount Factor for Continuous and Discrete-Time Control-Affine Systems and Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Optimal control; Bellman equation; Control theory (sociology); Mathematics; Weighting; Mathematical optimization; Linear-quadratic-Gaussian control; Quadratic equation; Linear-quadratic regulator; Computer science; Control (management)","score_opus":0.011549548085453835,"score_gpt":0.232297176825317,"score_spread":0.22074762873986317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4314946886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.066405684,0.00059074134,0.927886,0.0012559466,0.0003941303,0.0028604623,0.00025424673,0.0001908526,0.00016193933],"genre_scores_gemma":[0.9956927,0.00006607617,0.001189866,0.00079151744,0.00008525459,0.00091071846,0.000015989792,0.00004585365,0.0012020385],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99584705,0.00040189887,0.00072135834,0.0012595414,0.0009613227,0.0008088477],"domain_scores_gemma":[0.99668103,0.0014440209,0.0005275211,0.00062215974,0.00030260833,0.00042265936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010928712,0.00061519205,0.001164131,0.00028717585,0.0009859144,0.00094820216,0.00070914585,0.000117769414,0.00008542189],"category_scores_gemma":[0.00023234606,0.0004932847,0.00012523426,0.00022688888,0.00028470825,0.0005359061,0.00027323765,0.0006100478,0.000008556913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.03255627,0.0008211927,0.0059373216,0.00022953986,0.0025026207,0.0005491423,0.004419155,0.15500264,0.02645045,0.14214316,0.0016408017,0.6277477],"study_design_scores_gemma":[0.023023358,0.0046974146,0.00077509397,0.000081588085,0.00013023106,0.00008517658,0.0005746139,0.96346956,0.000008605235,0.00020980574,0.0062963823,0.0006481568],"about_ca_topic_score_codex":0.000083607345,"about_ca_topic_score_gemma":0.000028106126,"teacher_disagreement_score":0.929287,"about_ca_system_score_codex":0.00014940155,"about_ca_system_score_gemma":0.00018031347,"threshold_uncertainty_score":0.99975187},"labels":[],"label_agreement":null},{"id":"W4315489024","doi":"10.1109/cdc51059.2022.9992565","title":"Thompson-Sampling Based Reinforcement Learning for Networked Control of Unknown Linear Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Linear-quadratic-Gaussian control; Reinforcement learning; Logarithm; Regret; Network packet; Bounded function; Control theory (sociology); Generalization; Controller (irrigation); Sampling (signal processing); Gaussian; Discrete mathematics; Mathematics; Computer science; Optimal control; Control (management); Mathematical optimization; Artificial intelligence; Mathematical analysis; Statistics; Telecommunications","score_opus":0.03500695118355131,"score_gpt":0.2775513208392075,"score_spread":0.24254436965565623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023122118,0.00046738496,0.9929781,0.000665938,0.00129972,0.0017651666,0.00003379037,0.00016794796,0.0003097577],"genre_scores_gemma":[0.99280214,0.000024260684,0.0049818447,0.00070905976,0.00013752416,0.0007954936,0.000017890687,0.000034180368,0.000497615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995978,0.0004731988,0.0009335377,0.0009005943,0.0010290145,0.0006856489],"domain_scores_gemma":[0.99547726,0.0023895246,0.00067770184,0.00077915465,0.00044505746,0.00023127587],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021639627,0.00040854828,0.00088789256,0.0003248076,0.000746449,0.00026269324,0.0012277921,0.00011008113,0.00007363776],"category_scores_gemma":[0.00031308425,0.00038188323,0.0002654167,0.00043658566,0.000101854734,0.00020716865,0.00020748917,0.0005881175,0.000007674893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015253787,0.00013602847,0.0001472533,0.0000315205,0.00012510737,0.000012159246,0.00013533825,0.77047545,0.0021526755,0.059020407,0.00014189273,0.16609678],"study_design_scores_gemma":[0.009562808,0.0016105075,0.00006420166,0.00009484644,0.000056149915,0.0000068508252,0.00016697249,0.9658297,0.000027647831,0.0006444361,0.021559937,0.00037597504],"about_ca_topic_score_codex":0.000038001923,"about_ca_topic_score_gemma":0.0000074371546,"teacher_disagreement_score":0.9904899,"about_ca_system_score_codex":0.00014833864,"about_ca_system_score_gemma":0.00028993026,"threshold_uncertainty_score":0.9998633},"labels":[],"label_agreement":null},{"id":"W4315489189","doi":"10.1109/cdc51059.2022.9992884","title":"Finite-time Event-triggered Control for a Class of Nonlinear Systems","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 61st Conference on Decision and Control (CDC)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Riccati equation; Control theory (sociology); Lyapunov function; Nonlinear system; Mathematics; Controller (irrigation); Linear-quadratic-Gaussian control; Differential equation; Computer science; Optimal control; Mathematical optimization; Control (management); Mathematical analysis; Artificial intelligence","score_opus":0.01897881529610653,"score_gpt":0.2593500047105889,"score_spread":0.24037118941448235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315489189","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0075377617,0.00051558897,0.98651147,0.0010648097,0.0011851093,0.002111302,0.0006773216,0.0001562488,0.0002403956],"genre_scores_gemma":[0.9943013,0.000022271184,0.0027547607,0.00092910335,0.00009779829,0.00087645283,0.000018826424,0.00003527803,0.00096420065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957719,0.0005069996,0.0009767371,0.0010050507,0.0010857844,0.0006535193],"domain_scores_gemma":[0.9946738,0.0028635515,0.0006362531,0.0010416823,0.00051857677,0.00026617694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001667039,0.00043018087,0.0010574834,0.00040039935,0.0004874381,0.00028758767,0.001607765,0.00013645396,0.00011087956],"category_scores_gemma":[0.00044578922,0.00039875307,0.00032676378,0.0004940911,0.00013387775,0.00026185837,0.00024315075,0.00045220036,0.000040426436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0089327125,0.0020058532,0.0003842629,0.00013039794,0.0009791468,0.00016289145,0.0007503846,0.034667786,0.03406202,0.26174042,0.005026786,0.6511574],"study_design_scores_gemma":[0.011460547,0.0017310512,0.00009635827,0.000055748005,0.00006728246,0.000015550922,0.00016380804,0.97405356,0.000047355523,0.0029412552,0.008962532,0.000404972],"about_ca_topic_score_codex":0.000041113064,"about_ca_topic_score_gemma":0.000008459428,"teacher_disagreement_score":0.98676354,"about_ca_system_score_codex":0.00013674298,"about_ca_system_score_gemma":0.00036231658,"threshold_uncertainty_score":0.99984646},"labels":[],"label_agreement":null},{"id":"W4315640849","doi":"10.3389/fnbot.2022.1102259","title":"Adaptive optimal output regulation for wheel-legged robot Ollie: A data-driven approach","year":2023,"lang":"en","type":"article","venue":"Frontiers in Neurorobotics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Tencent","keywords":"Control theory (sociology); Robot; Computer science; Robustness (evolution); Controller (irrigation); Control engineering; Control (management); Artificial intelligence; Engineering","score_opus":0.055405230323865996,"score_gpt":0.26913883205625166,"score_spread":0.21373360173238568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315640849","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026282002,0.00009358475,0.9948314,0.00095101015,0.0018792821,0.001222963,0.000049190665,0.00056587846,0.0001438961],"genre_scores_gemma":[0.11616757,0.000019571798,0.8821953,0.00014874573,0.00014139246,0.00011632543,0.00022852744,0.00005277634,0.00092978345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692225,0.00018553919,0.00048388308,0.0011720613,0.00045651835,0.00077973824],"domain_scores_gemma":[0.997657,0.00020330868,0.00022259787,0.0016452643,0.00013800606,0.00013384862],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006367714,0.00032074872,0.00047034095,0.00044126762,0.00017916565,0.0001919344,0.0025469873,0.0001548824,4.559549e-7],"category_scores_gemma":[0.00030756433,0.0003454876,0.00010810555,0.0011803376,0.00013296862,0.0008681583,0.000991612,0.0003309435,0.0000150681535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007938318,0.00012173987,0.0008150171,0.000027959888,0.00006470515,0.000029294677,0.0005173351,0.9313877,0.00003849985,0.006703526,0.026134942,0.03407989],"study_design_scores_gemma":[0.0011807828,0.00016597305,0.0036227864,0.000020826466,0.000029703457,0.0000068155837,0.00013076676,0.9911435,0.000004199967,0.00169213,0.0016686163,0.00033388654],"about_ca_topic_score_codex":0.000007756044,"about_ca_topic_score_gemma":0.0000054552197,"teacher_disagreement_score":0.11590475,"about_ca_system_score_codex":0.00015819419,"about_ca_system_score_gemma":0.00014388762,"threshold_uncertainty_score":0.9998997},"labels":[],"label_agreement":null},{"id":"W4319453072","doi":"10.1109/tac.2023.3243165","title":"An Online Model-Following Projection Mechanism Using Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"National Science Foundation of Sri Lanka; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Reinforcement learning; Projection (relational algebra); Computer science; Control theory (sociology); Online model; Adaptive control; Adaptation (eye); Optimal control; Mathematical optimization; Control (management); Iterative learning control; Projection method; Horizon; Dykstra's projection algorithm; Artificial intelligence; Mathematics; Algorithm","score_opus":0.03278349811512623,"score_gpt":0.2848965783962839,"score_spread":0.2521130802811577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319453072","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06306045,0.0000035097803,0.93256074,0.0001835484,0.0006477743,0.00080962776,0.000004309404,0.0027068243,0.000023225772],"genre_scores_gemma":[0.95519286,0.0000016549122,0.04412473,0.00023055749,0.000032503536,0.00014851506,0.000004109993,0.000037917896,0.00022713498],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976476,0.00019624378,0.00048256133,0.0005391278,0.0005743912,0.00056007586],"domain_scores_gemma":[0.99884486,0.00015154453,0.00017157684,0.00060955057,0.000085053565,0.0001374116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065363897,0.00028867438,0.0003491934,0.0005395313,0.0005634932,0.00021039916,0.00055444136,0.00011409395,0.000008557184],"category_scores_gemma":[0.000019474868,0.00029259862,0.00024488804,0.0008552682,0.000024600688,0.0008205281,0.000004329411,0.00031318585,0.000058709033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010651482,0.000112813395,0.0000017708768,0.000011447829,0.00010215627,0.000016050042,0.0005408936,0.87051743,0.012958936,0.00089265197,0.0000012672822,0.114833936],"study_design_scores_gemma":[0.0016056554,0.0003267764,0.000014685183,0.00005859285,0.00008824186,0.0000114996055,0.00013862118,0.9961799,0.0006069586,0.00066943147,0.000007805723,0.000291855],"about_ca_topic_score_codex":0.00006459508,"about_ca_topic_score_gemma":0.000026717646,"teacher_disagreement_score":0.89213246,"about_ca_system_score_codex":0.00028495473,"about_ca_system_score_gemma":0.00017475607,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W4324130748","doi":"10.1002/rnc.6662","title":"Robust <i>H</i><sub>∞</sub> tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp>","year":2023,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Algebraic Riccati equation; Riccati equation; Bounded function; Algebraic number; Tracking (education); Control theory (sociology); Mathematics; Reinforcement learning; Discrete time and continuous time; Robust control; Norm (philosophy); Robustness (evolution); Stability (learning theory); Mathematical optimization; Computer science; Control system; Control (management); Differential equation; Artificial intelligence; Engineering","score_opus":0.022273173672116293,"score_gpt":0.250750505202805,"score_spread":0.22847733153068872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324130748","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41859472,0.00083676126,0.5785225,0.00022709131,0.0013345332,0.00024448658,0.00003768768,0.000111323425,0.00009090869],"genre_scores_gemma":[0.97737324,0.00019486848,0.020536957,0.000113964474,0.001492861,0.000006428266,0.000017320928,0.000058685502,0.00020567715],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99619406,0.00031213684,0.0012202975,0.00043401172,0.0012751123,0.0005643888],"domain_scores_gemma":[0.99423945,0.0018347822,0.0015426616,0.00027347566,0.0018436712,0.0002659801],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017809508,0.0003646261,0.00078713824,0.0007672474,0.00018808429,0.00040239346,0.0014192732,0.00019636107,0.0000011827383],"category_scores_gemma":[0.002051373,0.0003334544,0.00038077132,0.0006014421,0.00015577186,0.0009952036,0.00029054345,0.00072520744,0.000025524136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007427578,0.0002538802,0.007924925,0.00007120397,0.001646477,0.0008181699,0.0013053471,0.87199396,0.093067646,0.0011507869,0.0006485199,0.021044794],"study_design_scores_gemma":[0.0029790557,0.00029793795,0.0010762943,0.00031752823,0.00010522812,0.00051150186,0.00031549195,0.98971874,0.0019951165,0.00008038312,0.0025111365,0.000091600814],"about_ca_topic_score_codex":0.00002473665,"about_ca_topic_score_gemma":0.0000036767915,"teacher_disagreement_score":0.5587785,"about_ca_system_score_codex":0.00013208552,"about_ca_system_score_gemma":0.00028216137,"threshold_uncertainty_score":0.9999117},"labels":[],"label_agreement":null},{"id":"W4361026739","doi":"10.1016/j.engappai.2023.106068","title":"Optimal non-autonomous area coverage control with adaptive reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Voronoi diagram; Metric (unit); Artificial neural network; Maxima and minima; Mathematical optimization; Centroid; Optimal control; Lyapunov function; Artificial intelligence; Mathematics; Nonlinear system","score_opus":0.012648709307533966,"score_gpt":0.23209989740942874,"score_spread":0.21945118810189476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361026739","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038499394,0.000021476657,0.99462193,0.00012596916,0.000051198476,0.00064688653,0.0000033714161,0.0005195418,0.00015967427],"genre_scores_gemma":[0.9429949,0.000007042398,0.056314986,0.0000130555945,0.00003866504,0.0005028036,0.000007901503,0.00001948105,0.0001011559],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854755,0.000014659693,0.00039453176,0.00039624635,0.00027755924,0.0003694291],"domain_scores_gemma":[0.9987747,0.0002609182,0.00016169873,0.0005193586,0.00018955309,0.00009374019],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031697986,0.00019268839,0.0002307496,0.00024956148,0.00012762421,0.000072975396,0.00073759427,0.000054534423,0.000005346987],"category_scores_gemma":[0.000058297243,0.00019305244,0.000065430926,0.0010976081,0.000072135685,0.00021713138,0.0001242289,0.00023532305,0.000111317764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015826603,0.000024933433,0.000020068235,0.000008145056,0.0000383164,0.0000038807543,0.00027932363,0.8790365,0.0014553315,0.06934465,0.00000442723,0.04976864],"study_design_scores_gemma":[0.00006110868,0.00021975982,0.00009783673,0.000025281075,0.000011346345,0.0000036132894,0.00008983034,0.99304444,0.005284373,0.00040324967,0.0005569611,0.0002021835],"about_ca_topic_score_codex":0.00003216066,"about_ca_topic_score_gemma":0.0000024464734,"teacher_disagreement_score":0.93914497,"about_ca_system_score_codex":0.00007771865,"about_ca_system_score_gemma":0.00007752854,"threshold_uncertainty_score":0.78724504},"labels":[],"label_agreement":null},{"id":"W4364375123","doi":"10.1016/j.eswa.2023.120112","title":"Neural Network-based control using Actor-Critic Reinforcement Learning and Grey Wolf Optimizer with experimental servo system validation","year":2023,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ministry of Education and Research, Romania; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii; Corporation for National and Community Service","keywords":"Reinforcement learning; Computer science; Artificial neural network; Particle swarm optimization; Gradient descent; Convergence (economics); Process (computing); Controller (irrigation); Mathematical optimization; Servomechanism; Artificial intelligence; Machine learning; Control engineering; Mathematics; Engineering","score_opus":0.015174882540149644,"score_gpt":0.2595307435211804,"score_spread":0.24435586098103074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364375123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009770974,0.00047308204,0.98616594,0.000169242,0.000119761695,0.002271989,0.0000022881688,0.00091938884,0.00010731891],"genre_scores_gemma":[0.98015326,0.0000015740535,0.016159022,0.00007048986,0.00018175313,0.00325486,0.000033188655,0.0000433539,0.000102515856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978552,0.00017537696,0.0003807634,0.00061559456,0.0004498485,0.00052322337],"domain_scores_gemma":[0.99862915,0.00017669426,0.0002647018,0.00054014835,0.00020719656,0.0001821285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034277738,0.00029346146,0.00034684685,0.00013949271,0.0006241458,0.00042726152,0.00037691215,0.000072428775,0.0000014323366],"category_scores_gemma":[0.000007679695,0.00023830753,0.000041812793,0.00068249437,0.000091275346,0.00044002922,0.00007007579,0.0001578546,0.0000142115705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006188562,0.000031910004,0.0014669538,0.000067075336,0.00008602951,0.000015075799,0.0005114914,0.9852293,0.0021665727,0.009899206,0.000042290034,0.00042216977],"study_design_scores_gemma":[0.0016638904,0.0001911389,0.000071588904,0.00017263605,0.000022483442,0.000063605345,0.00093245826,0.9954854,0.00017642725,0.000001897046,0.0009142016,0.00030427746],"about_ca_topic_score_codex":0.0001839903,"about_ca_topic_score_gemma":0.0000030904844,"teacher_disagreement_score":0.9703823,"about_ca_system_score_codex":0.00026866354,"about_ca_system_score_gemma":0.00010232991,"threshold_uncertainty_score":0.9717899},"labels":[],"label_agreement":null},{"id":"W4376607624","doi":"10.1109/tsmc.2023.3264552","title":"Robust Self-Learning Fault-Tolerant Control for Hypersonic Flight Vehicle Based on ADHDP","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Control theory (sociology); Robustness (evolution); Computer science; Fault tolerance; Controller (irrigation); Lyapunov stability; Actuator; Hypersonic flight; Control engineering; Engineering; Artificial intelligence; Hypersonic speed; Control (management)","score_opus":0.018320908262551026,"score_gpt":0.2175829276640776,"score_spread":0.19926201940152657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376607624","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0071627307,0.00022630494,0.9862997,0.00033086818,0.0023281628,0.002032671,0.000045916608,0.0012337597,0.00033989653],"genre_scores_gemma":[0.9956115,0.000017524551,0.00064224977,0.0000955662,0.00014893386,0.0008501732,0.0000049209934,0.000067235254,0.0025619015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99687666,0.0003918142,0.0005906236,0.00083320384,0.000596297,0.0007113831],"domain_scores_gemma":[0.9978834,0.0007524736,0.00024355718,0.000668311,0.00019926229,0.00025298816],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088462105,0.00041172517,0.0005969975,0.00040250295,0.0005605968,0.00055615086,0.0005513473,0.00022005713,0.0000013517352],"category_scores_gemma":[0.000012922601,0.00038275446,0.00021054926,0.000546387,0.000057297682,0.00016606729,0.000004280595,0.00038601627,0.00013289029],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000096757525,0.00019947071,0.000052544663,0.00034899244,0.00021085129,0.000035070352,0.0007954368,0.9876642,0.0005352871,0.0045128576,0.00022958938,0.005318921],"study_design_scores_gemma":[0.0029341162,0.0007655582,0.00006457062,0.0003063817,0.000072597024,0.000027163029,0.0004351164,0.98769015,0.00006373115,0.000008536479,0.007218844,0.00041323857],"about_ca_topic_score_codex":0.00018156088,"about_ca_topic_score_gemma":0.000018971514,"teacher_disagreement_score":0.98844874,"about_ca_system_score_codex":0.00019697472,"about_ca_system_score_gemma":0.00008961336,"threshold_uncertainty_score":0.99986243},"labels":[],"label_agreement":null},{"id":"W4379983008","doi":"10.1002/rnc.6825","title":"Adaptive control for stochastic nonlinear systems with time‐varying delays via multidimensional Taylor network","year":2023,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care","funders":"Fundamental Research Funds for the Central Universities; Shanghai Aerospace Science and Technology Innovation Foundation; Priority Academic Program Development of Jiangsu Higher Education Institutions; National Natural Science Foundation of China","keywords":"Control theory (sociology); Nonlinear system; Computer science; Kalman filter; Covariance; Convergence (economics); Tracking error; Covariance matrix; Mathematical optimization; Mathematics; Control (management); Algorithm","score_opus":0.013318982818162699,"score_gpt":0.2383035412986893,"score_spread":0.2249845584805266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379983008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003425966,0.0004363356,0.9924809,0.0015295614,0.0012541015,0.0006582121,0.00011028528,0.00009232881,0.000012359443],"genre_scores_gemma":[0.8259293,0.000008822569,0.17128506,0.00038662693,0.0021677043,0.0000490027,0.000023605257,0.00004211048,0.000107783264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975131,0.00012465098,0.00070984184,0.00036433816,0.0008045969,0.00048345674],"domain_scores_gemma":[0.99561113,0.0014549538,0.0007340767,0.0001949733,0.0017848122,0.00022007473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011503419,0.00029543904,0.0005794736,0.00031817253,0.00017772845,0.00020033766,0.00078780774,0.000106308384,0.0000037422026],"category_scores_gemma":[0.00021418894,0.0002297867,0.00020024837,0.0002544516,0.000103816164,0.00055328535,0.000106038526,0.0003210733,0.000021455571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026911197,0.0001267832,0.00029170248,0.000009989318,0.0014466165,0.00028343147,0.00011735016,0.9768187,0.0005681687,0.001838356,0.00030438468,0.015503421],"study_design_scores_gemma":[0.009785897,0.0007925665,0.00016904969,0.00014715697,0.00011558486,0.00047954242,0.000025031886,0.9873573,0.0000043880327,0.00018939331,0.0006855104,0.00024858603],"about_ca_topic_score_codex":0.000014921298,"about_ca_topic_score_gemma":0.0000050406065,"teacher_disagreement_score":0.8225033,"about_ca_system_score_codex":0.00010609096,"about_ca_system_score_gemma":0.00019682513,"threshold_uncertainty_score":0.93704295},"labels":[],"label_agreement":null},{"id":"W4383506070","doi":"10.1016/j.automatica.2023.111162","title":"Model-free policy iteration approach to NCE-based strategy design for linear quadratic Gaussian games","year":2023,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mathematics; Applied mathematics; Mathematical optimization; Ode; Algebraic equation; Nonlinear system","score_opus":0.05972795425387742,"score_gpt":0.3052582785002979,"score_spread":0.2455303242464205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383506070","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006386821,0.000009782568,0.99148345,0.0045996215,0.00005343964,0.0014282714,0.000012423073,0.0012076426,0.00056667946],"genre_scores_gemma":[0.4228051,3.2638317e-7,0.57584286,0.0004532365,0.000059869697,0.00053864694,0.00001611509,0.000020284315,0.00026356702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811953,0.00012271082,0.00036446497,0.0004974708,0.00034369447,0.0005521074],"domain_scores_gemma":[0.99826354,0.0003493376,0.000104843886,0.0009929914,0.00011418925,0.00017511843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061944785,0.00022315874,0.00026600866,0.00036378406,0.00017605312,0.00031997744,0.0011907085,0.0000838056,9.35943e-7],"category_scores_gemma":[0.0005168523,0.00020388902,0.00009576339,0.001031627,0.000041780422,0.0003544368,0.00014389186,0.000088821274,0.00009076203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017950577,0.00012629759,0.0000038872063,0.000093241244,0.000033049182,0.0000033816536,0.0012396245,0.6233657,0.0005265095,0.3260988,0.0021997127,0.04629183],"study_design_scores_gemma":[0.0005920592,0.00022935019,0.0001202691,0.000028029413,0.000011449298,0.0000012921716,0.000025215013,0.963003,0.00014135933,0.035530105,0.000093672985,0.00022420984],"about_ca_topic_score_codex":0.000016545198,"about_ca_topic_score_gemma":0.000004120888,"teacher_disagreement_score":0.4221664,"about_ca_system_score_codex":0.00010787867,"about_ca_system_score_gemma":0.0004984707,"threshold_uncertainty_score":0.8314353},"labels":[],"label_agreement":null},{"id":"W4386883033","doi":"10.1109/tnnls.2023.3309326","title":"Adaptive Event-Triggered Bipartite Formation for Multiagent Systems via Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Fundamental Research Funds for the Central Universities; Higher Education Discipline Innovation Project","keywords":"Bipartite graph; Lyapunov function; Computer science; Reinforcement learning; Linearization; Adaptive control; Nonlinear system; Controller (irrigation); Artificial neural network; Convergence (economics); Control theory (sociology); Multi-agent system; Graph; Feedback linearization; Artificial intelligence; Control (management); Theoretical computer science","score_opus":0.02109190720631195,"score_gpt":0.24532823544262422,"score_spread":0.22423632823631226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386883033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003760656,0.0003322013,0.99153894,0.0001042503,0.0020334236,0.0014374865,0.0000022181362,0.0007762325,0.000014563247],"genre_scores_gemma":[0.9969115,0.000064182466,0.00028101075,0.000028710108,0.00016090156,0.00068536954,0.000014489471,0.000034532288,0.0018192532],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975026,0.00046364835,0.00056958414,0.0005008487,0.00034629545,0.0006170249],"domain_scores_gemma":[0.9985371,0.00054929266,0.00033493194,0.0002630058,0.00015418867,0.0001614826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009336879,0.00029317493,0.00036324645,0.0002711778,0.0010275852,0.00040162532,0.00027312658,0.00013905775,0.0000010508276],"category_scores_gemma":[0.00001784508,0.000271971,0.00015961664,0.0005807638,0.000038989456,0.00057910377,0.000008362919,0.0006329655,0.000020203956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006249908,0.000017671493,0.000012905968,0.000057050995,0.00006679641,0.000006134986,0.0004492117,0.9569518,0.00011359947,0.00026601634,0.00005471684,0.041941583],"study_design_scores_gemma":[0.00088451453,0.0007368431,0.00002889943,0.00014751089,0.0000330821,0.00002289712,0.00041527767,0.9956423,0.000017549708,0.0000045135607,0.0017832221,0.0002833966],"about_ca_topic_score_codex":0.00012374917,"about_ca_topic_score_gemma":0.000008433679,"teacher_disagreement_score":0.9931509,"about_ca_system_score_codex":0.0001238698,"about_ca_system_score_gemma":0.000017714694,"threshold_uncertainty_score":0.99997324},"labels":[],"label_agreement":null},{"id":"W4388430254","doi":"10.1109/tsusc.2023.3330573","title":"Parallel Trajectory Training of Recurrent Neural Network Controllers With Levenberg–Marquardt and Forward Accumulation Through Time in Closed-Loop Control Systems","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Directorate for Computer and Information Science and Engineering; National Science Foundation","keywords":"Levenberg–Marquardt algorithm; Trajectory; Control theory (sociology); Closed loop; Artificial neural network; Computer science; Loop (graph theory); Control engineering; Control (management); Artificial intelligence; Engineering; Mathematics; Physics","score_opus":0.028079199821574342,"score_gpt":0.2676599859668572,"score_spread":0.23958078614528286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388430254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09037223,0.00017749445,0.9071248,0.0002452022,0.00038636263,0.0012618896,0.0000049274045,0.0003469498,0.00008012891],"genre_scores_gemma":[0.9934283,0.000008884727,0.006049751,0.000045753084,0.00006184286,0.00008537588,0.0000031937168,0.000035417444,0.00028148113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99689645,0.0004058919,0.0006613889,0.0006315873,0.00041558678,0.000989114],"domain_scores_gemma":[0.9978505,0.0010846944,0.0003293438,0.00039055332,0.00023678548,0.00010812108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011848034,0.00033747207,0.0006934083,0.00035851775,0.000371204,0.00015882317,0.00040920707,0.00012546689,0.0000017976697],"category_scores_gemma":[0.000028003536,0.00032530222,0.0001297389,0.0013760832,0.000118807104,0.00059514446,0.000011141124,0.00042818367,0.000003728348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002487644,0.00006050781,0.00015071924,0.00009328241,0.000111118214,0.00006482163,0.0020577377,0.95317674,0.000030218334,0.0015196893,0.00002570592,0.042460702],"study_design_scores_gemma":[0.004590063,0.0004851136,0.0011620116,0.0001810496,0.000043118733,0.000019144838,0.0017391099,0.99114555,0.00000636389,0.00023169642,0.00008634716,0.00031045332],"about_ca_topic_score_codex":0.0002178363,"about_ca_topic_score_gemma":0.000033207198,"teacher_disagreement_score":0.9030561,"about_ca_system_score_codex":0.0002478371,"about_ca_system_score_gemma":0.00020431039,"threshold_uncertainty_score":0.9999199},"labels":[],"label_agreement":null},{"id":"W4388571386","doi":"10.1016/j.neucom.2023.127013","title":"Decentralized optimal control of large-scale partially unknown nonlinear mismatched interconnected systems based on dynamic event-triggered control","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Control theory (sociology); Computer science; Optimal control; Nonlinear system; Reinforcement learning; Decentralised system; Filter (signal processing); Stability (learning theory); Control (management); Artificial neural network; Bounded function; Scale (ratio); Mathematical optimization; Mathematics; Artificial intelligence","score_opus":0.00823570730478461,"score_gpt":0.2573743442197518,"score_spread":0.24913863691496718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388571386","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16977108,0.000046909194,0.826129,0.0006692601,0.00090873026,0.0013211512,0.00004947214,0.0010886593,0.00001573592],"genre_scores_gemma":[0.9862796,0.0000017278767,0.0127944425,0.0006306358,0.0000870903,0.00007833625,0.00003109161,0.000067218534,0.000029823266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950246,0.00074341206,0.0011582577,0.001050464,0.0007577501,0.0012655107],"domain_scores_gemma":[0.99596435,0.0017062983,0.00069431664,0.0009784693,0.00038075208,0.0002757922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013221396,0.0005053798,0.0009772639,0.00042806097,0.00023736834,0.00022746134,0.001501844,0.0001849867,0.0000048639326],"category_scores_gemma":[0.00052334025,0.0004963612,0.00038027967,0.0012417774,0.000079780155,0.00021432224,0.00022865251,0.00047229475,0.00006826468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005533914,0.0006199031,0.0014488914,0.00016108528,0.00020188883,0.00023467609,0.00052288425,0.9585316,0.024834663,0.0021506362,0.000083804654,0.010656561],"study_design_scores_gemma":[0.009875977,0.00044407023,0.0014933192,0.00021485318,0.00005293639,0.000009668759,0.00004188635,0.986634,0.00030897363,0.000017033,0.0005119006,0.0003953543],"about_ca_topic_score_codex":0.000023504095,"about_ca_topic_score_gemma":0.000010306804,"teacher_disagreement_score":0.81650853,"about_ca_system_score_codex":0.00012693019,"about_ca_system_score_gemma":0.00022640052,"threshold_uncertainty_score":0.9997488},"labels":[],"label_agreement":null},{"id":"W4388785240","doi":"10.1016/j.neucom.2023.127042","title":"Dynamic event-triggered-based online IRL algorithm for the decentralized control of the input and state constrained large-scale unmatched interconnected system","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Interconnection; Control theory (sociology); Decentralised system; State (computer science); Scale (ratio); Stability (learning theory); Computation; Mathematical optimization; Function (biology); Optimal control; Control (management); Mathematics; Algorithm; Artificial intelligence","score_opus":0.008015808123454937,"score_gpt":0.24752368198896935,"score_spread":0.23950787386551442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388785240","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.102810375,0.00008122071,0.8928603,0.0013993888,0.0005403451,0.0016807879,0.00015049377,0.00047502937,0.0000020849138],"genre_scores_gemma":[0.96931773,0.0000032981122,0.030107075,0.0004217416,0.00002857996,0.000059596634,0.000012427589,0.00003129969,0.000018261788],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974355,0.00037687283,0.0006376191,0.0005513522,0.00032830634,0.00067033194],"domain_scores_gemma":[0.99623674,0.002327153,0.00047035675,0.00062355306,0.00024984055,0.00009238121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094771525,0.00027852057,0.0004537036,0.00011852979,0.00037981584,0.00013468026,0.0011622045,0.00006834973,5.6682387e-7],"category_scores_gemma":[0.00022758308,0.00018457886,0.00021824508,0.00080634735,0.0001657785,0.00010181456,0.00037719356,0.00026968008,0.000002035635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018180124,0.00036113872,0.0015107134,0.0004560909,0.00045667216,0.00005082188,0.0029637564,0.043572858,0.010765355,0.0036150732,0.000084575266,0.93598115],"study_design_scores_gemma":[0.004586334,0.00011981551,0.0027495876,0.00014655046,0.00004931484,0.000014874745,0.00029535135,0.9913596,0.00018971351,0.00015701342,0.00016125414,0.00017062094],"about_ca_topic_score_codex":0.000020512633,"about_ca_topic_score_gemma":0.000045641646,"teacher_disagreement_score":0.9477867,"about_ca_system_score_codex":0.00007459192,"about_ca_system_score_gemma":0.00015998592,"threshold_uncertainty_score":0.7526908},"labels":[],"label_agreement":null},{"id":"W4390187516","doi":"10.1109/tim.2023.3346524","title":"Model-Free Force Control of Cable-Driven Parallel Manipulators for Weight-Shift Aircraft Actuation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Instrumentation and Measurement","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Control theory (sociology); Trajectory; Actuator; Control engineering; Controller (irrigation); Inverse dynamics; Torque; Optimal control; Kinematics; Parallel manipulator; Computer science; Engineering; Heuristic; Robot; Control (management); Artificial intelligence","score_opus":0.04563645080383398,"score_gpt":0.2600250896028202,"score_spread":0.21438863879898623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390187516","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006198941,0.000010506991,0.9909759,0.0011227134,0.000366548,0.0010656063,0.000036831203,0.00018698098,0.00003595212],"genre_scores_gemma":[0.96200335,0.000018837582,0.037283503,0.00015378889,0.000012823048,0.00042340514,0.000006055464,0.000014949194,0.000083289466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842495,0.000045082612,0.0003558166,0.00033923585,0.00057949364,0.000255441],"domain_scores_gemma":[0.9991605,0.0000648965,0.00015172943,0.00034335713,0.00018636258,0.00009314045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043198705,0.00017032822,0.000199937,0.00024843545,0.00021138987,0.000051330077,0.00028732404,0.00006483217,0.0000035674625],"category_scores_gemma":[0.0000116905585,0.0001702443,0.00010738161,0.0002489953,0.000042160886,0.00038354698,0.0000033232502,0.00008385873,0.000005307628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028810313,0.0002437262,0.0001244944,0.00009529099,0.0003035703,9.85014e-7,0.0016689412,0.8066805,0.0132360095,0.017034777,0.00017007715,0.16015354],"study_design_scores_gemma":[0.0043378454,0.00026126075,0.00046198702,0.000032858865,0.00006545305,0.0000010903756,0.00007587181,0.98806643,0.0028724507,0.0035857356,0.00007489921,0.00016411526],"about_ca_topic_score_codex":0.000032215576,"about_ca_topic_score_gemma":0.00011221948,"teacher_disagreement_score":0.9558044,"about_ca_system_score_codex":0.00016963172,"about_ca_system_score_gemma":0.00010868619,"threshold_uncertainty_score":0.6942361},"labels":[],"label_agreement":null},{"id":"W4390733893","doi":"10.1002/rnc.7189","title":"Efficient off‐policy Q‐learning for multi‐agent systems by solving dual games","year":2024,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Dual (grammatical number); Bounded function; Synchronization (alternating current); Nash equilibrium; Tracking (education); Mathematical optimization; Zero-sum game; Tracking error; Zero (linguistics); Multi-agent system; Potential game; Game theory; Control (management); Artificial neural network; Control theory (sociology); Artificial intelligence; Mathematics; Mathematical economics; Channel (broadcasting)","score_opus":0.015961719390741532,"score_gpt":0.28417058159568964,"score_spread":0.2682088622049481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390733893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009577744,0.008248172,0.977106,0.0028040376,0.0019452188,0.00021322015,0.000030109566,0.00005753961,0.000017953262],"genre_scores_gemma":[0.9606973,0.00010116944,0.037230987,0.00015026696,0.0013838348,0.000013755475,0.0000045019383,0.000019372092,0.0003988349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985153,0.00007672072,0.00048338698,0.00023001428,0.00045545408,0.00023909085],"domain_scores_gemma":[0.99852145,0.0004257478,0.00025345111,0.000086855835,0.0005930756,0.00011939718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079856423,0.00015437552,0.00025457973,0.0003120653,0.00007923,0.0006377983,0.00048946595,0.000059225644,0.0000016779055],"category_scores_gemma":[0.00040105596,0.00012607053,0.00017357431,0.00010491067,0.00004621338,0.0002169462,0.00008948857,0.00027006384,0.0000038050907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041437958,0.00043842816,0.0007399664,0.00011199441,0.002126326,0.00052508124,0.0015248356,0.45963973,0.007646901,0.024639284,0.0018995439,0.5002935],"study_design_scores_gemma":[0.0018883409,0.00017575845,0.0000620847,0.00016422058,0.00003058151,0.0002683981,0.00005891148,0.96212566,0.000022927536,0.000025076844,0.035059005,0.00011905988],"about_ca_topic_score_codex":0.000019535853,"about_ca_topic_score_gemma":0.0000017087888,"teacher_disagreement_score":0.95111954,"about_ca_system_score_codex":0.00014789325,"about_ca_system_score_gemma":0.00020026241,"threshold_uncertainty_score":0.61503035},"labels":[],"label_agreement":null},{"id":"W4390757324","doi":"10.22190/fume231011044z","title":"Q-LEARNING, POLICY ITERATION AND ACTOR-CRITIC REINFORCEMENT LEARNING COMBINED WITH METAHEURISTIC ALGORITHMS IN SERVO SYSTEM CONTROL","year":2023,"lang":"en","type":"article","venue":"Facta Universitatis Series Mechanical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Unitatea Executiva pentru Finantarea Invatamantului Superior, a Cercetarii, Dezvoltarii si Inovarii","keywords":"Reinforcement learning; Initialization; Computer science; Artificial neural network; Metaheuristic; Servomechanism; Algorithm; Mathematical optimization; Parametric statistics; Artificial intelligence; Machine learning; Mathematics; Control engineering; Engineering","score_opus":0.004149845208367344,"score_gpt":0.18436468813074813,"score_spread":0.1802148429223808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390757324","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022088122,0.000015855825,0.9760763,0.0004677481,0.0001101696,0.00035673563,0.000002890345,0.0008212299,0.000060945815],"genre_scores_gemma":[0.9902481,0.000010339814,0.009354164,0.000016022848,0.000022135246,0.000019328925,0.000019473666,0.000023778095,0.00028666196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985327,0.00010788969,0.00023590468,0.00038170986,0.00028317055,0.00045862858],"domain_scores_gemma":[0.9992022,0.00028363714,0.00008462312,0.00019333797,0.00008753432,0.00014866186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002737512,0.00023715704,0.0003354177,0.00042700313,0.00015690284,0.00016378926,0.00031104157,0.000077289405,0.0000024732874],"category_scores_gemma":[0.00023260152,0.00024211226,0.00003907815,0.0008328305,0.000024975288,0.00084153377,0.00019150495,0.0003489773,0.000009433037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014853175,0.000018410869,0.0002260587,0.00024546304,0.0001843388,0.00047929285,0.0021961126,0.5689987,0.0033492374,0.4198808,0.0000059908684,0.0042670267],"study_design_scores_gemma":[0.0016123779,0.000856215,0.0007252793,0.00012671984,0.000023675992,0.000026611799,0.0009233522,0.9950506,0.000064553424,0.00005638882,0.00027235478,0.0002618621],"about_ca_topic_score_codex":0.000086360975,"about_ca_topic_score_gemma":0.000014211802,"teacher_disagreement_score":0.96816,"about_ca_system_score_codex":0.00029682054,"about_ca_system_score_gemma":0.00005877617,"threshold_uncertainty_score":0.98730516},"labels":[],"label_agreement":null},{"id":"W4391019820","doi":"10.1109/cdc49753.2023.10383832","title":"Data-Driven Output Regulation Using Single-Gain Tuning Regulators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Control theory (sociology); Regulator; Computer science; MIMO; Control engineering; Convex optimization; Scalar (mathematics); Controller (irrigation); Linear system; Regular polygon; Engineering; Control (management); Mathematics; Channel (broadcasting)","score_opus":0.09231915592367608,"score_gpt":0.2936539176518024,"score_spread":0.2013347617281263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391019820","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01721727,0.000014320695,0.97939056,0.00061266695,0.0003490255,0.00019733033,0.000006045609,0.001312326,0.0009004491],"genre_scores_gemma":[0.7858364,5.995826e-7,0.2125139,0.00010264764,0.00009534597,0.000003516091,0.00005770708,0.000019427489,0.0013704449],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981506,0.00009907872,0.00027976363,0.0006517982,0.0003868686,0.00043189968],"domain_scores_gemma":[0.9979989,0.00013835393,0.00013159009,0.0015457115,0.00008862106,0.00009681262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006366975,0.00016015615,0.00017915617,0.000255733,0.00019209267,0.00024860367,0.0015472994,0.0000714679,0.0000059031713],"category_scores_gemma":[0.00015897969,0.0001561471,0.000046197052,0.0010195452,0.000059072256,0.0011695642,0.0012857132,0.0001055869,0.00010692061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014281265,0.00010470984,0.0021982687,0.000026515452,0.00013911616,0.00009175926,0.0010116047,0.08093869,0.03469772,0.19123855,0.00398759,0.68555117],"study_design_scores_gemma":[0.00019919981,0.000025442785,0.0014727068,0.000021912772,0.000008602778,0.00000921321,0.000043458716,0.9921933,0.00009937396,0.0023460756,0.0033887036,0.00019203742],"about_ca_topic_score_codex":0.000044380602,"about_ca_topic_score_gemma":0.000024034181,"teacher_disagreement_score":0.9112546,"about_ca_system_score_codex":0.00012650293,"about_ca_system_score_gemma":0.000072674506,"threshold_uncertainty_score":0.6367494},"labels":[],"label_agreement":null},{"id":"W4391306093","doi":"10.1109/rose60297.2023.10410776","title":"An Online Model-Free Reinforcement Learning Approach for 6-DOF Robot Manipulators","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Control theory (sociology); Robot; Adaptive control; MATLAB; Robot manipulator; Tracking error; Kernel (algebra); Degrees of freedom (physics and chemistry); Control (management); Control engineering; Artificial intelligence; Mathematics; Engineering","score_opus":0.05925569399817362,"score_gpt":0.2849001201848312,"score_spread":0.22564442618665756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391306093","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001655775,0.0000072757807,0.99524796,0.0003258767,0.00008169769,0.0005393923,0.0000020169068,0.0012687545,0.00087125326],"genre_scores_gemma":[0.54504156,0.0000013455164,0.4515886,0.00014418465,0.00004475126,0.00008291298,0.000080619575,0.000017824499,0.002998215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983414,0.000034314264,0.00026700392,0.00052745093,0.00031795315,0.00051190914],"domain_scores_gemma":[0.99871886,0.000052855525,0.00008735492,0.00090680167,0.00009977805,0.00013436556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047725433,0.00017995831,0.00019445768,0.00016481472,0.00018677562,0.00013859494,0.0015457931,0.00006644311,0.000002547841],"category_scores_gemma":[0.0000734005,0.00016314478,0.00009728268,0.00041924207,0.00002847546,0.00048371014,0.00046636382,0.00015133765,0.0000126020595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007127779,0.000046112524,0.00007059274,0.000009984324,0.000018711404,0.0000014105835,0.00017054226,0.8693861,0.00020012984,0.11395029,0.00021349487,0.015925543],"study_design_scores_gemma":[0.0006617135,0.00022146074,0.00014740364,0.000003521725,0.000007671813,0.0000017463071,0.00007596333,0.9953902,0.00003562587,0.002960365,0.0002815864,0.0002127395],"about_ca_topic_score_codex":0.00003110999,"about_ca_topic_score_gemma":0.000010981553,"teacher_disagreement_score":0.5436593,"about_ca_system_score_codex":0.00007198062,"about_ca_system_score_gemma":0.000056353536,"threshold_uncertainty_score":0.6652851},"labels":[],"label_agreement":null},{"id":"W4391306300","doi":"10.1109/rose60297.2023.10410754","title":"Behavior Replication of Cascaded Dynamic Systems Using Machine Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Reinforcement learning; Reference model; Convergence (economics); Process (computing); Replicate; Sensitivity (control systems); System dynamics; Replication (statistics); Projection (relational algebra); Component (thermodynamics); Control theory (sociology); Artificial intelligence; Control (management); Algorithm; Engineering; Mathematics","score_opus":0.030782973909780756,"score_gpt":0.29952938967637954,"score_spread":0.2687464157665988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391306300","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2378379,0.00008201567,0.7609086,0.00007763845,0.00015379734,0.0002921574,0.0000017809249,0.00055487297,0.00009121932],"genre_scores_gemma":[0.98295194,0.00000391875,0.015887668,0.000007952625,0.000009433793,0.000035710847,0.000010482787,0.000011516296,0.0010813739],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884415,0.00008118397,0.0002620987,0.0003764085,0.00022106693,0.00021511111],"domain_scores_gemma":[0.9989485,0.00007518949,0.00016974936,0.0006653422,0.000097800075,0.000043399577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005465582,0.00009323665,0.00016050503,0.00016902557,0.00008453303,0.000053940916,0.00047653698,0.000048849124,0.0000017814779],"category_scores_gemma":[0.000073595766,0.00008673328,0.00005044741,0.000667236,0.000028830455,0.00020077665,0.00019882052,0.000114565795,0.000025475301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021390966,0.00023620673,0.05108001,0.00016397469,0.00013938862,0.00011212951,0.0015213477,0.04557511,0.46233016,0.12998821,0.000048370504,0.3087837],"study_design_scores_gemma":[0.00016103257,0.000036967293,0.0043231,0.000013253064,0.000010931199,0.000022198854,0.00003836989,0.99481434,0.0003021968,0.000051085146,0.0001353864,0.00009114841],"about_ca_topic_score_codex":0.0006078108,"about_ca_topic_score_gemma":0.000020123663,"teacher_disagreement_score":0.9492392,"about_ca_system_score_codex":0.00007824771,"about_ca_system_score_gemma":0.00003457429,"threshold_uncertainty_score":0.35368806},"labels":[],"label_agreement":null},{"id":"W4391450137","doi":"10.1115/1.4064601","title":"Nonlinear Filtering and Reinforcement Learning Based Consensus Achievement of Uncertain Multi-Agent Systems","year":2024,"lang":"en","type":"article","venue":"Journal of Dynamic Systems Measurement and Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Nonlinear system; Multi-agent system; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology; Physics","score_opus":0.027248676278643084,"score_gpt":0.24938680326290075,"score_spread":0.22213812698425767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391450137","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013976524,0.017777337,0.9657204,0.00043946248,0.001283805,0.00072517834,0.0000047016824,0.000056103345,0.00001648855],"genre_scores_gemma":[0.9959398,0.00006165184,0.0037408904,0.000025711011,0.00008686338,0.000026918025,9.229001e-7,0.000019773239,0.00009746467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966621,0.0003683507,0.0012154428,0.00032524375,0.0010810619,0.00034784773],"domain_scores_gemma":[0.997987,0.0002289749,0.000748043,0.00024747476,0.0006060591,0.0001824783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038700018,0.00028479123,0.00067602517,0.00034021374,0.00011269352,0.00035766122,0.0003367089,0.000080133366,7.455591e-7],"category_scores_gemma":[0.0001546249,0.00022555438,0.00015006859,0.00017104983,0.000071606366,0.00018750869,0.000072767674,0.0003144263,0.0000011075914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090341317,0.0007158634,0.0067881416,0.0069656796,0.0059701256,0.001078361,0.0030628692,0.6458212,0.20683628,0.007828736,0.000104993196,0.1139243],"study_design_scores_gemma":[0.0032523612,0.00074656407,0.00029403556,0.0016760856,0.00014780623,0.0001393407,0.00033750592,0.9920062,0.000038685892,0.0000060357706,0.0011496842,0.00020570683],"about_ca_topic_score_codex":0.00009556416,"about_ca_topic_score_gemma":0.000008222125,"teacher_disagreement_score":0.9819633,"about_ca_system_score_codex":0.00036521352,"about_ca_system_score_gemma":0.0002563659,"threshold_uncertainty_score":0.91978407},"labels":[],"label_agreement":null},{"id":"W4391495714","doi":"10.1109/etfg55873.2023.10407820","title":"Integral Reinforcement Learning Control for a Class of Unknown Nonlinear Systems with an Application to a Microgrid System","year":2023,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Microgrid; Reinforcement learning; Nonlinear system; Class (philosophy); Computer science; Control (management); Control theory (sociology); Reinforcement; Control system; Control engineering; Artificial intelligence; Engineering; Structural engineering; Electrical engineering; Physics","score_opus":0.008847576481085459,"score_gpt":0.24376432971334683,"score_spread":0.23491675323226135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391495714","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005457926,0.000014859722,0.991071,0.00023389868,0.000106952466,0.0022821184,0.0000049150667,0.000681202,0.000147129],"genre_scores_gemma":[0.9486534,4.0392558e-7,0.049757596,0.000052184623,0.000065783635,0.0009765054,0.00002511575,0.000018691984,0.00045031437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984712,0.00006935342,0.00038024483,0.00043075305,0.00027739862,0.0003710741],"domain_scores_gemma":[0.99863297,0.0001442159,0.00020586405,0.00049985555,0.00038516754,0.00013194661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006996965,0.00016662457,0.0003207965,0.00019156965,0.00009834263,0.000112962254,0.0006424175,0.00005420779,2.1982609e-7],"category_scores_gemma":[0.00003612394,0.00012709672,0.00006286275,0.0005915619,0.000029865145,0.00020268578,0.00009034596,0.00009510262,0.000024579525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049561076,0.000094549396,0.00059089495,0.00044525872,0.000236818,0.000007731353,0.0010809579,0.42290482,0.008769185,0.4912097,0.00012998606,0.07403451],"study_design_scores_gemma":[0.0012004343,0.0012394158,0.000041406205,0.00008061864,0.000017984154,0.000008025157,0.0005819071,0.98988104,0.00017514531,0.000009054017,0.0066079395,0.00015703247],"about_ca_topic_score_codex":0.00021941672,"about_ca_topic_score_gemma":0.000047483336,"teacher_disagreement_score":0.94319546,"about_ca_system_score_codex":0.00013778501,"about_ca_system_score_gemma":0.00008438688,"threshold_uncertainty_score":0.5182854},"labels":[],"label_agreement":null},{"id":"W4392622485","doi":"10.1142/s1793962324500296","title":"An online model-free adaptive learning control solution for robotic arms","year":2024,"lang":"en","type":"article","venue":"Advances in Complex Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Ottawa","funders":"","keywords":"Computer science; Control (management); Adaptive control; Artificial intelligence","score_opus":0.04593087607144463,"score_gpt":0.3124840809376537,"score_spread":0.26655320486620904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392622485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001969243,0.0084755365,0.9880866,0.00035858696,0.0009933173,0.0011018589,0.000031987263,0.000644426,0.00011076067],"genre_scores_gemma":[0.8538549,0.00002586581,0.14541076,0.00005465092,0.00021955324,0.0002712306,0.000032055636,0.000030023826,0.00010095605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975755,0.00021929393,0.00051072886,0.0007830373,0.00033134842,0.0005800886],"domain_scores_gemma":[0.99841106,0.00051011326,0.00014929996,0.00066745013,0.00015642437,0.00010563835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006574753,0.00026851904,0.00045358422,0.0002276737,0.00014424937,0.0002922765,0.0012898822,0.00008248729,7.975737e-7],"category_scores_gemma":[0.00011843453,0.0002530907,0.00010822113,0.00039561055,0.000086680215,0.0017473267,0.00012499958,0.00030550428,0.0000083184395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000311444,0.000062714105,0.00007406629,0.00008150918,0.000024819004,0.000012221112,0.00031473656,0.8031613,0.0004434048,0.15515229,0.00003235392,0.040609434],"study_design_scores_gemma":[0.0010182557,0.00044110027,0.00007449984,0.00017623749,0.000015240846,0.000019357118,0.0001397768,0.98095256,0.000001523448,0.013929536,0.0029410047,0.0002908928],"about_ca_topic_score_codex":0.000069206995,"about_ca_topic_score_gemma":0.00021568284,"teacher_disagreement_score":0.85365796,"about_ca_system_score_codex":0.0002911593,"about_ca_system_score_gemma":0.00010055319,"threshold_uncertainty_score":0.99999213},"labels":[],"label_agreement":null},{"id":"W4392897838","doi":"10.32920/25412560.v1","title":"Deep Reinforcement Learning Controller Design for Unmanned Aerial Vehicles","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"PID controller; Control theory (sociology); Reinforcement learning; Controller (irrigation); Computer science; Trajectory; Linearization; Path (computing); Drone; Control engineering; Artificial intelligence; Control (management); Engineering; Nonlinear system; Physics","score_opus":0.025447196896500837,"score_gpt":0.265665793396314,"score_spread":0.2402185964998132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392897838","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007539113,0.0005136107,0.9913144,0.0013241357,0.0019805543,0.0027227846,0.0000012389046,0.0011006651,0.00096720125],"genre_scores_gemma":[0.70447725,0.000011158754,0.28768864,0.0003052425,0.00051274267,0.0013361316,0.00002133158,0.000057355617,0.00559013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969965,0.00018143482,0.0005977245,0.0011173555,0.00042516206,0.0006818277],"domain_scores_gemma":[0.9981079,0.00056875247,0.00026942953,0.00064927933,0.00026077585,0.00014386026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011302807,0.00048859225,0.00062536553,0.00022239072,0.0001844616,0.0009014917,0.0016136124,0.00034118516,0.000013941662],"category_scores_gemma":[0.00027065098,0.00042799686,0.0004080976,0.00014462086,0.00006427857,0.00012343121,0.0028519353,0.0008162632,0.00012129504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019731754,0.000029604596,0.0000025883578,0.0001286508,0.0004337761,0.000015335192,0.0004965936,0.7509422,0.00024602245,0.17990613,0.0010653983,0.06653642],"study_design_scores_gemma":[0.001347478,0.00028862737,0.000003406802,0.00008546351,0.00007652561,0.0000028572063,0.000023556648,0.9300258,0.00014573465,0.06414382,0.003403917,0.00045277778],"about_ca_topic_score_codex":0.00004894881,"about_ca_topic_score_gemma":0.0000074124086,"teacher_disagreement_score":0.70440185,"about_ca_system_score_codex":0.00025708947,"about_ca_system_score_gemma":0.00031803618,"threshold_uncertainty_score":0.9998172},"labels":[],"label_agreement":null},{"id":"W4392910934","doi":"10.32920/25412560","title":"Deep Reinforcement Learning Controller Design for Unmanned Aerial Vehicles","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"PID controller; Control theory (sociology); Reinforcement learning; Controller (irrigation); Trajectory; Computer science; Linearization; Path (computing); Track (disk drive); Drone; Tracking (education); Control engineering; Artificial intelligence; Engineering; Control (management); Nonlinear system; Physics","score_opus":0.025447196896500837,"score_gpt":0.265665793396314,"score_spread":0.2402185964998132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392910934","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007539113,0.0005136107,0.9913144,0.0013241357,0.0019805543,0.0027227846,0.0000012389046,0.0011006651,0.00096720125],"genre_scores_gemma":[0.70447725,0.000011158754,0.28768864,0.0003052425,0.00051274267,0.0013361316,0.00002133158,0.000057355617,0.00559013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969965,0.00018143482,0.0005977245,0.0011173555,0.00042516206,0.0006818277],"domain_scores_gemma":[0.9981079,0.00056875247,0.00026942953,0.00064927933,0.00026077585,0.00014386026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011302807,0.00048859225,0.00062536553,0.00022239072,0.0001844616,0.0009014917,0.0016136124,0.00034118516,0.000013941662],"category_scores_gemma":[0.00027065098,0.00042799686,0.0004080976,0.00014462086,0.00006427857,0.00012343121,0.0028519353,0.0008162632,0.00012129504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019731754,0.000029604596,0.0000025883578,0.0001286508,0.0004337761,0.000015335192,0.0004965936,0.7509422,0.00024602245,0.17990613,0.0010653983,0.06653642],"study_design_scores_gemma":[0.001347478,0.00028862737,0.000003406802,0.00008546351,0.00007652561,0.0000028572063,0.000023556648,0.9300258,0.00014573465,0.06414382,0.003403917,0.00045277778],"about_ca_topic_score_codex":0.00004894881,"about_ca_topic_score_gemma":0.0000074124086,"teacher_disagreement_score":0.70440185,"about_ca_system_score_codex":0.00025708947,"about_ca_system_score_gemma":0.00031803618,"threshold_uncertainty_score":0.9998172},"labels":[],"label_agreement":null},{"id":"W4393026775","doi":"","title":"Intelligent control for future and complex systems: editorial","year":2022,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Control (management); Cognitive science; Psychology; Artificial intelligence","score_opus":0.010919122132462105,"score_gpt":0.2206457712815301,"score_spread":0.209726649149068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393026775","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011338141,0.0007510521,0.9817492,0.008332336,0.006043354,0.00079532457,0.000052475556,0.00024061464,0.000901862],"genre_scores_gemma":[0.93749547,0.000024722272,0.05911691,0.0002686989,0.0010615719,0.00051717774,0.000075809854,0.000028371242,0.0014112678],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99560183,0.0027371051,0.00033297465,0.0005467337,0.00044450726,0.0003368489],"domain_scores_gemma":[0.99600106,0.0015099309,0.00025710883,0.0010220356,0.0010784098,0.00013147619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046790657,0.00017977838,0.00025308895,0.0001085664,0.00076354394,0.00039761805,0.0013679925,0.00006373586,0.0000120453105],"category_scores_gemma":[0.00045444537,0.00019095682,0.00010130293,0.00029877835,0.00010748674,0.00019402921,0.0006934187,0.00025869338,0.000004543575],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003426588,0.00027631418,0.0003314609,0.00003659718,0.000072625364,0.0000025811812,0.0044779833,0.00015231063,0.00092429394,0.9160129,0.010765851,0.06691285],"study_design_scores_gemma":[0.0013371077,0.000002742285,0.00032186482,0.000037322086,0.00001749722,0.000017655857,0.0003457135,0.450673,0.00016110644,0.0020622378,0.5447806,0.00024310702],"about_ca_topic_score_codex":0.00018962745,"about_ca_topic_score_gemma":0.00008014927,"teacher_disagreement_score":0.9363617,"about_ca_system_score_codex":0.00013703543,"about_ca_system_score_gemma":0.00012816153,"threshold_uncertainty_score":0.77869934},"labels":[],"label_agreement":null},{"id":"W4393103270","doi":"10.1016/j.automatica.2024.111642","title":"Stabilizing reinforcement learning control: A modular framework for optimizing over all stable behavior","year":2024,"lang":"en","type":"article","venue":"Automatica","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Honeywell (Canada); University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Modular design; Stability (learning theory); Reinforcement; Control (management); Computer science; Control theory (sociology); Control engineering; Engineering; Artificial intelligence; Machine learning; Structural engineering","score_opus":0.017381132492226135,"score_gpt":0.2899690171600185,"score_spread":0.2725878846677924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393103270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0041161785,0.0004718861,0.99135834,0.0006349716,0.00044576408,0.0011805313,0.0000033812385,0.0015899063,0.00019901147],"genre_scores_gemma":[0.60902566,0.0000035654034,0.3900344,0.00020255314,0.00005157268,0.0004719739,0.0000046779137,0.000031707204,0.00017390601],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773246,0.00008123798,0.00045881377,0.00059147686,0.00041933096,0.00071670837],"domain_scores_gemma":[0.9982968,0.0007620331,0.000114335264,0.000597173,0.0000901629,0.00013951864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00078516616,0.0002641902,0.0003410704,0.00014896118,0.00020360088,0.00075530045,0.0006779648,0.0001236669,0.000034324454],"category_scores_gemma":[0.00035527002,0.00024983412,0.00019878896,0.0002897215,0.000049853155,0.0007112919,0.000217511,0.0003710538,0.000044821158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002147523,0.000103456325,0.00013312051,0.00027262172,0.00035671442,0.00008870938,0.0029084936,0.067950144,0.0034279553,0.8457384,0.00019253406,0.07880634],"study_design_scores_gemma":[0.00049930136,0.00020786152,0.00011663696,0.00020277548,0.00010056651,0.000008008171,0.000056840894,0.9829187,0.00009458934,0.009220579,0.0062824744,0.00029167434],"about_ca_topic_score_codex":0.000019940617,"about_ca_topic_score_gemma":0.0000012659877,"teacher_disagreement_score":0.91496855,"about_ca_system_score_codex":0.00022324154,"about_ca_system_score_gemma":0.000121493846,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W4394930988","doi":"10.1049/cth2.12663","title":"An analytical adaptive optimal control approach without solving HJB equation for nonlinear systems with input constraints","year":2024,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Hamilton–Jacobi–Bellman equation; Nonlinear system; Optimal control; Control theory (sociology); Control (management); Computer science; Mathematical optimization; Applied mathematics; Mathematics; Artificial intelligence; Physics","score_opus":0.01645973642543845,"score_gpt":0.27292137618894996,"score_spread":0.2564616397635115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394930988","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037931182,0.0005386458,0.99476314,0.00025731683,0.000062028375,0.0029480734,0.00020500441,0.0004354952,0.00041101314],"genre_scores_gemma":[0.92242086,0.0000029513947,0.07434899,0.00017163597,0.00029114177,0.0026197531,0.00004039034,0.00002996304,0.00007433765],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99784696,0.0002926835,0.00036438415,0.000828657,0.0002385476,0.00042877748],"domain_scores_gemma":[0.99755,0.0012894594,0.00012913768,0.00055468443,0.00026259894,0.00021408254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016693083,0.00028704226,0.00040735945,0.00013758575,0.00034133758,0.00063895545,0.0005228663,0.00012347137,0.0000018594183],"category_scores_gemma":[0.000059881982,0.00023102836,0.00009182664,0.00028872624,0.00046172112,0.00059542654,0.00003379069,0.00024652248,0.000008280713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025279136,0.00012530519,0.000039452883,0.00003829149,0.00025904804,0.0000027354974,0.00022754318,0.010014569,0.0002420283,0.9478865,0.000007038871,0.040904645],"study_design_scores_gemma":[0.0020692393,0.0003798575,0.00003769513,0.00004300273,0.00020604813,0.000048987837,0.00029164672,0.987351,0.0000070135507,0.008223728,0.0010520186,0.00028978393],"about_ca_topic_score_codex":0.000005130886,"about_ca_topic_score_gemma":0.0000011304523,"teacher_disagreement_score":0.9773364,"about_ca_system_score_codex":0.00006271511,"about_ca_system_score_gemma":0.00019279117,"threshold_uncertainty_score":0.9421063},"labels":[],"label_agreement":null},{"id":"W4399968983","doi":"10.1007/s44196-024-00560-2","title":"Multi-agent Gradient-Based Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"International Journal of Computational Intelligence Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Wenzhou University; McGill University","keywords":"Reinforcement learning; Temporal difference learning; Generalization; Convergence (economics); Computer science; Stability (learning theory); Algorithm; Set (abstract data type); Rate of convergence; Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Key (lock)","score_opus":0.027518540415417264,"score_gpt":0.3322516421591333,"score_spread":0.30473310174371604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399968983","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020969199,0.0011587834,0.9918543,0.0014407563,0.004776507,0.00037634306,0.000048729853,0.00011763564,0.000017246022],"genre_scores_gemma":[0.85879254,0.000021489102,0.1400208,0.00012149953,0.0007442385,0.000043772015,0.000082832514,0.000021022628,0.00015180181],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968323,0.00013687336,0.0011449215,0.0003397554,0.0012139938,0.00033216458],"domain_scores_gemma":[0.9957617,0.0010390232,0.0005009926,0.00014726545,0.0023731082,0.00017793408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009612139,0.00024538694,0.00031001863,0.0007572325,0.000115107214,0.00087876176,0.0014549101,0.00007363263,0.000006376977],"category_scores_gemma":[0.00043127107,0.00022306832,0.00035088437,0.0004061955,0.00008593927,0.00069714093,0.00011485219,0.0003346827,0.00003031643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017751563,0.00007849432,0.000021167483,0.000030961208,0.00030689375,0.000094567375,0.00022253457,0.77061504,0.000045830784,0.050553937,0.00013117568,0.17788163],"study_design_scores_gemma":[0.00042498557,0.000289388,0.000060120325,0.0004101699,0.000021107737,0.00026302377,0.00011050225,0.9813492,0.00011515683,0.0031907316,0.013562212,0.00020342549],"about_ca_topic_score_codex":0.000040180377,"about_ca_topic_score_gemma":0.0000012175523,"teacher_disagreement_score":0.85858285,"about_ca_system_score_codex":0.0008873103,"about_ca_system_score_gemma":0.0008207517,"threshold_uncertainty_score":0.9096462},"labels":[],"label_agreement":null},{"id":"W4402264024","doi":"10.23919/acc60939.2024.10644694","title":"Synchronization Error Elimination for Heterogeneous Discrete-Time Multi-Agent Systems: A Reinforcement Learning Design Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Synchronization (alternating current); Multi-agent system; Discrete time and continuous time; Distributed computing; Control theory (sociology); Artificial intelligence; Control (management); Mathematics; Computer network","score_opus":0.029447153371063337,"score_gpt":0.2701662081594358,"score_spread":0.24071905478837247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402264024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000032484084,0.0004888775,0.99609834,0.00014826444,0.0003159075,0.0018786007,0.0000013427698,0.000887616,0.00014854902],"genre_scores_gemma":[0.7412665,0.0000036104907,0.25420862,0.000025194293,0.00005405746,0.0005461191,0.00004302146,0.000025900452,0.0038269851],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821323,0.00015118408,0.00035138332,0.0005902069,0.00031417055,0.00037982335],"domain_scores_gemma":[0.9991653,0.00018766714,0.00009759978,0.00031254799,0.00015374753,0.0000831691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072438316,0.0002149614,0.00019609027,0.0001706511,0.00019241599,0.0006194128,0.00044941608,0.00008096561,0.0000048217194],"category_scores_gemma":[0.00010758167,0.00018448368,0.000104326995,0.00028853136,0.000027086424,0.0004905432,0.00013915786,0.00010892047,0.00006887564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011283796,0.00003736073,0.0000024637893,0.00014767071,0.00008864771,0.0000068718937,0.0005407049,0.946051,0.0004356531,0.02249757,0.000096371165,0.030084401],"study_design_scores_gemma":[0.00037028242,0.00029428615,0.0000037970146,0.000059764843,0.000031445983,0.000023558485,0.000053576066,0.9977055,0.00012925777,0.000043352447,0.0010561458,0.0002290265],"about_ca_topic_score_codex":0.000017002358,"about_ca_topic_score_gemma":6.41651e-7,"teacher_disagreement_score":0.7418897,"about_ca_system_score_codex":0.00037261902,"about_ca_system_score_gemma":0.00009396545,"threshold_uncertainty_score":0.75230265},"labels":[],"label_agreement":null},{"id":"W4403677871","doi":"10.1109/case59546.2024.10711789","title":"An Application of Model-Free Reinforcement Learning to the Control of Aerial Vehicles With Slung Payloads","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Drone; Aeronautics; Aerodynamics; Aerospace engineering; Control engineering; Marine engineering; Engineering; Artificial intelligence; Biology","score_opus":0.007227896043263617,"score_gpt":0.2377574844089583,"score_spread":0.23052958836569468,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403677871","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007980219,0.000042852538,0.98996234,0.0010369322,0.000039115537,0.0004895981,0.0000015023212,0.0001321915,0.00031527728],"genre_scores_gemma":[0.9695852,8.205745e-7,0.03008698,0.000098821016,0.00003588693,0.00008312222,0.0000015908671,0.000007852589,0.00009975374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902904,0.00004571945,0.00022259528,0.0002440897,0.00029847783,0.00016010358],"domain_scores_gemma":[0.99904114,0.000080745514,0.000076010365,0.00063837576,0.00011558176,0.000048145845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042308096,0.00009386123,0.00014143436,0.00006238457,0.000048526803,0.00006757368,0.00088405923,0.00002686066,0.000001551184],"category_scores_gemma":[0.000022809638,0.000056554873,0.000037414888,0.00025367248,0.000045948687,0.00022234411,0.00012329596,0.00009053798,0.0000036828583],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005703185,0.00001737882,0.00011075621,0.000014683586,0.00004024935,5.6979917e-7,0.00091189,0.64215815,0.013765672,0.25953692,0.000024821413,0.08336189],"study_design_scores_gemma":[0.0003837709,0.00037441577,0.00009388082,0.000016351752,0.000016122623,0.0000011874853,0.000045417204,0.9967116,0.0011039318,0.00073798554,0.00044150066,0.00007380247],"about_ca_topic_score_codex":0.00013035047,"about_ca_topic_score_gemma":0.00003921518,"teacher_disagreement_score":0.96160495,"about_ca_system_score_codex":0.000030574436,"about_ca_system_score_gemma":0.00007113716,"threshold_uncertainty_score":0.23062408},"labels":[],"label_agreement":null},{"id":"W4404688066","doi":"10.1109/tac.2024.3505812","title":"Linear Convergent Distributed Nash Equilibrium Seeking With Compression","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Nash equilibrium; Mathematical economics; Epsilon-equilibrium; Compression (physics); Best response; Mathematics; Computer science; Mathematical optimization; Thermodynamics; Physics","score_opus":0.010352131341741634,"score_gpt":0.2418424198324642,"score_spread":0.2314902884907226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404688066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0046680355,0.000114140916,0.98909134,0.0017337187,0.0012024515,0.0007482179,0.00006997739,0.0023065496,0.000065565284],"genre_scores_gemma":[0.98749244,0.0000025955007,0.011750778,0.00023926419,0.000050702332,0.00018627873,0.0000053882522,0.000037265123,0.00023530818],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775565,0.00015568534,0.00042338544,0.00061629247,0.0005461726,0.0005028192],"domain_scores_gemma":[0.9983902,0.0005223293,0.00009230859,0.00069746294,0.000105876745,0.00019182672],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029274804,0.00033454245,0.00038812522,0.00022458221,0.00018810638,0.0003329169,0.00063429057,0.0001011487,0.00007343341],"category_scores_gemma":[0.00000912339,0.00026243477,0.00019101972,0.0006071867,0.00009628732,0.00050651026,0.000005480728,0.00033044914,0.00020526601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027570766,0.001122977,0.000036978356,0.00054836407,0.0019056224,0.0007672662,0.0017239804,0.14785595,0.032993134,0.0061668134,0.00076424977,0.80583894],"study_design_scores_gemma":[0.0016018596,0.0002982053,0.00008861936,0.0003445233,0.000106248764,0.000063228355,0.000018203762,0.9949852,0.00091480394,0.00015656344,0.0011135663,0.0003089399],"about_ca_topic_score_codex":0.000022086706,"about_ca_topic_score_gemma":0.000012614171,"teacher_disagreement_score":0.9828244,"about_ca_system_score_codex":0.00019163525,"about_ca_system_score_gemma":0.00018633272,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null},{"id":"W4404940644","doi":"10.1007/s11071-024-10698-5","title":"Constrained predictive control for consensus of nonlinear multi-agent systems by using game Q-learning","year":2024,"lang":"en","type":"article","venue":"Nonlinear Dynamics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Nonlinear system; Model predictive control; Control theory (sociology); Computer science; Multi-agent system; Control (management); Mathematics; Artificial intelligence; Machine learning; Physics","score_opus":0.01627242911429019,"score_gpt":0.27279503223025864,"score_spread":0.2565226031159685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404940644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013044271,0.001061203,0.9812352,0.00018367593,0.0011361062,0.001442324,0.0013378899,0.00052199856,0.000037339163],"genre_scores_gemma":[0.725022,0.0000110656265,0.27418658,0.00004377874,0.00017262176,0.00006166989,0.00013835407,0.00006770946,0.00029618127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726486,0.00019206968,0.0007637218,0.0007523464,0.0004125382,0.0006144607],"domain_scores_gemma":[0.99758977,0.000933933,0.00032184442,0.00047036126,0.0005079025,0.00017616518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007926839,0.00037498464,0.0006186914,0.00021245846,0.00012754681,0.0002419628,0.0006515405,0.00022710845,0.0000015655987],"category_scores_gemma":[0.00037721457,0.00036801785,0.00026641355,0.00041009142,0.00029833845,0.00018663265,0.0001403499,0.0004467022,0.0000074437435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00075285794,0.0016468993,0.0028641194,0.0023725447,0.0037293124,0.00038824233,0.0030121794,0.7753369,0.03258339,0.04986205,0.00032141674,0.12713005],"study_design_scores_gemma":[0.0020353645,0.00037943298,0.000010827313,0.00020606667,0.00012000878,0.000064932225,0.00021876542,0.99491006,0.00005828362,0.00003585398,0.0016245922,0.00033583032],"about_ca_topic_score_codex":0.00009295147,"about_ca_topic_score_gemma":0.000016231843,"teacher_disagreement_score":0.7119778,"about_ca_system_score_codex":0.0003774665,"about_ca_system_score_gemma":0.0004591196,"threshold_uncertainty_score":0.99987715},"labels":[],"label_agreement":null},{"id":"W4405166175","doi":"10.1007/s12555-024-0321-6","title":"Output Feedback Control of Variable-loaded Four-joint Manipulators With Unknown Saturated Actuator Dynamics","year":2024,"lang":"en","type":"article","venue":"International Journal of Control Automation and Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Memorial University of Newfoundland","funders":"","keywords":"Mechatronics; Robotics; Control theory (sociology); Dynamics (music); Actuator; Variable (mathematics); Joint (building); Control (management); Robot manipulator; Artificial intelligence; Control engineering; Feedback control; Computer science; Engineering; Mathematics; Robot; Physics; Mathematical analysis; Structural engineering","score_opus":0.012951002446884024,"score_gpt":0.2280800964824202,"score_spread":0.21512909403553618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405166175","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01983844,0.0007671307,0.974719,0.0017443409,0.002246317,0.00035774618,0.00003163035,0.000114512564,0.00018086882],"genre_scores_gemma":[0.9947943,0.000009251097,0.0046549346,0.000116981624,0.00022751212,0.000011579418,0.000005182578,0.000017904256,0.00016234045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973673,0.00020692268,0.0010398471,0.00024181079,0.0009381953,0.00020588243],"domain_scores_gemma":[0.9970082,0.00035622407,0.00089282694,0.00019157596,0.0014172774,0.00013388983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010431343,0.00022241916,0.0005375018,0.0004791653,0.000046195237,0.0006162677,0.00062505575,0.00010539484,0.000005639169],"category_scores_gemma":[0.00015220762,0.00016071773,0.00013548654,0.0002470702,0.00007069494,0.0009051691,0.000039903003,0.00025307192,0.0000049001737],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068396813,0.00018971051,0.0016439338,0.00024420003,0.0045799185,0.00048913684,0.00091414433,0.024614183,0.00792394,0.8903599,0.00030732993,0.06804966],"study_design_scores_gemma":[0.0035667513,0.00026298614,0.0031022383,0.000561401,0.00008860259,0.0009128806,0.00006807922,0.9894159,0.000027774053,0.0006924553,0.0011370236,0.0001639053],"about_ca_topic_score_codex":0.000048199254,"about_ca_topic_score_gemma":0.0000068167888,"teacher_disagreement_score":0.97495586,"about_ca_system_score_codex":0.00028714212,"about_ca_system_score_gemma":0.00030582142,"threshold_uncertainty_score":0.6553879},"labels":[],"label_agreement":null},{"id":"W4406053750","doi":"10.1016/j.isatra.2024.12.045","title":"Fuzzy reinforcement learning based control of linear systems with input saturation","year":2025,"lang":"en","type":"article","venue":"ISA Transactions","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Control theory (sociology); Artificial intelligence; Control engineering; Control (management); Engineering","score_opus":0.006506808054315666,"score_gpt":0.2226989623850349,"score_spread":0.21619215433071923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406053750","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026733588,0.000072404415,0.99693286,0.0006409084,0.00022544865,0.00042183368,0.0000022639747,0.00016988043,0.0012670358],"genre_scores_gemma":[0.990175,0.0000019710021,0.008905487,0.00009209676,0.000013413465,0.00008072543,0.000003592509,0.000005834799,0.0007218897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905366,0.0000855909,0.00025800007,0.00021518949,0.00021130513,0.00017626294],"domain_scores_gemma":[0.99920607,0.00015568854,0.000112177055,0.00029573374,0.00019115416,0.000039156144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018976755,0.00011465862,0.0001842943,0.0001658584,0.00017905448,0.000056301287,0.0002481442,0.000054229607,0.0000030474887],"category_scores_gemma":[0.000016229817,0.00010006298,0.00006413617,0.0004331142,0.000050605653,0.00024500708,0.0000032692615,0.00019480898,0.0000042963934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053616302,0.000045546352,0.00010689147,0.000039807623,0.000096556745,0.0000020011908,0.0001786316,0.97459173,0.0010673155,0.014635929,0.000005764613,0.009176221],"study_design_scores_gemma":[0.0013604056,0.0001828336,0.00021427264,0.000085599735,0.000049664824,0.000002154067,0.00005508293,0.9957982,0.00048744623,0.0000381329,0.0016288754,0.0000973375],"about_ca_topic_score_codex":0.00011429283,"about_ca_topic_score_gemma":0.000031918753,"teacher_disagreement_score":0.9899077,"about_ca_system_score_codex":0.000076284945,"about_ca_system_score_gemma":0.00017806186,"threshold_uncertainty_score":0.408045},"labels":[],"label_agreement":null},{"id":"W4406274801","doi":"10.1007/s40998-024-00782-2","title":"Robust $${H}_{\\infty }$$ Output Consensus in Heterogeneous Multi-agent Discrete-Time Systems Using Q-Learning Algorithm","year":2025,"lang":"en","type":"article","venue":"Iranian Journal of Science and Technology Transactions of Electrical Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Robustness (evolution); Computer science; Upper and lower bounds; Discrete time and continuous time; Multi-agent system; Stability theory; Control theory (sociology); Stability (learning theory); System dynamics; Algorithm; Mathematical optimization; Mathematics; Control (management); Nonlinear system; Artificial intelligence; Machine learning","score_opus":0.009852557882422003,"score_gpt":0.22272833942317066,"score_spread":0.21287578154074865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406274801","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048234876,0.0010605205,0.95010364,0.00022754687,0.00018053125,0.00012365433,8.8049825e-7,0.000064728076,0.000003616846],"genre_scores_gemma":[0.8519253,0.000021286087,0.14802295,0.0000046146615,0.000005596975,0.000002604818,3.0259358e-8,0.0000054414463,0.000012145395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984988,0.000029515904,0.00052854663,0.000256882,0.00028612086,0.00040011783],"domain_scores_gemma":[0.99907464,0.00011178587,0.0001782387,0.00017530123,0.0003716088,0.0000884189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077268353,0.00014616572,0.0003642447,0.0021407215,0.00016196864,0.0000661591,0.00068274245,0.00012061282,3.5263167e-7],"category_scores_gemma":[0.00023919702,0.00013822455,0.000060681527,0.0034048664,0.00043890357,0.00026695782,0.000034374752,0.00060355937,2.830664e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010737449,0.00011957142,0.00029044042,0.000028487919,0.00008062466,0.0001312832,0.0001277156,0.802746,0.04712089,0.0012652717,5.3009495e-7,0.14807847],"study_design_scores_gemma":[0.0005805338,0.00021362127,0.00011716678,0.000121491714,0.000022692897,0.0005420335,0.00004693285,0.9962397,0.0019194,0.00004445398,0.00003929909,0.00011263514],"about_ca_topic_score_codex":0.000014972746,"about_ca_topic_score_gemma":8.1655315e-7,"teacher_disagreement_score":0.80369043,"about_ca_system_score_codex":0.0002254286,"about_ca_system_score_gemma":0.00029248773,"threshold_uncertainty_score":0.56366336},"labels":[],"label_agreement":null},{"id":"W4407949080","doi":"10.1109/cdc56724.2024.10886170","title":"Leveraging Control Inputs to Enforce Constraints in Differential Dynamic Programming for Nonlinear Optimization*","year":2024,"lang":"en","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Differential dynamic programming; Nonlinear system; Dynamic programming; Differential (mechanical device); Control theory (sociology); Nonlinear programming; Mathematical optimization; Control (management); Algorithm; Mathematics; Artificial intelligence; Engineering","score_opus":0.009406045092775307,"score_gpt":0.26468479950902857,"score_spread":0.25527875441625325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407949080","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001279381,0.000051791663,0.9935825,0.0021112435,0.0005794735,0.0015794251,0.000014331428,0.0006289576,0.00017288393],"genre_scores_gemma":[0.60869545,8.383417e-7,0.39039516,0.00033711345,0.0000441562,0.0002152949,0.000013465763,0.000019120649,0.00027940187],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979817,0.00004763332,0.00041340775,0.00069152977,0.00024846234,0.00061726064],"domain_scores_gemma":[0.99905014,0.00030366328,0.000046270896,0.00033391087,0.0001148477,0.00015117365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035906283,0.0002460907,0.00028681205,0.00037063958,0.00009022167,0.00064440124,0.0006814552,0.00008077219,0.000019837515],"category_scores_gemma":[0.00013131191,0.00023012517,0.00011982989,0.0005728824,0.00006755113,0.00044692738,0.00016288988,0.00018264576,0.000020697044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000451156,0.00012561609,0.00018616971,0.00009675037,0.000114738024,0.000063114836,0.0013263294,0.114246376,0.00057133375,0.05163666,0.000055551125,0.83153224],"study_design_scores_gemma":[0.0011005814,0.00009895668,0.000060218892,0.00009117859,0.000012356531,0.000013609768,0.000026900345,0.9960723,0.00003371383,0.00026744462,0.0019496832,0.00027308622],"about_ca_topic_score_codex":0.000018797347,"about_ca_topic_score_gemma":0.000034070352,"teacher_disagreement_score":0.8818259,"about_ca_system_score_codex":0.0002036992,"about_ca_system_score_gemma":0.00017762798,"threshold_uncertainty_score":0.93842316},"labels":[],"label_agreement":null},{"id":"W4408017106","doi":"10.1109/tcns.2025.3546785","title":"Distributed Fixed-Time Nash Equilibrium Seeking for Noncooperative Games","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Control of Network Systems","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"National Natural Science Foundation of China","keywords":"Nash equilibrium; Epsilon-equilibrium; Computer science; Mathematical optimization; Game theory; Best response; Mathematical economics; Mathematics","score_opus":0.00811472733126547,"score_gpt":0.23666487334137398,"score_spread":0.2285501460101085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408017106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002733527,0.00054400665,0.99355876,0.00062358397,0.0024302418,0.001851605,0.00018921745,0.00030931272,0.0002199119],"genre_scores_gemma":[0.9938456,0.0000035669514,0.0040736515,0.0001671554,0.00017128976,0.00058805366,0.000007963137,0.000021817996,0.0011209126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975274,0.0002901224,0.0007245221,0.00057746697,0.0002879764,0.00059251086],"domain_scores_gemma":[0.9969519,0.0014910125,0.00029299664,0.00069402973,0.000471733,0.00009832307],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006830651,0.000319316,0.0007743678,0.00017519711,0.00024435687,0.00018932977,0.00082884746,0.00016551175,0.0000031033287],"category_scores_gemma":[0.000028650878,0.00030259372,0.00033097522,0.0007643836,0.00010056546,0.00033386284,0.0000058630003,0.00023109079,0.00001246499],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004053404,0.00024455905,0.000036650006,0.00011476535,0.001040364,0.000006705968,0.00014904662,0.9561998,0.005752392,0.009531674,0.0020871144,0.024431543],"study_design_scores_gemma":[0.0028362093,0.00034258675,0.000027306558,0.0003069235,0.00011688808,0.0000049494943,0.000024662302,0.99234146,0.0003319484,0.00017346143,0.0032469619,0.00024661454],"about_ca_topic_score_codex":0.000031808788,"about_ca_topic_score_gemma":0.000018719615,"teacher_disagreement_score":0.99357224,"about_ca_system_score_codex":0.00018266065,"about_ca_system_score_gemma":0.00021279715,"threshold_uncertainty_score":0.9999426},"labels":[],"label_agreement":null},{"id":"W4408346432","doi":"10.1016/j.conengprac.2025.106313","title":"Two-stage three-phase photovoltaic grid-connected inverter control method based on off-policy integral reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Natural Science Foundation of China","keywords":"Photovoltaic system; Inverter; Grid; Reinforcement learning; Control theory (sociology); Stage (stratigraphy); Phase (matter); Three-phase; Control (management); Computer science; Electronic engineering; Engineering; Mathematics; Electrical engineering; Physics; Voltage; Artificial intelligence; Biology","score_opus":0.007856394716716102,"score_gpt":0.30010370410503107,"score_spread":0.29224730938831495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408346432","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008961503,0.00019477906,0.98985535,0.0041703284,0.00086704205,0.0012824003,0.00001027525,0.0010831095,0.00244708],"genre_scores_gemma":[0.9317844,0.000004748754,0.05946827,0.007457825,0.0002443382,0.0004112701,0.000015320924,0.00005732095,0.00055654155],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961879,0.00052198477,0.00074975926,0.0009300124,0.00060677284,0.0010035718],"domain_scores_gemma":[0.9924888,0.00515242,0.00042942684,0.0011935191,0.0004671273,0.0002687005],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021673455,0.00063522457,0.00075771863,0.00089910487,0.00025381913,0.00046466762,0.0012538274,0.00018639484,0.000019561601],"category_scores_gemma":[0.009602523,0.0006252569,0.00028464585,0.0012135642,0.00005439899,0.0011226756,0.00016979656,0.0013445015,0.000050267052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00065289426,0.00018769753,0.000037914295,0.000039652357,0.0003827508,0.00009130243,0.000092753275,0.8923984,0.004372623,0.059103876,0.00008799217,0.042552114],"study_design_scores_gemma":[0.017291093,0.0005568523,0.00007929376,0.00012117749,0.00017285979,0.000011976373,0.000025688685,0.9321932,0.00023615993,0.00005976098,0.048747137,0.0005048037],"about_ca_topic_score_codex":0.0004858302,"about_ca_topic_score_gemma":0.000021528742,"teacher_disagreement_score":0.93169475,"about_ca_system_score_codex":0.00061536924,"about_ca_system_score_gemma":0.0006580913,"threshold_uncertainty_score":0.9996199},"labels":[],"label_agreement":null},{"id":"W4409785434","doi":"10.61091/jcmcc127b-506","title":"Reinforcement learning-based state space dimensionality reduction and optimal control strategy design in robot navigation systems","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Dimensionality reduction; State space; Computer science; Reduction (mathematics); Control (management); State (computer science); Robot; Artificial intelligence; Curse of dimensionality; Space (punctuation); Robot learning; Control engineering; Control theory (sociology); Engineering; Mobile robot; Mathematics; Algorithm","score_opus":0.012314661775984894,"score_gpt":0.25544694319744843,"score_spread":0.24313228142146354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409785434","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12745507,0.000344673,0.8669354,0.00020471652,0.0044546193,0.0005319908,2.7048586e-7,0.00004066935,0.000032588523],"genre_scores_gemma":[0.9865763,0.000009969123,0.013230083,0.000008348324,0.00014644339,0.00000606797,8.7351503e-7,0.000012556947,0.000009329935],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99719024,0.00046549173,0.0011431572,0.00029757837,0.000566541,0.00033698403],"domain_scores_gemma":[0.99701506,0.0009326138,0.0011029007,0.00021566206,0.0006048524,0.0001288937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0035601275,0.00027152558,0.0006919187,0.00029392887,0.0002637414,0.00046679733,0.00036804614,0.0001276627,2.6764457e-7],"category_scores_gemma":[0.0003478372,0.00025578286,0.0000827524,0.00042053347,0.00009021449,0.00037793082,0.00015922399,0.0005827574,3.3152816e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019154733,0.00023229168,0.0000934748,0.00015007184,0.00008308632,0.000028365372,0.00034121302,0.43827355,0.00056504976,0.55824065,0.000013027023,0.0017876921],"study_design_scores_gemma":[0.0064599183,0.0008727196,0.00013728949,0.0006072512,0.000043660264,0.00004926741,0.0001507128,0.88255066,0.00018831764,0.10870863,0.00003067278,0.00020089978],"about_ca_topic_score_codex":0.000034014414,"about_ca_topic_score_gemma":1.3892546e-7,"teacher_disagreement_score":0.85912126,"about_ca_system_score_codex":0.00023091951,"about_ca_system_score_gemma":0.00034494427,"threshold_uncertainty_score":0.99998945},"labels":[],"label_agreement":null},{"id":"W4413337006","doi":"10.1002/rnc.70150","title":"Strategic Learning for Disturbance Rejection in Multi‐Agent Systems: Nash and Minmax in Graphical Games","year":2025,"lang":"en","type":"article","venue":"International Journal of Robust and Nonlinear Control","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada","keywords":"Minimax; Computer science; Nash equilibrium; Disturbance (geology); Mathematical optimization; Artificial intelligence; Mathematical economics; Mathematics; Biology","score_opus":0.018026759236959483,"score_gpt":0.2772433489958614,"score_spread":0.25921658975890194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413337006","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14377268,0.003020593,0.85061055,0.0016816796,0.00065413554,0.00022633877,0.0000035668838,0.00001022429,0.000020254007],"genre_scores_gemma":[0.98718196,0.00019346409,0.012361208,0.00008267377,0.00008838163,0.000013909903,0.0000012500876,0.0000040255954,0.00007314917],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998997,0.00009514329,0.0004183038,0.00017619299,0.00017634517,0.00013703204],"domain_scores_gemma":[0.99914074,0.000275558,0.00020936223,0.000055717177,0.00028135264,0.000037265243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006326415,0.00009913104,0.00023121637,0.0003794429,0.000031841035,0.00016210083,0.00027400703,0.00005939263,2.052573e-7],"category_scores_gemma":[0.0001817666,0.00008687735,0.00005598214,0.00013394434,0.000043422922,0.00029348067,0.000043369797,0.00025361837,1.1491725e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003527363,0.0012226184,0.44908467,0.0003156299,0.0010687003,0.0006864034,0.0017098252,0.1476196,0.0022453489,0.16106829,0.00009064353,0.23136088],"study_design_scores_gemma":[0.005101471,0.00013908856,0.016851995,0.00023657022,0.000010951095,0.000053369655,0.0001648575,0.9755402,0.000005552859,0.0007810874,0.001029269,0.00008555571],"about_ca_topic_score_codex":0.000032795804,"about_ca_topic_score_gemma":0.00009668289,"teacher_disagreement_score":0.84340924,"about_ca_system_score_codex":0.000092271366,"about_ca_system_score_gemma":0.00007895896,"threshold_uncertainty_score":0.35427555},"labels":[],"label_agreement":null},{"id":"W4415054220","doi":"10.1016/j.oceaneng.2025.123056","title":"Value decomposition reinforcement learning-based formation control for multi-USVs with incomplete information","year":2025,"lang":"en","type":"article","venue":"Ocean Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Shanghai Municipal Education Commission; National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Control theory (sociology); Reinforcement learning; Complete information; Convergence (economics); Controller (irrigation); Kalman filter; Position (finance); Filter (signal processing); Observer (physics); Decomposition","score_opus":0.005645907648123808,"score_gpt":0.22253361206875372,"score_spread":0.2168877044206299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415054220","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001132016,0.000015942584,0.99731296,0.00024271444,0.00012340183,0.00073438225,0.0000032704722,0.00039016583,0.000045166413],"genre_scores_gemma":[0.8307261,4.4179524e-7,0.16888323,0.00022188107,0.00001269655,0.000058200894,0.00006854849,0.00000723754,0.000021690566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99913275,0.000018127384,0.00028490752,0.00014339166,0.00015664997,0.00026417256],"domain_scores_gemma":[0.9993566,0.000107665575,0.00012412567,0.00020690628,0.00015828625,0.000046374553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026738443,0.00015714056,0.00016333851,0.000260047,0.00013547519,0.00015995675,0.00027772633,0.000045532983,5.1356824e-7],"category_scores_gemma":[0.000075024975,0.00015180309,0.000055886114,0.00024623313,0.00001114709,0.0011505651,0.00003574472,0.00012035418,0.0000039816878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034300218,0.000010287079,0.0000533142,0.00007210282,0.00002765679,5.8905687e-7,0.00009983526,0.96543014,0.00016071464,0.02779006,0.000023611576,0.0062973793],"study_design_scores_gemma":[0.0028271836,0.00016659216,0.00040271584,0.00009508053,0.000017695003,0.0000021878782,0.000008791035,0.9921465,0.0005115975,0.0000317332,0.0036282698,0.00016168905],"about_ca_topic_score_codex":0.0000076674405,"about_ca_topic_score_gemma":0.0000014565558,"teacher_disagreement_score":0.8295941,"about_ca_system_score_codex":0.00020196736,"about_ca_system_score_gemma":0.000051033778,"threshold_uncertainty_score":0.619035},"labels":[],"label_agreement":null},{"id":"W4415820437","doi":"10.1109/tase.2025.3628059","title":"Distributed ADP-Based Optimal Security Control of Multiagent Systems Against DoS Attacks Within Differential Adversarial Game Framework","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Liaoning Revitalization Talents Program","keywords":"Optimal control; Differential game; Adversarial system; Multi-agent system; Nash equilibrium; Differential (mechanical device); State (computer science); Control (management); Game theory","score_opus":0.006941797571003428,"score_gpt":0.23688986323388997,"score_spread":0.22994806566288653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415820437","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09084855,0.000087001856,0.9023791,0.00021798407,0.004944802,0.0010132211,0.00017835354,0.00032548656,0.000005520515],"genre_scores_gemma":[0.9925894,0.0000114500435,0.0071454626,0.000060953225,0.000050073937,0.000112169844,0.0000051688216,0.00001698204,0.000008352566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960533,0.00012464052,0.001019994,0.0009214322,0.001184646,0.00069598155],"domain_scores_gemma":[0.9974705,0.00049978204,0.0003691326,0.0007156349,0.00065850123,0.00028647538],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011822765,0.00047622412,0.0006296566,0.0009174702,0.0005103378,0.00064866646,0.00091923843,0.00028394183,0.0000053571403],"category_scores_gemma":[0.0002196888,0.00049953547,0.00019003994,0.0023457725,0.0005756473,0.0009775537,0.000015187156,0.00067129056,0.000005392275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009214255,0.00023839994,0.000012280927,0.0001983017,0.00011121372,0.000004532055,0.00085035636,0.9769134,0.009446387,0.0020602501,0.0000023912391,0.010070345],"study_design_scores_gemma":[0.0023810563,0.00018356656,0.0005509141,0.0008241596,0.00012494365,0.0000028488973,0.00011730852,0.9899331,0.0054425322,0.000013670884,0.000036716498,0.00038923818],"about_ca_topic_score_codex":0.000041324467,"about_ca_topic_score_gemma":0.0000030056028,"teacher_disagreement_score":0.90174085,"about_ca_system_score_codex":0.0005358344,"about_ca_system_score_gemma":0.0007803582,"threshold_uncertainty_score":0.9997456},"labels":[],"label_agreement":null},{"id":"W4416394014","doi":"10.1016/j.ifacol.2025.11.073","title":"An adaptive extremum-seeking control approach to reinforcement learning","year":2025,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Reinforcement learning; Control theory (sociology); Adaptive control; Nonlinear system; Convergence (economics); Basis (linear algebra); Stability (learning theory); Parametrization (atmospheric modeling); Optimal control","score_opus":0.011354211083284825,"score_gpt":0.2549083754554547,"score_spread":0.24355416437216987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416394014","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001150543,0.0001446171,0.9869556,0.0012419855,0.00028383592,0.00079895166,0.0000036943618,0.0005717949,0.0088490015],"genre_scores_gemma":[0.56203985,0.0000019211966,0.43487114,0.0014981102,0.00009071458,0.00008660626,0.000011840402,0.000015101184,0.001384755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720615,0.00021131904,0.00044087236,0.0009353316,0.0004666811,0.0007396347],"domain_scores_gemma":[0.9983289,0.00018699125,0.0001579583,0.00084580935,0.00022569128,0.00025459938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000669462,0.00036892944,0.00044350303,0.00031460077,0.00035601956,0.00026435396,0.0014766043,0.00012535197,0.000008684463],"category_scores_gemma":[0.00018979954,0.00035390523,0.00014479445,0.00078163546,0.000072013085,0.00055773277,0.00027967634,0.00046808922,0.000047459525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004975452,0.00072714296,0.0012476797,0.000049070244,0.00048673354,0.00005554072,0.0045871097,0.2994322,0.03303388,0.20900798,0.000028242412,0.45084688],"study_design_scores_gemma":[0.0014312556,0.00051130506,0.0004877559,0.00005341626,0.000032365377,0.000006061012,0.0004554652,0.9946445,0.00004657766,0.00020377863,0.001762164,0.00036532033],"about_ca_topic_score_codex":0.00010207353,"about_ca_topic_score_gemma":0.000019851012,"teacher_disagreement_score":0.69521236,"about_ca_system_score_codex":0.00026521136,"about_ca_system_score_gemma":0.00016840617,"threshold_uncertainty_score":0.9998913},"labels":[],"label_agreement":null},{"id":"W4416513177","doi":"10.1109/tcyb.2025.3630679","title":"HSMS-Based Event-Triggered Adaptive Dynamic Programming for Pursuit–Evasion Differential Games of Multiagent Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Liaoning Revitalization Talents Program","keywords":"Pursuer; Multi-agent system; Dynamic programming; Graph; Artificial neural network; Optimal control; Algebraic connectivity; Decentralised system; Differential game","score_opus":0.013725855747029034,"score_gpt":0.2699817020915951,"score_spread":0.25625584634456605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416513177","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0063378843,0.00021339451,0.9889462,0.0002331817,0.0017963866,0.0021229435,0.00007410633,0.00025082636,0.000025088402],"genre_scores_gemma":[0.9449236,0.000013146131,0.053685565,0.000040275463,0.000017527916,0.0005773699,0.0000075106755,0.000028184533,0.0007068147],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997574,0.00015347206,0.00063692837,0.00063973194,0.0004908688,0.00050503865],"domain_scores_gemma":[0.99798435,0.0005349314,0.00027376774,0.000732922,0.0003614355,0.00011261548],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027332176,0.00034533115,0.000468115,0.00040818547,0.00020897127,0.00015066528,0.00088974385,0.00018736414,0.0000033935137],"category_scores_gemma":[0.000023686176,0.0003373503,0.00036260235,0.00054069655,0.00014278833,0.00013812589,0.000009378727,0.0002684276,0.000005084849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005171364,0.0019918543,0.000019108113,0.00031146727,0.00051762344,0.000007816317,0.00044105816,0.17488842,0.0084527815,0.00936933,0.000060663388,0.80342275],"study_design_scores_gemma":[0.0023476852,0.0007151561,0.00013624545,0.0002909954,0.0001656383,0.0000014665405,0.00008537811,0.9859177,0.00920613,0.00028250134,0.0005618876,0.00028922845],"about_ca_topic_score_codex":0.00008331004,"about_ca_topic_score_gemma":0.000092063856,"teacher_disagreement_score":0.9385857,"about_ca_system_score_codex":0.00028515587,"about_ca_system_score_gemma":0.00024129606,"threshold_uncertainty_score":0.99990785},"labels":[],"label_agreement":null},{"id":"W4416551961","doi":"10.1049/cth2.70091","title":"Q‐Learning‐Based Controller Design for Logarithmic Quantised Input Systems","year":2025,"lang":"en","type":"article","venue":"IET Control Theory and Applications","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Dimension (graph theory); Control theory (sociology); Logarithm; Controller (irrigation); Scaling; Quadratic equation; Optimal control; Selection (genetic algorithm); Dynamical systems theory","score_opus":0.010001194281100637,"score_gpt":0.25917201403705514,"score_spread":0.2491708197559545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416551961","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000071837276,0.00084806076,0.99367064,0.0009892805,0.00010355929,0.003656953,0.000019249866,0.00033735568,0.00030306983],"genre_scores_gemma":[0.98002666,0.0000064449996,0.011777801,0.00082432415,0.00006688498,0.0062695625,0.000006870571,0.00001340179,0.0010080631],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981876,0.00052981864,0.00032212,0.00051510736,0.00011035524,0.00033499082],"domain_scores_gemma":[0.99535394,0.0037352184,0.0001623968,0.00044202755,0.00022099684,0.000085412976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017618984,0.00020297967,0.0003593307,0.00015007469,0.00047485947,0.00025205396,0.00060638064,0.00011203033,0.0000012714975],"category_scores_gemma":[0.00025315466,0.00018664669,0.0001081102,0.00028699837,0.0001452639,0.00013868966,0.00004819019,0.00017587432,0.00001057486],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022296773,0.00007202842,0.000041661533,0.00002499866,0.0001077513,5.190914e-7,0.000029119241,0.0092869215,0.00095721,0.95443606,0.00008986319,0.034730896],"study_design_scores_gemma":[0.005136726,0.00014074304,0.000106100306,0.000025115472,0.00008117931,0.0000020005268,0.000036625894,0.87351876,0.00004987604,0.091233805,0.02947696,0.00019210552],"about_ca_topic_score_codex":0.0000046751716,"about_ca_topic_score_gemma":7.3734606e-7,"teacher_disagreement_score":0.9818928,"about_ca_system_score_codex":0.000041917552,"about_ca_system_score_gemma":0.00013299703,"threshold_uncertainty_score":0.7611231},"labels":[],"label_agreement":null},{"id":"W4416937974","doi":"10.1103/5591-xjfr","title":"Reinforcement learning for optimal control of spin magnetometers","year":2025,"lang":"en","type":"article","venue":"Physical review. A/Physical review, A","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Hamiltonian (control theory); Reinforcement learning; Control theory (sociology); Quantum; Optimal control; Magnetometer; Quantum decoherence; Sensitivity (control systems); Quantum sensor","score_opus":0.01122195449124617,"score_gpt":0.3546552700581199,"score_spread":0.34343331556687373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416937974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002133536,0.04674383,0.9437541,0.0029116508,0.00013129869,0.0033391702,0.000005553983,0.00014818623,0.0008327187],"genre_scores_gemma":[0.9689634,0.017224716,0.0075586713,0.004416353,0.00016268509,0.0013420165,0.00001836123,0.0000323334,0.0002814975],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964594,0.00034067367,0.00095833564,0.0008563514,0.000660715,0.0007244796],"domain_scores_gemma":[0.9965486,0.0011215468,0.0006148184,0.0010653717,0.00043912747,0.00021052157],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090403226,0.00049817504,0.0020173853,0.00010102977,0.00012622817,0.00005661648,0.0015458897,0.000038862523,0.000006362723],"category_scores_gemma":[0.0020078027,0.00040683374,0.0012439193,0.0011395629,0.00018172032,0.00036843691,0.00039466898,0.0004426991,0.000065872846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006801132,0.0007454176,0.00007266538,0.016512515,0.00037991325,0.0000058111823,0.00007192609,0.00097199436,0.014940881,0.41136736,0.0018916079,0.5529719],"study_design_scores_gemma":[0.0019059532,0.0013975636,0.00017652339,0.016834147,0.0009400213,0.0000023151688,0.000004225913,0.8765733,0.0020066914,0.011198787,0.0882309,0.000729541],"about_ca_topic_score_codex":0.0000096428985,"about_ca_topic_score_gemma":3.7304073e-7,"teacher_disagreement_score":0.96682984,"about_ca_system_score_codex":0.00013249676,"about_ca_system_score_gemma":0.00018067447,"threshold_uncertainty_score":0.99983835},"labels":[],"label_agreement":null},{"id":"W6889105574","doi":"10.25384/sage.19100454.v1","title":"sj-docx-1-cjk-10.1177_20543581211072330 – Supplemental material for Designing an App for Immunosuppression Adherence and Communication: A Qualitative Approach","year":2022,"lang":"en","type":"article","venue":"Figshare","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Immunosuppression; Kidney disease; Qualitative research; Disease; mHealth; Kidney transplant","score_opus":0.07274771029118997,"score_gpt":0.33899621623686726,"score_spread":0.2662485059456773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6889105574","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00064008194,0.0005399184,0.3618459,0.00035426772,0.00018435335,0.005099363,0.63056535,0.00048465523,0.0002861109],"genre_scores_gemma":[0.28309247,5.900517e-7,0.34427342,0.00014015654,0.00007267212,0.014532711,0.3574661,0.00004058441,0.0003812957],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981012,0.00040713864,0.000297864,0.00055379566,0.00025714975,0.0003828533],"domain_scores_gemma":[0.9982591,0.00058707676,0.00024908467,0.0006498078,0.00016599151,0.00008888352],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00050797063,0.00020815572,0.00023553726,0.00007255544,0.0009145243,0.00031175208,0.0014696438,0.00005094001,0.018379865],"category_scores_gemma":[0.00018983246,0.00021779063,0.00007922246,0.00015463757,0.000025718686,0.00065643986,0.0012062375,0.00014653633,0.000010356794],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014439372,0.0011652899,0.000015507656,0.00064570276,0.00030355944,0.0000096224885,0.078297056,0.00042919765,0.009692651,0.02340109,0.7602786,0.12431777],"study_design_scores_gemma":[0.0061056893,0.0032426028,0.00008232912,0.00025248068,0.000040901235,0.00005914166,0.013661264,0.58782107,0.002500571,0.00567667,0.3793836,0.0011736737],"about_ca_topic_score_codex":0.000017665656,"about_ca_topic_score_gemma":0.00000365586,"teacher_disagreement_score":0.58739185,"about_ca_system_score_codex":0.00010576013,"about_ca_system_score_gemma":0.000096313976,"threshold_uncertainty_score":0.9825175},"labels":[],"label_agreement":null},{"id":"W6892972884","doi":"10.5281/zenodo.13312339","title":"Quantum Étale","year":2024,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Journal of Student Science and Technology","funders":"","keywords":"Quantum; Quantum system; Field (mathematics); Work (physics); Quantum entanglement","score_opus":0.04369204971112968,"score_gpt":0.2626687139271764,"score_spread":0.21897666421604672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892972884","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00072305434,0.010291079,0.8680312,0.018112307,0.002616156,0.0006655808,0.00029273832,0.0037770597,0.0954908],"genre_scores_gemma":[0.933887,0.0006241226,0.0054327026,0.0005735456,0.0014065499,1.1775162e-7,0.0008784258,0.0044939625,0.052703597],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679285,0.00060052477,0.00035016664,0.0008963194,0.0005609597,0.00079916505],"domain_scores_gemma":[0.99808437,0.00008105413,0.000076627926,0.0008167036,0.00062762894,0.00031359697],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012734451,0.00025542764,0.0002082006,0.0003211523,0.0019962888,0.00575014,0.0024255028,0.00013124505,0.007853029],"category_scores_gemma":[0.00060841464,0.00029023897,0.00013821702,0.0013669867,0.00046404856,0.0011511608,0.002733473,0.0006312276,0.057700064],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009203244,0.000084658255,1.9953646e-7,0.00012102601,0.00006333043,0.00016702086,0.0013229726,0.00004003356,0.0004986259,0.3816941,0.13269006,0.48330876],"study_design_scores_gemma":[0.0002112347,0.00027699833,0.000045983747,0.0001637384,0.000023269453,0.00047300456,0.00009192304,0.21450172,0.00003633421,0.0034330192,0.78050333,0.00023941697],"about_ca_topic_score_codex":0.00005125355,"about_ca_topic_score_gemma":4.0878047e-7,"teacher_disagreement_score":0.93316394,"about_ca_system_score_codex":0.00037976558,"about_ca_system_score_gemma":0.00001921748,"threshold_uncertainty_score":0.999955},"labels":[],"label_agreement":null},{"id":"W6925069730","doi":"10.17605/osf.io/6z352","title":"Supporting information for Scripts and datasets related to Carturan et al. 2023. Bumble bee pollination and the wildflower/crop trade-off: When do wildflower enhancements improve crop yield?","year":2022,"lang":"en","type":"article","venue":"OSF Preprints (OSF Preprints)","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wildflower; Pollination; Crop; Scripting language; Pollinator; Moorland","score_opus":0.008014052949171206,"score_gpt":0.2580603256777459,"score_spread":0.2500462727285747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925069730","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20058177,0.00005074571,0.7314456,0.039045762,0.0018716682,0.012167955,0.0008143383,0.00048165047,0.013540504],"genre_scores_gemma":[0.97172195,0.000043635824,0.013239827,0.0062117083,0.00002245985,0.0015556028,0.00024083402,0.000035991547,0.0069279806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9961175,0.0004790767,0.00081411115,0.0014290077,0.00059776637,0.0005625829],"domain_scores_gemma":[0.99689513,0.00052282994,0.00051171676,0.0017554114,0.00012226198,0.00019263489],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007737882,0.00030831186,0.0003615668,0.00018600083,0.00073389197,0.0006250746,0.0013847066,0.00009077117,0.0022544966],"category_scores_gemma":[0.0022758925,0.0002962877,0.0001043049,0.00029220298,0.00013261195,0.001805894,0.0030494195,0.00050454034,0.0023322578],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013656287,0.00055968313,0.0018092274,0.00015111298,0.00066143554,0.000022301867,0.03893219,0.0047672787,0.022466233,0.03773919,0.116747476,0.77477825],"study_design_scores_gemma":[0.008091454,0.000057247555,0.0057349703,0.00010970686,0.00014805236,0.00010821934,0.000930065,0.3337498,0.002586501,0.015812024,0.63151336,0.0011586214],"about_ca_topic_score_codex":0.00025330696,"about_ca_topic_score_gemma":0.00003814961,"teacher_disagreement_score":0.77361965,"about_ca_system_score_codex":0.00021923841,"about_ca_system_score_gemma":0.0001380034,"threshold_uncertainty_score":0.9999489},"labels":[],"label_agreement":null},{"id":"W6979308798","doi":"","title":"Strategic learning for disturbance rejection in multi-agent systems: Nash and Minmax in graphical games","year":2025,"lang":"en","type":"article","venue":"ArXiv.org","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Minimax; Nash equilibrium; Stability (learning theory); Reinforcement learning; Graphical model; Game theory; Control (management)","score_opus":0.03439879304186491,"score_gpt":0.2793073937287574,"score_spread":0.2449086006868925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979308798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.63688564,0.001145246,0.3609511,0.00028236315,0.00023642804,0.00039197985,4.976844e-7,0.00006520773,0.00004152045],"genre_scores_gemma":[0.9970258,0.000041913296,0.0023158356,0.000055200955,0.00001566343,0.00017961214,0.0000019951426,0.0000065575264,0.00035741166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99877155,0.00012629974,0.0002688371,0.00045712263,0.00009070126,0.00028546894],"domain_scores_gemma":[0.9994499,0.00017864168,0.00007807348,0.00021011403,0.000048213642,0.000035053028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042643002,0.00013229309,0.00021043287,0.0002105229,0.00007473807,0.000086984124,0.00026336568,0.00008292222,1.4662733e-7],"category_scores_gemma":[0.00012480759,0.00012914799,0.00004027686,0.00050540507,0.000057624526,0.00023318133,0.00010081306,0.00023761432,0.0000017813221],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027067603,0.0000887844,0.95965564,0.00011214642,0.000017276427,0.000017008591,0.0004140262,0.0009939624,0.00040974747,0.031680007,0.000008949783,0.0065753846],"study_design_scores_gemma":[0.0013378522,0.000097222626,0.51826394,0.0001755552,0.0000056759172,0.0000032221633,0.0003339309,0.4778768,0.000026888127,0.0008949444,0.0008160105,0.00016795586],"about_ca_topic_score_codex":0.00015928654,"about_ca_topic_score_gemma":0.00033482778,"teacher_disagreement_score":0.47688285,"about_ca_system_score_codex":0.00012043593,"about_ca_system_score_gemma":0.000052083727,"threshold_uncertainty_score":0.5266502},"labels":[],"label_agreement":null},{"id":"W7123338223","doi":"10.1109/cdc57313.2025.11312866","title":"Stochastic Reinforcement Learning with Stability Guarantees for Control of Unknown Nonlinear Systems","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Convergence (economics); Stability (learning theory); Nonlinear system; Representation (politics); Control theory (sociology); Controller (irrigation); Control (management); Artificial neural network","score_opus":0.010934864706497797,"score_gpt":0.24366932706177477,"score_spread":0.23273446235527698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123338223","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019835255,0.0010777971,0.9895976,0.0004962015,0.00077432615,0.005208578,0.000019585503,0.0001732496,0.0006690973],"genre_scores_gemma":[0.9810605,0.0000050120975,0.015353317,0.00009081487,0.000067472436,0.00038033456,0.000007776053,0.000024837993,0.0030099219],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99554646,0.00030940084,0.0014336406,0.0010810476,0.00067323033,0.0009562501],"domain_scores_gemma":[0.9945561,0.0016549444,0.0007779575,0.0011363719,0.0017279118,0.00014668512],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019553476,0.00055948994,0.0012220325,0.00027773262,0.00036732343,0.00029402206,0.0012417024,0.00018112932,0.000016376252],"category_scores_gemma":[0.0006988355,0.00045424665,0.0002838573,0.0007769697,0.0005081794,0.00040118638,0.0002886123,0.00041576105,0.0000049050072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014935328,0.0003749576,0.0005551099,0.0010122559,0.0009166552,0.0000030704002,0.00065701024,0.76231194,0.00039275718,0.20924854,0.00001315453,0.023021018],"study_design_scores_gemma":[0.006924737,0.0026512097,0.000076028125,0.00072592637,0.0003036584,0.000003589427,0.00051932014,0.9870769,0.00013718348,0.00013506308,0.0010330726,0.00041334546],"about_ca_topic_score_codex":0.00030991514,"about_ca_topic_score_gemma":0.00006506122,"teacher_disagreement_score":0.979077,"about_ca_system_score_codex":0.00031060344,"about_ca_system_score_gemma":0.0010804471,"threshold_uncertainty_score":0.9997909},"labels":[],"label_agreement":null},{"id":"W7123346315","doi":"10.1109/cdc57313.2025.11312819","title":"Complementary Tracking Control for Linear Systems Subject to External Disturbances and Stochastic Noise","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Control theory (sociology); Noise (video); Tracking (education); Controller (irrigation); Linear system; Robust control; Robustness (evolution); Noise measurement","score_opus":0.017747322238096663,"score_gpt":0.2869506044502084,"score_spread":0.26920328221211176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123346315","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005728087,0.005080648,0.9787221,0.0024748722,0.0026424213,0.00494239,0.00016078657,0.00015633492,0.00009236726],"genre_scores_gemma":[0.9671012,0.0000069219377,0.029462378,0.0013738921,0.00034910638,0.00047490498,0.0000054029642,0.000025641608,0.0012005622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99598336,0.00021052409,0.0009815481,0.0013223942,0.0004480683,0.0010541069],"domain_scores_gemma":[0.99680716,0.0014688168,0.00027154104,0.0006880369,0.00043148946,0.00033296327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011296546,0.00055904425,0.00090278167,0.00032082887,0.00060104055,0.0010194959,0.0012565303,0.00010643142,0.000008202747],"category_scores_gemma":[0.0002499346,0.0005267822,0.00020527287,0.00049727457,0.00020242934,0.0005146791,0.0004490624,0.0002520194,0.00000983548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020735972,0.0006742623,0.0075377943,0.0011642524,0.0013954516,0.000050050883,0.002219546,0.039616615,0.0032618192,0.32309878,0.0010853723,0.61782247],"study_design_scores_gemma":[0.004952699,0.0007506515,0.0041489694,0.00070860086,0.00021846547,0.000013819443,0.00027865882,0.9859233,0.000028113609,0.0009830008,0.0014713161,0.0005223998],"about_ca_topic_score_codex":0.00067475607,"about_ca_topic_score_gemma":0.00022659203,"teacher_disagreement_score":0.9613731,"about_ca_system_score_codex":0.00023691934,"about_ca_system_score_gemma":0.00024221968,"threshold_uncertainty_score":0.99971837},"labels":[],"label_agreement":null},{"id":"W7123357605","doi":"10.1109/cdc57313.2025.11312431","title":"Convergence of regularized agent-state-based Q-learning in POMDPs","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Convergence (economics); Salient; Regularization (linguistics); Reinforcement learning; State (computer science); Fixed point; Stationary point","score_opus":0.007703628012805853,"score_gpt":0.24500675620056078,"score_spread":0.23730312818775492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123357605","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030316722,0.00047155275,0.9631988,0.0019853585,0.00088975375,0.0008238795,0.0000023303587,0.00023681732,0.002074831],"genre_scores_gemma":[0.91175616,0.000030073314,0.080774195,0.00055040896,0.0000088188,0.000035579244,0.0000024002381,0.000015079974,0.0068272804],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957401,0.0006528514,0.0012000593,0.0010173752,0.0005394838,0.00085012213],"domain_scores_gemma":[0.99748015,0.0005045727,0.00045895381,0.0010208235,0.0003969698,0.00013853428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015682022,0.00040675374,0.00076022506,0.0007006363,0.00013365668,0.00014722493,0.0017517057,0.00018700771,0.00011631462],"category_scores_gemma":[0.00049541274,0.00043652472,0.0002560119,0.0024871738,0.00031253145,0.00035599805,0.000632592,0.00061564916,0.000049015118],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086430885,0.0023341766,0.11523732,0.0008928802,0.0005785807,0.00030765127,0.0033682946,0.037650187,0.018331598,0.2590096,0.00035912215,0.56106627],"study_design_scores_gemma":[0.003529783,0.00024209658,0.012856365,0.00033621755,0.00003368074,9.1571883e-7,0.000057574263,0.975263,0.0031193583,0.0020582292,0.002148353,0.00035441032],"about_ca_topic_score_codex":0.0005006893,"about_ca_topic_score_gemma":0.000114033115,"teacher_disagreement_score":0.93761283,"about_ca_system_score_codex":0.0002989257,"about_ca_system_score_gemma":0.001421777,"threshold_uncertainty_score":0.99980867},"labels":[],"label_agreement":null},{"id":"W7123361893","doi":"10.1109/cdc57313.2025.11312082","title":"Discrete-Time Mean-Field-Type Control Problems with Higher-Order Costs","year":2025,"lang":"","type":"article","venue":"","topic":"Adaptive Dynamic Programming Control","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"Air Force Office of Scientific Research","keywords":"Multiplicative function; Optimal control; Quadratic equation; Key (lock); Control (management); State (computer science)","score_opus":0.005777589889421146,"score_gpt":0.23194398901574464,"score_spread":0.2261663991263235,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123361893","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00039763775,0.0012756602,0.9285117,0.01826828,0.0014770555,0.0024595892,0.000008108698,0.0005763395,0.04702565],"genre_scores_gemma":[0.8947684,0.000027226833,0.025001729,0.005474492,0.00013699263,0.00013504698,0.000007218766,0.000051958767,0.07439689],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942243,0.00041032973,0.0009676149,0.0018389841,0.0009419788,0.0016167843],"domain_scores_gemma":[0.994813,0.0009364251,0.00040181834,0.0020667708,0.0013910783,0.00039085373],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000837905,0.00093238894,0.001135117,0.0003550993,0.00050459063,0.0010542097,0.002567505,0.00041107726,0.0005618666],"category_scores_gemma":[0.00020779051,0.00072439003,0.00022040406,0.0028075587,0.00043296232,0.0010539147,0.0007172015,0.00083914684,0.0005913515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001614288,0.0010161793,0.004153979,0.00019909236,0.0028100575,0.00017403043,0.00075710064,0.001950709,0.0018669177,0.50818825,0.006856969,0.47041243],"study_design_scores_gemma":[0.008958412,0.0031634439,0.0013020982,0.0006419763,0.00045512288,0.000018651614,0.000051532534,0.9504927,0.00018886852,0.0029081362,0.03043532,0.0013837653],"about_ca_topic_score_codex":0.0006377317,"about_ca_topic_score_gemma":0.00033637526,"teacher_disagreement_score":0.94854194,"about_ca_system_score_codex":0.0004410953,"about_ca_system_score_gemma":0.0011037354,"threshold_uncertainty_score":0.9999828},"labels":[],"label_agreement":null}]}