{"meta":{"query_hash":"29852c204d50","filters":{"topic":"Reinforcement Learning in Robotics"},"cohort_total":1145,"direct_labels_cover":2,"predictions_cover":1145,"exported":1145,"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/29852c204d50","api":"https://metacan.xera.ac/api/v1/cohort?topic=Reinforcement+Learning+in+Robotics"},"results":[{"id":"W102912931","doi":"","title":"Inter-Layer Learning Towards Emergent Cooperative Behavior","year":2000,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Testbed; Reinforcement learning; Layer (electronics); Heuristics; Artificial intelligence; Abstraction; Architecture; Process (computing); Simple (philosophy); Abstraction layer; Machine learning; Distributed computing; Online machine learning; Human–computer interaction; Unsupervised learning","score_opus":0.028209157006429064,"score_gpt":0.284066985288857,"score_spread":0.2558578282824279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W102912931","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":[0.01959628,0.000014270171,0.8975459,0.00033220474,0.00022866203,0.00015886316,1.4228333e-7,0.00034356007,0.08178015],"genre_scores_gemma":[0.8737683,0.000033810735,0.016741518,0.0004264606,0.000050424707,0.000028490991,0.000003525044,0.000013269926,0.10893415],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872476,0.00008086416,0.0002598711,0.00032614236,0.0002936352,0.00031472964],"domain_scores_gemma":[0.99936044,0.000021672557,0.000044834174,0.00038122287,0.0000868412,0.00010501218],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017571975,0.00015710607,0.00013994223,0.00006263395,0.00016607765,0.00019878648,0.0006818373,0.000052960702,0.0076266313],"category_scores_gemma":[0.00003018299,0.00013327863,0.00006629685,0.0002745762,0.000033146403,0.0004397286,0.00019035398,0.0002756316,0.0016296466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061190412,0.00007256713,0.0026781857,0.0000047727654,0.000031751686,0.00003348746,0.00191269,0.75546056,0.00067945285,0.010178939,0.003419041,0.22552244],"study_design_scores_gemma":[0.0005029289,0.00055653893,0.0039222734,0.000022641576,0.000018551375,0.000025700509,0.0001339476,0.82148045,0.005466623,0.000025603313,0.16730703,0.00053768855],"about_ca_topic_score_codex":0.000050628558,"about_ca_topic_score_gemma":0.0000032643438,"teacher_disagreement_score":0.88080436,"about_ca_system_score_codex":0.000052221247,"about_ca_system_score_gemma":0.000048449398,"threshold_uncertainty_score":0.9991477},"labels":[],"label_agreement":null},{"id":"W1037351197","doi":"10.1613/jair.4676","title":"Approximate Value Iteration with Temporally Extended Actions","year":2015,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"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; European Commission","keywords":"Landmark; Computer science; Convergence (economics); Bellman equation; Mathematical optimization; Reinforcement learning; Value (mathematics); Function (biology); Term (time); State space; Mathematics; Artificial intelligence; Machine learning; Statistics","score_opus":0.3129026095091614,"score_gpt":0.4403874809011682,"score_spread":0.12748487139200682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1037351197","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":[0.0058895596,0.00004413497,0.98907715,0.0023429203,0.0003474538,0.00016781094,2.0766439e-7,0.000029754756,0.0021010193],"genre_scores_gemma":[0.8755842,0.000032473476,0.12357999,0.00005334305,0.0003195096,0.0000051943157,8.1035125e-7,0.000014059084,0.00041041075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965006,0.00037039127,0.0006449328,0.00020415854,0.0018593626,0.00042057328],"domain_scores_gemma":[0.9963797,0.00024776618,0.00031170197,0.00040328366,0.002350853,0.00030671046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004761231,0.00011444859,0.00018726851,0.00058172183,0.00023106358,0.0007168989,0.0010764931,0.00006657666,0.000016923814],"category_scores_gemma":[0.0007684708,0.00008539605,0.000062470084,0.0011652311,0.0001700007,0.0013771408,0.00016885245,0.00078821456,0.00010691651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000189924,0.00018304108,0.0001290981,0.000015767038,0.00004868655,0.00013908761,0.0030127808,0.7680834,0.0028026074,0.17401065,0.0010006395,0.050384343],"study_design_scores_gemma":[0.00008520187,0.002237396,0.000052340987,0.00010207959,0.0000075778735,0.00024067014,0.0018335835,0.93347174,0.028519746,0.030397616,0.0028771688,0.00017486369],"about_ca_topic_score_codex":0.00002482724,"about_ca_topic_score_gemma":0.000005977709,"teacher_disagreement_score":0.86969465,"about_ca_system_score_codex":0.00021586785,"about_ca_system_score_gemma":0.00082869217,"threshold_uncertainty_score":0.69130725},"labels":[],"label_agreement":null},{"id":"W115994101","doi":"","title":"Robust Online Optimization of Reward-Uncertain MDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of Toronto","funders":"","keywords":"Regret; Computer science; Leverage (statistics); Markov decision process; Minimax; Mathematical optimization; Set (abstract data type); Pruning; Computation; Artificial intelligence; Markov process; Machine learning; Mathematics; Algorithm","score_opus":0.05854918816098995,"score_gpt":0.26757053188534,"score_spread":0.20902134372435008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W115994101","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":[0.00027618845,0.000030344198,0.98589957,0.00027019848,0.00024915993,0.00006882634,3.2879532e-7,0.000104849714,0.013100519],"genre_scores_gemma":[0.248199,0.000015018894,0.74949455,0.00017224916,0.000061940445,0.0000012499249,0.000008765715,0.0000059113668,0.0020413422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992147,0.000033188953,0.00020783416,0.00010829669,0.0002259636,0.00021001398],"domain_scores_gemma":[0.99933386,0.000050994353,0.00010350199,0.00036805795,0.00007880032,0.000064789674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023367151,0.00007232249,0.00009641631,0.00006678815,0.000033877925,0.000025516167,0.00041254508,0.00004055957,0.00011289187],"category_scores_gemma":[0.00008052866,0.000062064406,0.00003174287,0.00026162152,0.000022040875,0.00050867576,0.00023010738,0.000066133995,0.000024103669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.419466e-7,0.000030237114,0.001495677,0.0000070142933,0.0000053553767,1.8315322e-7,0.00018081514,0.98362887,0.00002322582,0.013289638,0.0005780281,0.00076011184],"study_design_scores_gemma":[0.00011003782,0.000037117436,0.0005428003,0.00000864001,0.0000032266614,0.0000023820605,0.000028131952,0.99810815,0.0002675766,0.00001885916,0.000795018,0.00007804723],"about_ca_topic_score_codex":0.000018489067,"about_ca_topic_score_gemma":6.5940503e-7,"teacher_disagreement_score":0.24792281,"about_ca_system_score_codex":0.00002559237,"about_ca_system_score_gemma":0.000025169893,"threshold_uncertainty_score":0.25309128},"labels":[],"label_agreement":null},{"id":"W1178556121","doi":"10.1609/aaai.v29i1.9613","title":"Policy Tree: Adaptive Representation for Policy Gradient","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Softmax function; Representation (politics); Computer science; Tree (set theory); Decision tree; Reinforcement learning; Tree structure; Mathematical optimization; Focus (optics); Base (topology); Artificial intelligence; Machine learning; Mathematics; Algorithm; Political science; Binary tree; Law; Artificial neural network","score_opus":0.18186388199228115,"score_gpt":0.36106959719988463,"score_spread":0.17920571520760348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1178556121","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":[0.006611168,0.000008470672,0.9412423,0.017923992,0.0005574466,0.0010521498,0.0000044850676,0.00015528566,0.032444745],"genre_scores_gemma":[0.9847885,0.000012095725,0.013436931,0.00031541302,0.0002460002,0.000059624224,9.0302166e-7,0.000014688974,0.0011258448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979375,0.000021348194,0.00054011453,0.00046425822,0.00061961694,0.0004171579],"domain_scores_gemma":[0.99759316,0.00012229841,0.0005161914,0.00037509613,0.0012275107,0.00016575125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005329148,0.00021515526,0.00024321117,0.00031059305,0.00016313598,0.00026062905,0.0019333806,0.00008181843,0.000003344009],"category_scores_gemma":[0.0022558528,0.00016894644,0.00013703493,0.0012097406,0.0002514786,0.0005287059,0.00040503257,0.00019785923,0.00005051513],"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":[0.000078683064,0.000050493134,0.00007318834,0.000012745196,0.000014491681,1.2974292e-7,0.0021662242,0.009988277,0.0022023441,0.9518257,0.00036543387,0.03322229],"study_design_scores_gemma":[0.00006699236,0.00057298254,0.00008335784,0.00008093109,0.000009473509,0.0000033676697,0.00071381324,0.46229425,0.15521082,0.38057035,0.00019853852,0.00019513351],"about_ca_topic_score_codex":0.0002117187,"about_ca_topic_score_gemma":0.000008000897,"teacher_disagreement_score":0.9781773,"about_ca_system_score_codex":0.00019853639,"about_ca_system_score_gemma":0.00049493974,"threshold_uncertainty_score":0.68894356},"labels":[],"label_agreement":null},{"id":"W1190299041","doi":"10.3233/wia-140298","title":"Learning cooperative behavior for the shout-ahead architecture","year":2014,"lang":"en","type":"article","venue":"Web Intelligence and Agent Systems An International Journal","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Look-ahead; Architecture; Computer science; Computer architecture; History; Archaeology","score_opus":0.037285219547616065,"score_gpt":0.3072938326640247,"score_spread":0.27000861311640867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1190299041","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":[0.0109745925,0.00010586529,0.9855286,0.00054095034,0.0022633,0.00026806956,0.0000018078587,0.00004407418,0.00027274078],"genre_scores_gemma":[0.99447376,0.00018282635,0.002904984,0.0002521267,0.0009133732,0.00004473755,0.000004324114,0.000012206067,0.0012116735],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984425,0.0001654209,0.00040001672,0.00024728608,0.00051044725,0.00023434308],"domain_scores_gemma":[0.99873984,0.0002632712,0.00024978124,0.00020455952,0.00041938171,0.00012317814],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00096655387,0.00015554583,0.0001436309,0.00011782115,0.00050017424,0.0013943473,0.0012515844,0.000053641576,0.000021312311],"category_scores_gemma":[0.00019941744,0.00010104898,0.00008141263,0.00007957735,0.0000674482,0.00047341018,0.00013672921,0.00042872902,0.000018478084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011876628,0.00002302442,0.0018277653,0.0000063879993,0.000069852766,0.000009136871,0.0014612409,0.8944283,0.00034000483,0.041033395,0.00011951268,0.060669508],"study_design_scores_gemma":[0.00015439837,0.00043554403,0.0008459925,0.000085268155,0.000014482599,0.00043115672,0.00062591635,0.9483362,0.0001850071,0.00017764165,0.048537675,0.00017075065],"about_ca_topic_score_codex":0.000026747774,"about_ca_topic_score_gemma":0.000005733057,"teacher_disagreement_score":0.98349917,"about_ca_system_score_codex":0.000055438322,"about_ca_system_score_gemma":0.000060880036,"threshold_uncertainty_score":0.9996423},"labels":[],"label_agreement":null},{"id":"W13294968","doi":"10.1016/0021-8707(56)90033-8","title":"Toward Off-Policy Learning Control with Function Approximation","year":2010,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":175,"is_retracted":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":"Temporal difference learning; Function approximation; Approximation algorithm; Function (biology); Computer science; Linear approximation; Bellman equation; Optimal control; Extension (predicate logic); Mathematical optimization; Control (management); Artificial intelligence; Mathematics; Reinforcement learning; Artificial neural network; Nonlinear system","score_opus":0.022667319724685036,"score_gpt":0.27060077476957206,"score_spread":0.24793345504488704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W13294968","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":[0.010637496,0.0000060764123,0.93269134,0.004855052,0.0006330823,0.00018600453,0.0000011222951,0.00046299314,0.050526842],"genre_scores_gemma":[0.98772514,0.00001586709,0.0078101256,0.000462858,0.0003230211,0.000028780556,0.00005251193,0.000026189013,0.0035555132],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978631,0.00015633852,0.00032513146,0.00049073703,0.0008307642,0.0003339077],"domain_scores_gemma":[0.9986272,0.00016847801,0.00036972738,0.0003038158,0.00041494818,0.000115861614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050584465,0.00026501218,0.00020328785,0.00041778525,0.00027424985,0.0006056678,0.00091474684,0.00011294749,0.00034063842],"category_scores_gemma":[0.0006329065,0.00023052351,0.00006914238,0.000303596,0.0000715315,0.00073665293,0.00014165201,0.0017606268,0.00027020022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001057528,0.00003190959,0.009701381,0.0000085443735,0.00006762356,0.0000094324505,0.00039676926,0.51574236,0.003923931,0.4264555,0.00001624982,0.04354053],"study_design_scores_gemma":[0.001065407,0.0005315858,0.0034238668,0.000040017156,0.000009685872,0.00003256329,0.000048973256,0.97862613,0.00018851185,0.0009824905,0.014780527,0.0002702108],"about_ca_topic_score_codex":0.00008420838,"about_ca_topic_score_gemma":0.000015204975,"teacher_disagreement_score":0.9770876,"about_ca_system_score_codex":0.0000818189,"about_ca_system_score_gemma":0.00016840616,"threshold_uncertainty_score":0.94004756},"labels":[],"label_agreement":null},{"id":"W136985510","doi":"10.5555/2034396.2034517","title":"Escaping local optima in POMDP planning as inference","year":2011,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","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":"Inference; Partially observable Markov decision process; Local optimum; Reinforcement learning; Computer science; Mathematical optimization; Observable; Greedy algorithm; Artificial intelligence; Machine learning; Mathematics; Markov chain; Markov model","score_opus":0.14580520123192156,"score_gpt":0.3207535313869368,"score_spread":0.17494833015501524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W136985510","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":[0.03692525,0.00034758777,0.95564127,0.000009500646,0.0006961336,0.0004958632,0.000001530719,0.000107558466,0.005775293],"genre_scores_gemma":[0.9844389,0.00005264179,0.0144496225,0.00014135843,0.000031294392,0.00003574352,0.000003146525,0.000020943364,0.00082635484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778146,0.00017562736,0.0005130767,0.00059405656,0.0003895269,0.0005462286],"domain_scores_gemma":[0.99893075,0.000086265194,0.00024499654,0.00044975846,0.000090721165,0.0001974884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042809665,0.0002922819,0.000330724,0.00023062402,0.00016323398,0.00018255274,0.00070974196,0.00012311478,0.000019902594],"category_scores_gemma":[0.00006657723,0.0002723748,0.00004996403,0.00027730025,0.00008966195,0.0006984895,0.0005076737,0.00026578925,0.00014011325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006434666,0.00035194223,0.13716485,0.00017200805,0.0002686074,0.00085955625,0.04207514,0.7818159,0.00015617364,0.025463112,0.000440442,0.01116796],"study_design_scores_gemma":[0.0009258892,0.00018930185,0.049014412,0.0003496743,0.000008620755,0.000021895758,0.0013820856,0.9471146,0.00006440315,0.000028640703,0.0005655186,0.00033494705],"about_ca_topic_score_codex":0.0014594301,"about_ca_topic_score_gemma":0.000008596812,"teacher_disagreement_score":0.94751364,"about_ca_system_score_codex":0.00010344989,"about_ca_system_score_gemma":0.000057257228,"threshold_uncertainty_score":0.9999728},"labels":[],"label_agreement":null},{"id":"W137325057","doi":"10.1609/aaai.v26i1.8319","title":"Approximate Policy Iteration with Linear Action Models","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates - Technology Futures","keywords":"Benchmark (surveying); Computer science; Action (physics); Mathematical optimization; Linear model; Machine learning; Mathematics","score_opus":0.12002286483175004,"score_gpt":0.3180867896487678,"score_spread":0.19806392481701776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W137325057","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":[0.017426582,0.0000060140806,0.96449673,0.003932693,0.00018699454,0.000232238,9.991127e-7,0.000107017695,0.013610735],"genre_scores_gemma":[0.9766212,0.00003578874,0.022155099,0.0002542939,0.000091559144,0.00001557141,0.0000011655347,0.0000122136635,0.0008131003],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983486,0.000018366325,0.00038816268,0.00041039818,0.00055192574,0.000282542],"domain_scores_gemma":[0.9982091,0.000042780623,0.0003384989,0.0003336522,0.0010100498,0.00006590266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024994963,0.00018316366,0.00018393353,0.00012343827,0.00019884369,0.0003713414,0.0009817776,0.00007344024,0.0000207106],"category_scores_gemma":[0.00022708533,0.00013397772,0.00006717301,0.0009342728,0.00012580409,0.00090090744,0.000278634,0.0002758847,0.000035151254],"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":[0.000026995376,0.000048800808,0.000033941058,0.000035689605,0.000012140419,6.057008e-7,0.00092401804,0.117277,0.019816786,0.8484454,0.000019418436,0.013359188],"study_design_scores_gemma":[0.000017335096,0.000093646755,0.000015035174,0.00010234714,0.0000052318783,0.0000075330413,0.00017695961,0.6102195,0.3456791,0.04354263,0.00003424531,0.00010643823],"about_ca_topic_score_codex":0.000022197164,"about_ca_topic_score_gemma":0.0000047685903,"teacher_disagreement_score":0.9591946,"about_ca_system_score_codex":0.00006645644,"about_ca_system_score_gemma":0.00025417085,"threshold_uncertainty_score":0.5463453},"labels":[],"label_agreement":null},{"id":"W1433129784","doi":"10.1007/978-3-642-29946-9_16","title":"Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metrics","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Bisimulation; Metric (unit); Set (abstract data type); Markov process; Process (computing); Q-learning; Performance metric; Artificial intelligence; Theoretical computer science; Mathematical optimization; Algorithm; Mathematics; Programming language","score_opus":0.056064834870291215,"score_gpt":0.3043537203516835,"score_spread":0.2482888854813923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1433129784","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":[0.00025624895,0.00014677884,0.99620515,0.00007869527,0.002184525,0.0006461242,0.0000035350179,0.0001369382,0.00034202018],"genre_scores_gemma":[0.1991293,0.000012280062,0.8005054,0.00007299622,0.00019492109,0.0000043387704,0.00000625824,0.000023888815,0.000050604976],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970983,0.000032752905,0.00076127023,0.0007076273,0.00091522175,0.00048478696],"domain_scores_gemma":[0.99674636,0.0007749382,0.00090637954,0.0009502696,0.0005085315,0.00011349703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00095855567,0.00036492266,0.00048774082,0.0016006192,0.0002653188,0.0002482792,0.0014001572,0.00030144714,0.000015510037],"category_scores_gemma":[0.00028504466,0.0003607639,0.00015468962,0.0010436921,0.000472019,0.0009926512,0.0004778915,0.00040693756,0.0000051929565],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019525341,0.000011274057,0.00010271487,0.00007563243,0.00001339243,9.839949e-7,0.0001978824,0.6930733,0.00018438837,0.017280305,0.0000014820941,0.28905672],"study_design_scores_gemma":[0.00022503441,0.00012278526,0.0001350535,0.00022321822,0.000028151326,0.000032648695,2.9220743e-7,0.97301364,0.0009607902,0.024677917,0.00023803591,0.00034243675],"about_ca_topic_score_codex":0.000010403278,"about_ca_topic_score_gemma":0.0000032077292,"teacher_disagreement_score":0.2887143,"about_ca_system_score_codex":0.00041060394,"about_ca_system_score_gemma":0.0005397045,"threshold_uncertainty_score":0.9998844},"labels":[],"label_agreement":null},{"id":"W1482535585","doi":"10.1007/978-3-642-41575-3_15","title":"Controller Compilation and Compression for Resource Constrained Applications","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Benchmark (surveying); Lookup table; Controller (irrigation); Compiler; Set (abstract data type); Markov decision process; Computation; Table (database); Decision table; Point (geometry); Resource (disambiguation); Distributed computing; Computer engineering; Algorithm; Artificial intelligence; Data mining; Markov process; Programming language","score_opus":0.016047394966606572,"score_gpt":0.24618815952536066,"score_spread":0.2301407645587541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1482535585","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":[0.000003451917,0.00021908773,0.99234307,0.0006998253,0.0002584203,0.0017455468,0.00001042911,0.0001561689,0.0045639775],"genre_scores_gemma":[0.06481024,0.000030668176,0.9308301,0.0017717797,0.00043787007,0.00015832814,0.00005281662,0.00004909202,0.0018591152],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973248,0.000027806316,0.0005242185,0.0010780327,0.00058297295,0.00046215698],"domain_scores_gemma":[0.9972813,0.0010756677,0.00039850728,0.0007980605,0.00028808645,0.00015839314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005571145,0.00039495924,0.0004679421,0.00046753295,0.0004049234,0.0006247872,0.001530989,0.00027042668,0.000014483281],"category_scores_gemma":[0.0000692686,0.00035870916,0.00008213679,0.00023784577,0.0007460544,0.00041496343,0.0007037907,0.00046548116,0.00002633592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073143997,0.000010956799,0.00002543834,0.000056892903,0.000013015431,0.0000020030031,0.00024077232,0.5014769,0.00022233104,0.08522074,0.00010950652,0.41261417],"study_design_scores_gemma":[0.0006056667,0.00011941987,0.000069492686,0.00017690833,0.000008981684,0.000020398746,1.8788755e-7,0.93981844,0.00010328695,0.041411478,0.017284436,0.00038130648],"about_ca_topic_score_codex":0.0000030236781,"about_ca_topic_score_gemma":0.000001834242,"teacher_disagreement_score":0.43834156,"about_ca_system_score_codex":0.0001276257,"about_ca_system_score_gemma":0.0001699543,"threshold_uncertainty_score":0.9998865},"labels":[],"label_agreement":null},{"id":"W1491129446","doi":"10.1007/978-3-540-39857-8_29","title":"Using MDP Characteristics to Guide Exploration in Reinforcement Learning","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Artificial intelligence; Bellman equation; Machine learning; State space; Computation; Focus (optics); Variance (accounting); Markov process; Mathematical optimization; Algorithm","score_opus":0.044656664918599175,"score_gpt":0.28567957287483425,"score_spread":0.24102290795623507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1491129446","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":[0.000084630825,0.000037906946,0.9933434,0.00042737904,0.0017312762,0.0006162493,4.201741e-7,0.00012281707,0.0036359183],"genre_scores_gemma":[0.11268286,0.00007686661,0.8799276,0.0038851737,0.0004381693,0.000021217864,0.000016822898,0.00009219153,0.0028591005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951622,0.00007544892,0.0011111149,0.0014087692,0.0013345536,0.0009079277],"domain_scores_gemma":[0.9974659,0.00025050732,0.0005278275,0.0012329347,0.00030253734,0.0002202706],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015099754,0.00060718064,0.0006157045,0.0015498498,0.00028234575,0.0007852214,0.0023434677,0.00030767094,0.000023503873],"category_scores_gemma":[0.00043391547,0.00064557453,0.000081869024,0.0010561664,0.00020682707,0.0011074143,0.0013006495,0.0011634761,0.00007718629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032776954,0.0000055461933,0.000108923145,0.00002409247,0.0000045566176,0.00005322036,0.0012835365,0.9507159,0.0002061319,0.004758101,0.000011343033,0.042825375],"study_design_scores_gemma":[0.0002142651,0.0002476955,0.000044502784,0.00057669426,0.0000055290084,0.000024160454,7.4332013e-7,0.98910385,0.0005019771,0.0027477143,0.0058150683,0.0007177697],"about_ca_topic_score_codex":0.000033795608,"about_ca_topic_score_gemma":0.000020694008,"teacher_disagreement_score":0.1134158,"about_ca_system_score_codex":0.0012687228,"about_ca_system_score_gemma":0.00055589544,"threshold_uncertainty_score":0.9995996},"labels":[],"label_agreement":null},{"id":"W1493024987","doi":"10.48550/arxiv.1205.2651","title":"Seeing the Forest Despite the Trees: Large Scale Spatial-Temporal Decision Making","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Scale (ratio); Action (physics); Spatial planning; Space (punctuation); Point (geometry); Spatial ecology; State space; State (computer science); Artificial intelligence; Operations research; Geography; Environmental planning; Mathematics; Cartography; Algorithm","score_opus":0.04397477088403532,"score_gpt":0.20018948106472031,"score_spread":0.156214710180685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493024987","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":[0.21469004,0.000036227353,0.7832263,0.00008638901,0.00036030525,0.0001492392,5.041168e-7,0.00009534565,0.0013556398],"genre_scores_gemma":[0.9963019,0.000013736743,0.0025833377,0.0002691272,0.00011518092,5.045258e-7,0.0000013140714,0.000012702255,0.00070222706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866885,0.0001507525,0.00016231422,0.00030943932,0.00016535557,0.00054329244],"domain_scores_gemma":[0.99830455,0.0004222804,0.00016969994,0.00095076335,0.000061956605,0.00009073037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007555182,0.00016507083,0.00012240063,0.00008846908,0.0007024544,0.00016613086,0.001605063,0.000067960296,0.000029886289],"category_scores_gemma":[0.000072034076,0.00011146706,0.000116596384,0.00067083637,0.000096976706,0.00086428935,0.00078295515,0.00026089017,0.0001850149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011816798,0.000024874433,0.29508883,0.000003349169,0.000016944721,0.0000149937705,0.0010823993,0.6620807,0.000006563706,0.039963845,0.00020671586,0.0014989276],"study_design_scores_gemma":[0.00027444866,0.000035729932,0.06529117,0.00003823674,0.00002235001,0.0000066563807,0.00029365852,0.9271634,0.000014913267,0.0010501952,0.0056449613,0.0001642327],"about_ca_topic_score_codex":0.000063541826,"about_ca_topic_score_gemma":0.00027416708,"teacher_disagreement_score":0.7816118,"about_ca_system_score_codex":0.00009106579,"about_ca_system_score_gemma":0.000036258887,"threshold_uncertainty_score":0.54027826},"labels":[],"label_agreement":null},{"id":"W1493952344","doi":"10.1007/978-3-540-24677-0_102","title":"Multiple Reinforcement Learning Agents in a Static Environment","year":2004,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Reinforcement learning; Computer science; Testbed; Reinforcement; Artificial intelligence; Error-driven learning; State (computer science); Learning classifier system; Human–computer interaction; Machine learning; Computer network","score_opus":0.020084878225391827,"score_gpt":0.24644086449333158,"score_spread":0.22635598626793976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1493952344","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":[0.000083536885,0.000105966996,0.9957057,0.00027345028,0.0009334214,0.00080876105,5.3071244e-7,0.00014975235,0.0019388407],"genre_scores_gemma":[0.44508797,0.00015937282,0.5451761,0.00195685,0.00031458284,0.000075013326,0.00004659927,0.00010010473,0.007083444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940186,0.00011739561,0.0009882762,0.0016914484,0.0019269016,0.0012573415],"domain_scores_gemma":[0.99714684,0.0005690863,0.00052855007,0.0014632276,0.000069760536,0.00022253986],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012954219,0.00068450003,0.0006494261,0.0012717211,0.000256938,0.0005830552,0.0038224186,0.00031336193,0.00004180464],"category_scores_gemma":[0.00028468558,0.0006907678,0.00012979818,0.0010286177,0.0005113702,0.00074343145,0.0023430323,0.0017392283,0.0001526346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039159995,0.000029854604,0.00046701194,0.00006773468,0.0000085417905,0.00013353681,0.0022307783,0.9593435,0.000014624668,0.00044909824,0.000016549284,0.037234876],"study_design_scores_gemma":[0.00085414,0.00032062343,0.00034487352,0.0006638143,0.0000054461357,0.000017809209,5.0294375e-7,0.98728347,0.0002051467,0.0065088123,0.0030923847,0.00070296024],"about_ca_topic_score_codex":0.00006280355,"about_ca_topic_score_gemma":0.000024440924,"teacher_disagreement_score":0.45052966,"about_ca_system_score_codex":0.0049196766,"about_ca_system_score_gemma":0.002332008,"threshold_uncertainty_score":0.99955434},"labels":[],"label_agreement":null},{"id":"W1496855202","doi":"10.48550/arxiv.1301.6690","title":"Model-Based Bayesian Exploration","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":235,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Reinforcement learning; Value of information; Action (physics); Bayesian probability; Quality (philosophy); Artificial intelligence; Value (mathematics); Machine learning; Probability distribution; Mathematical optimization; Mathematics; Statistics","score_opus":0.07631130262408777,"score_gpt":0.1767027802933835,"score_spread":0.10039147766929572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496855202","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":[0.011036627,0.0000017144135,0.9833527,0.00026704863,0.000091629314,0.00014659841,1.5959473e-7,0.00023091858,0.0048725978],"genre_scores_gemma":[0.9812556,0.0000039247384,0.015828429,0.00025525354,0.000014264931,8.150006e-7,0.0000027763672,0.000007546967,0.0026314093],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992237,0.000043110143,0.000099236444,0.00033652235,0.0000725649,0.00022487993],"domain_scores_gemma":[0.99911183,0.00003861427,0.000076848584,0.00056253397,0.000102731145,0.00010746426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007955314,0.00011035268,0.00008587811,0.00012383917,0.00012689535,0.00011808579,0.0006973111,0.00005624745,0.000056288834],"category_scores_gemma":[0.000017873894,0.00012388945,0.000053788346,0.00045090614,0.000040142797,0.0016234516,0.00012251387,0.000106848,0.000526075],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014262449,0.000011361445,0.0005378191,0.000003535274,0.000004370388,0.000007356103,0.00005994866,0.89806026,0.00007524983,0.10065047,0.0003345115,0.00025367466],"study_design_scores_gemma":[0.00024751617,0.00004017923,0.00015889412,0.000006533234,0.000005108656,3.237427e-7,0.00002290058,0.99208796,0.00018732803,0.0069709285,0.00012454536,0.00014776338],"about_ca_topic_score_codex":0.000026456906,"about_ca_topic_score_gemma":0.0000030042536,"teacher_disagreement_score":0.97021896,"about_ca_system_score_codex":0.000073709016,"about_ca_system_score_gemma":0.000064118954,"threshold_uncertainty_score":0.67618054},"labels":[],"label_agreement":null},{"id":"W1498235675","doi":"","title":"AEMS: an anytime online search algorithm for approximate policy refinement in large POMDPs","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Partially observable Markov decision process; Markov decision process; Computation; Task (project management); Mathematical optimization; State space; State (computer science); Function (biology); Bellman equation; Online algorithm; Observable; Algorithm; Markov process; Markov chain; Machine learning; Markov model; Mathematics","score_opus":0.03203246700207627,"score_gpt":0.34282257742561884,"score_spread":0.31079011042354254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1498235675","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":[0.0037712296,0.000012332022,0.9918442,0.00078541826,0.00011293191,0.00049717334,0.000006687127,0.00029324082,0.0026768267],"genre_scores_gemma":[0.02813558,0.000012260886,0.9673994,0.0010860377,0.0002387791,0.0000144778605,0.00005650365,0.000023580664,0.003033352],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977039,0.0000454184,0.00044933727,0.00044511087,0.00045057942,0.00090565864],"domain_scores_gemma":[0.99886817,0.000091688635,0.0000614757,0.00067334704,0.0001233142,0.00018201696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018092896,0.00017780646,0.00019513658,0.00045683273,0.000110709545,0.00013527885,0.0009376105,0.000085467436,0.000031213767],"category_scores_gemma":[0.000050083912,0.00016293992,0.000056171128,0.0007185733,0.000022116918,0.0004374674,0.00037890347,0.00019975021,0.000034981065],"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":[0.000039704326,0.0021986088,0.0026274717,0.00013668663,0.00008061356,0.00007228323,0.004720513,0.14862329,0.0010695629,0.33733255,0.0008593947,0.50223935],"study_design_scores_gemma":[0.0010397453,0.00034295104,0.0020656022,0.000011951472,0.0000020930156,0.000005352184,0.00013100654,0.98940027,0.0007526678,0.00019979016,0.0058417604,0.00020680462],"about_ca_topic_score_codex":0.00024818387,"about_ca_topic_score_gemma":0.000099512654,"teacher_disagreement_score":0.840777,"about_ca_system_score_codex":0.00021042634,"about_ca_system_score_gemma":0.00015405452,"threshold_uncertainty_score":0.66444975},"labels":[],"label_agreement":null},{"id":"W1503109067","doi":"","title":"Point-Based Value Iteration for Constrained POMDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov decision process; Mathematical optimization; Bellman equation; Computer science; Dynamic programming; Minimax; Linear programming; Value (mathematics); Scalability; Function (biology); Point (geometry); Markov process; Mathematics","score_opus":0.02092790281422207,"score_gpt":0.26621454782228016,"score_spread":0.24528664500805808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503109067","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":[0.0004403031,0.000007123725,0.98684657,0.00094153965,0.00042183357,0.00023900617,3.461804e-7,0.00028177619,0.010821483],"genre_scores_gemma":[0.54579484,1.6088994e-7,0.45211524,0.0013170628,0.000087857356,0.000014272907,0.0000062454387,0.000004888925,0.000659398],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99929607,0.000020264213,0.00015258364,0.000121676196,0.00014691484,0.0002624812],"domain_scores_gemma":[0.99940103,0.00014480099,0.000058600708,0.0002681887,0.00006518309,0.00006216416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032001894,0.00007989119,0.00007255595,0.00006143504,0.000081103266,0.00013904682,0.00026391857,0.000038128554,0.00003880953],"category_scores_gemma":[0.00008115696,0.000070372465,0.000047817237,0.00010657478,0.000015929418,0.0006927361,0.00003896514,0.00004431991,0.000086241256],"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":[0.0000027841293,0.000040535746,0.00060821086,0.000016599086,0.000008489084,2.1139218e-7,0.0001899906,0.093233906,0.00061111286,0.9024014,0.0018866137,0.0010001551],"study_design_scores_gemma":[0.0003991692,0.00008411358,0.00019432406,0.000005044091,0.0000042869415,0.000002308087,0.0000075591524,0.98592854,0.0033838954,0.00026578366,0.009615591,0.00010938002],"about_ca_topic_score_codex":0.0000025893853,"about_ca_topic_score_gemma":1.743106e-7,"teacher_disagreement_score":0.9021356,"about_ca_system_score_codex":0.00003096545,"about_ca_system_score_gemma":0.000046769113,"threshold_uncertainty_score":0.2869706},"labels":[],"label_agreement":null},{"id":"W150352456","doi":"10.5072/zenodo.49098","title":"Learning by Automatic Option Discovery from Conditionally Terminating Sequences","year":2006,"lang":"en","type":"article","venue":"OpenMETU (Middle East Technical University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Normalization property; Computer science; Reinforcement learning; Tree (set theory); Tree structure; Artificial intelligence; Machine learning; Theoretical computer science; Data structure; Programming language; Mathematics","score_opus":0.012963262884764256,"score_gpt":0.19508612386393304,"score_spread":0.18212286097916877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W150352456","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":[0.04535938,0.00001920168,0.93298465,0.00023430737,0.00010108626,0.0001875075,0.000011099668,0.00045922038,0.020643571],"genre_scores_gemma":[0.93513083,0.0000052700193,0.04935737,0.000049571052,0.00004564617,0.0000019008331,0.00012029122,0.000012582828,0.015276531],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982593,0.00015227991,0.0002793681,0.0004964572,0.00048580466,0.00032680476],"domain_scores_gemma":[0.99899745,0.00021878969,0.00026592118,0.00036623603,0.00006852632,0.000083080835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021602905,0.00019886957,0.00022659385,0.0002017017,0.00039146346,0.0004402136,0.0013074357,0.00013173837,0.00007169474],"category_scores_gemma":[0.00008836498,0.00021714836,0.00010123692,0.0006699977,0.00015798735,0.0022218924,0.0005875435,0.00038463052,0.00011391795],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019726342,0.0002678488,0.0051755793,0.000048862472,0.000086689666,0.0003780014,0.00022397713,0.5463316,0.035756215,0.4003079,0.0016880068,0.009715641],"study_design_scores_gemma":[0.0015994301,0.00048160634,0.010187079,0.00045557224,0.00008961108,0.000046586123,0.0006403773,0.9550464,0.0018348877,0.004773656,0.023575777,0.001268998],"about_ca_topic_score_codex":0.00020006056,"about_ca_topic_score_gemma":0.000012296144,"teacher_disagreement_score":0.88977146,"about_ca_system_score_codex":0.00024919887,"about_ca_system_score_gemma":0.000085308864,"threshold_uncertainty_score":0.8855053},"labels":[],"label_agreement":null},{"id":"W1504915502","doi":"10.1609/aaai.v24i1.7751","title":"Using Bisimulation for Policy Transfer in MDPs","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":27,"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":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Bisimulation; Computer science; Pessimism; Task (project management); Metric (unit); Markov decision process; Transfer (computing); Action (physics); Quality (philosophy); Theoretical computer science; Artificial intelligence; Markov process; Mathematics; Economics","score_opus":0.13511302919804696,"score_gpt":0.35650515512498543,"score_spread":0.22139212592693847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504915502","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":[0.26632667,0.0000012803968,0.72847337,0.0020253717,0.00040691742,0.000529301,0.0000013371744,0.00004787216,0.002187859],"genre_scores_gemma":[0.98424345,0.0000034259585,0.015433941,0.0001233703,0.00009056441,0.000014740963,2.7850115e-7,0.000011330035,0.000078891404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99851656,0.00000851062,0.00049120386,0.0003320576,0.0003311961,0.00032046458],"domain_scores_gemma":[0.9990047,0.00011292921,0.0001565868,0.00024459153,0.00042688398,0.000054305685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050033495,0.00016197533,0.00018516996,0.000263923,0.0001281397,0.000198497,0.0013794834,0.00010745072,0.00001359263],"category_scores_gemma":[0.00062738877,0.00013149677,0.00009246519,0.0007690908,0.00015785982,0.00044943465,0.00013230758,0.0003377634,0.000011178895],"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":[0.000023566494,0.000034709443,0.00035579078,0.000022694534,0.0000034921795,5.961643e-8,0.0007024275,0.031539567,0.12777175,0.82857877,0.0000032350981,0.010963935],"study_design_scores_gemma":[0.00003171389,0.00008502901,0.00016784205,0.00006005424,0.0000034441423,0.0000011168491,0.0000422446,0.6853062,0.2513439,0.06279636,0.000047020854,0.00011509155],"about_ca_topic_score_codex":0.000090459485,"about_ca_topic_score_gemma":0.000025282301,"teacher_disagreement_score":0.7657824,"about_ca_system_score_codex":0.00004839562,"about_ca_system_score_gemma":0.00016288046,"threshold_uncertainty_score":0.53622824},"labels":[],"label_agreement":null},{"id":"W1507852408","doi":"10.48550/arxiv.1206.3281","title":"Model-Based Bayesian Reinforcement Learning in Large Structured Domains","year":2012,"lang":"en","type":"preprint","venue":"PubMed","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Institute of Mental Health","keywords":"Reinforcement learning; Computer science; Scalability; Artificial intelligence; Bayesian probability; Machine learning; Bayesian inference","score_opus":0.025380733767491163,"score_gpt":0.24242802852349365,"score_spread":0.21704729475600248,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1507852408","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":[0.0012946172,0.00011609531,0.98865193,0.0004088978,0.0014779174,0.0017411198,0.0000026002133,0.0004941691,0.0058126426],"genre_scores_gemma":[0.96598816,0.000017030521,0.030073365,0.00045291346,0.00020310874,0.0015528596,0.00009514784,0.000056586377,0.0015608523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953641,0.0002331277,0.000845381,0.00090330554,0.0009583247,0.0016957138],"domain_scores_gemma":[0.99721044,0.00010054378,0.0006131907,0.0016073778,0.000097046686,0.00037142477],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016231687,0.0005730608,0.0005860101,0.00056902994,0.0001739396,0.00043108495,0.0022368738,0.000514642,0.000024270897],"category_scores_gemma":[0.00023247406,0.0005984779,0.00022546887,0.00041558687,0.000052745607,0.00040534636,0.0024105026,0.002019771,0.000020445435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010924794,0.000027649316,0.005224332,0.00012360924,0.00003369991,0.000010483894,0.00049348053,0.98067313,0.000002560786,0.005361933,0.00010937378,0.007928846],"study_design_scores_gemma":[0.0008852113,0.000012254029,0.020474091,0.00005144823,0.000021418378,0.0000014818461,0.0000096535505,0.9756273,0.00007785191,0.00080889394,0.0014174258,0.0006129417],"about_ca_topic_score_codex":0.000028353346,"about_ca_topic_score_gemma":0.000021942673,"teacher_disagreement_score":0.96469355,"about_ca_system_score_codex":0.0006714841,"about_ca_system_score_gemma":0.00029388146,"threshold_uncertainty_score":0.99964666},"labels":[],"label_agreement":null},{"id":"W1508997545","doi":"10.1609/aimag.v31i2.2227","title":"The Reinforcement Learning Competitions","year":2010,"lang":"en","type":"article","venue":"AI Magazine","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Institute of Standards and Technology; University of Southern California; Toyota Research Institute, North America; Toyota Research Institute; University of Alberta; International Business Machines Corporation","keywords":"Reinforcement learning; Competition (biology); Computer science; Reinforcement; Focus (optics); Data science; Artificial intelligence; Engineering","score_opus":0.007611555982384794,"score_gpt":0.24271572478864836,"score_spread":0.23510416880626356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508997545","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":[0.00051941804,0.000013684605,0.927186,0.007755911,0.00093098794,0.0001282108,8.230758e-8,0.0002638483,0.06320183],"genre_scores_gemma":[0.9548194,0.000030161598,0.011875277,0.0011985004,0.00016382798,0.000021130432,0.000007717619,0.0000134535385,0.031870577],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889994,0.00003704982,0.00022849167,0.00019030571,0.00032030934,0.0003239351],"domain_scores_gemma":[0.9988467,0.00019282832,0.000095625444,0.0006685686,0.00011562879,0.000080657905],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038761043,0.00011324805,0.00008379537,0.00004824893,0.00064880983,0.00046527467,0.0009229869,0.000042928084,0.000121316465],"category_scores_gemma":[0.0001860823,0.000082507395,0.00005249772,0.00025143192,0.00009898181,0.0003022055,0.00034309056,0.0006574242,0.0014778423],"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":[0.0000019211966,0.000008243044,0.000574935,0.0000037302777,0.000014695293,0.000005052424,0.0001404551,0.37465903,0.002794472,0.6080033,0.0080602635,0.00573391],"study_design_scores_gemma":[0.00014562065,0.00006149209,0.0015580856,0.0000045191264,0.0000029256314,0.000011415953,0.0000059024546,0.42592713,0.00016661831,0.0004887465,0.5715296,0.000097947035],"about_ca_topic_score_codex":0.0000047720764,"about_ca_topic_score_gemma":0.000011841545,"teacher_disagreement_score":0.9542999,"about_ca_system_score_codex":0.00001692093,"about_ca_system_score_gemma":0.000048176556,"threshold_uncertainty_score":0.99929965},"labels":[],"label_agreement":null},{"id":"W1511842811","doi":"10.1007/11766247_31","title":"Partial Local FriendQ Multiagent Learning: Application to Team Automobile Coordination Problem","year":2006,"lang":"en","type":"article","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Observability; Reinforcement learning; Computer science; Multi-agent system; Degree (music); Observable; Mathematical optimization; Computation; Artificial intelligence; Mathematics; Algorithm; Applied mathematics","score_opus":0.006367876696141645,"score_gpt":0.24259299922135455,"score_spread":0.2362251225252129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1511842811","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":[0.004498298,0.000014684478,0.99284256,0.001015272,0.00046657963,0.00064939674,2.4676885e-7,0.00037504797,0.00013793929],"genre_scores_gemma":[0.66361135,3.5000073e-7,0.33591855,0.00026426013,0.00013193027,0.00005136871,0.0000034309871,0.000008566793,0.000010199625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969391,0.0000932474,0.00043928061,0.0009930088,0.00085893465,0.0006764194],"domain_scores_gemma":[0.99859035,0.0001989745,0.00017081432,0.00068173377,0.00021358524,0.00014454372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000941892,0.00023941441,0.00020156118,0.00041903937,0.00036795036,0.0004914094,0.0016809596,0.00009624056,0.000004753355],"category_scores_gemma":[0.000107914275,0.00022914598,0.0000489477,0.0024574364,0.00023951937,0.0006643368,0.0007200404,0.00037691492,0.000100824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023617695,0.000041479678,0.0017171053,0.000006474717,0.0000010938104,0.0000026409282,0.0004929047,0.80816656,0.001766702,0.0014556941,0.00003259225,0.18631437],"study_design_scores_gemma":[0.0002640618,0.00021667435,0.0024689746,0.000025315725,0.0000019001313,0.000010513566,0.0000010932779,0.97785515,0.0154152885,0.0014144434,0.0020500503,0.00027656436],"about_ca_topic_score_codex":0.0001820573,"about_ca_topic_score_gemma":0.000035281882,"teacher_disagreement_score":0.65911305,"about_ca_system_score_codex":0.00036403607,"about_ca_system_score_gemma":0.00019056875,"threshold_uncertainty_score":0.9344302},"labels":[],"label_agreement":null},{"id":"W1512866498","doi":"10.1609/aaai.v26i1.8321","title":"Investigating Contingency Awareness Using Atari 2600 Games","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":76,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Alberta Innovates; Western Canada Research Grid; Compute Canada","keywords":"Contingency; Reinforcement learning; Exploit; Computer science; Function (biology); Control (management); Value (mathematics); Reinforcement; Artificial intelligence; Contingency management; Bellman equation; Human–computer interaction; Machine learning; Psychology; Social psychology; Computer security","score_opus":0.13878597859183864,"score_gpt":0.32726220209429063,"score_spread":0.188476223502452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1512866498","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":[0.39238918,0.000069392554,0.59055233,0.0025900805,0.0012159426,0.00038470145,0.0000026598275,0.00020925415,0.012586476],"genre_scores_gemma":[0.9695887,0.000022958428,0.029609198,0.0002932278,0.000084028674,0.000008434507,7.4649535e-7,0.000017572378,0.00037515545],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973864,0.000037691596,0.00076225604,0.0006207523,0.00071986933,0.00047302543],"domain_scores_gemma":[0.9972873,0.00014591747,0.0006543864,0.0004873212,0.001306781,0.00011830183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000566803,0.0002732167,0.00033755004,0.00011067472,0.00038723144,0.0005537325,0.0021233805,0.00011099501,0.00006721472],"category_scores_gemma":[0.0016697827,0.00023126673,0.00014157395,0.0010710596,0.0003133959,0.0006359436,0.0009401903,0.00042766143,0.0000443355],"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":[0.0000059023328,0.00006443905,0.0045475597,0.000094989286,0.00002993782,0.000002039441,0.0020746945,0.02340828,0.1324855,0.8216764,0.000058221598,0.015552089],"study_design_scores_gemma":[0.000020173324,0.000047605557,0.0002166911,0.00036523963,0.0000135838145,0.000009669414,0.0005069002,0.48353928,0.48338702,0.03159981,0.0000774367,0.00021660839],"about_ca_topic_score_codex":0.000074682124,"about_ca_topic_score_gemma":0.0000076667075,"teacher_disagreement_score":0.79007655,"about_ca_system_score_codex":0.00007152263,"about_ca_system_score_gemma":0.00043590248,"threshold_uncertainty_score":0.94307834},"labels":[],"label_agreement":null},{"id":"W1513366144","doi":"10.1007/11527503_11","title":"Multiagent Association Rules Mining in Cooperative Learning Systems","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Robustness (evolution); Association rule learning; Machine learning; Multi-agent system; Domain (mathematical analysis)","score_opus":0.017857517415009107,"score_gpt":0.247376344211483,"score_spread":0.2295188267964739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1513366144","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":[0.00025683758,0.0004435226,0.991934,0.00044131916,0.0018190996,0.00048713214,0.0000012552488,0.00018152813,0.0044352813],"genre_scores_gemma":[0.4272636,0.00026022806,0.55388355,0.0010781311,0.001477267,0.00004572299,0.000029934266,0.00011994681,0.015841644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99544525,0.00014200699,0.0007549011,0.0013282074,0.001474453,0.00085519074],"domain_scores_gemma":[0.9969879,0.0010842014,0.00071303424,0.00073870143,0.00034362578,0.00013255185],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020041952,0.0005445249,0.00064197404,0.0010619472,0.00029783297,0.0010999481,0.0022530556,0.0004499822,0.000014543305],"category_scores_gemma":[0.00057180616,0.0005416687,0.00009651367,0.0006137992,0.00019129233,0.0008459566,0.0010616899,0.0014947031,0.000111959154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018130494,0.00000974845,0.00090129225,0.000021689717,0.000011300184,0.000040116003,0.0016040875,0.9387239,0.000024585865,0.0027328352,0.000016852213,0.055911765],"study_design_scores_gemma":[0.00032313666,0.00013234738,0.00030550768,0.00064351026,0.00000544413,0.00001441284,0.0000014470338,0.99397355,0.00008803369,0.00027294183,0.0036667488,0.0005729069],"about_ca_topic_score_codex":0.000039226295,"about_ca_topic_score_gemma":0.00006016554,"teacher_disagreement_score":0.43805048,"about_ca_system_score_codex":0.001997255,"about_ca_system_score_gemma":0.00048593467,"threshold_uncertainty_score":0.999937},"labels":[],"label_agreement":null},{"id":"W1517412219","doi":"10.1109/nafips.2001.944350","title":"On playing games without knowing the rules","year":2002,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Premise; Salient; Adversary; Task (project management); Metagaming; Video game design; Non-cooperative game; Artificial intelligence; Screening game; Game mechanics; Game design; Repeated game; Game theory; Mechanism (biology); Sequential game; Human–computer interaction; Combinatorial game theory; Simultaneous game; Computer security; Mathematical economics; Engineering; Mathematics; Epistemology","score_opus":0.029908834774834876,"score_gpt":0.24536985819494986,"score_spread":0.21546102342011497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1517412219","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":[0.0054801377,0.0000363449,0.8062906,0.0011986888,0.00020128275,0.00007254627,3.7215372e-8,0.00020507672,0.18651524],"genre_scores_gemma":[0.95280707,0.000011450975,0.030798234,0.0013680448,0.000048398477,0.0000044978897,1.8672227e-7,0.0000074429713,0.014954704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991925,0.000036906542,0.00012086965,0.00017485811,0.00026621466,0.00020865105],"domain_scores_gemma":[0.9992082,0.00021312613,0.000043200842,0.0004836891,0.00001834251,0.000033411856],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016397017,0.00008884837,0.00007085252,0.000042916658,0.00022305342,0.00024841478,0.00075118616,0.000024496396,0.00015962415],"category_scores_gemma":[0.00007713957,0.00005312222,0.00003763101,0.00012161789,0.000029373556,0.00022472537,0.00015920796,0.00014408462,0.00097645883],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013527775,0.000021871443,0.0022285825,0.000006734469,0.000025169795,0.000007548197,0.0019755801,0.4860013,0.00011439557,0.46405026,0.009462992,0.036104202],"study_design_scores_gemma":[0.00009703639,0.00004248573,0.00070759526,0.000017940005,0.0000019164052,0.00000458417,0.000025098352,0.99257165,0.00015693632,0.00036997942,0.005910897,0.000093874565],"about_ca_topic_score_codex":0.0000057421666,"about_ca_topic_score_gemma":4.836875e-7,"teacher_disagreement_score":0.9473269,"about_ca_system_score_codex":0.000019367062,"about_ca_system_score_gemma":0.0000048998318,"threshold_uncertainty_score":0.9998014},"labels":[],"label_agreement":null},{"id":"W1519610715","doi":"10.1109/ijcnn.1999.833418","title":"Reinforcement learning for autonomous robot navigation","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Bellman equation; Computer science; Mobile robot; Motion planning; Robot; Piecewise linear function; Robot learning; Artificial intelligence; Function (biology); Function approximation; Piecewise; Path (computing); Mobile robot navigation; Robot control; Mathematical optimization; Mathematics; Artificial neural network","score_opus":0.02127075616356644,"score_gpt":0.26146204335521966,"score_spread":0.24019128719165322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1519610715","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":[0.00021238608,0.000012463935,0.96066946,0.00016696981,0.00033667323,0.00032280706,2.3106152e-8,0.0003220598,0.03795713],"genre_scores_gemma":[0.7426046,0.0000032854148,0.23529515,0.00022958881,0.00002692274,0.000045537516,0.00000963117,0.0000124048165,0.02177284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988218,0.000046043067,0.00028492927,0.00027650292,0.00023527197,0.000335465],"domain_scores_gemma":[0.9992296,0.000113844355,0.00012748306,0.00035012545,0.00010297126,0.00007594217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044840397,0.00013025277,0.000118776006,0.00006975583,0.00023324357,0.00019059204,0.00038231464,0.000055503722,0.000057956164],"category_scores_gemma":[0.00016884264,0.00012477905,0.00007035917,0.0001983834,0.000017973061,0.00042560042,0.000068374626,0.00013376282,0.00011193921],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.421022e-7,0.0000040854775,0.00011554727,0.000008866041,0.0000075011517,5.8496306e-7,0.00013268788,0.7650393,0.00020690034,0.23266405,0.00019821158,0.0016212888],"study_design_scores_gemma":[0.000379565,0.0002004885,0.000057457335,0.0000116387555,0.0000046005885,0.000007111884,0.000029818239,0.9370896,0.0048090713,0.0006890316,0.056540124,0.0001814673],"about_ca_topic_score_codex":0.0000059367485,"about_ca_topic_score_gemma":2.7861265e-7,"teacher_disagreement_score":0.74239224,"about_ca_system_score_codex":0.00009340584,"about_ca_system_score_gemma":0.0000776544,"threshold_uncertainty_score":0.5088342},"labels":[],"label_agreement":null},{"id":"W1521332421","doi":"","title":"A Bayesian approach to imitation in reinforcement learning","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":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; University of British Columbia","funders":"","keywords":"Imitation; Computer science; Bayesian probability; Reinforcement learning; Artificial intelligence; Machine learning; Bayesian network; Bayesian inference; Social learning; Knowledge management; Psychology","score_opus":0.019689779485534634,"score_gpt":0.24364885994542235,"score_spread":0.22395908045988772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521332421","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":[0.00027043343,0.0000030828944,0.7328128,0.00009973155,0.00006660235,0.00018196377,3.9799017e-9,0.00009513102,0.26647025],"genre_scores_gemma":[0.74398357,0.000001613627,0.2502601,0.00034874695,0.0000062132676,0.00002255995,0.000001347735,0.0000063244893,0.005369511],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987351,0.00009659808,0.0002655124,0.00028780662,0.00030173664,0.00031330535],"domain_scores_gemma":[0.9994489,0.00004934193,0.00005462898,0.00031363772,0.000039571438,0.00009393296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005266697,0.00011088153,0.00010827918,0.00022902839,0.00007085861,0.00013818672,0.00036552406,0.0000406889,0.000026611291],"category_scores_gemma":[0.000234944,0.00010751943,0.000023424036,0.000666922,0.000008517165,0.00033819163,0.000088666005,0.00016901191,0.00012430802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.8040167e-7,0.000009915105,0.0008040337,0.0000046594814,0.0000022785948,9.3553314e-7,0.00091397366,0.8197457,0.00006058462,0.17760628,0.00011041849,0.0007403443],"study_design_scores_gemma":[0.00024884887,0.00011150368,0.00054741255,0.000009209174,0.0000010018016,0.0000034718155,0.00017559587,0.99262416,0.00033130383,0.00021388805,0.005572086,0.00016153246],"about_ca_topic_score_codex":0.000018912806,"about_ca_topic_score_gemma":0.000001992317,"teacher_disagreement_score":0.74371314,"about_ca_system_score_codex":0.00009688717,"about_ca_system_score_gemma":0.000044927558,"threshold_uncertainty_score":0.43845153},"labels":[],"label_agreement":null},{"id":"W1526654727","doi":"","title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Upper and lower bounds; Logarithm; Computer science; Probably approximately correct learning; Markov process; Sample complexity; Contrast (vision); Binary logarithm; Exploratory analysis; Q-learning; Algorithm; Exploratory research; Markov chain; Process (computing); Mathematics; Artificial intelligence; Combinatorics; Machine learning; Active learning (machine learning); Computational learning theory; Statistics","score_opus":0.04441804103927028,"score_gpt":0.2579625849142766,"score_spread":0.21354454387500632,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1526654727","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":[0.0049824044,0.0000012162228,0.9684016,0.00090130814,0.00018822099,0.00021373155,1.0248906e-7,0.000496041,0.024815364],"genre_scores_gemma":[0.7391004,6.8700973e-7,0.25664857,0.00037261055,0.000035043053,0.000018303028,0.000018188066,0.000013642131,0.0037925376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983113,0.000040361745,0.0002856723,0.00037356952,0.0006139561,0.00037518813],"domain_scores_gemma":[0.99873203,0.00005212837,0.0001680237,0.0007122034,0.0001949375,0.00014068335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000355473,0.00020312076,0.00015965317,0.00012480002,0.00039655715,0.0005844307,0.0007089482,0.0000787195,0.00012027429],"category_scores_gemma":[0.00004230235,0.00016413699,0.000047449223,0.00033029544,0.00013407286,0.0013675966,0.00015029313,0.0005463532,0.00013401508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009412914,0.000012354234,0.00050918746,0.0000069774205,0.0000075193097,0.0000020614066,0.00030287754,0.8894727,0.0008206456,0.108161435,0.00016627931,0.0005285315],"study_design_scores_gemma":[0.00048812234,0.00029849983,0.00017850458,0.0000103204175,0.000005571679,0.0000026130265,0.00001748834,0.9929459,0.0017198131,0.0005594099,0.003522617,0.00025112534],"about_ca_topic_score_codex":0.00003820553,"about_ca_topic_score_gemma":0.000048379825,"teacher_disagreement_score":0.734118,"about_ca_system_score_codex":0.000046681387,"about_ca_system_score_gemma":0.00020371853,"threshold_uncertainty_score":0.66933125},"labels":[],"label_agreement":null},{"id":"W1530545262","doi":"10.1007/978-3-642-04380-2_84","title":"A Real-Time Transfer and Adaptive Learning Approach for Game Agents in a Layered Architecture","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Architecture; Transfer of learning; Artificial intelligence; Human–computer interaction; Real-time computing; Distributed computing; Computer architecture","score_opus":0.026707445206418993,"score_gpt":0.249829523060819,"score_spread":0.2231220778544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530545262","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":[0.00014739616,0.00010397107,0.99400556,0.00020145983,0.00018292443,0.0011132458,0.000002704225,0.00016753878,0.004075204],"genre_scores_gemma":[0.11183737,0.00008489638,0.8856673,0.0005241315,0.00021598906,0.000033438,0.000017210557,0.00006275065,0.0015569172],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99577606,0.00008400731,0.00060717465,0.0017708627,0.0008545179,0.00090740883],"domain_scores_gemma":[0.99815947,0.00052400527,0.0001892718,0.0007955695,0.00014271558,0.00018895135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009983003,0.00066551997,0.00075812364,0.0010848161,0.00019791853,0.00048304527,0.0021101618,0.00043239546,0.0000067246647],"category_scores_gemma":[0.000103787184,0.00062877615,0.00014703057,0.0005964924,0.00044766534,0.0004011163,0.0005388176,0.0013492445,0.000006522696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000233383,0.000016078291,0.000025692414,0.000037836806,0.000010252023,0.000023571352,0.001860667,0.80060536,0.00011026583,0.002520967,0.0000022340291,0.19476376],"study_design_scores_gemma":[0.00072233885,0.00062587054,0.00022138833,0.00031728207,0.000009506524,0.000032250016,4.1382881e-7,0.98391265,0.000100934376,0.012997102,0.00039666917,0.0006635744],"about_ca_topic_score_codex":0.000024005996,"about_ca_topic_score_gemma":0.000012560747,"teacher_disagreement_score":0.19410019,"about_ca_system_score_codex":0.0002803612,"about_ca_system_score_gemma":0.00032096167,"threshold_uncertainty_score":0.9996164},"labels":[],"label_agreement":null},{"id":"W1530573725","doi":"10.48550/arxiv.1206.6879","title":"Practical Linear Value-approximation Techniques for First-order MDPs","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Computer science; Bellman equation; Mathematical optimization; Linear programming; Probabilistic logic; Set (abstract data type); Function (biology); Domain (mathematical analysis); Value (mathematics); Markov process; Order (exchange); Algorithm; Mathematics; Artificial intelligence; Machine learning","score_opus":0.09509342492505367,"score_gpt":0.23970681743159786,"score_spread":0.1446133925065442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530573725","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":[0.0023667468,0.0000053214235,0.9936504,0.00039163322,0.00019857817,0.0003315111,6.693095e-7,0.00033301784,0.0027221295],"genre_scores_gemma":[0.7291979,0.000015972219,0.26932433,0.00014362068,0.000101691374,0.0000020155303,0.0000047368567,0.000011155331,0.0011985551],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905103,0.00005479244,0.00013535045,0.00029934774,0.000088873465,0.00037062104],"domain_scores_gemma":[0.9988718,0.00024023921,0.00013288812,0.00047694432,0.0001529343,0.00012518484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003924123,0.00013292005,0.00012131566,0.00011452568,0.00020308323,0.000053024414,0.0004619773,0.00010745713,0.000016337417],"category_scores_gemma":[0.00022786552,0.0001436589,0.00007263045,0.00048013436,0.00005223856,0.0014919201,0.00021861315,0.00015277501,0.000095161486],"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":[0.00001688722,0.00008335105,0.0023902806,0.000032632714,0.000025235315,0.0000056031904,0.00020466813,0.21607627,0.000048391237,0.7795788,0.0012603173,0.00027753826],"study_design_scores_gemma":[0.0002440269,0.00009977334,0.00022839777,0.000013018728,0.000025277744,0.0000055623204,0.000031111565,0.9795176,0.0009601673,0.0014427014,0.01724145,0.0001909475],"about_ca_topic_score_codex":0.00000777551,"about_ca_topic_score_gemma":8.888517e-7,"teacher_disagreement_score":0.77813613,"about_ca_system_score_codex":0.000101918704,"about_ca_system_score_gemma":0.00005111517,"threshold_uncertainty_score":0.58582395},"labels":[],"label_agreement":null},{"id":"W1535857328","doi":"10.1002/9780470724163.ch30","title":"Approximation and Perception in Ethology‐Based Reinforcement Learning","year":2008,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","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 Manitoba","funders":"","keywords":"Ethology; Reinforcement; Perception; Reinforcement learning; Animal learning; Psychology; Cognitive psychology; Artificial intelligence; Computer science; Cognitive science; Neuroscience; Social psychology; Biology; Ecology","score_opus":0.018992809401622634,"score_gpt":0.2527448291641516,"score_spread":0.23375201976252896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1535857328","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001117315,0.000027227352,0.6517444,0.000086684464,0.00008681698,0.00020029375,3.823218e-8,0.00027047694,0.34757283],"genre_scores_gemma":[0.011924946,0.0003558011,0.1769226,0.0003891198,0.00007145531,0.000035133417,0.000047977654,0.00013868038,0.81011426],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874675,0.00010657708,0.0002542515,0.00038260486,0.0002740436,0.00023579155],"domain_scores_gemma":[0.99935704,0.00004182384,0.00020415177,0.00033464518,0.000018124238,0.000044239292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023637107,0.00020642049,0.00021977519,0.0005305241,0.000053198226,0.000063939646,0.00029913386,0.00027577864,0.00038606013],"category_scores_gemma":[0.00004842658,0.000200739,0.00003182864,0.00020545228,0.000059109145,0.00012740493,0.00014464857,0.00038344218,0.00012628738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033088536,0.0000141799765,0.0012162805,0.00011161314,0.000011511537,0.000016082253,0.00066434557,0.9561424,0.00005472756,0.0036742033,0.030882876,0.007208432],"study_design_scores_gemma":[0.00040530134,0.00008969848,0.00071223057,0.00010313009,0.000003090994,0.000008493954,0.000025867139,0.9347006,0.000006971972,0.0000106526295,0.063691534,0.00024243369],"about_ca_topic_score_codex":0.00010633149,"about_ca_topic_score_gemma":0.000012212271,"teacher_disagreement_score":0.47482184,"about_ca_system_score_codex":0.00007961885,"about_ca_system_score_gemma":0.00004748865,"threshold_uncertainty_score":0.8185899},"labels":[],"label_agreement":null},{"id":"W1537507437","doi":"10.1007/11766247_42","title":"The K Best-Paths Approach to Approximate Dynamic Programming with Application to Portfolio Optimization","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Computer science; Dynamic programming; Reinforcement learning; Mathematical optimization; Markov decision process; Portfolio; Kernel (algebra); Controller (irrigation); Sharpe ratio; Project portfolio management; Portfolio optimization; Artificial intelligence; Markov process; Algorithm; Mathematics; Finance; Project management","score_opus":0.008187980339184919,"score_gpt":0.22828879796239565,"score_spread":0.22010081762321074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537507437","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":[0.0000054172383,0.00006423254,0.991424,0.00047033656,0.00035707492,0.0020172424,0.000001092323,0.00023368714,0.005426908],"genre_scores_gemma":[0.016434718,0.000009677003,0.98171735,0.0005596998,0.00013845351,0.00014970097,0.000020891168,0.00005546774,0.000914069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99559855,0.000029226996,0.00057145767,0.0016005255,0.0013602581,0.0008399599],"domain_scores_gemma":[0.99699473,0.00018443166,0.00038169618,0.0018384887,0.00038358298,0.00021704592],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00091023097,0.00054910657,0.00037798184,0.00066338025,0.0006089241,0.0014468108,0.003749519,0.00020498282,7.8625976e-7],"category_scores_gemma":[0.000055278386,0.0004031801,0.00006883285,0.0014537085,0.00033333848,0.0004218682,0.0011597738,0.0005841971,0.000028889903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044747176,0.000016093041,0.000014138703,0.000016586926,0.000005035641,0.000003663107,0.00019173695,0.77763736,0.0000057551188,0.004459505,0.000010085346,0.21763559],"study_design_scores_gemma":[0.000117998236,0.000262579,0.000016943959,0.00014514089,0.000009600365,0.00003577699,6.100121e-7,0.99522215,0.00003990412,0.0012141328,0.002397696,0.00053747476],"about_ca_topic_score_codex":0.000026396514,"about_ca_topic_score_gemma":0.000021109885,"teacher_disagreement_score":0.2175848,"about_ca_system_score_codex":0.00046625367,"about_ca_system_score_gemma":0.0003408119,"threshold_uncertainty_score":0.999842},"labels":[],"label_agreement":null},{"id":"W1537974983","doi":"","title":"Reinforcement using supervised learning for policy generalization","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Reinforcement learning; Markov decision process; Bellman equation; Computer science; Function approximation; Q-learning; Artificial intelligence; Mathematical optimization; Temporal difference learning; Generalization; Machine learning; Formalism (music); Markov process; Mathematics; Artificial neural network","score_opus":0.03822809926627745,"score_gpt":0.3112965769924141,"score_spread":0.2730684777261366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1537974983","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":[0.0022586973,0.000008156542,0.9906393,0.00026106552,0.00020016021,0.00028317762,4.473869e-8,0.00024544442,0.006103928],"genre_scores_gemma":[0.625504,0.0000057861275,0.36798137,0.00072831655,0.00024041407,0.00000460142,0.000011827428,0.00001706127,0.005506632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986839,0.000021479753,0.00033422405,0.00023602768,0.00028243527,0.00044188974],"domain_scores_gemma":[0.9992668,0.00008355009,0.000111312096,0.00029787357,0.00014738677,0.00009308148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063189375,0.00012656125,0.00011149925,0.00025845505,0.00024922192,0.00016575941,0.00041853703,0.000060722377,0.00001903349],"category_scores_gemma":[0.00016082561,0.00012314503,0.000064434054,0.00048433043,0.000019941419,0.00043900256,0.00015674125,0.00008255894,0.000015194064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036798103,0.000003523224,0.00045751524,0.000010079585,0.000007912501,6.566333e-7,0.00020739668,0.84151673,0.0028785742,0.15200745,0.00006878794,0.0028376759],"study_design_scores_gemma":[0.0003885152,0.00009569419,0.00012955167,0.000008347268,0.00000409566,0.0000036479216,0.000026541322,0.9852433,0.0057679866,0.00021205192,0.0079603335,0.00015993157],"about_ca_topic_score_codex":0.00010148436,"about_ca_topic_score_gemma":0.0000028851996,"teacher_disagreement_score":0.6232453,"about_ca_system_score_codex":0.00018443036,"about_ca_system_score_gemma":0.000106925974,"threshold_uncertainty_score":0.50217086},"labels":[],"label_agreement":null},{"id":"W1538703232","doi":"10.1007/978-3-642-04428-1_39","title":"Anytime Self-play Learning to Satisfy Functional Optimality Criteria","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.01797993096656769,"score_gpt":0.2577936049483812,"score_spread":0.23981367398181352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1538703232","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":[0.000081860984,0.00008124345,0.9876983,0.0011124141,0.0019647216,0.0004687057,0.0000016238956,0.0005771336,0.008013955],"genre_scores_gemma":[0.070733435,0.000018286762,0.92268944,0.0029933364,0.0007692907,0.000009393733,0.000013257247,0.00005086192,0.0027226869],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99437,0.00009159259,0.0007675806,0.0019961733,0.00175945,0.0010152112],"domain_scores_gemma":[0.9968368,0.00050319335,0.00037375654,0.0015064914,0.00039863677,0.00038113107],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015149488,0.0007320727,0.00065944233,0.0010304312,0.0005270005,0.0012492675,0.0033147465,0.00040423416,0.0001476235],"category_scores_gemma":[0.00024558828,0.00073644763,0.0001701442,0.0008789998,0.00029123237,0.000853812,0.0017320795,0.0015423348,0.0003634329],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005912207,0.000014542905,0.00012117021,0.000017421387,0.000013180487,0.000040522787,0.0007436466,0.86261606,0.00013377752,0.0039893794,0.000102400736,0.13220201],"study_design_scores_gemma":[0.00027607963,0.000569318,0.002661989,0.0002870183,0.000012845907,0.00009877104,1.8823775e-7,0.97461504,0.00034511587,0.010672948,0.009410883,0.0010497957],"about_ca_topic_score_codex":0.000015414163,"about_ca_topic_score_gemma":0.000008457592,"teacher_disagreement_score":0.13115221,"about_ca_system_score_codex":0.00064478285,"about_ca_system_score_gemma":0.00065477996,"threshold_uncertainty_score":0.9997875},"labels":[],"label_agreement":null},{"id":"W1541317966","doi":"10.1609/aaai.v24i1.7740","title":"Robust Policy Computation in Reward-Uncertain MDPs Using Nondominated Policies","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Markov decision process; Minimax; Computer science; Mathematical optimization; Set (abstract data type); Computation; Parallels; Exploit; Mathematics; Markov process; Algorithm; Machine learning; Economics","score_opus":0.12308326003183422,"score_gpt":0.3346686475142595,"score_spread":0.21158538748242528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1541317966","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":[0.46239653,0.00000569461,0.5161762,0.005125727,0.0008815795,0.0007454656,0.0000023066464,0.0001671327,0.014499364],"genre_scores_gemma":[0.9785025,0.000008654375,0.021050623,0.00019090179,0.00009255003,0.000009723738,5.7634804e-7,0.00001556093,0.00012886863],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99778163,0.000028095517,0.0007084955,0.0004453324,0.00056090526,0.00047556104],"domain_scores_gemma":[0.998288,0.00014239008,0.0005325306,0.0003068382,0.00064133154,0.00008893226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073210895,0.00025254794,0.00029782162,0.00047759642,0.00019978108,0.00035525745,0.0019273813,0.0001429204,0.0000215452],"category_scores_gemma":[0.0011682498,0.00020890993,0.0000951567,0.0016401889,0.00033964653,0.0005431751,0.00061150064,0.0006494951,0.000035140674],"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":[0.000032900778,0.000070535796,0.000625311,0.000031918098,0.00000803781,7.471086e-7,0.0022107342,0.306659,0.09016816,0.58903694,0.000027168344,0.011128538],"study_design_scores_gemma":[0.00005172836,0.00008198752,0.00046443086,0.00014680233,0.0000052351274,0.000007585079,0.00032957576,0.8605183,0.10069244,0.037472147,0.00001817526,0.0002115995],"about_ca_topic_score_codex":0.0006387252,"about_ca_topic_score_gemma":0.000048708804,"teacher_disagreement_score":0.5538593,"about_ca_system_score_codex":0.00011045727,"about_ca_system_score_gemma":0.00026957414,"threshold_uncertainty_score":0.85191},"labels":[],"label_agreement":null},{"id":"W1544231892","doi":"10.48550/arxiv.1212.2471","title":"Monte Carlo Matrix Inversion Policy Evaluation","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Monte Carlo method; Computer science; Inverse; Inversion (geology); Algorithm; Matrix (chemical analysis); Mathematical optimization; Mathematics; Statistics","score_opus":0.08529009758601776,"score_gpt":0.22615303763203295,"score_spread":0.14086294004601518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544231892","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":[0.28637537,0.00003324787,0.7076795,0.00019063483,0.00034179506,0.00017382845,4.3835658e-7,0.00016283599,0.0050423313],"genre_scores_gemma":[0.9948216,0.000021188464,0.0012019827,0.00012269705,0.0001058225,3.0227508e-7,0.0000015013044,0.00000799891,0.003716896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989104,0.00013918488,0.00011112283,0.0002831674,0.0001752564,0.00038082682],"domain_scores_gemma":[0.9989464,0.000054388136,0.000115590425,0.0005757719,0.00013007039,0.00017775873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004651708,0.00012734388,0.000103479935,0.00025661816,0.00016370574,0.000052789648,0.0006790402,0.00007538094,0.00004617269],"category_scores_gemma":[0.00009241997,0.00014338606,0.000072974515,0.0008825325,0.00004203359,0.0014068657,0.0003423977,0.00013491148,0.00044527982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004692361,0.00001754201,0.011654512,0.0000051309044,0.000013493249,0.0000047165913,0.00030078387,0.86528945,0.000043462875,0.12180854,0.00039679502,0.00046087438],"study_design_scores_gemma":[0.0004157218,0.000038169386,0.0036963408,0.0000072950806,0.000026514059,0.000002639096,0.00007211478,0.992566,0.00009831566,0.00038509094,0.0025264926,0.0001653408],"about_ca_topic_score_codex":0.00010284384,"about_ca_topic_score_gemma":0.0000025298702,"teacher_disagreement_score":0.70844626,"about_ca_system_score_codex":0.00036113948,"about_ca_system_score_gemma":0.00011521128,"threshold_uncertainty_score":0.58471143},"labels":[],"label_agreement":null},{"id":"W1545201153","doi":"","title":"Exploiting the Fascination: Video Games in Machine Learning Research and Education","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Perspective (graphical); Turns, rounds and time-keeping systems in games; Point (geometry); Computer science; Video game; Game mechanics; Multimedia; Artificial neural network; Artificial intelligence; Video game design; Mathematics education; Psychology; Mathematics","score_opus":0.051549863138243085,"score_gpt":0.3323159438679224,"score_spread":0.28076608072967935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1545201153","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":[0.07838531,0.00027926685,0.8848005,0.011842481,0.00014710137,0.00024466423,2.2469527e-8,0.00011204474,0.02418863],"genre_scores_gemma":[0.98153496,0.000052903633,0.014725124,0.00016655303,0.00003932483,0.000018474662,0.0000010057096,0.00000481278,0.0034568417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900967,0.000107746884,0.00014773328,0.00019777135,0.00033432595,0.00020278008],"domain_scores_gemma":[0.9993615,0.00023912502,0.000039236842,0.00022127222,0.00010665109,0.000032191332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012455641,0.000057854133,0.000054265838,0.00017484436,0.00025931903,0.0002871221,0.000381314,0.00002502515,0.0000111765885],"category_scores_gemma":[0.00035315767,0.000041988762,0.00000934033,0.0005718068,0.000056994086,0.00045932332,0.0002595779,0.00036256269,0.000025752208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020324478,0.00003991454,0.015514087,0.00001691405,0.000003647682,0.000002387561,0.0059237718,0.50323164,0.00022930893,0.41635117,0.00011591166,0.058569185],"study_design_scores_gemma":[0.0008552769,0.00034858185,0.036007006,0.00019292402,0.0000020153172,0.00003909203,0.004238077,0.908825,0.0020088837,0.037084654,0.010093462,0.00030505346],"about_ca_topic_score_codex":0.00024610115,"about_ca_topic_score_gemma":0.000037031623,"teacher_disagreement_score":0.90314966,"about_ca_system_score_codex":0.00008353216,"about_ca_system_score_gemma":0.00011285414,"threshold_uncertainty_score":0.2768725},"labels":[],"label_agreement":null},{"id":"W1548867233","doi":"10.1007/978-3-540-30115-8_33","title":"Sparse Distributed Memories for On-Line Value-Based Reinforcement Learning","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; A priori and a posteriori; Bellman equation; Line (geometry); Function (biology); Scheme (mathematics); Dynamic random-access memory; Distributed computing; Artificial intelligence; Mathematical optimization; Semiconductor memory; Computer hardware","score_opus":0.030305597366027073,"score_gpt":0.26716725850461265,"score_spread":0.2368616611385856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548867233","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":[0.000009171076,0.00006600611,0.9935191,0.0012669107,0.0020792228,0.001061247,0.000007080265,0.00038556094,0.001605679],"genre_scores_gemma":[0.35105243,0.000022894732,0.643036,0.0032373553,0.00082808064,0.00006553116,0.0001830725,0.00011577774,0.0014588302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443525,0.000041464635,0.00091178244,0.0017663996,0.0017125926,0.0011325248],"domain_scores_gemma":[0.99586433,0.0010756177,0.0006743161,0.0016778915,0.00045068434,0.00025714113],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012324188,0.00085944857,0.0007583576,0.0008837247,0.0006353983,0.0008314013,0.0035723364,0.00040419653,0.000031826447],"category_scores_gemma":[0.00055243896,0.0008081136,0.00028033243,0.0006920395,0.0007063178,0.00047224827,0.0009262704,0.001301766,0.000057780355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023989674,0.00001842091,0.00001336681,0.00007326604,0.00001698473,0.00003122017,0.00018845798,0.9098111,0.000016766162,0.064436615,0.000015603575,0.025354201],"study_design_scores_gemma":[0.0010050182,0.0013989824,0.000012603186,0.00075846247,0.000018316876,0.000008807978,1.9036645e-7,0.95705116,0.0026092057,0.032982085,0.0033048138,0.00085036294],"about_ca_topic_score_codex":0.000012861842,"about_ca_topic_score_gemma":0.0000058163423,"teacher_disagreement_score":0.35104325,"about_ca_system_score_codex":0.0011216066,"about_ca_system_score_gemma":0.0013942573,"threshold_uncertainty_score":0.999437},"labels":[],"label_agreement":null},{"id":"W1552645109","doi":"10.1184/r1/6558128","title":"Plays as Effective Multiagent Plans Enabling Opponent-Adaptive Play Selection","year":2018,"lang":"en","type":"article","venue":"Figshare","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":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":"U.S. Air Force","keywords":"Computer science; Adversarial system; Adversary; Robot; Set (abstract data type); Adaptation (eye); Domain (mathematical analysis); Focus (optics); Plan (archaeology); Artificial intelligence; Human–computer interaction; Selection (genetic algorithm); Multi-agent system; Computer security","score_opus":0.03495788689315934,"score_gpt":0.27230603584848434,"score_spread":0.237348148955325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1552645109","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":[0.0037645332,0.0001152877,0.9398901,0.00025542302,0.0014392751,0.0029964957,0.0101624485,0.0021297245,0.03924674],"genre_scores_gemma":[0.9870774,0.0000016289167,0.006354023,0.00046578544,0.00059061794,0.00026483077,0.0040705563,0.000035475085,0.0011396643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984372,0.000095124524,0.0001929438,0.0004734196,0.00038841672,0.0004128459],"domain_scores_gemma":[0.9988356,0.00027940454,0.00015775536,0.00034785838,0.00024597044,0.00013339288],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010160495,0.00020515901,0.00015068769,0.00014140939,0.00032586924,0.00021889052,0.0006645929,0.000115132956,0.012137896],"category_scores_gemma":[0.00074911333,0.00020100012,0.0000697024,0.0003887012,0.00001310943,0.00053780974,0.00035285595,0.000265108,0.009761291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015782482,0.00017677632,0.00044901407,0.0001901593,0.00037281698,0.00015316253,0.0114893215,0.6531018,0.0041173617,0.003587851,0.3020364,0.024167482],"study_design_scores_gemma":[0.0006440619,0.0010588603,0.003736899,0.000813212,0.000010446248,0.000048963917,0.00006124926,0.90062886,0.033697635,0.00005806854,0.058744043,0.0004976962],"about_ca_topic_score_codex":0.000022309983,"about_ca_topic_score_gemma":0.000010456308,"teacher_disagreement_score":0.9833129,"about_ca_system_score_codex":0.00016714357,"about_ca_system_score_gemma":0.000089019035,"threshold_uncertainty_score":0.9910097},"labels":[],"label_agreement":null},{"id":"W1552684655","doi":"","title":"Using linear programming for Bayesian exploration in Markov decision processes","year":2007,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Computer science; Bellman equation; Reinforcement learning; Mathematical optimization; Markov process; Linear programming; Machine learning; Representation (politics); Artificial intelligence; Markov chain; Key (lock); Bayesian probability; Partially observable Markov decision process; Markov model; Algorithm; Mathematics","score_opus":0.2143689443380605,"score_gpt":0.3942220206217933,"score_spread":0.1798530762837328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1552684655","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":[0.0024075194,0.000006063945,0.99356043,0.0011579943,0.0010405645,0.0005269353,0.0000017504071,0.000104419494,0.0011943255],"genre_scores_gemma":[0.67148167,0.000014250851,0.32809162,0.00017321241,0.00014174794,0.000027050251,0.000008788706,0.0000117914715,0.00004987633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755514,0.00003150483,0.0008522841,0.0005238088,0.0006356875,0.00040155667],"domain_scores_gemma":[0.9981309,0.00041777772,0.0002841508,0.0002984485,0.0007758776,0.00009280629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010967144,0.00020631851,0.00018530758,0.00050986157,0.00012288651,0.0003920841,0.0008631855,0.00009992422,0.000039226634],"category_scores_gemma":[0.0013586597,0.00020889033,0.00006751872,0.0005514615,0.00006652463,0.0009552589,0.00014608375,0.00022444747,0.00004868241],"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":[0.00015157065,0.00014344329,0.0001790877,0.000026308819,0.000012438278,0.000020255986,0.0009005344,0.27996916,0.0019709775,0.2238199,0.000015345346,0.49279097],"study_design_scores_gemma":[0.00006143513,0.00016743902,0.000054982844,0.00027081123,0.000002578771,0.0000057631146,0.00030532866,0.9341963,0.03173863,0.032327667,0.00063807383,0.000231001],"about_ca_topic_score_codex":0.000037258746,"about_ca_topic_score_gemma":0.00020878222,"teacher_disagreement_score":0.6690741,"about_ca_system_score_codex":0.00021091106,"about_ca_system_score_gemma":0.00021219518,"threshold_uncertainty_score":0.85183007},"labels":[],"label_agreement":null},{"id":"W1554247770","doi":"10.5555/1838206.1838354","title":"Cultivating desired behaviour: policy teaching via environment-dynamics tweaks","year":2010,"lang":"en","type":"article","venue":"ePrints Soton (University of Southampton)","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Dynamics (music); Order (exchange); Function (biology); Control (management); Balance (ability); Ideal (ethics); System dynamics; Process management; Management science; Artificial intelligence; Engineering; Business; Psychology; Pedagogy; Political science","score_opus":0.007248548219061583,"score_gpt":0.19957262442598298,"score_spread":0.19232407620692138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554247770","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":[0.36108068,7.781709e-7,0.6350909,0.0001494384,0.000109123735,0.00013153612,0.0000022077475,0.00011164421,0.0033237182],"genre_scores_gemma":[0.79836214,0.0000021905912,0.19961968,0.000023186312,0.000033062544,2.832619e-7,0.0000097684515,0.000012970275,0.0019367391],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984088,0.000089024594,0.00020657814,0.0004651317,0.00043341456,0.00039705317],"domain_scores_gemma":[0.99849075,0.00009447211,0.00033169324,0.00086627057,0.00004513332,0.00017165669],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004928526,0.00019965536,0.00022991248,0.00025798968,0.00048554948,0.00006161427,0.0015323594,0.000162877,0.00025562433],"category_scores_gemma":[0.000095986295,0.0002583795,0.00014677325,0.00018765565,0.0002154267,0.0005950235,0.0011047352,0.00074439,0.00024264301],"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":[0.00003901781,0.00037079668,0.68437964,0.00009505478,0.00015942354,0.000056683806,0.028494405,0.08594332,0.037946988,0.10364861,0.00010039017,0.058765672],"study_design_scores_gemma":[0.0013306933,0.000104182305,0.14132272,0.000055456512,0.000037399623,0.000023667804,0.0027690984,0.84975415,0.0015277542,0.0009686829,0.0013831097,0.00072308764],"about_ca_topic_score_codex":0.0008991412,"about_ca_topic_score_gemma":0.00004403633,"teacher_disagreement_score":0.7638108,"about_ca_system_score_codex":0.00015884105,"about_ca_system_score_gemma":0.00008704636,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W1554366315","doi":"10.1023/a:1022145020786","title":"Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes","year":2003,"lang":"en","type":"article","venue":"Discrete Event Dynamic Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":52,"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":"Convergence (economics); Variance (accounting); Markov chain; Computer science; Markov process; Gradient descent; Path (computing); Set (abstract data type); Mathematics; Process (computing); Mathematical optimization; Algorithm; Artificial intelligence; Statistics; Artificial neural network","score_opus":0.012337159850539526,"score_gpt":0.3126734131687594,"score_spread":0.3003362533182199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1554366315","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":[0.00051955896,0.0003928673,0.99465704,0.00014282102,0.0005365216,0.000613825,0.0000028627242,0.00009454922,0.0030399722],"genre_scores_gemma":[0.66055053,0.00010871054,0.33807567,0.000016192846,0.000016724063,0.00007923828,0.000016454727,0.000028085982,0.0011083891],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973853,0.0006198775,0.00071438873,0.00042900752,0.00043068748,0.00042072218],"domain_scores_gemma":[0.99843705,0.00016600474,0.0004920283,0.0006750582,0.00014301857,0.0000868676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014036342,0.00022685557,0.00038527368,0.00038936856,0.00006020597,0.00010682685,0.00065848243,0.00009310546,0.00000294395],"category_scores_gemma":[0.0006004188,0.00020768806,0.000073707044,0.0013585363,0.0000494124,0.00034965397,0.00012550416,0.00013670315,0.0000034512116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034993445,0.000023016048,0.0010168804,0.00043732597,0.000020686106,0.0000028794934,0.00082217215,0.9731426,0.00009012218,0.02424264,0.000017163551,0.00018097891],"study_design_scores_gemma":[0.00032311105,0.00007683814,0.00012648453,0.0003126537,0.000007744342,0.000018410132,0.0002797845,0.9979719,0.00020096095,0.00017472106,0.00028728458,0.0002201256],"about_ca_topic_score_codex":0.000156252,"about_ca_topic_score_gemma":0.0000068594527,"teacher_disagreement_score":0.66003096,"about_ca_system_score_codex":0.00026254618,"about_ca_system_score_gemma":0.00023849514,"threshold_uncertainty_score":0.84692734},"labels":[],"label_agreement":null},{"id":"W1555338578","doi":"10.5555/1838206.1838401","title":"Using bisimulation for policy transfer in MDPs","year":2010,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Markov decision process; Computer science; Bisimulation; Artificial intelligence; Markov process; Work (physics); Theoretical computer science; Mathematics","score_opus":0.12857996272755987,"score_gpt":0.35545820968810005,"score_spread":0.22687824696054018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1555338578","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":[0.1618139,0.000026264355,0.8362215,0.00004938491,0.00080224563,0.0008798485,0.0000063392627,0.0000451384,0.00015538743],"genre_scores_gemma":[0.9801678,0.00001168891,0.019095128,0.00009867714,0.00012352393,0.000032717973,0.000005768107,0.00002053577,0.00044414547],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853426,0.00007165417,0.00038294308,0.000400286,0.00024061528,0.0003702175],"domain_scores_gemma":[0.99929094,0.00008075221,0.00009036305,0.00031810463,0.00010358646,0.00011627182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035890916,0.00019336004,0.00022717183,0.0002670496,0.00015818907,0.00018188183,0.0003343244,0.0001205586,0.0000025455508],"category_scores_gemma":[0.000060862738,0.0001790246,0.000057315458,0.00027192888,0.000042862008,0.00047370096,0.00008850333,0.0001677586,0.000008193044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003427463,0.00018166618,0.02503603,0.00014244662,0.000113428876,0.000017063106,0.004427384,0.9009987,0.00936086,0.05498131,0.00009625358,0.0046105785],"study_design_scores_gemma":[0.0014193809,0.00007965182,0.012048979,0.00005056735,0.000008773159,0.000005859238,0.000058001155,0.98372823,0.00012531437,0.000028313218,0.0022469927,0.00019993626],"about_ca_topic_score_codex":0.0011033905,"about_ca_topic_score_gemma":0.000055137803,"teacher_disagreement_score":0.8183539,"about_ca_system_score_codex":0.00007082217,"about_ca_system_score_gemma":0.00006606551,"threshold_uncertainty_score":0.73004115},"labels":[],"label_agreement":null},{"id":"W1556824961","doi":"10.1007/3-540-45622-8_16","title":"Learning Options in Reinforcement Learning","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":270,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Psychology; Artificial intelligence","score_opus":0.021089761123276374,"score_gpt":0.2445734416842048,"score_spread":0.22348368056092843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1556824961","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":[0.000038500322,0.00019999423,0.974399,0.0003995299,0.0010603956,0.00043466158,1.7681589e-7,0.00031192106,0.023155848],"genre_scores_gemma":[0.6001106,0.00071263756,0.37265012,0.0010515209,0.0006231231,0.000037170714,0.000020703204,0.000134026,0.024660103],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994575,0.00009721199,0.0009717394,0.0016623603,0.0015447064,0.0011489352],"domain_scores_gemma":[0.99723357,0.0005613707,0.00053502433,0.0012487009,0.00021093088,0.00021043238],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014484585,0.0006915959,0.0006557687,0.0018623538,0.00047306612,0.00081072113,0.0033717763,0.00042242414,0.0001405219],"category_scores_gemma":[0.0003523065,0.0007209074,0.00014217352,0.0011599432,0.0004966671,0.0009313479,0.0019982364,0.003139857,0.00027795433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018002879,0.000009474928,0.00019449994,0.000024491124,0.000007078985,0.00008053609,0.0010000612,0.8959591,0.00002666361,0.012402527,0.0000069096072,0.090286896],"study_design_scores_gemma":[0.00034355317,0.00041554903,0.00013665791,0.00052906165,0.000005770522,0.000040334216,5.469884e-7,0.98733693,0.000068382105,0.0049506975,0.0054143355,0.0007581717],"about_ca_topic_score_codex":0.00003021724,"about_ca_topic_score_gemma":0.00001797927,"teacher_disagreement_score":0.6017488,"about_ca_system_score_codex":0.00083680754,"about_ca_system_score_gemma":0.0003227981,"threshold_uncertainty_score":0.9995242},"labels":[],"label_agreement":null},{"id":"W15601695","doi":"10.1128/jb.187.1.114-124.2005","title":"Autolysis of Lactococcus lactis is increased upon D-alanine depletion of peptidoglycan and lipoteichoic acids.","year":2005,"lang":"en","type":"article","venue":"PubMed","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Kernel (algebra); Kernel method; Mathematical optimization; Algorithm; Artificial intelligence; Mathematics; Discrete mathematics","score_opus":0.01333494179846988,"score_gpt":0.21369268491157492,"score_spread":0.20035774311310503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W15601695","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":[0.7970043,0.00015780036,0.19804619,0.0012973566,0.0001941772,0.0008284714,0.000008128918,0.00016685667,0.0022967583],"genre_scores_gemma":[0.99130714,0.00003545377,0.007987784,0.00012268007,0.00006830898,0.0000881986,0.000003967304,0.00001060996,0.00037585228],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9986513,0.000066312976,0.00036819789,0.00026272135,0.00036201678,0.00028942138],"domain_scores_gemma":[0.99888015,0.00010774199,0.00031961768,0.0004788141,0.0000935557,0.0001201001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038325414,0.00013448574,0.00025794882,0.00019264763,0.00004173997,0.00004558941,0.00040181138,0.00007483857,0.00002193741],"category_scores_gemma":[0.00016369973,0.00013014852,0.00006577228,0.00038513704,0.000053057876,0.00037247592,0.00017756702,0.000113378126,0.000006062113],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011869525,0.0002269908,0.3525073,0.00027835395,0.00029750695,0.000006956911,0.002461639,0.046659734,0.00481418,0.0028034246,0.0017168359,0.5881084],"study_design_scores_gemma":[0.00093118043,0.00009060816,0.87395895,0.000021812162,0.000034608816,0.0000072260714,0.00001526299,0.09888639,0.020299906,0.000046844936,0.0054845717,0.00022266425],"about_ca_topic_score_codex":0.00015528237,"about_ca_topic_score_gemma":0.0000216284,"teacher_disagreement_score":0.58788574,"about_ca_system_score_codex":0.000052066112,"about_ca_system_score_gemma":0.000030012092,"threshold_uncertainty_score":0.53073025},"labels":[],"label_agreement":null},{"id":"W1561485809","doi":"10.1007/978-3-540-70829-2_11","title":"The Concept of Opposition and Its Use in Q-Learning and Q(λ) Techniques","year":2008,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Opposition (politics); Q-learning; Artificial intelligence; TRACE (psycholinguistics); Mathematical optimization; Mathematics","score_opus":0.09245566855671966,"score_gpt":0.3442205430760504,"score_spread":0.2517648745193307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561485809","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":[0.0006300887,0.029727425,0.9514805,0.0005610095,0.00044475068,0.0010171257,0.0000057627517,0.00013125375,0.01600208],"genre_scores_gemma":[0.8295595,0.07511276,0.072801284,0.00018057937,0.00009534007,0.000049698097,0.00001867475,0.000051950756,0.022130195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986583,0.00005547467,0.00051096553,0.00031800984,0.0003099129,0.00014730994],"domain_scores_gemma":[0.9972669,0.0020122987,0.00028230812,0.00011271302,0.00030234832,0.000023442755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029129168,0.00019205043,0.0002787466,0.0001855194,0.00016000331,0.000055434644,0.00027612355,0.000091874186,0.0000013920368],"category_scores_gemma":[0.0002978515,0.00016517012,0.000028050377,0.00008814631,0.0005344695,0.00023115135,0.0005346089,0.00040650682,0.0000018435818],"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":[0.0000079761085,0.0000051967027,0.00018953596,0.00004720443,0.00004705833,0.000026413127,0.002572936,0.4594203,0.0000021400338,0.51941466,0.000074128155,0.01819246],"study_design_scores_gemma":[0.00023585418,0.00070300355,0.00060205883,0.0029198376,0.0000223635,0.00015885624,0.00057488243,0.8700594,0.00075257,0.10595358,0.017060053,0.00095754163],"about_ca_topic_score_codex":0.0000072995467,"about_ca_topic_score_gemma":0.000009995042,"teacher_disagreement_score":0.8786792,"about_ca_system_score_codex":0.000076642165,"about_ca_system_score_gemma":0.000046498702,"threshold_uncertainty_score":0.67354417},"labels":[],"label_agreement":null},{"id":"W1562324652","doi":"10.1111/coin.12060","title":"Concurrent Individual And Social Learning In Robot Teams","year":2015,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Reinforcement Learning in Robotics","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":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Robot; Computer science; Team learning; Relation (database); Human–computer interaction; Artificial intelligence; Knowledge management; Cooperative learning; Psychology; Teaching method; Open learning","score_opus":0.07697776732268413,"score_gpt":0.3196348699339635,"score_spread":0.24265710261127937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1562324652","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":[0.0064601847,0.000111563575,0.9918087,0.00055188563,0.00026200595,0.00009230395,4.237922e-7,0.00009469482,0.0006182434],"genre_scores_gemma":[0.97265375,0.0000041031194,0.026953198,0.00019733072,0.000048986385,0.000006041789,0.000014528304,0.0000062100926,0.00011588012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864566,0.000099999066,0.00028736613,0.0002825212,0.0004641624,0.00022029046],"domain_scores_gemma":[0.9993763,0.0002182843,0.00010514194,0.00007807214,0.0001395346,0.00008265068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004841859,0.000118727476,0.00013180748,0.00014107172,0.00010184942,0.00020327818,0.0004773619,0.000050790906,0.000006401582],"category_scores_gemma":[0.00013688135,0.00012662556,0.00002308031,0.00029755424,0.00010191989,0.00034205435,0.0003614388,0.0003000517,0.00007166407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011097703,0.000013844436,0.004076176,0.0000054336247,0.000005466779,0.0000051350994,0.0032322558,0.89080715,0.0000012567388,0.05634881,0.00010075223,0.045402598],"study_design_scores_gemma":[0.0001430735,0.00008895948,0.008253476,0.000015816368,0.00000214471,0.000013953917,0.00034051342,0.9838639,0.000030403085,0.006143024,0.0009477448,0.00015700886],"about_ca_topic_score_codex":0.000013473365,"about_ca_topic_score_gemma":0.00000192071,"teacher_disagreement_score":0.96619356,"about_ca_system_score_codex":0.00007831584,"about_ca_system_score_gemma":0.00016809205,"threshold_uncertainty_score":0.51636404},"labels":[],"label_agreement":null},{"id":"W1565394148","doi":"","title":"Solving POMDPs with continuous or large discrete observation spaces","year":2005,"lang":"en","type":"article","venue":"Discovery Research Portal (University of Dundee)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Toronto","funders":"","keywords":"Discretization; Markov decision process; Partially observable Markov decision process; Partition (number theory); Computer science; A priori and a posteriori; Observable; Task (project management); Domain (mathematical analysis); Mathematical optimization; Space (punctuation); Markov chain; Markov process; Theoretical computer science; Mathematics; Markov model; Machine learning","score_opus":0.046985247959016346,"score_gpt":0.29276817378004755,"score_spread":0.2457829258210312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565394148","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":[0.26968324,0.000050667037,0.7108397,0.0013164325,0.00005293007,0.0003394888,0.000007927732,0.00013237701,0.017577251],"genre_scores_gemma":[0.95904434,0.00008811311,0.02654484,0.00003296493,0.000040395324,4.4538763e-7,0.000020158723,0.000011615061,0.0142171355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975943,0.00013895471,0.00015387355,0.00039724936,0.0011240502,0.0005915954],"domain_scores_gemma":[0.99867475,0.00018872313,0.00017334035,0.00056446024,0.00026262217,0.0001360803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008314434,0.00014091188,0.00022689936,0.00024357472,0.0004205968,0.0002594009,0.0011099726,0.000073682735,0.00013881196],"category_scores_gemma":[0.00006396885,0.00012697944,0.00007613484,0.0006483931,0.00020051941,0.003951567,0.0006359052,0.00035461778,0.00004466796],"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":[0.001683598,0.0014139162,0.22427219,0.00066100503,0.0011840506,0.002562731,0.040725693,0.14651063,0.0035387666,0.537892,0.018254938,0.021300491],"study_design_scores_gemma":[0.0059054135,0.0036620805,0.14124049,0.00067919336,0.00008380294,0.000088581066,0.04448136,0.7508317,0.0009888115,0.0006765385,0.04987818,0.0014838282],"about_ca_topic_score_codex":0.0002670277,"about_ca_topic_score_gemma":0.0008435079,"teacher_disagreement_score":0.6893611,"about_ca_system_score_codex":0.00006539403,"about_ca_system_score_gemma":0.00031405067,"threshold_uncertainty_score":0.5178071},"labels":[],"label_agreement":null},{"id":"W1565405003","doi":"10.1007/978-3-540-68825-9_13","title":"Point-Based Planning for Predictive State Representations","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Observability; Computer science; Partially observable Markov decision process; Representation (politics); Observable; Markov decision process; Automated planning and scheduling; State (computer science); Point (geometry); Mathematical optimization; Artificial intelligence; Markov chain; Algorithm; Theoretical computer science; Markov process; Machine learning; Markov model; Mathematics; Applied mathematics","score_opus":0.02775704980736581,"score_gpt":0.2808852751791834,"score_spread":0.25312822537181756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565405003","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":[0.000010590264,0.00013764677,0.99369186,0.00052409206,0.001372619,0.00086536777,0.000011738166,0.00027501848,0.0031110384],"genre_scores_gemma":[0.035859317,0.000025799809,0.9603595,0.0016829319,0.0003612519,0.000054247375,0.000032879263,0.00006454792,0.0015594861],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961385,0.00003283872,0.00060764427,0.0014516636,0.0010420444,0.0007273242],"domain_scores_gemma":[0.99626476,0.0013041849,0.00045447022,0.0013875504,0.0004150579,0.00017395332],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00060954684,0.000482889,0.00045540766,0.00092438457,0.00048538126,0.00045063614,0.0027544734,0.00021236323,0.0000097928905],"category_scores_gemma":[0.00028201545,0.00047881206,0.00017126376,0.0005136511,0.00066534604,0.00069921673,0.0007010542,0.00070844346,0.000020467745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001092931,0.000009462705,0.000075554904,0.000025322308,0.000013014842,0.000047896334,0.001080621,0.97136706,0.0000129340415,0.0013165222,0.00016764957,0.025873005],"study_design_scores_gemma":[0.00043222838,0.00034233154,0.000104224215,0.00030253257,0.000007763867,0.000028900666,2.25028e-7,0.9799962,0.00065799465,0.0159685,0.0016719201,0.00048717894],"about_ca_topic_score_codex":0.000009979569,"about_ca_topic_score_gemma":0.0000047411318,"teacher_disagreement_score":0.035848726,"about_ca_system_score_codex":0.00034508941,"about_ca_system_score_gemma":0.0009248069,"threshold_uncertainty_score":0.99976635},"labels":[],"label_agreement":null},{"id":"W1569513695","doi":"10.1007/978-3-540-24840-8_30","title":"Multi-attribute Decision Making in a Complex Multiagent Environment Using Reinforcement Learning with Selective Perception","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Perception; Artificial intelligence; Machine learning; Human–computer interaction","score_opus":0.03624636363657711,"score_gpt":0.27589725601734344,"score_spread":0.23965089238076634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569513695","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":[0.00085793546,0.000058055477,0.99736285,0.000062471285,0.00032381428,0.0010262349,8.374313e-7,0.00013842672,0.00016937547],"genre_scores_gemma":[0.48945558,0.00002410027,0.51012087,0.00024263091,0.00006305808,0.000008477135,0.0000072099524,0.000036191865,0.000041853207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940781,0.0000818006,0.00094287156,0.0019491101,0.001859563,0.0010885352],"domain_scores_gemma":[0.99753773,0.00034560572,0.00068091834,0.0010968086,0.00018218235,0.00015677176],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010977329,0.00082914287,0.00071840244,0.0014078525,0.0004990694,0.000567285,0.0021012188,0.0003509145,0.000059004502],"category_scores_gemma":[0.00009580055,0.00076861965,0.00013252467,0.0007685847,0.00052277395,0.0008120486,0.00169274,0.0016579205,0.00004921894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019305291,0.00003075158,0.00095697003,0.000028934275,0.000014906674,0.0001090996,0.00216468,0.9465256,0.0004192832,0.00025710172,5.251152e-7,0.049472895],"study_design_scores_gemma":[0.0011544762,0.0004862364,0.0038397738,0.0015300312,0.000014420984,0.00007485309,0.0000023634468,0.99095005,0.00012168031,0.0008490243,0.00009479853,0.0008822911],"about_ca_topic_score_codex":0.00007395181,"about_ca_topic_score_gemma":0.000058036778,"teacher_disagreement_score":0.48859766,"about_ca_system_score_codex":0.0043051466,"about_ca_system_score_gemma":0.000578296,"threshold_uncertainty_score":0.99951714},"labels":[],"label_agreement":null},{"id":"W1591992921","doi":"10.48550/arxiv.1207.4114","title":"Metrics for Finite Markov Decision Processes","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Metric (unit); Markov process; Computer science; Markov kernel; Markov chain; Aggregate (composite); Bellman equation; Mathematical optimization; Q-learning; Similarity (geometry); Variable-order Markov model; Artificial intelligence; Markov model; Machine learning; Mathematics","score_opus":0.07973034372712487,"score_gpt":0.2043299711430501,"score_spread":0.12459962741592523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1591992921","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":[0.01110911,0.00006123252,0.98591685,0.00002600211,0.0003754594,0.00017656387,0.000001310818,0.00014127344,0.0021922155],"genre_scores_gemma":[0.9564404,0.00006251216,0.040905062,0.00010672356,0.00005870471,6.6161346e-7,0.0000028916795,0.000009903136,0.002413123],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990542,0.00002760374,0.0001238766,0.00030389745,0.00009661146,0.00039381484],"domain_scores_gemma":[0.9981385,0.0009351609,0.00011389795,0.0004650801,0.00019649779,0.00015089396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003209275,0.00012766507,0.00012309733,0.0002499302,0.00017266313,0.000074396616,0.00087435986,0.00007234482,0.000017969314],"category_scores_gemma":[0.00069833326,0.0001336738,0.0000683374,0.0015747958,0.000033709617,0.0011436589,0.00028212316,0.00009544312,0.000109687324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003016163,0.00006125461,0.019646158,0.00005867731,0.000026832091,0.000008882616,0.00019045113,0.8819661,0.000010882701,0.0934475,0.0010527517,0.0035003563],"study_design_scores_gemma":[0.0005478081,0.000103721344,0.0012410061,0.000022201748,0.00002737857,0.0000023997152,0.00004066181,0.97610396,0.00025831553,0.0019070632,0.019489152,0.00025633443],"about_ca_topic_score_codex":0.0000034963173,"about_ca_topic_score_gemma":0.0000012768992,"teacher_disagreement_score":0.94533134,"about_ca_system_score_codex":0.000077205645,"about_ca_system_score_gemma":0.000066477034,"threshold_uncertainty_score":0.545106},"labels":[],"label_agreement":null},{"id":"W1595080983","doi":"10.1109/acc.2015.7171887","title":"Finite state approximations of Markov decision processes with general state and action spaces","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Markov decision process; Action (physics); Finite state; Markov process; Complement (music); State space; Mathematical optimization; Markov chain; Applied mathematics; Mathematics; State (computer science); Partially observable Markov decision process; Markov model; Stochastic process; Markov kernel; Approximations of π; Computer science; Variable-order Markov model; Algorithm","score_opus":0.034492949131916716,"score_gpt":0.2734357435885215,"score_spread":0.2389427944566048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1595080983","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":[0.11639724,0.00001718877,0.88181996,0.00010601216,0.000046516907,0.00011028444,6.941096e-7,0.000047465,0.0014546493],"genre_scores_gemma":[0.47671944,0.00007177121,0.5192798,0.0000395784,0.000008967285,0.0000063479542,0.000002509393,0.000006706175,0.0038649312],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992052,0.000023283963,0.00016238034,0.00017006777,0.00031041793,0.00012867004],"domain_scores_gemma":[0.99919987,0.000121468394,0.00013190828,0.00020930242,0.0002609503,0.00007653075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019275877,0.00008466821,0.000096874355,0.000096410884,0.000046751775,0.0001569307,0.0001893569,0.000016227354,0.0000048852467],"category_scores_gemma":[0.00014146249,0.00006024035,0.000007618904,0.00033064504,0.000044540197,0.0007295236,0.00010882132,0.000052257637,0.0000075464236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023813653,0.000015908496,0.0021533147,0.00005906085,0.000012234038,0.0000022339243,0.001245275,0.9830353,0.000048117996,0.0006447783,0.00032917215,0.012430783],"study_design_scores_gemma":[0.00048269404,0.00031517565,0.0014400203,0.00004389471,0.0000052063083,0.000011340948,0.00011590613,0.9934305,0.0021895631,0.0011685719,0.000663854,0.0001332636],"about_ca_topic_score_codex":0.00003238026,"about_ca_topic_score_gemma":0.0000484882,"teacher_disagreement_score":0.3625402,"about_ca_system_score_codex":0.000016528065,"about_ca_system_score_gemma":0.0001570049,"threshold_uncertainty_score":0.245653},"labels":[],"label_agreement":null},{"id":"W1600046456","doi":"","title":"Off-Policy Temporal Difference Learning with Function Approximation","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":254,"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":"Temporal difference learning; Computer science; Function approximation; Function (biology); Artificial intelligence; Reinforcement learning; Artificial neural network","score_opus":0.01561973101356947,"score_gpt":0.23147654686657615,"score_spread":0.21585681585300667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600046456","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":[0.015585635,0.00000786569,0.9553232,0.00049109955,0.00007130956,0.00011271368,1.9220357e-8,0.00043027737,0.02797789],"genre_scores_gemma":[0.9432571,0.000013174531,0.039087582,0.00022192657,0.00008110137,0.000009377155,0.0000059189024,0.000008985148,0.017314848],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989574,0.00005043814,0.0001620384,0.0002522212,0.0003323207,0.00024559055],"domain_scores_gemma":[0.9993996,0.000039396986,0.00011201656,0.00030839088,0.00007594762,0.000064674605],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015135053,0.000121329984,0.00009936544,0.00014617709,0.0001631823,0.00021004914,0.00033445723,0.000043773023,0.00003732549],"category_scores_gemma":[0.000051394003,0.000092312046,0.000023086955,0.0005853257,0.00003022502,0.00052038336,0.000103120736,0.00018465763,0.000113141454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027402994,0.000031882402,0.073660135,0.000013853395,0.00002018632,0.000006965558,0.00043933504,0.700115,0.0003113858,0.08705508,0.000098362056,0.13822041],"study_design_scores_gemma":[0.00029025643,0.00034068993,0.021858588,0.000014663854,0.0000037700302,0.00002140267,0.000043643147,0.97027445,0.00008383077,0.00035194057,0.0065560024,0.00016073567],"about_ca_topic_score_codex":0.00006489439,"about_ca_topic_score_gemma":0.0000065793047,"teacher_disagreement_score":0.92767143,"about_ca_system_score_codex":0.000055447857,"about_ca_system_score_gemma":0.00006954476,"threshold_uncertainty_score":0.3764376},"labels":[],"label_agreement":null},{"id":"W1601777908","doi":"10.1007/3-540-36755-1_33","title":"Characterizing Markov Decision Processes","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Randomness; Artificial intelligence; Markov chain; Machine learning; Markov process; Measure (data warehouse); Quality (philosophy); Mathematical optimization; Decision problem; Algorithm; Data mining; Mathematics; Statistics","score_opus":0.019528231396003598,"score_gpt":0.243811645501996,"score_spread":0.2242834141059924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1601777908","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":[0.000023737155,0.00032434083,0.98593646,0.0004710245,0.0020668032,0.00036786668,0.000001508157,0.00028551597,0.010522745],"genre_scores_gemma":[0.060235623,0.00039584227,0.9330956,0.0025413085,0.0007819463,0.0000128973315,0.000007661786,0.00008606448,0.0028430643],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99505156,0.000024429548,0.00071636087,0.0017016791,0.0016421949,0.00086376787],"domain_scores_gemma":[0.9963029,0.0008670126,0.00047998584,0.0017449834,0.00039689333,0.00020821569],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007656733,0.00065073237,0.00058132946,0.0010412459,0.00034512326,0.0012011939,0.004903324,0.00036855388,0.000090355345],"category_scores_gemma":[0.00041534772,0.0006001848,0.00011808495,0.0009896817,0.00047098476,0.0011901805,0.0020541013,0.0010341849,0.00023533154],"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":[0.000004738401,0.000017544593,0.00007109214,0.00011060826,0.000010215068,0.00012489512,0.00067740696,0.22913873,0.000072820585,0.0030392061,0.000044850076,0.76668787],"study_design_scores_gemma":[0.00027365328,0.00021960869,0.00013939601,0.0013151349,0.000008770367,0.00011907168,7.973425e-8,0.9669989,0.00081005914,0.0193725,0.009715052,0.0010278022],"about_ca_topic_score_codex":0.0000039779525,"about_ca_topic_score_gemma":0.0000058767373,"teacher_disagreement_score":0.7656601,"about_ca_system_score_codex":0.00034176893,"about_ca_system_score_gemma":0.00047699394,"threshold_uncertainty_score":0.99983567},"labels":[],"label_agreement":null},{"id":"W1602154927","doi":"10.48550/arxiv.1301.2343","title":"Planning by Prioritized Sweeping with Small Backups","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Business; Computer science; Process management","score_opus":0.07880461453518656,"score_gpt":0.18244058612788147,"score_spread":0.10363597159269491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1602154927","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":[0.086029075,0.0000622758,0.9075045,0.00007531168,0.0003895656,0.00040737985,0.0000024281974,0.00046899548,0.005060476],"genre_scores_gemma":[0.9598354,0.000064868174,0.032115854,0.00016819527,0.00009399778,0.0000021502174,0.000033086042,0.000042786964,0.007643652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763596,0.00013621693,0.00025981714,0.00121022,0.00016200726,0.000595751],"domain_scores_gemma":[0.9975467,0.00015772512,0.0004352602,0.0014308367,0.00019502331,0.00023445307],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022729982,0.00044636521,0.0004371346,0.00023533069,0.00022463425,0.00042395075,0.0025130264,0.00031591003,0.000030197676],"category_scores_gemma":[0.000034550616,0.0004825341,0.00013456772,0.0004694804,0.00012194505,0.00048746195,0.002259073,0.0010171947,0.00018864934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014940679,0.00001883309,0.002946601,0.000078135985,0.000102030586,0.00018195811,0.00027336722,0.98169893,0.000036459944,0.01371402,0.00074931287,0.00018542644],"study_design_scores_gemma":[0.0008380897,0.00009974433,0.00048983307,0.00039659158,0.000061811195,0.000008153706,0.00007745908,0.9932662,0.000093510884,0.0013645452,0.002532314,0.00077171164],"about_ca_topic_score_codex":0.00014905236,"about_ca_topic_score_gemma":0.0000033232432,"teacher_disagreement_score":0.8753886,"about_ca_system_score_codex":0.00024126943,"about_ca_system_score_gemma":0.00021110672,"threshold_uncertainty_score":0.99976265},"labels":[],"label_agreement":null},{"id":"W161119602","doi":"10.1007/978-1-84628-758-9_9","title":"Reinforcement Agents for E-Learning Applications","year":2007,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Process (computing); Set (abstract data type); Reinforcement; Error-driven learning; Human–computer interaction; Artificial intelligence; Punishment (psychology); Engineering","score_opus":0.029622643948588556,"score_gpt":0.30180862920811563,"score_spread":0.2721859852595271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W161119602","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2234993e-7,0.000468517,0.5808268,0.000022106184,0.00010124047,0.0005405451,9.3946824e-7,0.00017988996,0.41785982],"genre_scores_gemma":[0.0032646079,0.001098951,0.24711584,0.00087982276,0.0002839048,0.000385304,0.0005117878,0.00008176514,0.746378],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983475,0.0000069038265,0.00076674524,0.0002732557,0.00027315892,0.00033240608],"domain_scores_gemma":[0.9981286,0.0001069902,0.00077417237,0.00029445,0.00056204293,0.00013374723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004473194,0.00032962675,0.0002718435,0.000398364,0.0006929338,0.00040197765,0.00043739768,0.00022285551,0.000017178229],"category_scores_gemma":[0.00006991616,0.0003456587,0.000079898964,0.00011402737,0.00006373571,0.0023897334,0.00025644308,0.0004593764,0.00015120456],"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":[0.00000706816,0.0000029823584,0.0000011564359,0.0005287993,0.000014794135,1.3642884e-7,0.0010885138,0.031066993,0.0000022217473,0.21423778,0.0001341393,0.7529154],"study_design_scores_gemma":[0.00037402575,0.00006512262,0.0000014208041,0.00022162072,0.00001517697,0.0000039866322,0.000047089386,0.28069627,0.000029812425,0.0016660659,0.7165865,0.00029294612],"about_ca_topic_score_codex":2.4914672e-7,"about_ca_topic_score_gemma":5.567946e-7,"teacher_disagreement_score":0.7526225,"about_ca_system_score_codex":0.00014263575,"about_ca_system_score_gemma":0.00018592332,"threshold_uncertainty_score":0.99989957},"labels":[],"label_agreement":null},{"id":"W1672238326","doi":"10.1109/ccece.2015.7129412","title":"The residual gradient FACL algorithm for differential games","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Fuzzy logic; Algorithm; Convergence (economics); Computer science; Reinforcement learning; Residual; Fuzzy control system; Adaptive neuro fuzzy inference system; Control theory (sociology); Artificial intelligence; Mathematics; Control (management)","score_opus":0.03577575525246496,"score_gpt":0.26973635512533206,"score_spread":0.2339605998728671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1672238326","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":[0.0003713534,0.000033066113,0.9940012,0.0012509155,0.0010696665,0.00021771152,7.12419e-7,0.00014829217,0.002907083],"genre_scores_gemma":[0.15103945,0.000032655997,0.775356,0.0006427851,0.00078930584,0.00012945582,0.000015714057,0.00003667266,0.07195795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989336,0.0000363606,0.0001763289,0.00020251643,0.00034221655,0.00030896958],"domain_scores_gemma":[0.9990917,0.00017731918,0.00006170057,0.0004467174,0.00011579609,0.00010676411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028700163,0.00009942463,0.0000868368,0.00003034285,0.00019574663,0.0003512046,0.0008720509,0.00003291599,0.0000048248207],"category_scores_gemma":[0.000091069945,0.000059693204,0.000050156777,0.000090828136,0.00005162362,0.00016547187,0.00027516388,0.00007726522,0.000045885256],"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":[0.000014620965,0.000049952825,0.00019906263,0.000007491511,0.00008720386,0.000004590504,0.001877763,0.04217795,0.000042130603,0.3334037,0.13607365,0.48606187],"study_design_scores_gemma":[0.00042956852,0.00019439976,0.00021653519,0.0000027463461,0.0000046294153,0.0000033707292,0.000088561486,0.9293089,0.00050651195,0.0020172787,0.06711507,0.000112409354],"about_ca_topic_score_codex":0.000012476652,"about_ca_topic_score_gemma":0.0000033662368,"teacher_disagreement_score":0.887131,"about_ca_system_score_codex":0.00003703281,"about_ca_system_score_gemma":0.00005893835,"threshold_uncertainty_score":0.3386674},"labels":[],"label_agreement":null},{"id":"W1758031947","doi":"10.48550/arxiv.1206.3285","title":"Dyna-Style Planning with Linear Function Approximation and Prioritized Sweeping","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Function (biology); Limit (mathematics); Mathematical optimization; Function approximation; State (computer science); Linear approximation; Linear programming; Artificial intelligence; Algorithm; Mathematics; Nonlinear system; Artificial neural network","score_opus":0.0529436338934253,"score_gpt":0.18302947821939336,"score_spread":0.13008584432596806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1758031947","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":[0.1747361,0.00002108137,0.8230492,0.000017285603,0.00009858234,0.00009571839,1.1821213e-7,0.00014611942,0.0018358023],"genre_scores_gemma":[0.9878357,0.0000070893243,0.011494349,0.000052762105,0.000058492686,2.9964318e-7,0.000003155426,0.000007728426,0.00054042373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992925,0.00004635317,0.00008598977,0.00024703893,0.00007362192,0.0002544982],"domain_scores_gemma":[0.9994273,0.000059922244,0.00010203538,0.00025802237,0.000049924114,0.00010275933],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020257584,0.00010687027,0.00010049133,0.0001114037,0.00018358839,0.000057209585,0.00019896464,0.000052771964,0.0000054609845],"category_scores_gemma":[0.000020288626,0.000109630906,0.000021147667,0.00037528964,0.000042685242,0.0012743379,0.00013013081,0.00013287859,0.000025585794],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043197535,0.00001975267,0.04204223,0.000028223456,0.00003088632,0.000012356719,0.0007536652,0.8852861,0.00012396845,0.07096841,0.000015618145,0.00067558716],"study_design_scores_gemma":[0.0005733097,0.00008765526,0.010100587,0.000033925473,0.000024374182,0.000007861775,0.0001628294,0.9881592,0.000068754634,0.00012107427,0.0004977189,0.00016275108],"about_ca_topic_score_codex":0.000008326833,"about_ca_topic_score_gemma":5.329262e-7,"teacher_disagreement_score":0.8130996,"about_ca_system_score_codex":0.000055728877,"about_ca_system_score_gemma":0.000019318815,"threshold_uncertainty_score":0.44706187},"labels":[],"label_agreement":null},{"id":"W176737593","doi":"","title":"Planning and programming with first-order markov decision processes: insights and challenges","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Markov decision process; Bellman equation; Computer science; Dynamic programming; Mathematical optimization; State space; Representation (politics); Markov process; Automated planning and scheduling; State (computer science); Function (biology); Markov chain; Mathematics; Artificial intelligence; Algorithm; Machine learning","score_opus":0.02615278811115168,"score_gpt":0.2471596119159763,"score_spread":0.22100682380482461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W176737593","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":[0.012356843,0.0035351322,0.9790482,0.00066752883,0.000031609667,0.00018069736,1.3617221e-8,0.00016029755,0.0040197102],"genre_scores_gemma":[0.46739933,0.0035632516,0.52842927,0.00011304474,0.000029215156,0.000018385692,6.074147e-7,0.000013805303,0.0004330891],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999057,0.000011998609,0.00013054226,0.00034243104,0.00024085422,0.00021716223],"domain_scores_gemma":[0.99929094,0.00024665336,0.000058520065,0.00022001466,0.00009796616,0.00008589698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000110317545,0.00013385223,0.00011709504,0.0000914619,0.0001864392,0.0002869838,0.00022315733,0.000046065383,0.000003480227],"category_scores_gemma":[0.00009146481,0.000092170994,0.000005560048,0.00029554314,0.00004889751,0.00059113075,0.00020807044,0.00008839157,0.0000026559987],"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":[0.00012987012,0.0001129802,0.06295986,0.0010617841,0.00008051481,0.0003219718,0.024619095,0.08873014,0.000010845315,0.017375793,0.00020953435,0.8043876],"study_design_scores_gemma":[0.0024810964,0.0018474577,0.026744667,0.0014980908,0.000029020932,0.0006357,0.0021329082,0.71984226,0.00008434456,0.0011141369,0.24244036,0.0011499651],"about_ca_topic_score_codex":0.000005662496,"about_ca_topic_score_gemma":0.000049870545,"teacher_disagreement_score":0.8032377,"about_ca_system_score_codex":0.000009459642,"about_ca_system_score_gemma":0.000037634378,"threshold_uncertainty_score":0.37586242},"labels":[],"label_agreement":null},{"id":"W1787017840","doi":"10.1016/j.jmaa.2015.10.008","title":"Near optimality of quantized policies in stochastic control under weak continuity conditions","year":2015,"lang":"en","type":"preprint","venue":"Journal of Mathematical Analysis and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Discretization; Constructive; Markov process; Mathematical optimization; Optimal control; Stochastic control; Mathematics; Partially observable Markov decision process; Reduction (mathematics); Markov chain; Class (philosophy); Applied mathematics; Computer science; Process (computing); Mathematical analysis","score_opus":0.030012285172124363,"score_gpt":0.32465065521903924,"score_spread":0.2946383700469149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1787017840","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":[0.022262275,0.00010697748,0.97604173,0.00084306876,0.000014208463,0.00029562484,0.000016783812,0.000012072649,0.0004072546],"genre_scores_gemma":[0.9641783,0.000020316907,0.035635754,0.000037357866,0.000032780095,0.000030464895,0.0000064304318,0.000006093429,0.00005245218],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976266,0.00014093821,0.0013499779,0.00021123963,0.0005005657,0.00017067],"domain_scores_gemma":[0.9965993,0.0006146907,0.0014681688,0.0005564726,0.00059967436,0.00016168103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014021862,0.0001776585,0.0010838419,0.0004156328,0.000068029134,0.00019024301,0.00071090495,0.00013609056,0.000024440666],"category_scores_gemma":[0.00023493032,0.0001418709,0.00035962378,0.00070040557,0.00023628543,0.000119690536,0.00032513568,0.00048452633,0.000004705917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050369963,0.00016049414,0.00045639393,0.00006039628,0.0005728402,5.153399e-7,0.0002276215,0.82870394,0.000033278673,0.16968787,0.000038005048,0.000053611504],"study_design_scores_gemma":[0.0005693681,0.000043371605,0.0062647383,0.00010430381,0.001140812,0.000009769485,0.0001539728,0.86803263,0.000008679668,0.12349234,0.000032888245,0.0001471325],"about_ca_topic_score_codex":0.000028815746,"about_ca_topic_score_gemma":0.000007897571,"teacher_disagreement_score":0.94191605,"about_ca_system_score_codex":0.00006266202,"about_ca_system_score_gemma":0.00021657394,"threshold_uncertainty_score":0.5785327},"labels":[],"label_agreement":null},{"id":"W1799762961","doi":"10.1613/jair.904","title":"Accelerating Reinforcement Learning by Composing Solutions of Automatically Identified Subtasks","year":2002,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"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; Government of Ontario","keywords":"Reinforcement learning; Exploit; Partition (number theory); Function (biology); Base (topology); State space; Reinforcement; Function approximation","score_opus":0.2748869913500262,"score_gpt":0.396747064427609,"score_spread":0.12186007307758279,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1799762961","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":[0.010750928,0.00022188597,0.98530376,0.0010879447,0.0003047289,0.00018035188,2.653346e-7,0.00003623838,0.0021139227],"genre_scores_gemma":[0.9750773,0.00014242255,0.02402497,0.000021920625,0.00011555934,0.0000027616304,9.130298e-7,0.000014361459,0.00059983577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99458545,0.0005479954,0.0017414482,0.00023876896,0.002137171,0.00074917276],"domain_scores_gemma":[0.9959714,0.0010673987,0.00076004304,0.0004041972,0.0015740006,0.00022296912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005513628,0.00015821347,0.0003574942,0.0006347562,0.00064905774,0.0006008826,0.0015324506,0.00010353777,0.00028639458],"category_scores_gemma":[0.0019822696,0.0001477241,0.00016959048,0.0012061176,0.0003029009,0.0009707657,0.00048619506,0.0013404291,0.00011760809],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018447217,0.00015224972,0.00008921423,0.000054812223,0.000065592256,0.000026360376,0.0028752813,0.840547,0.073575184,0.035861198,0.0018617394,0.04487291],"study_design_scores_gemma":[0.000047974256,0.0006240203,0.000015838537,0.00018827942,0.000008033384,0.000038728158,0.0006874988,0.94608265,0.050352473,0.0014668049,0.00035904907,0.0001286611],"about_ca_topic_score_codex":0.00003391218,"about_ca_topic_score_gemma":0.0000018600249,"teacher_disagreement_score":0.9643263,"about_ca_system_score_codex":0.00020241906,"about_ca_system_score_gemma":0.00013934674,"threshold_uncertainty_score":0.6024014},"labels":[],"label_agreement":null},{"id":"W1801772197","doi":"10.1007/978-3-540-72665-4_5","title":"R-FRTDP: A Real-Time DP Algorithm with Tight Bounds for a Stochastic Resource Allocation Problem","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Computer science; Markov decision process; Mathematical optimization; Resource allocation; Heuristic; Context (archaeology); Task (project management); Stochastic programming; Dynamic programming; Resource (disambiguation); Markov process; Algorithm; Artificial intelligence; Mathematics","score_opus":0.014734208176855099,"score_gpt":0.24645569856153343,"score_spread":0.23172149038467832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1801772197","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":[0.0000035760816,0.000070338756,0.9913605,0.0004954741,0.00042545193,0.001443167,0.0000043179225,0.0003501799,0.005846979],"genre_scores_gemma":[0.0012874765,0.000008406224,0.99320704,0.00070039014,0.00049428275,0.000045914905,0.000034304416,0.00008347569,0.0041387235],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945735,0.000035421475,0.0007516339,0.0018727615,0.001650336,0.0011163563],"domain_scores_gemma":[0.99593216,0.00092198513,0.0006317957,0.0016937768,0.00055993855,0.0002603132],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016759349,0.00074275304,0.00065379526,0.0011145092,0.0004790421,0.0009219185,0.0034234675,0.0004239415,0.00001387208],"category_scores_gemma":[0.00008885818,0.0006446521,0.00013684804,0.00091408606,0.0008008597,0.00063835137,0.00085209863,0.00081471435,0.000052281754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017509456,0.000018185723,0.0000019442903,0.000051097857,0.00002245341,0.000025623845,0.00069963984,0.74312484,0.000049675848,0.008424956,0.00006233403,0.2475017],"study_design_scores_gemma":[0.00054315146,0.00084312784,0.000011296001,0.0006402226,0.00002423996,0.00009676333,2.4903375e-7,0.9802047,0.00015541786,0.0125276735,0.00413013,0.00082302873],"about_ca_topic_score_codex":0.000022935019,"about_ca_topic_score_gemma":0.000022321045,"teacher_disagreement_score":0.24667868,"about_ca_system_score_codex":0.0006210286,"about_ca_system_score_gemma":0.000931589,"threshold_uncertainty_score":0.99960047},"labels":[],"label_agreement":null},{"id":"W180335381","doi":"","title":"Modeling Students' Emotions to Improve Learning with Educational Games","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Function (biology); State (computer science); Personality; Human–computer interaction; Psychology; Cognitive psychology; Artificial intelligence; Cognitive science; Social psychology","score_opus":0.014679573392387055,"score_gpt":0.2826964279880916,"score_spread":0.2680168545957045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W180335381","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":[0.062513486,0.000004080332,0.92641646,0.002079366,0.00014922691,0.00014093592,5.0367667e-8,0.00015652664,0.00853986],"genre_scores_gemma":[0.844159,0.000004488709,0.13029297,0.00040224212,0.00007198997,0.000016799782,0.0000018961692,0.000009083402,0.025041537],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881524,0.000025259149,0.00016108836,0.0002926499,0.00045086787,0.000254893],"domain_scores_gemma":[0.9993458,0.000046798534,0.000034515844,0.00032194145,0.00013298466,0.0001180068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001643495,0.000105798514,0.00008484823,0.0001180721,0.00019161955,0.00032009327,0.0006907899,0.000024314602,0.000093795636],"category_scores_gemma":[0.000062523,0.00008823139,0.000024941513,0.000372382,0.000011386247,0.0003893675,0.00024373074,0.00015887561,0.00024847875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019471781,0.000024519628,0.008370256,0.0000017263726,0.000011608744,0.0000011533411,0.0004766745,0.9793319,0.00005911432,0.010246251,0.000079171405,0.0013956802],"study_design_scores_gemma":[0.00015924184,0.0001475431,0.0023785823,0.000016455886,0.0000037570346,0.000011283382,0.00013172247,0.99581075,0.00001898245,0.00012800789,0.0010497182,0.0001439822],"about_ca_topic_score_codex":0.000043938926,"about_ca_topic_score_gemma":0.000007786723,"teacher_disagreement_score":0.7961235,"about_ca_system_score_codex":0.00005636412,"about_ca_system_score_gemma":0.00008537875,"threshold_uncertainty_score":0.35979718},"labels":[],"label_agreement":null},{"id":"W18175453","doi":"10.1525/tph.2007.29.3.87","title":"Algorithm-Directed Exploration for Model-Based Reinforcement Learning in Factored MDPs","year":2002,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":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; Oracle; Computer science; Planner; Mathematical optimization; Linear programming; Artificial intelligence; Machine learning; Algorithm; Mathematics","score_opus":0.08004596865886063,"score_gpt":0.30279357989068106,"score_spread":0.22274761123182044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W18175453","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":[0.00057143345,0.000014727539,0.987839,0.002149628,0.00035961941,0.00036370195,0.000002186419,0.00052545033,0.008174283],"genre_scores_gemma":[0.9196168,0.000042376407,0.07337959,0.00031144742,0.00007037633,0.00011604885,0.000169501,0.000030056608,0.0062638135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976214,0.00014916097,0.0005450438,0.00055479276,0.00071786327,0.00041171358],"domain_scores_gemma":[0.99870545,0.0002293574,0.00034783393,0.00028010056,0.0003419766,0.000095302836],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000438578,0.00029395375,0.00024929846,0.0005202671,0.00021891529,0.0003912879,0.000911106,0.0001116512,0.0002661272],"category_scores_gemma":[0.00054680335,0.0003073795,0.00010631567,0.0002961423,0.000034319975,0.0008108103,0.00013799655,0.00076965353,0.00009174106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023887576,0.000040291096,0.00070953934,0.0000086507,0.00001967703,0.000004901631,0.0006396675,0.94885665,0.00029066316,0.015777815,0.000049801616,0.03357848],"study_design_scores_gemma":[0.0012978452,0.0003495623,0.000111078654,0.000091775226,0.0000043547525,0.0000013693992,0.000040475945,0.9944002,0.00031586937,0.0007590117,0.0023073454,0.00032110055],"about_ca_topic_score_codex":0.00004275498,"about_ca_topic_score_gemma":0.00000992181,"teacher_disagreement_score":0.9190453,"about_ca_system_score_codex":0.00025770417,"about_ca_system_score_gemma":0.000068969945,"threshold_uncertainty_score":0.99993783},"labels":[],"label_agreement":null},{"id":"W1821963137","doi":"","title":"State similarity based approach for improving performance in RL","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Similarity (geometry); Computer science; Context (archaeology); State (computer science); Artificial intelligence; Function (biology); Tree (set theory); Bellman equation; Action (physics); Machine learning; Data mining; Mathematical optimization; Algorithm; Mathematics","score_opus":0.022259558712616864,"score_gpt":0.24901772870665248,"score_spread":0.2267581699940356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1821963137","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":[0.008100802,0.0000040045306,0.98286945,0.000057907244,0.000095755066,0.00030284197,2.2371154e-7,0.00012550264,0.008443494],"genre_scores_gemma":[0.57652676,4.0964835e-7,0.4226845,0.0002367427,0.000011448449,0.000006942369,0.0000022313477,0.000004902256,0.0005260748],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884653,0.0000139445065,0.00025453832,0.00026683437,0.00020419294,0.0004139808],"domain_scores_gemma":[0.9993373,0.00012195819,0.00007116977,0.0003554607,0.00005579358,0.000058284717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012863243,0.000102349426,0.00010477898,0.00013398257,0.00007719007,0.0000896705,0.00054481,0.000043350683,0.000003945939],"category_scores_gemma":[0.000059253714,0.000093839866,0.00003408222,0.00029081517,0.000020767187,0.0003948712,0.00011410778,0.00014578724,0.00000483186],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011888977,0.000027184593,0.01243303,0.00007531301,0.0000017336744,0.0000011660168,0.00013104119,0.9685346,0.00013887385,0.0017173442,0.000026829342,0.016901009],"study_design_scores_gemma":[0.00044330422,0.00008963722,0.009075493,0.0000040761884,9.688823e-7,6.076764e-7,0.000011546051,0.9866547,0.0031079447,0.000024723528,0.00045682956,0.00013016093],"about_ca_topic_score_codex":0.000019512461,"about_ca_topic_score_gemma":0.000008149606,"teacher_disagreement_score":0.56842595,"about_ca_system_score_codex":0.000073057934,"about_ca_system_score_gemma":0.000064260625,"threshold_uncertainty_score":0.38266787},"labels":[],"label_agreement":null},{"id":"W183139520","doi":"","title":"Stochastic local search for POMDP controllers","year":2004,"lang":"en","type":"article","venue":"TSpace","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":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":"Partially observable Markov decision process; Heuristics; Computer science; Markov decision process; Mathematical optimization; Dynamic programming; Observable; Controller (irrigation); State (computer science); Markov process; Markov chain; Mathematics; Algorithm; Machine learning; Markov model","score_opus":0.02851222499342767,"score_gpt":0.32275675840771967,"score_spread":0.294244533414292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W183139520","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":[0.0011592722,0.000031833453,0.99311155,0.0032193,0.0002346172,0.0003364542,2.5896202e-7,0.00015754034,0.0017491704],"genre_scores_gemma":[0.9501579,0.0000011993837,0.047034856,0.00028962715,0.000057750036,0.000019419967,0.0000014656907,0.000011989125,0.0024258362],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989797,0.000018513609,0.00012235553,0.00023455406,0.0002753301,0.00036957086],"domain_scores_gemma":[0.99925923,0.000143229,0.000040922478,0.00037102055,0.000082911836,0.00010270106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023476771,0.000104721046,0.00013306024,0.00006911819,0.00011988693,0.000101206795,0.0005549854,0.00004732991,0.00001193317],"category_scores_gemma":[0.00005680722,0.00009897384,0.00006198263,0.0001763692,0.00006620698,0.00013629234,0.0001198205,0.0001258261,0.00014826684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011848377,0.000009280388,0.000005415369,0.000007093986,0.000011586288,0.000002647425,0.0011327047,0.93807673,0.00013966959,0.05930942,0.00015750644,0.0011361211],"study_design_scores_gemma":[0.0021783519,0.00030180562,0.000072581664,0.000021866586,0.0000066102352,0.000007979172,0.00032747266,0.99417657,0.00089289306,0.0007444065,0.001094403,0.00017507488],"about_ca_topic_score_codex":0.00004704953,"about_ca_topic_score_gemma":0.0000023611317,"teacher_disagreement_score":0.9489986,"about_ca_system_score_codex":0.00011880548,"about_ca_system_score_gemma":0.00014479268,"threshold_uncertainty_score":0.40360358},"labels":[],"label_agreement":null},{"id":"W185706336","doi":"","title":"Labeled Initialized Adaptive Play Q-learning for Stochastic Games","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Q-learning; Computer science; Context (archaeology); Process (computing); Artificial intelligence; Optimal stopping; Point (geometry); Mathematical optimization; Adaptive learning; Grid; Quality (philosophy); Mathematics; Reinforcement learning","score_opus":0.027898508620810496,"score_gpt":0.2864012359353325,"score_spread":0.258502727314522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W185706336","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":[0.0010456316,0.000018708784,0.98817,0.00010957477,0.00033508777,0.00036216303,2.282827e-7,0.00040109298,0.009557491],"genre_scores_gemma":[0.78347,0.0000011965575,0.21147934,0.00031152435,0.00008727526,0.000017709235,0.0000038247563,0.00001603706,0.004613122],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985598,0.00004010242,0.00030369408,0.00031296586,0.0002978473,0.0004855975],"domain_scores_gemma":[0.9984031,0.00090668764,0.00013995604,0.00028106375,0.00015865106,0.00011058412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076110987,0.00015639726,0.00018692325,0.00014927465,0.00018768127,0.00013197483,0.0005601041,0.00007490853,0.00005078949],"category_scores_gemma":[0.00042930522,0.00014229333,0.00007486472,0.00028455185,0.00004237862,0.0003191088,0.00017258717,0.00019990941,0.00008159103],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006617391,0.000020495809,0.000091799884,0.00000922733,0.000046246412,0.00000772877,0.0011391159,0.8157823,0.000495235,0.174312,0.00049384113,0.0075358544],"study_design_scores_gemma":[0.0011833373,0.00046815953,0.00027707368,0.000022715598,0.000010856877,0.000008691815,0.00017111044,0.9922735,0.0011969967,0.00070627045,0.0034195448,0.00026172146],"about_ca_topic_score_codex":0.000010488462,"about_ca_topic_score_gemma":0.0000048899096,"teacher_disagreement_score":0.78242433,"about_ca_system_score_codex":0.00005476308,"about_ca_system_score_gemma":0.000060465896,"threshold_uncertainty_score":0.5802553},"labels":[],"label_agreement":null},{"id":"W1862757251","doi":"10.1007/978-3-642-27645-3_11","title":"Bayesian Reinforcement Learning","year":2012,"lang":"en","type":"book-chapter","venue":"Adaptation, learning, and optimization","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Bayesian probability; Artificial intelligence; Computer science; Machine learning; Posterior probability; Prior probability; Domain (mathematical analysis); Bayesian inference; Function (biology); Bellman equation; Mathematics; Mathematical optimization","score_opus":0.015541756629481101,"score_gpt":0.22207336376070658,"score_spread":0.20653160713122548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1862757251","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.0115194e-7,0.0007295642,0.77318436,0.00009499544,0.0002676383,0.00026768877,2.0299103e-7,0.00034267138,0.22511259],"genre_scores_gemma":[0.012701577,0.005031708,0.13511075,0.00014470286,0.00033005013,0.000019308147,0.0004014485,0.00012281859,0.84613764],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997571,0.00009182664,0.00064750906,0.00059343094,0.00065457204,0.00044165069],"domain_scores_gemma":[0.99803376,0.0001454081,0.00090957544,0.0003573959,0.00034052992,0.00021334697],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047452428,0.00048458547,0.00037768998,0.0003638072,0.00062528555,0.0003835787,0.00037150912,0.0003965187,0.0008058111],"category_scores_gemma":[0.00017029938,0.00053424103,0.00010538781,0.000115874995,0.000087596425,0.0009160081,0.00024033875,0.00085799146,0.00013251245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004958766,0.0000038261996,0.00009262943,0.000038922055,0.000053145264,0.0000024321337,0.001634021,0.9017928,8.623766e-7,0.08558561,0.00021924026,0.010571518],"study_design_scores_gemma":[0.00026345276,0.00016910442,0.00001182984,0.00009166006,0.000055499575,0.000010102388,0.000052292045,0.77657145,0.0000023128675,0.0002543843,0.22206622,0.0004517145],"about_ca_topic_score_codex":0.000013345013,"about_ca_topic_score_gemma":0.0000025213612,"teacher_disagreement_score":0.6380736,"about_ca_system_score_codex":0.00012558339,"about_ca_system_score_gemma":0.00012211197,"threshold_uncertainty_score":0.9997109},"labels":[],"label_agreement":null},{"id":"W1870822514","doi":"","title":"A Deeper Look at Planning as Learning from Replay","year":2015,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Markov decision process; Function (biology); Temporal difference learning; Markov chain; Equivalence (formal languages); Artificial intelligence; Markov process; Machine learning; Mathematical optimization; Mathematics","score_opus":0.07534542055669481,"score_gpt":0.32282196044179445,"score_spread":0.24747653988509966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1870822514","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":[0.085250124,0.00010536725,0.71848,0.0023775126,0.0013323702,0.00015749675,0.0000020100417,0.00070919713,0.19158591],"genre_scores_gemma":[0.96582514,0.000018343011,0.009287778,0.00067788095,0.00022936612,0.000014469501,0.00012833592,0.0000344765,0.023784235],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969473,0.0002907915,0.00043635795,0.00072363636,0.001187111,0.00041481585],"domain_scores_gemma":[0.9982561,0.00031494442,0.00038280064,0.00043335106,0.00035027793,0.000262551],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00061218033,0.0003173217,0.00026410123,0.0002656038,0.0002931421,0.00057634694,0.0014803634,0.00012629616,0.0008789888],"category_scores_gemma":[0.0014174223,0.00031214432,0.000097391036,0.00019141447,0.000060399667,0.000606096,0.00087858655,0.0012340683,0.0022255785],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008889432,0.000021960512,0.054060034,0.0000023733392,0.000075939504,0.00011787117,0.0025145896,0.89241874,0.000575754,0.047108695,0.00032438236,0.0026907728],"study_design_scores_gemma":[0.00084878283,0.00037126968,0.0013105155,0.00011994465,0.000008131918,0.000040813404,0.00025496454,0.9564802,0.00037145996,0.0024312336,0.037385754,0.00037694414],"about_ca_topic_score_codex":0.00035314524,"about_ca_topic_score_gemma":0.000010044379,"teacher_disagreement_score":0.880575,"about_ca_system_score_codex":0.0003370574,"about_ca_system_score_gemma":0.0001619256,"threshold_uncertainty_score":0.99993306},"labels":[],"label_agreement":null},{"id":"W187740018","doi":"10.1007/978-1-4757-3561-1_5","title":"On Optimal Policies of Multichain Finite State Compact Action Markov Decision Processes","year":2002,"lang":"en","type":"book-chapter","venue":"Advances in computational management science","topic":"Reinforcement Learning in Robotics","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":"Group for Research in Decision Analysis; HEC Montréal","funders":"","keywords":"Markov decision process; Markov process; Action (physics); Set (abstract data type); Mathematical optimization; Markov chain; State (computer science); Finite set; Markov model; Computer science; Mathematics; Mathematical economics; Applied mathematics; Algorithm","score_opus":0.02400273753884332,"score_gpt":0.30644236955273346,"score_spread":0.28243963201389016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W187740018","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":[0.00011217071,0.00020284083,0.87341154,0.00011525498,0.00045384155,0.00045385596,0.000007292273,0.00007930381,0.12516388],"genre_scores_gemma":[0.4230037,0.0040201056,0.49410933,0.0006000182,0.00007725186,0.000027351556,0.00003906348,0.00007536538,0.07804781],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958037,0.000024024965,0.00075845374,0.00085744757,0.002127324,0.00042904704],"domain_scores_gemma":[0.99692166,0.0013470586,0.00076177303,0.0005524806,0.00032457898,0.00009246554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006396351,0.00038082406,0.00036690573,0.0014429722,0.00022101613,0.000212979,0.0018725885,0.00006139148,0.000038002567],"category_scores_gemma":[0.00023539238,0.00037764263,0.000070872295,0.0008191494,0.00057025184,0.0016230321,0.0005085522,0.0002972574,0.000070773436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001857348,0.000031484644,0.000027527545,0.00015302554,0.000010385667,0.000023070632,0.00013011783,0.77191776,4.277587e-7,0.19974889,0.00005929158,0.027879411],"study_design_scores_gemma":[0.00043410496,0.00022584801,0.00051601074,0.0009022484,0.000008826568,0.000005453226,0.00001563082,0.9126065,0.000016697599,0.078496404,0.0063655153,0.00040676224],"about_ca_topic_score_codex":0.0000041336452,"about_ca_topic_score_gemma":0.000004493701,"teacher_disagreement_score":0.42289153,"about_ca_system_score_codex":0.0003050675,"about_ca_system_score_gemma":0.00010619408,"threshold_uncertainty_score":0.99986756},"labels":[],"label_agreement":null},{"id":"W1888020014","doi":"10.1109/icsmc.1999.825317","title":"An approach to design autonomous agents within ModSAF","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada","funders":"","keywords":"Exploit; Robustness (evolution); Computer science; Human–computer interaction; Autonomous agent; Artificial intelligence; Distributed computing; Computer security","score_opus":0.05927460155812025,"score_gpt":0.27625970169207037,"score_spread":0.21698510013395012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888020014","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":[0.00047068886,0.0000023089226,0.916488,0.00004704797,0.00021213075,0.00025930748,5.1289796e-8,0.00029741667,0.08222308],"genre_scores_gemma":[0.3512056,2.3264546e-7,0.6443342,0.0007626937,0.000009565565,0.000012114713,6.146776e-7,0.000008670217,0.003666344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986341,0.0001582164,0.0002130708,0.00039621553,0.00028880936,0.00030956304],"domain_scores_gemma":[0.99885726,0.000028897113,0.000054566794,0.00079992285,0.00004500493,0.00021434906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058452965,0.00013689739,0.00011664473,0.00009678907,0.0001087199,0.00026380984,0.0009647106,0.000050734532,0.000031534317],"category_scores_gemma":[0.00006210953,0.00012161031,0.000027102888,0.00034989679,0.000015211801,0.0004362037,0.00008412693,0.00010614184,0.00027361742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.813051e-7,0.00003795767,0.000089119414,0.0000019416393,0.0000054085053,0.0000017309688,0.0007552256,0.86106074,0.000089013236,0.13686383,0.0006954566,0.00039866878],"study_design_scores_gemma":[0.00013380164,0.00013936107,0.00020453997,0.0000021299672,0.0000022280533,0.000009245872,0.000038779886,0.9956195,0.0017993738,0.00043081996,0.0014348848,0.00018533746],"about_ca_topic_score_codex":0.000010006544,"about_ca_topic_score_gemma":1.787745e-7,"teacher_disagreement_score":0.3507349,"about_ca_system_score_codex":0.00005926666,"about_ca_system_score_gemma":0.00008914695,"threshold_uncertainty_score":0.49591246},"labels":[],"label_agreement":null},{"id":"W189498254","doi":"10.1609/icaps.v19i1.13365","title":"Minimal Sufficient Explanations for Factored Markov Decision Processes","year":2009,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Task (project management); Markov decision process; Computer science; Set (abstract data type); Template; Domain (mathematical analysis); Probabilistic logic; Selection (genetic algorithm); Markov chain; Markov process; Markov model; Machine learning; Artificial intelligence; Programming language; Mathematics; Engineering","score_opus":0.04320861166281764,"score_gpt":0.3100428253267046,"score_spread":0.26683421366388693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W189498254","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":[0.7493236,0.000041986874,0.24178335,0.0032483053,0.00043424827,0.00031998742,0.0000087637945,0.00043319617,0.004406555],"genre_scores_gemma":[0.93278325,0.000008455696,0.06692025,0.00015118656,0.000026570313,0.000008744174,0.0000042238917,0.0000048789057,0.00009244245],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988248,0.0000035266596,0.00029318524,0.00026442655,0.00044254906,0.00017156152],"domain_scores_gemma":[0.9987393,0.00018285237,0.0002859181,0.000082641986,0.00066288665,0.000046404028],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027014484,0.00013263848,0.00013237099,0.00016337946,0.00018591323,0.0003646491,0.00091202295,0.00005949617,0.0000036588513],"category_scores_gemma":[0.00085834524,0.00010035459,0.000041211453,0.00020678603,0.0000314317,0.00032409202,0.00010561718,0.00013283847,0.0000011824488],"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":[0.0004954312,0.0003118708,0.015566513,0.00027585437,0.00019120585,0.0000030055614,0.0087752845,0.40425557,0.051232502,0.5023435,0.0029345024,0.013614763],"study_design_scores_gemma":[0.00031665733,0.0001661594,0.0049752574,0.00052871235,0.0000070689994,0.000007949621,0.00031733446,0.98549926,0.0067497054,0.0011846181,0.00012270539,0.00012459034],"about_ca_topic_score_codex":0.0000013466326,"about_ca_topic_score_gemma":1.0495749e-7,"teacher_disagreement_score":0.58124363,"about_ca_system_score_codex":0.000033243294,"about_ca_system_score_gemma":0.00007849734,"threshold_uncertainty_score":0.40923414},"labels":[],"label_agreement":null},{"id":"W189510620","doi":"10.5555/1838206.1838300","title":"Optimal policy switching algorithms for reinforcement learning","year":2010,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Function approximation; Term (time); Function (biology); Artificial intelligence; Mathematical optimization; Q-learning; Machine learning; Algorithm; Mathematics; Artificial neural network; Engineering","score_opus":0.05548713756434804,"score_gpt":0.3163627497273219,"score_spread":0.2608756121629739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W189510620","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":[0.013757881,0.00008064912,0.98219275,0.00011634703,0.0016838941,0.0011918395,0.0000027518963,0.0001990298,0.0007748594],"genre_scores_gemma":[0.91898805,0.00006690561,0.075395055,0.00017970368,0.00037848618,0.00013834532,0.0000158374,0.000043164524,0.0047944486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973838,0.000094315365,0.0005935272,0.0006824409,0.00050600007,0.0007399363],"domain_scores_gemma":[0.99838734,0.00014134031,0.00041046325,0.00053597783,0.00021848109,0.00030638085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072665,0.00037481345,0.0003739524,0.00026392174,0.00065535295,0.00064293534,0.00076277903,0.00016346038,0.000008847484],"category_scores_gemma":[0.00020196152,0.00034143234,0.00012512278,0.00025157747,0.00005588511,0.00081182533,0.0005037243,0.00048936723,0.00004698865],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021244261,0.000070264236,0.0013390088,0.00009151302,0.00022526308,0.000018112321,0.0033704054,0.96173525,0.002095703,0.017861316,0.00046847452,0.012703452],"study_design_scores_gemma":[0.001594601,0.00029063065,0.0011245162,0.00008843073,0.000020960106,0.000023605333,0.0003784449,0.9735807,0.00015025215,0.000009275698,0.02235008,0.00038845857],"about_ca_topic_score_codex":0.0005621783,"about_ca_topic_score_gemma":0.0000059151853,"teacher_disagreement_score":0.9067977,"about_ca_system_score_codex":0.00009004336,"about_ca_system_score_gemma":0.000104732666,"threshold_uncertainty_score":0.9999038},"labels":[],"label_agreement":null},{"id":"W1895872655","doi":"10.1002/9780470400531.eorms0714","title":"Reinforcement Learning Algorithms for<scp>MDPs</scp>","year":2011,"lang":"en","type":"other","venue":"Wiley Encyclopedia of Operations Research and Management Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Learning classifier system; Machine learning; Focus (optics); Engineering","score_opus":0.04620281988043152,"score_gpt":0.32626495270884837,"score_spread":0.28006213282841685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1895872655","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005558186,0.00025781724,0.49709344,0.000040174353,0.00027812837,0.0011987782,0.000002380077,0.00010705033,0.5010167],"genre_scores_gemma":[0.00042041618,0.02011356,0.15098411,0.000037565012,0.00013448727,0.00040837284,0.000029144105,0.00009830519,0.82777405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99555314,0.0000950814,0.0005052484,0.0010412703,0.0017584411,0.0010468432],"domain_scores_gemma":[0.99781007,0.00017764821,0.00016189308,0.0010945612,0.0004447536,0.000311059],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0025403285,0.0003235987,0.00033988702,0.0020157148,0.00087936706,0.0005279546,0.0026480688,0.00013577958,0.00009932122],"category_scores_gemma":[0.0005934448,0.0003042056,0.000066081,0.0017434745,0.0011185805,0.0007664787,0.0019806044,0.00045334612,0.00010471557],"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":[0.0000046812015,0.00017051128,0.00016355862,0.0009077063,0.00018665165,0.000022126136,0.002217821,0.1042396,0.00007519977,0.43207794,0.42258784,0.037346344],"study_design_scores_gemma":[0.0003986011,0.0005881379,0.00007473315,0.0003381694,0.000016941716,0.0000023496564,0.00024077439,0.20377481,0.00009271094,0.00027467514,0.7940202,0.00017794083],"about_ca_topic_score_codex":0.00023349871,"about_ca_topic_score_gemma":0.000036715177,"teacher_disagreement_score":0.4318033,"about_ca_system_score_codex":0.0000993702,"about_ca_system_score_gemma":0.0002993525,"threshold_uncertainty_score":0.999941},"labels":[],"label_agreement":null},{"id":"W1898595911","doi":"10.1109/roman.1995.531970","title":"Elements of artificial emotion","year":2002,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cisco Systems (Canada)","funders":"","keywords":"Implementation; Situated; Curiosity; Computer science; Affection; Anger; Action selection; Embodied cognition; Artificial intelligence; Action (physics); Human–computer interaction; Robot; Autonomous agent; Cognitive science; Cognitive psychology; Psychology; Social psychology; Software engineering","score_opus":0.037571531359785026,"score_gpt":0.24743231552303907,"score_spread":0.20986078416325404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1898595911","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":[0.005321454,0.000003744022,0.96591544,0.00017612324,0.00015705588,0.000043694974,5.3032945e-8,0.000060670438,0.028321762],"genre_scores_gemma":[0.9193429,0.000003501838,0.07713928,0.000087891865,0.000021628588,7.7739685e-7,4.1649392e-7,0.0000022901927,0.0034013442],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999416,0.000014401338,0.0001826909,0.00009335775,0.00019105837,0.00010251536],"domain_scores_gemma":[0.99963695,0.000014223604,0.00006610804,0.00022832368,0.000032841926,0.000021570773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000092133065,0.000039175146,0.00005113893,0.00004716326,0.000026429654,0.000027050053,0.0002755173,0.000017533428,0.0004245789],"category_scores_gemma":[0.000022050368,0.000035625086,0.000022440647,0.000152061,0.000012199442,0.0001748378,0.00007254169,0.000034072305,0.00024906913],"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":[0.0000021559317,0.00016486863,0.0058270423,0.00002789509,0.000035205878,0.000004600128,0.0013535097,0.26308513,0.006220728,0.4786951,0.01056377,0.23402002],"study_design_scores_gemma":[0.00006425109,0.00005682531,0.0005624906,0.0000032744715,0.0000011397502,6.9539425e-7,0.000008424521,0.99432313,0.003430141,0.00027638703,0.0012290014,0.00004424454],"about_ca_topic_score_codex":0.0000029995242,"about_ca_topic_score_gemma":3.086052e-7,"teacher_disagreement_score":0.91402143,"about_ca_system_score_codex":0.000009774784,"about_ca_system_score_gemma":0.0000028226075,"threshold_uncertainty_score":0.46488413},"labels":[],"label_agreement":null},{"id":"W190427941","doi":"10.20965/jaciii.2006.p0578","title":"Opposition-Based Reinforcement Learning","year":2006,"lang":"en","type":"article","venue":"Journal of Advanced Computational Intelligence and Intelligent Informatics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":207,"is_retracted":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; Expediting; Artificial intelligence; A priori and a posteriori; Probabilistic logic; Grid; Machine learning; Opposition (politics); Convergence (economics); Learning classifier system; Engineering; Mathematics","score_opus":0.01614136464924268,"score_gpt":0.26280084582795943,"score_spread":0.24665948117871675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W190427941","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":[0.0024846909,0.00017757669,0.9947917,0.00025838212,0.00032039193,0.00014571231,3.9512446e-7,0.00005071062,0.0017704597],"genre_scores_gemma":[0.712014,0.00011982701,0.28721824,0.00041581294,0.00006795237,0.0000027845063,0.000013280199,0.000009202067,0.00013887408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970205,0.000047145688,0.001684827,0.000117314754,0.0008316338,0.00029856942],"domain_scores_gemma":[0.99711835,0.00046537127,0.0012379842,0.00018222506,0.0008631263,0.00013296532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005498489,0.00023067136,0.00029372185,0.00042712467,0.00021184867,0.00029993564,0.0006300904,0.000070622125,0.00002680802],"category_scores_gemma":[0.00012181149,0.00020716421,0.00014109157,0.00040918036,0.000096273325,0.0015081535,0.00012316562,0.00042983223,0.000036956677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016651898,0.00003243827,0.00013714044,0.000041809253,0.000023452068,0.000006417903,0.00041124434,0.9284414,0.000024723082,0.052180752,0.00011285951,0.018571123],"study_design_scores_gemma":[0.00019010741,0.00068210665,0.0000877072,0.00014781565,0.000013897794,0.000097868775,0.00042339097,0.9779323,0.0037634054,0.01207858,0.004354897,0.00022796389],"about_ca_topic_score_codex":0.000003933322,"about_ca_topic_score_gemma":3.057756e-7,"teacher_disagreement_score":0.70952934,"about_ca_system_score_codex":0.00013336392,"about_ca_system_score_gemma":0.00018933747,"threshold_uncertainty_score":0.8447911},"labels":[],"label_agreement":null},{"id":"W1904406446","doi":"","title":"Using predictive representations to improve generalization in reinforcement learning","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":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":"Generalization; Reinforcement learning; Computer science; Representation (politics); Artificial intelligence; Task (project management); State (computer science); Machine learning; Grid; Reinforcement; Algorithm; Mathematics; Psychology; Social psychology; Engineering","score_opus":0.029941249022495058,"score_gpt":0.30813073930994245,"score_spread":0.2781894902874474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904406446","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":[0.0055598486,0.0000048772326,0.9814273,0.00052191236,0.00014566933,0.0003224565,7.7013844e-8,0.00015182006,0.011866013],"genre_scores_gemma":[0.76422715,0.000004438094,0.2308096,0.00047738958,0.00008318221,0.000019966852,0.000004481071,0.000008932482,0.0043648626],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871373,0.000058010337,0.00033525095,0.0003161243,0.00030463198,0.00027227873],"domain_scores_gemma":[0.99936324,0.000038147748,0.00009188029,0.00033456032,0.00008932288,0.000082827086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019906796,0.00010629407,0.00009891468,0.0002514132,0.000115368435,0.000139075,0.00034351676,0.000040899486,0.000047223224],"category_scores_gemma":[0.000133338,0.000109874316,0.000023381606,0.0005991648,0.00001154711,0.0007816578,0.00027069874,0.00013508124,0.00006570664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027076874,0.0000074193763,0.0016642504,0.0000023024556,0.0000053477356,9.976446e-7,0.0011459423,0.9805189,0.0037545054,0.011215358,0.00010031627,0.0015819739],"study_design_scores_gemma":[0.00023718775,0.000100149,0.0010827364,0.000012571116,0.0000026929374,0.0000016111305,0.00006939652,0.99365383,0.0032537794,0.000035601268,0.0014239461,0.00012647592],"about_ca_topic_score_codex":0.00012880319,"about_ca_topic_score_gemma":0.000017751892,"teacher_disagreement_score":0.7586673,"about_ca_system_score_codex":0.0002444497,"about_ca_system_score_gemma":0.00005630468,"threshold_uncertainty_score":0.44805446},"labels":[],"label_agreement":null},{"id":"W19532835","doi":"10.1609/aiide.v4i1.18667","title":"Agent Learning Using Action-Dependent Learning Rates in Computer Role-Playing Games","year":2008,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Action (physics); Computer science; Reinforcement learning; Scripting language; Artificial intelligence; Error-driven learning; Learning effect; Human–computer interaction","score_opus":0.07247847678986213,"score_gpt":0.30101875507031534,"score_spread":0.2285402782804532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W19532835","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":[0.7933535,0.00001531512,0.20318197,0.00022551221,0.00027802336,0.00031188485,7.751946e-7,0.000052727904,0.0025802713],"genre_scores_gemma":[0.9985801,0.00009069919,0.00088190695,0.000084197214,0.000046487916,0.000015235329,0.0000013486512,0.000016097532,0.00028391674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785906,0.000037960708,0.0006328596,0.0005420245,0.0005264468,0.00040167058],"domain_scores_gemma":[0.9988247,0.00015812406,0.0005041723,0.00014563836,0.00027673424,0.000090633606],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002450825,0.000301759,0.00031331397,0.00024618846,0.00033052,0.0005542227,0.0007105392,0.00007034087,0.000022735283],"category_scores_gemma":[0.00022614245,0.00024609003,0.000115519724,0.00029659516,0.00018857396,0.0015481838,0.00063144334,0.0006674526,0.000025600792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004911857,0.00074857665,0.12682481,0.0001206475,0.00021441322,0.000021968868,0.030688088,0.514202,0.04556563,0.046328433,0.000019462908,0.23477478],"study_design_scores_gemma":[0.00009142872,0.0005229782,0.0011992927,0.0005025052,0.000007553123,0.000037935963,0.003974015,0.9216982,0.07024205,0.0013635064,0.00006499197,0.0002955541],"about_ca_topic_score_codex":0.000054329004,"about_ca_topic_score_gemma":0.0000022303511,"teacher_disagreement_score":0.4074962,"about_ca_system_score_codex":0.00021519563,"about_ca_system_score_gemma":0.00005276229,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W1973749650","doi":"10.1016/j.artint.2012.04.006","title":"Reinforcement learning with limited reinforcement: Using Bayes risk for active learning in POMDPs","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Task (project management); Artificial intelligence; Machine learning; Action (physics); Variety (cybernetics); Bayes' theorem; Bayesian probability; Markov chain; Markov process; Markov model; Mathematics","score_opus":0.06131471456678903,"score_gpt":0.3031917075469479,"score_spread":0.24187699298015888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1973749650","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":[0.035592463,0.000054159667,0.96144897,0.00008047197,0.00035120203,0.0007710181,4.1696802e-7,0.00033131652,0.0013699684],"genre_scores_gemma":[0.94815445,0.00006331709,0.05106556,0.00009206697,0.00017084808,0.00007032926,0.000013403844,0.000041981202,0.00032806848],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965747,0.00021393634,0.00084035087,0.0005583704,0.0006031219,0.0012095358],"domain_scores_gemma":[0.99777204,0.0006275699,0.0006263431,0.00051088247,0.00024289613,0.00022024463],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012825058,0.00038812828,0.0003617155,0.0004226545,0.00062472915,0.00027932014,0.00077022833,0.00014500126,0.00004995654],"category_scores_gemma":[0.00072865124,0.00036873273,0.000114263916,0.0010442369,0.00010117913,0.0017003538,0.00032874063,0.0008035433,0.0000954072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010931322,0.000049305272,0.005010305,0.000025183703,0.000052225772,0.0000031516795,0.0058900253,0.9379852,0.00047468042,0.02871855,0.000004299323,0.021677755],"study_design_scores_gemma":[0.00014760297,0.00065458025,0.00032310086,0.00010860251,0.000035951114,0.000008079205,0.0012780357,0.9719432,0.022901662,0.00043776765,0.0016681461,0.00049325865],"about_ca_topic_score_codex":0.00023304726,"about_ca_topic_score_gemma":0.000023811364,"teacher_disagreement_score":0.91256195,"about_ca_system_score_codex":0.000348397,"about_ca_system_score_gemma":0.00013708434,"threshold_uncertainty_score":0.99987644},"labels":[],"label_agreement":null},{"id":"W1978322215","doi":"10.1109/tcyb.2014.2375817","title":"Energy Efficient Execution of POMDP Policies","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"Ontario Ministry of Research and Innovation; Natural Sciences and Engineering Research Council of Canada; Ontario Ministry of Research, Innovation and Science; Toronto Rehabilitation Institute; Alzheimer's Association","keywords":"Partially observable Markov decision process; Computer science; Benchmark (surveying); Markov decision process; Compiler; Mathematical optimization; Markov chain; Markov process; Machine learning; Markov model","score_opus":0.027320007767192143,"score_gpt":0.24979685337084656,"score_spread":0.2224768456036544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978322215","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":[0.0048118564,0.000028650387,0.9890832,0.00021723619,0.000848197,0.0000708987,0.000003942769,0.00012800118,0.0048080403],"genre_scores_gemma":[0.9865507,0.000025332662,0.0118897725,0.0001323729,0.000025614976,0.0000065184704,0.0000010076154,0.000012406249,0.0013562705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868447,0.00005892422,0.00029703064,0.00020946177,0.0005096042,0.00024051323],"domain_scores_gemma":[0.9989706,0.00007699661,0.00011711863,0.000524805,0.00017441092,0.0001360505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015614393,0.00014109258,0.00015204705,0.0002007597,0.000066062945,0.000050273036,0.0004801441,0.00008211444,0.000009921425],"category_scores_gemma":[0.000007870532,0.0001399689,0.00008128105,0.0004341504,0.00008825055,0.000090788184,0.0000052815803,0.00013654158,0.00003233369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007162373,0.00008372387,0.0000039086744,0.0000043061373,0.000015093561,0.0000013690426,0.0007216629,0.9812284,0.00047126028,0.01179128,0.00021065841,0.005461144],"study_design_scores_gemma":[0.0004069851,0.00036722238,0.000064549764,0.000024153196,0.000017901268,0.000010457322,0.00006086743,0.93345374,0.062569864,0.00025976324,0.0025881713,0.0001763382],"about_ca_topic_score_codex":0.0001474869,"about_ca_topic_score_gemma":0.000009037562,"teacher_disagreement_score":0.98173887,"about_ca_system_score_codex":0.00009485169,"about_ca_system_score_gemma":0.00010828026,"threshold_uncertainty_score":0.57077664},"labels":[],"label_agreement":null},{"id":"W1978640853","doi":"10.1533/abbi.2005.0021","title":"A Game Theoretic Approach to Swarm Robotics","year":2006,"lang":"en","type":"article","venue":"Applied Bionics and Biomechanics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Swarm robotics; Robotics; Artificial intelligence; Swarm behaviour; Computer science; Human–computer interaction; Engineering; Robot","score_opus":0.008186755589107645,"score_gpt":0.19745562999519717,"score_spread":0.18926887440608953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978640853","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":[0.001469105,0.00007096098,0.9873876,0.00042618145,0.00019122008,0.00036097626,0.000001908961,0.00020552416,0.009886516],"genre_scores_gemma":[0.8172194,0.00005080321,0.18173487,0.00059102656,0.00007161718,0.000020237741,0.000019753346,0.000020857035,0.00027146432],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983069,0.000018495455,0.00031090062,0.00053978176,0.00036221804,0.00046173585],"domain_scores_gemma":[0.9990414,0.00004091116,0.00010824585,0.0006077335,0.000057796296,0.000143959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003462909,0.00023963882,0.00021202423,0.00018749172,0.00014779878,0.0003408137,0.00073049,0.00014332078,0.0000016244859],"category_scores_gemma":[0.000007642654,0.0002078115,0.000050050272,0.000786791,0.000048619655,0.00008167231,0.00057230797,0.00016271263,0.00007328913],"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":[0.000003826651,0.000053232066,0.0000024467058,0.000023791985,0.000009076283,0.0000013899074,0.00008295462,0.054488834,0.0031660246,0.93907076,0.0001952255,0.002902432],"study_design_scores_gemma":[0.00040507162,0.00014008887,0.000015185206,0.0000130589815,0.000017691571,0.00002029334,0.000042347765,0.9185756,0.0057575987,0.06554227,0.009009397,0.00046138506],"about_ca_topic_score_codex":0.0000106413245,"about_ca_topic_score_gemma":6.7432296e-7,"teacher_disagreement_score":0.8735285,"about_ca_system_score_codex":0.000048553,"about_ca_system_score_gemma":0.0000423083,"threshold_uncertainty_score":0.84743077},"labels":[],"label_agreement":null},{"id":"W1979239334","doi":"10.1109/acc.2010.5530771","title":"An investigation of guarding a territory problem in a grid world","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Minimax; Grid; Artificial intelligence; Climbing; Hill climbing; Machine learning; Mathematical optimization; Geography; Mathematics","score_opus":0.011641736698358983,"score_gpt":0.24617533696483948,"score_spread":0.23453360026648049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1979239334","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":[0.41949502,0.0000023589353,0.56890255,0.00044023813,0.0007983478,0.00021481814,1.07727026e-7,0.00015322636,0.009993323],"genre_scores_gemma":[0.75313157,2.7492965e-7,0.24634495,0.00008979716,0.0000666941,0.0000051563634,0.0000011876604,0.0000035258556,0.00035685583],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992737,0.00003482768,0.00021960563,0.00016163923,0.00017707865,0.00013315903],"domain_scores_gemma":[0.99944955,0.00003603716,0.00008336612,0.00035769338,0.00003292153,0.000040444473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003710774,0.00006167929,0.000082987404,0.00022170889,0.000023474557,0.00005845424,0.0004821473,0.000031852018,0.000014467612],"category_scores_gemma":[0.000015581198,0.000057205114,0.000017643211,0.00032864878,0.000039755014,0.0006074199,0.00008158903,0.0001917355,0.000008139082],"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":[0.000003298505,0.000037431775,0.35224378,0.00004185421,0.00000815463,0.000005250312,0.0044912538,0.33067846,0.13547848,0.17145255,0.0011461339,0.004413328],"study_design_scores_gemma":[0.00025796393,0.000088430315,0.042271018,0.000040482475,0.0000016965777,0.000002869321,0.00004156296,0.9368616,0.017700016,0.0016725826,0.00090479734,0.00015702753],"about_ca_topic_score_codex":0.00011118044,"about_ca_topic_score_gemma":0.00028367198,"teacher_disagreement_score":0.60618305,"about_ca_system_score_codex":0.000015388125,"about_ca_system_score_gemma":0.00005345781,"threshold_uncertainty_score":0.2332757},"labels":[],"label_agreement":null},{"id":"W1980722163","doi":"10.1007/s10846-015-0222-2","title":"Multiple Model Q-Learning for Stochastic Asynchronous Rewards","year":2015,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Military College of Canada; Carleton University","funders":"","keywords":"Reinforcement learning; Asynchronous communication; Mobile robot; Computer science; Convergence (economics); Stochastic approximation; SIGNAL (programming language); Robot; Relaxation (psychology); Simulation; Real-time computing; Artificial intelligence","score_opus":0.060132220187145424,"score_gpt":0.28683430531278326,"score_spread":0.22670208512563783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1980722163","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":[0.0006082229,0.0008279278,0.9938694,0.00016295248,0.0037145,0.00046712617,3.620311e-7,0.00007838765,0.00027106798],"genre_scores_gemma":[0.9159481,0.00001764988,0.08227744,0.00004881873,0.0004985038,0.000014483252,0.0000017206149,0.000037387766,0.0011559076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966932,0.0001682762,0.0013429574,0.00028074428,0.0010062143,0.0005086205],"domain_scores_gemma":[0.9959522,0.0005616772,0.0012787774,0.00046096364,0.0013260962,0.00042031013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002244879,0.0002761946,0.0006255845,0.0003470578,0.00013598197,0.0003776385,0.0013101415,0.0001306591,0.0000017920411],"category_scores_gemma":[0.0018254821,0.0002324678,0.00027568816,0.00028293428,0.000044631408,0.00057087967,0.00017974463,0.0004597361,0.000049794104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003242014,0.000046923735,0.00021249725,0.00006363154,0.00010210953,0.0000141347155,0.0013986682,0.99317026,0.000061842184,0.0026941262,0.0014925214,0.00071087474],"study_design_scores_gemma":[0.0006889433,0.00095556764,0.000009079496,0.00029726198,0.000047891328,0.00033833607,0.0006210301,0.9957096,0.0001295666,0.00025283417,0.00070469617,0.0002451722],"about_ca_topic_score_codex":0.000019269055,"about_ca_topic_score_gemma":9.755212e-7,"teacher_disagreement_score":0.9153399,"about_ca_system_score_codex":0.00052765326,"about_ca_system_score_gemma":0.00057099847,"threshold_uncertainty_score":0.9479762},"labels":[],"label_agreement":null},{"id":"W1982435807","doi":"10.1142/s0218488511007416","title":"MULTIAGENT EXPEDITION WITH GRAPHICAL MODELS","year":2011,"lang":"en","type":"article","venue":"International Journal of Uncertainty Fuzziness and Knowledge-Based Systems","topic":"Reinforcement Learning in Robotics","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 Guelph","funders":"","keywords":"Scalability; Computer science; Graphical model; Set (abstract data type); Class (philosophy); Observable; Markov decision process; Multi-agent system; Artificial intelligence; Partially observable Markov decision process; Markov chain; Mathematical optimization; Markov process; Machine learning; Markov model; Mathematics","score_opus":0.04116553772219097,"score_gpt":0.25485211612003783,"score_spread":0.21368657839784685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982435807","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":[0.013685345,0.000351314,0.9815253,0.00018049745,0.0022206749,0.00012619833,0.000002437928,0.0000349125,0.0018733031],"genre_scores_gemma":[0.9949796,0.000037274218,0.0044795186,0.000052656404,0.00034642665,0.000010990536,0.0000037815198,0.000011610183,0.00007809934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982682,0.000120537785,0.0005717665,0.00020563994,0.000649595,0.00018426639],"domain_scores_gemma":[0.9974237,0.00013229622,0.0005175305,0.00020385942,0.0015631592,0.00015944897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005436024,0.0001766837,0.00025834833,0.00038112584,0.000074323434,0.00020163995,0.00083998725,0.00007203422,0.000007817103],"category_scores_gemma":[0.0000403006,0.00012476432,0.00009677712,0.00019183473,0.00009131642,0.0006487177,0.00008304792,0.00021251602,0.0000048150273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003212485,0.00031348766,0.0024551577,0.00008456682,0.00030314454,0.0002279165,0.0025343029,0.921946,0.00018846673,0.06769481,0.0004982326,0.0034326804],"study_design_scores_gemma":[0.0018765006,0.00046099012,0.0006564016,0.00048544243,0.000024027382,0.00023280214,0.00024895254,0.9938915,0.00021862755,0.000573093,0.001117298,0.00021435879],"about_ca_topic_score_codex":0.000070816925,"about_ca_topic_score_gemma":0.0000090434905,"teacher_disagreement_score":0.9812943,"about_ca_system_score_codex":0.00009813329,"about_ca_system_score_gemma":0.00022261083,"threshold_uncertainty_score":0.50877416},"labels":[],"label_agreement":null},{"id":"W1985646234","doi":"10.1115/imece2007-41643","title":"A Modified Q-Learning Algorithm for Multi-Robot Decision Making","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Robot; Computer science; Q-learning; Markov decision process; Artificial intelligence; Algorithm; Kalman filter; Robot learning; Domain (mathematical analysis); Markov chain; Reinforcement learning; Markov process; Machine learning; Mobile robot; Mathematics","score_opus":0.05076914814580656,"score_gpt":0.3375238673067552,"score_spread":0.28675471916094863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1985646234","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":[0.00017805785,0.000020143705,0.99592924,0.000035322162,0.0004802162,0.00030248292,1.760862e-7,0.00042412255,0.0026302354],"genre_scores_gemma":[0.14778574,0.0000025958004,0.8497532,0.0002295325,0.00006806726,0.000007943666,0.0000017640631,0.000016499522,0.0021346603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831516,0.000023694276,0.00037390448,0.00039734042,0.0003605632,0.000529326],"domain_scores_gemma":[0.9986123,0.0006194846,0.00013920094,0.0003952368,0.00014143404,0.00009233995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011304792,0.00016223443,0.00016272548,0.00019221105,0.00027128123,0.00022799817,0.0007630908,0.00009550472,0.000015946413],"category_scores_gemma":[0.00028732597,0.0001479643,0.00009942487,0.000331232,0.000023045362,0.00037439467,0.00030308164,0.00021392264,0.000060731112],"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":[0.0000052944065,0.00001442322,0.00010687762,0.0000041531457,0.000008530698,0.0000060300963,0.00018249758,0.46049663,0.000085574946,0.006764994,0.000092214315,0.53223276],"study_design_scores_gemma":[0.0006523587,0.00011189373,0.00082104723,0.00003556375,0.000004016548,0.000009071255,0.000044076576,0.9951027,0.0003697084,0.00024521185,0.0024001456,0.00020418635],"about_ca_topic_score_codex":0.00000618667,"about_ca_topic_score_gemma":0.0000034874206,"teacher_disagreement_score":0.5346061,"about_ca_system_score_codex":0.000074522985,"about_ca_system_score_gemma":0.00003135299,"threshold_uncertainty_score":0.60338086},"labels":[],"label_agreement":null},{"id":"W1986670254","doi":"10.1115/imece2007-41644","title":"Assess Team Q-Learning Algorithm in a Purely Cooperative Multi-Robot Task","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Robot; Computer science; Task (project management); Artificial intelligence; Convergence (economics); Q-learning; Robot learning; Object (grammar); Robotics; Markov decision process; Algorithm; Machine learning; Markov process; Reinforcement learning; Mobile robot; Engineering","score_opus":0.0296036776211122,"score_gpt":0.29674846523905857,"score_spread":0.26714478761794636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986670254","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":[0.0006152568,0.00002623227,0.98374313,0.00013482972,0.00029653875,0.0002488251,1.9699581e-7,0.00031058452,0.014624394],"genre_scores_gemma":[0.34935692,0.000010075345,0.6415346,0.00038877252,0.00005031076,0.000009009825,0.0000047587814,0.000018167912,0.008627364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997932,0.00012406713,0.00044169318,0.00046862374,0.00042690252,0.0006067253],"domain_scores_gemma":[0.99892074,0.00027813867,0.00012499423,0.0003873537,0.00015241315,0.00013636418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012241788,0.00021479894,0.00023186824,0.00026859372,0.00015698533,0.00027137742,0.00083227886,0.00011776717,0.000040589486],"category_scores_gemma":[0.00025177622,0.00019497007,0.000051977022,0.0008619176,0.000054694425,0.00067768083,0.00036975672,0.0006419562,0.00021866545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046723667,0.000108867986,0.0072725727,0.000008189699,0.000023164814,0.00009978534,0.0019597462,0.94015473,0.0011388249,0.008193345,0.00034816263,0.040687934],"study_design_scores_gemma":[0.00071379653,0.00015722378,0.009957734,0.000025848944,0.000002403166,0.000015702743,0.00028251868,0.9827801,0.0012968738,0.00001423764,0.004471004,0.0002825715],"about_ca_topic_score_codex":0.000108314925,"about_ca_topic_score_gemma":0.000056993358,"teacher_disagreement_score":0.34874165,"about_ca_system_score_codex":0.0001465463,"about_ca_system_score_gemma":0.00009832773,"threshold_uncertainty_score":0.79506487},"labels":[],"label_agreement":null},{"id":"W1990320219","doi":"10.1145/2739480.2754798","title":"Knowledge Transfer from Keepaway Soccer to Half-field Offense through Program Symbiosis","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Testbed; Computer science; Artificial intelligence; Task (project management); Modular design; Transfer of learning; Function (biology); Genetic programming; Machine learning; Engineering","score_opus":0.0649594141187844,"score_gpt":0.3187345708745497,"score_spread":0.2537751567557653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1990320219","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":[0.006889178,0.00005759907,0.9107405,0.0031212538,0.0008034632,0.00048740127,6.907471e-7,0.00072456134,0.07717534],"genre_scores_gemma":[0.75019974,0.0000074981544,0.2403563,0.0033322764,0.00018157951,0.00007744085,0.0000058289984,0.000027128219,0.0058122375],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982081,0.00007846856,0.00031673533,0.00051642855,0.0004138052,0.0004664734],"domain_scores_gemma":[0.99846554,0.00017337962,0.000026335976,0.00083775393,0.00019587387,0.00030113925],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023087204,0.0002286304,0.00024051002,0.0000700448,0.00008704087,0.00032786885,0.001096152,0.00013470344,0.0001494336],"category_scores_gemma":[0.00011064652,0.00019548369,0.00010729834,0.00048767988,0.00003141438,0.00056665065,0.00030666977,0.00020863913,0.0015409595],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015951857,0.0015568929,0.009142651,0.00009017628,0.00055732945,0.00009900943,0.07070075,0.05754244,0.0018818567,0.28279048,0.30452913,0.27094975],"study_design_scores_gemma":[0.0025508574,0.0032340528,0.0012022699,0.00014257988,0.000077878525,0.000012401413,0.00060116814,0.37285987,0.049952965,0.0035817144,0.5641077,0.0016765605],"about_ca_topic_score_codex":0.00032436187,"about_ca_topic_score_gemma":0.00005608135,"teacher_disagreement_score":0.7433105,"about_ca_system_score_codex":0.000073351424,"about_ca_system_score_gemma":0.00012488323,"threshold_uncertainty_score":0.99923646},"labels":[],"label_agreement":null},{"id":"W1998172110","doi":"10.1007/s10479-005-5732-z","title":"Basis Function Adaptation in Temporal Difference Reinforcement Learning","year":2005,"lang":"en","type":"article","venue":"Annals of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":190,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Bellman equation; Temporal difference learning; Basis function; Function approximation; Mathematical optimization; Basis (linear algebra); Computer science; Theory of computation; Q-learning; Convergence (economics); Markov process; Mathematics; Artificial intelligence; Algorithm; Artificial neural network","score_opus":0.22553966350065155,"score_gpt":0.41189285311802815,"score_spread":0.1863531896173766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998172110","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":[0.05995004,0.00007519144,0.9328964,0.0033148674,0.000050758146,0.0002850705,2.2697165e-7,0.00004330525,0.0033841585],"genre_scores_gemma":[0.98458445,0.00016146085,0.010895407,0.00010736886,0.000047183377,0.00004593613,0.000016319875,0.0000070375977,0.0041348375],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977658,0.00032180603,0.00043448442,0.00026197176,0.0008473764,0.00036859463],"domain_scores_gemma":[0.9986761,0.00014993684,0.000045106448,0.0003815484,0.000675984,0.00007130287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017954679,0.00009287867,0.0001281759,0.00059908425,0.00027256834,0.00020029761,0.00050489284,0.000059849335,0.00008719236],"category_scores_gemma":[0.0004803068,0.00009155396,0.00003942791,0.0010151046,0.00006737973,0.00087124185,0.00020831902,0.00043671508,0.000104727675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010656557,0.000034828987,0.0014116098,0.000008560532,0.0000071761956,7.9220536e-7,0.001046489,0.95965844,0.0006477443,0.0179498,0.00020573457,0.019018194],"study_design_scores_gemma":[0.00018890043,0.00034062687,0.007907618,0.00003693445,8.063308e-7,6.6718434e-7,0.00021471403,0.98675364,0.0020504624,0.00006248661,0.0023549881,0.00008817683],"about_ca_topic_score_codex":0.00041235387,"about_ca_topic_score_gemma":0.00023016403,"teacher_disagreement_score":0.9246344,"about_ca_system_score_codex":0.00005640941,"about_ca_system_score_gemma":0.00019100327,"threshold_uncertainty_score":0.37334618},"labels":[],"label_agreement":null},{"id":"W1998314229","doi":"10.1145/1089827.1089829","title":"Reinforcement learning for active model selection","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Artificial intelligence; Machine learning; Learning classifier system; Classifier (UML); Feature selection; Selection (genetic algorithm); Training set; Feature (linguistics); Active learning (machine learning); Markov process; Mathematics","score_opus":0.02332588564199617,"score_gpt":0.27049509625491275,"score_spread":0.24716921061291658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1998314229","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":[0.0002859446,0.0000027685976,0.9736742,0.00062096806,0.000066559056,0.00025593906,3.6686e-8,0.00033510738,0.024758516],"genre_scores_gemma":[0.6680903,0.0000045545985,0.3007622,0.00038501289,0.00007485474,0.000037150683,0.0000032222601,0.000009055167,0.030633656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903095,0.000015079278,0.00019394817,0.00024356427,0.000223054,0.0002933772],"domain_scores_gemma":[0.9994892,0.000061189225,0.00009400239,0.00017961835,0.00011680982,0.00005918847],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001795588,0.000110930334,0.00009471399,0.00008854566,0.00021229847,0.00010971185,0.00034440603,0.000050051978,0.00003329236],"category_scores_gemma":[0.00006133135,0.00010547191,0.00005998846,0.00016497255,0.00001123978,0.00073789386,0.00010840103,0.0001458023,0.000073256895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065778368,0.000005814331,0.000018948116,0.0000037745692,0.000011041373,4.2646096e-8,0.00029823137,0.93008375,0.00039295017,0.053235892,0.00075762335,0.015185348],"study_design_scores_gemma":[0.0003081999,0.00013877625,0.000017578104,0.0000041313833,0.000004218291,0.0000016979574,0.000016021591,0.9789624,0.006806335,0.00021718554,0.013386749,0.00013668403],"about_ca_topic_score_codex":0.0000042631905,"about_ca_topic_score_gemma":0.0000024527728,"teacher_disagreement_score":0.67291194,"about_ca_system_score_codex":0.00014769615,"about_ca_system_score_gemma":0.000061304934,"threshold_uncertainty_score":0.430102},"labels":[],"label_agreement":null},{"id":"W1999095902","doi":"10.1109/cig.2013.6633642","title":"Stacked calibration of off-policy policy evaluation for video game matchmaking","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ubisoft (Canada); Université de Montréal","funders":"","keywords":"Computer science; Function (biology); Calibration; Video game; Simple (philosophy); Statistics; Multimedia; Mathematics","score_opus":0.03258298194827107,"score_gpt":0.32181601398908705,"score_spread":0.28923303204081596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999095902","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":[0.008540989,0.000010166659,0.98365134,0.0023495185,0.00010332922,0.00085712067,6.2687377e-7,0.00010639253,0.0043805433],"genre_scores_gemma":[0.9387755,0.000003458101,0.0587288,0.00078942545,0.00017151417,0.00009808203,0.000009739681,0.000011815611,0.0014117049],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986354,0.00007110781,0.0003712065,0.0002131619,0.00045954823,0.0002495503],"domain_scores_gemma":[0.9987107,0.000146781,0.00024812005,0.0004529857,0.00038460412,0.000056804212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004615623,0.00010744962,0.00013844263,0.00027528557,0.000055856355,0.00018236604,0.00045075227,0.00004881064,0.00011401008],"category_scores_gemma":[0.00051392807,0.00009732493,0.000058797155,0.0004782983,0.000029456445,0.0010572608,0.00013031614,0.000051893632,0.000043370525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039684082,0.00002097543,0.00021898578,0.00004991825,0.00002235206,9.9513166e-8,0.001036535,0.562798,0.0028692759,0.38371745,0.002084884,0.047177546],"study_design_scores_gemma":[0.00038918838,0.00009493505,0.00088398793,0.000015453914,0.000005630007,0.0000012995089,0.000030739564,0.9860126,0.0029804707,0.008685154,0.0007966855,0.00010389851],"about_ca_topic_score_codex":0.00043525267,"about_ca_topic_score_gemma":0.000003989676,"teacher_disagreement_score":0.9302345,"about_ca_system_score_codex":0.00012988476,"about_ca_system_score_gemma":0.0003901295,"threshold_uncertainty_score":0.39687955},"labels":[],"label_agreement":null},{"id":"W2001487393","doi":"10.1155/2009/984752","title":"Vector Field Driven Design for Lightweight Signal Processing and Control Schemes for Autonomous Robotic Navigation","year":2009,"lang":"en","type":"article","venue":"EURASIP Journal on Advances in Signal Processing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Neuromorphic engineering; Robotics; Artificial intelligence; Field (mathematics); Exploit; Signal processing; SIGNAL (programming language); Computer architecture; Control engineering; Robot; Human–computer interaction; Digital signal processing; Computer hardware; Artificial neural network","score_opus":0.019334171976119554,"score_gpt":0.29524634823391543,"score_spread":0.2759121762577959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001487393","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":[0.0006915607,0.0034190714,0.99339116,0.0014482398,0.0001624655,0.0006966697,6.015266e-7,0.0000950871,0.00009513325],"genre_scores_gemma":[0.7538237,0.00004856055,0.24506985,0.00067009625,0.00029009464,0.00002992463,0.0000017333922,0.000020839596,0.000045173612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976366,0.000108312415,0.00072851114,0.00049201795,0.00043990667,0.0005946615],"domain_scores_gemma":[0.99788076,0.00078812765,0.00071177224,0.00013307872,0.00032078047,0.00016550305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008301608,0.000327594,0.0004227015,0.00026239097,0.00065958843,0.00087260356,0.00060008984,0.00011894281,0.0000042846705],"category_scores_gemma":[0.00017029374,0.0002867913,0.00009780467,0.00034033114,0.00005724621,0.0027581197,0.000028286353,0.0005199735,0.0000015374297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021635882,0.000052282878,0.00014620283,0.00013039442,0.000008507449,0.00001700304,0.00037333838,0.6174798,0.002445123,0.00083575654,0.00002340026,0.37827185],"study_design_scores_gemma":[0.0020386977,0.002127232,0.0001155675,0.0011238934,0.000026428634,0.00010487288,0.000039436207,0.97944796,0.006335353,0.006615726,0.00164207,0.00038274284],"about_ca_topic_score_codex":1.3540775e-7,"about_ca_topic_score_gemma":1.5633753e-7,"teacher_disagreement_score":0.75313216,"about_ca_system_score_codex":0.00016292374,"about_ca_system_score_gemma":0.00027191595,"threshold_uncertainty_score":0.9999584},"labels":[],"label_agreement":null},{"id":"W2002256627","doi":"10.1109/adprl.2013.6614986","title":"Exponential moving average Q-learning algorithm","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Variety (cybernetics); Computer science; Q-learning; Exponential function; Algorithm; Policy learning; Markov decision process; State (computer science); Mathematical optimization; Matrix (chemical analysis); Artificial intelligence; Machine learning; Mathematics; Markov process","score_opus":0.007682844823853384,"score_gpt":0.2071727335532115,"score_spread":0.1994898887293581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002256627","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":[0.0014398281,0.0000097253815,0.9703557,0.00021199159,0.000379267,0.00012967219,3.449936e-8,0.00049672305,0.026977083],"genre_scores_gemma":[0.51436824,0.0000070758833,0.4629816,0.00035643228,0.00011651006,0.000016927534,0.0000026059608,0.000014319041,0.022136278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875987,0.00005892874,0.00021133258,0.00027854115,0.00033510558,0.00035620912],"domain_scores_gemma":[0.9992983,0.00007414232,0.000077007404,0.00037246483,0.0000741506,0.000103964514],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016253379,0.00012505725,0.000109416316,0.000090832946,0.00018036317,0.0005147482,0.0007013982,0.000051305324,0.0010189309],"category_scores_gemma":[0.000054065393,0.00011391598,0.000055525976,0.00020292285,0.000021522173,0.0010145186,0.0004454528,0.00024435815,0.0023739298],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.0437876e-7,0.000024086872,0.0012762998,0.000010590553,0.00003253487,0.00001926675,0.00092303834,0.70244086,0.0023338085,0.016768198,0.00387778,0.27229303],"study_design_scores_gemma":[0.00014799453,0.00004610051,0.0011212159,0.000006794403,0.0000013082333,0.00000784958,0.000031595202,0.9936446,0.0007316298,0.00020131814,0.0038983994,0.00016120906],"about_ca_topic_score_codex":0.00010460844,"about_ca_topic_score_gemma":1.9636094e-7,"teacher_disagreement_score":0.5129284,"about_ca_system_score_codex":0.000032567135,"about_ca_system_score_gemma":0.000019561847,"threshold_uncertainty_score":0.99989426},"labels":[],"label_agreement":null},{"id":"W200360931","doi":"","title":"Turning lights out with DQ-learning","year":2006,"lang":"en","type":"article","venue":"International conference on Artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Computer science; Discretization; Premise; Arity; Overhead (engineering); Byte; Table (database); Representation (politics); Reinforcement learning; Artificial intelligence; State (computer science); Algorithm; Theoretical computer science; Mathematics; Discrete mathematics; Programming language; Database","score_opus":0.06063246829204915,"score_gpt":0.308802611147818,"score_spread":0.24817014285576883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W200360931","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":[0.0012407398,0.000009610243,0.9429966,0.0019732015,0.000110367335,0.00018594204,0.0000012558654,0.00015506138,0.0533272],"genre_scores_gemma":[0.9892534,0.000028967452,0.008375598,0.0001412903,0.0002194096,0.00009754885,0.000019832196,0.000009332684,0.00185461],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871355,0.00002693392,0.00030054597,0.00039578506,0.00036000708,0.00020319503],"domain_scores_gemma":[0.99916804,0.00010672105,0.00015639351,0.00025051605,0.00025487423,0.00006346013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013013123,0.00015237847,0.0001088697,0.00014385686,0.00027408206,0.0005206705,0.00062252005,0.000051612264,0.00007773738],"category_scores_gemma":[0.000022667935,0.00013239354,0.000029619983,0.0001901523,0.000104530394,0.00030214133,0.00010285743,0.00026314554,0.00032823198],"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":[0.0000064066217,0.00003602434,0.00021463893,0.000002049077,0.000009449975,0.0000023459488,0.00013633654,0.08858942,0.0008575185,0.8825097,0.000025386005,0.027610725],"study_design_scores_gemma":[0.000059623013,0.00022791131,0.0004598377,0.00007818531,0.000010266555,0.00001431538,0.000368784,0.8298621,0.015113909,0.1270107,0.026364233,0.00043009798],"about_ca_topic_score_codex":0.00003978351,"about_ca_topic_score_gemma":0.000037336205,"teacher_disagreement_score":0.9880127,"about_ca_system_score_codex":0.000037012807,"about_ca_system_score_gemma":0.00005081029,"threshold_uncertainty_score":0.5398852},"labels":[],"label_agreement":null},{"id":"W2006330826","doi":"10.1007/s10994-011-5254-7","title":"Model selection in reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematics; Estimator; Oracle; Bellman equation; Function (biology); Regularization (linguistics); Countable set; Sequence (biology); Combinatorics; Rate of convergence; Discrete mathematics; Mathematical optimization; Computer science; Artificial intelligence; Statistics","score_opus":0.03659510899503107,"score_gpt":0.24580997705280483,"score_spread":0.20921486805777376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006330826","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":[0.011630058,0.000032261352,0.95233506,0.00005427527,0.0000875936,0.00014456488,2.4758874e-8,0.0004751324,0.035241026],"genre_scores_gemma":[0.9450121,0.000022998864,0.04760224,0.00012001906,0.000026164897,0.000017012218,0.0000047837857,0.00002597894,0.007168737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980894,0.00017286876,0.00041560244,0.0004235083,0.00037620112,0.00052242656],"domain_scores_gemma":[0.9993745,0.000050998355,0.00020816305,0.00021750944,0.000056722907,0.00009208832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072162424,0.00022232444,0.00020933771,0.00035403066,0.00025698816,0.000104198385,0.0006113523,0.00009321766,0.00012050052],"category_scores_gemma":[0.00021140643,0.00023082737,0.00005644726,0.0006207123,0.000025038764,0.0006239088,0.00035339664,0.00097225,0.000120692195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009690553,0.000014581834,0.04922677,0.000010969682,0.000008971184,0.000007598156,0.0026841678,0.93778723,0.00047906884,0.0067916154,0.000014693481,0.0029646424],"study_design_scores_gemma":[0.0003952052,0.00024998034,0.003296698,0.00002753902,0.0000043152136,0.000010029676,0.00003269272,0.9940863,0.00032765605,0.00024449057,0.0010667791,0.00025829588],"about_ca_topic_score_codex":0.00026800553,"about_ca_topic_score_gemma":0.000031890402,"teacher_disagreement_score":0.93338203,"about_ca_system_score_codex":0.00014025607,"about_ca_system_score_gemma":0.00005610281,"threshold_uncertainty_score":0.9412867},"labels":[],"label_agreement":null},{"id":"W2008768326","doi":"10.1023/b:jotp.0000011995.28536.ef","title":"Continuity of the Value of Competitive Markov Decision Processes","year":2003,"lang":"en","type":"article","venue":"Journal of Theoretical Probability","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Mathematics; Markov decision process; Markov chain; Upper and lower bounds; Markov process; Markov kernel; Discounting; Value (mathematics); Mathematical optimization; Partially observable Markov decision process; Space (punctuation); Bellman equation; Function (biology); Markov model; Mathematical economics; Statistics; Variable-order Markov model; Computer science; Mathematical analysis; Economics","score_opus":0.008738568404383095,"score_gpt":0.247020988068592,"score_spread":0.2382824196642089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2008768326","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":[0.2001693,0.000054683383,0.7928119,0.00026997345,0.00029075323,0.00021040233,0.0000011078229,0.000006357884,0.006185557],"genre_scores_gemma":[0.92373276,0.0000072379667,0.07619293,0.00003878019,0.000012817989,6.317566e-7,3.800623e-8,0.000004015749,0.000010769982],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99741596,0.00059213897,0.000902623,0.00015303507,0.00076259364,0.0001736636],"domain_scores_gemma":[0.9956352,0.0017162312,0.00087232736,0.00055186724,0.0011446384,0.00007975174],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0031750528,0.00011422027,0.00037588557,0.000045750665,0.000051010662,0.000029680208,0.0012009053,0.00006985619,0.000050323324],"category_scores_gemma":[0.012888983,0.00006595083,0.00020723921,0.00041984415,0.0010336448,0.00020384749,0.00024350348,0.00032900486,0.0000010996316],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006397497,0.00015100339,0.010628803,0.000117723524,0.000022771585,0.0000010008995,0.00024983237,0.013267901,0.00020379662,0.97457117,0.000017828112,0.00070420565],"study_design_scores_gemma":[0.0006045145,0.0005098988,0.015269707,0.00034670494,0.000038508784,0.00004524945,0.00005109856,0.0066700964,0.03016278,0.9460148,0.00017472614,0.000111907495],"about_ca_topic_score_codex":8.078832e-7,"about_ca_topic_score_gemma":5.034146e-7,"teacher_disagreement_score":0.7235635,"about_ca_system_score_codex":0.000062816194,"about_ca_system_score_gemma":0.00034616128,"threshold_uncertainty_score":0.9954259},"labels":[],"label_agreement":null},{"id":"W2010124866","doi":"10.2316/journal.206.2006.2.206-2795","title":"FUZZY REINFORCEMENT LEARNING FOR EMBEDDED SOCCER AGENTS IN A MULTI-AGENT CONTEXT","year":2006,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Fuzzy logic; Context (archaeology); Artificial intelligence; Reinforcement; Machine learning; Engineering","score_opus":0.03483910685198837,"score_gpt":0.30849806606312313,"score_spread":0.27365895921113476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2010124866","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":[0.0077207335,0.00004978112,0.98993194,0.0011371727,0.00074201194,0.00014804395,2.835257e-7,0.00002053605,0.00024951],"genre_scores_gemma":[0.9138546,0.00004148812,0.08533664,0.00024038457,0.0000711937,0.000003786661,0.000009998437,0.00000717938,0.00043474595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868596,0.000045571167,0.00059237203,0.00011251557,0.00042882707,0.00013475354],"domain_scores_gemma":[0.9986573,0.000080759186,0.0005656063,0.00007082856,0.0005891662,0.00003638141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051424094,0.00010034713,0.00014304339,0.00026632764,0.000048140748,0.00024450492,0.0003389928,0.00004359551,0.000003639423],"category_scores_gemma":[0.00017394587,0.000093328585,0.00005761569,0.00011369688,0.000016814038,0.0005582566,0.00008785961,0.00014718284,0.0000031733675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010855594,0.000037727226,0.0021553356,0.000008149954,0.000030907777,0.00000970397,0.00039359948,0.9575871,0.00016351043,0.035028413,0.00021946522,0.004355224],"study_design_scores_gemma":[0.0015884537,0.00011359212,0.014533644,0.00009704919,0.000007267307,0.000026247606,0.00005809929,0.9813913,0.00015130336,0.0009143032,0.0010237122,0.00009500883],"about_ca_topic_score_codex":0.000018972603,"about_ca_topic_score_gemma":0.00000725642,"teacher_disagreement_score":0.90613383,"about_ca_system_score_codex":0.0001359486,"about_ca_system_score_gemma":0.000073266485,"threshold_uncertainty_score":0.38058293},"labels":[],"label_agreement":null},{"id":"W2011033111","doi":"10.1109/adprl.2007.368201","title":"Opposition-Based Q(&amp;#x003BB;) with Non-Markovian Update","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Opposition (politics); Computer science; Markov process; Algorithm; Theoretical computer science; Statistical physics; Mathematics; Physics; Law; Statistics","score_opus":0.009002528772758794,"score_gpt":0.23877252817285816,"score_spread":0.22976999940009937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011033111","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":[0.002045406,0.000003593253,0.95190984,0.0009151564,0.00020344746,0.00014714868,2.6423842e-7,0.00027364842,0.044501524],"genre_scores_gemma":[0.5183142,8.913318e-7,0.47700128,0.0022962315,0.00005425663,0.0000036152226,0.000010395198,0.000012398478,0.002306765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858254,0.000020702182,0.00023038356,0.0003141383,0.00042590598,0.00042634836],"domain_scores_gemma":[0.99878645,0.00012336565,0.00008951632,0.00072178326,0.000113775095,0.00016511822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045549675,0.00015820205,0.00012285887,0.00015504315,0.00015415429,0.00021124109,0.00072833884,0.000055238535,0.00014425417],"category_scores_gemma":[0.000018331693,0.00012525984,0.00004237454,0.00049310544,0.00005426115,0.00035354105,0.0000953108,0.00015745552,0.00050341396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004915352,0.00010449432,0.0077271434,0.000035797824,0.000057001333,0.000059778486,0.0003086355,0.9344596,0.0017437094,0.03864873,0.007093958,0.009711982],"study_design_scores_gemma":[0.0016676905,0.00050998427,0.007299663,0.000088487155,0.000022950653,0.000036498826,0.000040035848,0.90681463,0.009162733,0.00021077678,0.07325622,0.00089030364],"about_ca_topic_score_codex":0.00003056196,"about_ca_topic_score_gemma":0.00004210229,"teacher_disagreement_score":0.5162688,"about_ca_system_score_codex":0.000058717593,"about_ca_system_score_gemma":0.00009883947,"threshold_uncertainty_score":0.6470536},"labels":[],"label_agreement":null},{"id":"W2011231614","doi":"10.1145/1329125.1329178","title":"Reducing the complexity of multiagent reinforcement learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Reinforcement learning; Initialization; Computer science; Function (biology); Artificial intelligence; Representation (politics); Class (philosophy); Multi-agent system; Function approximation; Mathematical optimization; Sample complexity; Computational complexity theory; Action (physics); Mathematics; Algorithm; Artificial neural network","score_opus":0.060374917235600525,"score_gpt":0.28898364382667147,"score_spread":0.22860872659107095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011231614","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":[0.0034549383,0.000016622604,0.95700836,0.00046805173,0.00022113406,0.00016757795,2.123004e-8,0.00012316961,0.038540147],"genre_scores_gemma":[0.9383803,0.0000061712353,0.058351025,0.00017644877,0.000033622906,0.0000016263122,0.0000012148587,0.0000058629375,0.0030437405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985097,0.00005271903,0.0004409475,0.0001967846,0.0004697312,0.00033008968],"domain_scores_gemma":[0.9988457,0.00018889197,0.00022803794,0.00057204906,0.00010261823,0.000062685416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014668733,0.00011057752,0.00012786167,0.000077726545,0.00021950413,0.000060403127,0.0008749124,0.00003408472,0.00008684521],"category_scores_gemma":[0.00014214584,0.000075048636,0.0000705817,0.00031663082,0.00019377412,0.00018758715,0.00043186534,0.00023745782,0.000042355638],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033676404,0.000008026256,0.000447187,0.000008765644,0.000014547381,0.0000018244999,0.0011405853,0.8736878,0.0009772364,0.11947486,0.00014579494,0.0040899953],"study_design_scores_gemma":[0.00021255028,0.00011713523,0.0040496704,0.000020316522,0.0000047506137,0.000005428678,0.00025375953,0.9749985,0.016029974,0.00018641575,0.0039993175,0.00012219332],"about_ca_topic_score_codex":0.0001478422,"about_ca_topic_score_gemma":0.0000051141387,"teacher_disagreement_score":0.9349254,"about_ca_system_score_codex":0.000054188306,"about_ca_system_score_gemma":0.00003160392,"threshold_uncertainty_score":0.30603945},"labels":[],"label_agreement":null},{"id":"W2011233848","doi":"10.1145/1143844.1143901","title":"Automatic basis function construction for approximate dynamic programming and reinforcement learning","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":162,"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":"Bellman equation; Markov decision process; Reinforcement learning; Computer science; Basis (linear algebra); Function approximation; Dynamic programming; Curse of dimensionality; Basis function; Mathematical optimization; State space; Temporal difference learning; Markov process; Dimensionality reduction; Q-learning; Function (biology); Space (punctuation); Artificial intelligence; Algorithm; Mathematics; Artificial neural network","score_opus":0.007772714293839559,"score_gpt":0.22287687197202508,"score_spread":0.21510415767818553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011233848","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":[0.0066302796,0.000020470943,0.99024796,0.00014128302,0.00022810235,0.0005401471,7.069852e-8,0.00060709484,0.0015845955],"genre_scores_gemma":[0.6213385,0.0000039460056,0.37701827,0.00003420488,0.00002467402,0.000071044495,0.00001504772,0.000010827158,0.0014835183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882185,0.00002864943,0.00032353535,0.0002978648,0.00022047517,0.00030763622],"domain_scores_gemma":[0.99940664,0.000081161415,0.00018138064,0.00020977647,0.00007789013,0.00004314812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031674217,0.00014624633,0.00013863249,0.00013040693,0.00030200795,0.0003277692,0.00015779135,0.000058180463,0.000017301167],"category_scores_gemma":[0.00003346111,0.00013750793,0.0000471305,0.00020631355,0.000051335577,0.00049993634,0.00010145688,0.00010542993,0.00000830102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060917323,0.00001052799,0.001597743,0.00013761158,0.000023548448,5.533726e-7,0.00009775284,0.70137167,0.00024010708,0.082980044,0.000062004554,0.21347235],"study_design_scores_gemma":[0.00042844174,0.00022539216,0.00084280135,0.000023515526,0.000019045594,0.000014697485,0.000087223954,0.9951972,0.00016256186,0.000848104,0.001983804,0.00016721997],"about_ca_topic_score_codex":0.000024813186,"about_ca_topic_score_gemma":0.0000029665932,"teacher_disagreement_score":0.6147082,"about_ca_system_score_codex":0.00007394009,"about_ca_system_score_gemma":0.000024131592,"threshold_uncertainty_score":0.56074107},"labels":[],"label_agreement":null},{"id":"W2012045703","doi":"10.1287/moor.27.3.545.316","title":"Achieving Target State-Action Frequencies in Multichain Average-Reward Markov Decision Processes","year":2002,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Markov decision process; Stochastic game; Construct (python library); Mathematics; Action (physics); Mathematical optimization; Markov process; State space; Markov chain; State (computer science); Space (punctuation); Decision problem; Mathematical economics; Computer science; Algorithm; Statistics","score_opus":0.12878878589770923,"score_gpt":0.37332200477531274,"score_spread":0.24453321887760351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012045703","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":[0.105741605,0.000109730514,0.8913088,0.0003155125,0.000062276384,0.0004642529,0.0000021249346,0.000051663883,0.0019440239],"genre_scores_gemma":[0.6136735,0.00014481402,0.3847877,0.000008554014,0.000011286869,0.000042094438,0.0000023236314,0.000011940007,0.0013177322],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974393,0.00018240453,0.00059906254,0.00028553384,0.0010940197,0.00039965508],"domain_scores_gemma":[0.9975976,0.00092259067,0.00006317652,0.0006382023,0.0007052718,0.00007320711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019280576,0.00013309515,0.00021774747,0.00064513704,0.0002917592,0.00039562356,0.000906223,0.00006534365,0.00012917828],"category_scores_gemma":[0.0036142506,0.000120923854,0.000034594552,0.0013885522,0.000112347545,0.00089030317,0.0003326246,0.00039364913,0.00011586486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022990866,0.000181441,0.0003476327,0.0002714632,0.000008802008,0.000007071317,0.007752599,0.98271734,0.0025956666,0.0035919591,0.00017515884,0.0023485825],"study_design_scores_gemma":[0.00021895011,0.000102604004,0.00016789045,0.00020148625,0.0000010650532,0.0000041140797,0.00035191528,0.9946882,0.0032006402,0.00078023225,0.00016198316,0.000120913464],"about_ca_topic_score_codex":0.00007101005,"about_ca_topic_score_gemma":0.00010658202,"teacher_disagreement_score":0.50793195,"about_ca_system_score_codex":0.00014540827,"about_ca_system_score_gemma":0.00012401195,"threshold_uncertainty_score":0.49311316},"labels":[],"label_agreement":null},{"id":"W2014744886","doi":"10.1109/cig.2006.311676","title":"Grid-Robot Drivers: an Evolutionary Multi-agent Virtual Robotics Task","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of Guelph","funders":"University of Guelph","keywords":"Computer science; Artificial intelligence; Robot; Grid; Context (archaeology); Prisoner's dilemma; Task (project management); Reinforcement learning; Dilemma; Simulation; Engineering","score_opus":0.019255348371642514,"score_gpt":0.24418496478241183,"score_spread":0.2249296164107693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014744886","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":[0.00088762486,0.000027129634,0.99380326,0.00039898377,0.0010760612,0.00018889297,0.0000017068262,0.00058926595,0.0030270761],"genre_scores_gemma":[0.33835083,0.000008897339,0.65060484,0.00039301254,0.00029597213,0.0000069174775,0.0000473906,0.000021301164,0.010270847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978991,0.00009345087,0.00038950407,0.0005305032,0.00058201794,0.00050541793],"domain_scores_gemma":[0.99863565,0.00007131119,0.00013052583,0.000862522,0.00013780921,0.00016217337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019369219,0.0002425197,0.00018452428,0.00015553572,0.00026407876,0.00022988656,0.001204989,0.000112495836,0.000069101814],"category_scores_gemma":[0.000029429293,0.00023284582,0.00009412382,0.00036850583,0.0001000385,0.00109067,0.0004485804,0.00022209727,0.0005673411],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016060582,0.00011791929,0.0032413548,0.0000032318549,0.000011227356,0.000019592675,0.00009620325,0.9283167,0.00044323457,0.0635753,0.0036808148,0.00049281586],"study_design_scores_gemma":[0.0004985916,0.00022817666,0.02043626,0.000009081223,0.00000943358,0.000010435585,0.000050284234,0.97348773,0.00013879855,0.0001775625,0.0046198913,0.00033375405],"about_ca_topic_score_codex":0.00015654165,"about_ca_topic_score_gemma":0.00001940437,"teacher_disagreement_score":0.34319842,"about_ca_system_score_codex":0.00017691613,"about_ca_system_score_gemma":0.00010063277,"threshold_uncertainty_score":0.9495177},"labels":[],"label_agreement":null},{"id":"W2023718460","doi":"10.3166/ria.20.203-234","title":"Prise de décision en temps-réel pour des POMDP de grande taille","year":2006,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.042396513919707404,"score_gpt":0.28318727660601534,"score_spread":0.24079076268630795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023718460","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":[0.031463165,0.0035181933,0.9451111,0.0035978637,0.0010792704,0.00042204696,0.000004658327,0.00022452815,0.014579192],"genre_scores_gemma":[0.71668476,0.0010797437,0.10926328,0.00029479992,0.0007222584,0.00002930344,0.000010665906,0.000072432915,0.17184277],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955813,0.00048715968,0.0010574602,0.0008497416,0.0004857764,0.001538512],"domain_scores_gemma":[0.9969861,0.0008363552,0.00034075344,0.0011812202,0.00032174276,0.0003338421],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019794705,0.00047950062,0.00043520535,0.00024956884,0.0006360793,0.0006179421,0.0016071785,0.00038139912,0.00060213683],"category_scores_gemma":[0.0007003198,0.0005344026,0.00030635684,0.0010386909,0.00045097186,0.0007541291,0.00051262294,0.0007037236,0.002748011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001981818,0.00024947917,0.0034881325,0.00019197844,0.000021676493,0.00014112103,0.0045467736,0.8974334,0.0043220953,0.03569178,0.0046195174,0.04927421],"study_design_scores_gemma":[0.000111431735,0.00022521071,0.00068873144,0.00056264777,0.00004194222,0.00026064416,0.00067650096,0.88032234,0.041589376,0.017407183,0.05758049,0.0005334788],"about_ca_topic_score_codex":0.0024528576,"about_ca_topic_score_gemma":0.00012766499,"teacher_disagreement_score":0.8358478,"about_ca_system_score_codex":0.0006550322,"about_ca_system_score_gemma":0.00045471633,"threshold_uncertainty_score":0.99971074},"labels":[],"label_agreement":null},{"id":"W2024074370","doi":"10.3166/ria.20.275-310","title":"Apprentissage par renforcement dans le cadre des processus décisionnels de Markov factorisés observables dans le désordre. Etude expérimentale du Q-Learning parallèle appliqué aux problèmes du labyrinthe et du New York Driving","year":2006,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Markov decision process; Observable; Architecture; Computer science; Markov chain; Partially observable Markov decision process; Humanities; Markov process; Artificial intelligence; Markov model; Mathematics; Physics; Machine learning; Philosophy; Art; Statistics","score_opus":0.03862456106017156,"score_gpt":0.2586800958815554,"score_spread":0.22005553482138382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024074370","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":[0.14018722,0.0021938598,0.8462477,0.0021292118,0.00086097524,0.0011759568,0.0000067135147,0.00042292316,0.006775459],"genre_scores_gemma":[0.906325,0.0008518247,0.040169407,0.00009186957,0.00059091736,0.0001585459,0.00007368885,0.00014421609,0.05159455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99306136,0.00071725075,0.0017809964,0.0016158649,0.00092547137,0.0018990232],"domain_scores_gemma":[0.99625176,0.00066799973,0.0009292401,0.0013039663,0.00033664444,0.0005103625],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020861323,0.0009756104,0.00082610984,0.00022144256,0.0023479443,0.0014704807,0.0025996924,0.0004082778,0.00040774696],"category_scores_gemma":[0.00047499023,0.0010828045,0.0004037705,0.00130325,0.0007715769,0.0016044442,0.0013133307,0.0010430523,0.0003288238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032483586,0.00056828925,0.05966366,0.00038921696,0.00009604753,0.00010207932,0.025778854,0.8680281,0.008356716,0.026135828,0.0032687318,0.0075799758],"study_design_scores_gemma":[0.0003226954,0.00041102277,0.0031842731,0.0012148246,0.00008502345,0.00014277613,0.015894413,0.83528775,0.11555807,0.0024400055,0.024324078,0.0011350416],"about_ca_topic_score_codex":0.013697733,"about_ca_topic_score_gemma":0.0013320207,"teacher_disagreement_score":0.80607826,"about_ca_system_score_codex":0.0006416522,"about_ca_system_score_gemma":0.0010906891,"threshold_uncertainty_score":0.9995661},"labels":[],"label_agreement":null},{"id":"W2027648864","doi":"10.2991/agi.2010.22","title":"GQ( ): A general gradient algorithm for temporal-difference prediction learning with eligibility traces","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":109,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Algorithm; Temporal difference learning; Artificial intelligence; Reinforcement learning","score_opus":0.01308984256616065,"score_gpt":0.25791150519595524,"score_spread":0.2448216626297946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027648864","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":[0.13151808,0.0000049181126,0.8664453,0.0001775486,0.0004156128,0.00038063113,0.0000015463083,0.00035614357,0.0007002243],"genre_scores_gemma":[0.44799787,0.0000031155178,0.5469892,0.00005634071,0.00011228266,0.000055115637,0.000012923255,0.000010630149,0.004762543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984556,0.00004132954,0.0002747715,0.00051228737,0.00035459045,0.00036142973],"domain_scores_gemma":[0.9989601,0.00010716689,0.00014543389,0.00049387966,0.00016772236,0.00012574832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045051088,0.00018262387,0.00017067003,0.00007936605,0.00026343274,0.000246102,0.00055795826,0.000086987,0.00001960147],"category_scores_gemma":[0.00007276851,0.00013523665,0.000060444178,0.00021681558,0.000079287034,0.00039208753,0.00010345726,0.0003940005,0.000010300213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005295107,0.0003826831,0.16304357,0.00009862524,0.0001323855,0.000010237077,0.0025718643,0.4418991,0.008004176,0.034007844,0.001271263,0.34852532],"study_design_scores_gemma":[0.00045073146,0.00069196464,0.01398781,0.0000086762975,0.0000082086435,0.000014483729,0.0000243212,0.9795952,0.0014967894,0.0002739739,0.0032665273,0.0001813111],"about_ca_topic_score_codex":0.00007327184,"about_ca_topic_score_gemma":0.000037085094,"teacher_disagreement_score":0.5376961,"about_ca_system_score_codex":0.000032099084,"about_ca_system_score_gemma":0.00007800527,"threshold_uncertainty_score":0.55147904},"labels":[],"label_agreement":null},{"id":"W2027757692","doi":"10.1080/10798587.2005.10642903","title":"Behavior Arbitration using a Fuzzy Reinforcement Learning Approach","year":2005,"lang":"en","type":"article","venue":"Intelligent Automation & Soft Computing","topic":"Reinforcement Learning in Robotics","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":"Computer science; Arbitration; Reinforcement learning; Fuzzy logic; Artificial intelligence; Law","score_opus":0.03712224588085534,"score_gpt":0.29007950211920536,"score_spread":0.25295725623835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2027757692","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":[0.030819843,0.000047792055,0.96257085,0.00009544896,0.0003700177,0.00051170634,1.1096099e-7,0.0011520357,0.0044322275],"genre_scores_gemma":[0.7261389,0.0000038533462,0.27313587,0.0002048205,0.00021827107,0.000011161196,0.00002027918,0.000022451391,0.00024440806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997003,0.00015178666,0.00096555817,0.0005428955,0.00078528834,0.0005514314],"domain_scores_gemma":[0.9983888,0.00013686596,0.0006161092,0.00049296225,0.00023645181,0.00012877987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087120733,0.00031051732,0.0002612322,0.0003239284,0.00057011814,0.0006024687,0.0007627621,0.0001257023,0.000028839455],"category_scores_gemma":[0.00015181873,0.00033718423,0.0001403854,0.00060805364,0.000044293945,0.0010525348,0.00038003354,0.00046439908,0.00019529485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001901371,0.00004499102,0.00063575705,0.000022613785,0.000019260839,0.0000019405245,0.00208343,0.9432879,0.00090628734,0.0076196673,0.000028695857,0.045347523],"study_design_scores_gemma":[0.00019462763,0.00007147799,0.0003842984,0.00006374564,0.000023482877,0.00003909429,0.00010836085,0.9940304,0.0030565786,0.00004257624,0.0016271845,0.00035816195],"about_ca_topic_score_codex":0.000018547998,"about_ca_topic_score_gemma":8.945627e-7,"teacher_disagreement_score":0.69531906,"about_ca_system_score_codex":0.00043386314,"about_ca_system_score_gemma":0.00011274881,"threshold_uncertainty_score":0.99990803},"labels":[],"label_agreement":null},{"id":"W2029155741","doi":"10.1109/siu.2010.5651543","title":"When does feedback not increase capacity for channels with memory?","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Independent and identically distributed random variables; Markov process; Symmetry (geometry); Markov chain; Finite state; Topology (electrical circuits); Channel (broadcasting); Channel capacity; Control theory (sociology); Distributed computing; Algorithm; Theoretical computer science; Mathematics; Random variable; Computer network; Artificial intelligence; Machine learning; Combinatorics; Statistics","score_opus":0.01784659395454224,"score_gpt":0.22661355291017482,"score_spread":0.20876695895563258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029155741","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":[0.056073494,5.8206575e-7,0.93469363,0.0017265207,0.00072522816,0.0003759345,0.0000015993421,0.00024772368,0.006155302],"genre_scores_gemma":[0.52538383,4.3603606e-7,0.4636652,0.00088291784,0.0001634684,0.00003416976,0.000002424661,0.000013105049,0.00985445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988143,0.000021592447,0.00017470807,0.0003477799,0.00029295226,0.00034869328],"domain_scores_gemma":[0.9987034,0.00016978986,0.000095870346,0.0007168923,0.00015887324,0.00015514463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036288748,0.00016111755,0.00015774588,0.00006799547,0.00015174034,0.00027595257,0.00088686106,0.00007453979,0.00012574815],"category_scores_gemma":[0.00012988993,0.00009811584,0.000050293256,0.00011031161,0.00008699371,0.00054143637,0.00018051916,0.00022153698,0.0000729417],"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":[0.0003182739,0.00034834715,0.004738192,0.00037130518,0.00032730022,0.000036433554,0.008999207,0.25716832,0.039964795,0.62637174,0.025913708,0.035442382],"study_design_scores_gemma":[0.0019588624,0.0005068908,0.0008850041,0.000028903698,0.000025897349,0.000033938355,0.00006967442,0.8660126,0.08822157,0.0030908203,0.038408134,0.00075775344],"about_ca_topic_score_codex":0.00019448854,"about_ca_topic_score_gemma":0.00009904877,"teacher_disagreement_score":0.62328094,"about_ca_system_score_codex":0.000016358164,"about_ca_system_score_gemma":0.0000592631,"threshold_uncertainty_score":0.40010476},"labels":[],"label_agreement":null},{"id":"W2034217237","doi":"10.1145/2668956.2668963","title":"On designing migrating agents","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Human–computer interaction; Autonomous agent; Architecture; Distributed computing; Robot; Multi-agent system; Testbed; Avatar; Agent architecture; Artificial intelligence","score_opus":0.02156622164906063,"score_gpt":0.25015359849880964,"score_spread":0.228587376849749,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034217237","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":[0.0018017958,0.0000013135638,0.9183615,0.00016158982,0.00015595199,0.00003890633,6.4127486e-9,0.00018530113,0.07929365],"genre_scores_gemma":[0.7710695,4.3243148e-7,0.22480829,0.0012361209,0.000025730918,0.0000017408007,2.9443564e-7,0.0000044137714,0.002853459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930173,0.00004750802,0.000110198365,0.00016470379,0.00020545369,0.00017043075],"domain_scores_gemma":[0.99939585,0.00017885055,0.00004603846,0.0003146197,0.000019688596,0.000044975925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026384098,0.00006737093,0.00005848558,0.000046676927,0.00009562098,0.0001351493,0.00044344083,0.000021796572,0.00003445264],"category_scores_gemma":[0.00014121992,0.00005653933,0.00002358475,0.00011587072,0.000007952756,0.00015585123,0.000097628,0.00007805577,0.00039790387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.167157e-7,0.000006030059,0.00058715855,0.00000319675,0.000004137615,0.0000012664816,0.00023399484,0.7289649,0.00033890092,0.25092417,0.0033601255,0.015575558],"study_design_scores_gemma":[0.00009523497,0.000093778246,0.0003592262,0.000012944333,7.5161546e-7,9.30412e-7,0.0000053370886,0.9940949,0.0022029933,0.00076689123,0.0022859701,0.00008100624],"about_ca_topic_score_codex":0.000005452898,"about_ca_topic_score_gemma":4.4311673e-7,"teacher_disagreement_score":0.76926774,"about_ca_system_score_codex":0.000015110479,"about_ca_system_score_gemma":0.000007692134,"threshold_uncertainty_score":0.5114382},"labels":[],"label_agreement":null},{"id":"W2034960258","doi":"10.1109/devlrn.2012.6400860","title":"Scaling life-long off-policy learning","year":2012,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Estimator; Artificial intelligence; Scaling; Convergence (economics); Machine learning; Scale (ratio); Value (mathematics); Coding (social sciences); Mathematics; Economics; Economic growth","score_opus":0.030943412808817627,"score_gpt":0.287813299354403,"score_spread":0.25686988654558535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2034960258","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":[0.0012149443,0.00047865525,0.9425294,0.0011073371,0.0014815743,0.0002504562,2.5220308e-7,0.0010544367,0.051882956],"genre_scores_gemma":[0.86641777,0.00028262183,0.11266453,0.00093948643,0.0017937563,0.00002995899,0.000025096893,0.00006851876,0.017778266],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969461,0.00019711457,0.0005861064,0.00071083644,0.00071187364,0.00084799493],"domain_scores_gemma":[0.9973803,0.00024767328,0.0004507656,0.0013807898,0.0001490597,0.00039140144],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00086107134,0.0004349161,0.0004431008,0.00040117936,0.0002488881,0.00082009984,0.0024609375,0.0004199558,0.00013585982],"category_scores_gemma":[0.00096521067,0.0004234183,0.0002242118,0.00037978846,0.00006009888,0.00046820747,0.006291157,0.001916858,0.000823352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010955641,0.000012934578,0.00297847,0.00008680908,0.00005369012,0.000004784163,0.0007368334,0.9479091,0.000010618071,0.023912013,0.00035202687,0.023941603],"study_design_scores_gemma":[0.00016403013,0.000022286586,0.0024278646,0.00015396002,0.00002200224,0.0000095879905,0.000029618112,0.98012346,0.00012356631,0.0004022268,0.015864683,0.00065670686],"about_ca_topic_score_codex":0.00016530455,"about_ca_topic_score_gemma":0.0000015610701,"teacher_disagreement_score":0.86520284,"about_ca_system_score_codex":0.00019681797,"about_ca_system_score_gemma":0.00056954636,"threshold_uncertainty_score":0.99995464},"labels":[],"label_agreement":null},{"id":"W2038818712","doi":"10.1111/j.0824-7935.2004.00252.x","title":"The Advantages of Designing Adaptive Business Agents Using Reputation Modeling Compared to the Approach of Recursive Modeling","year":2004,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reputation; Computer science; Purchasing; Exploit; Reinforcement learning; Quality (philosophy); Risk analysis (engineering); Complex adaptive system; Artificial intelligence; Computer security; Business; Marketing","score_opus":0.1203924856587944,"score_gpt":0.32916524780149004,"score_spread":0.20877276214269563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038818712","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":[0.01648185,0.000134941,0.9824988,0.00016281393,0.0001947315,0.00039898697,0.0000015771942,0.000031873955,0.0000944082],"genre_scores_gemma":[0.6055266,0.0000103127195,0.39438674,0.000037221103,0.00001713911,0.0000064625783,0.0000044697795,0.0000074235572,0.0000036006466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799895,0.00011269599,0.0006665705,0.0003245012,0.0006619087,0.00023536794],"domain_scores_gemma":[0.9975445,0.0003998779,0.00036457868,0.00035282256,0.0012874563,0.000050724666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006514619,0.00016134969,0.00019893263,0.00012855619,0.00038445642,0.00009339595,0.0010973628,0.00003891966,5.7487085e-7],"category_scores_gemma":[0.00028276804,0.00011886874,0.000066013396,0.0009333374,0.000119909535,0.00036788182,0.00028148553,0.00015748126,0.0000041226353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022063614,0.000021512087,0.000010901322,0.000014963751,0.00002813111,6.6746225e-7,0.0045772097,0.9546034,0.000057650945,0.039495587,0.0000016585216,0.001166253],"study_design_scores_gemma":[0.000077524506,0.000043676035,0.000029827317,0.00015937856,0.000012363673,0.000008706319,0.0014506852,0.9800886,0.0005925661,0.017411195,0.0000017097054,0.00012376634],"about_ca_topic_score_codex":0.00010967853,"about_ca_topic_score_gemma":0.0000018732243,"teacher_disagreement_score":0.5890448,"about_ca_system_score_codex":0.00012225144,"about_ca_system_score_gemma":0.00023846536,"threshold_uncertainty_score":0.48473266},"labels":[],"label_agreement":null},{"id":"W2045192098","doi":"10.1109/iat.2006.108","title":"Resolution-Based Policy Search for Imperfect Information Differential Games","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Laval","funders":"","keywords":"Perfect information; Imperfect; Computer science; Discretization; Differential game; Sequential game; Differential (mechanical device); Mathematical optimization; Zero-sum game; Game theory; Nash equilibrium; Mathematical economics; Mathematics","score_opus":0.0111374520453231,"score_gpt":0.2576978047175407,"score_spread":0.24656035267221763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2045192098","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":[0.003304023,0.0000030121628,0.98657215,0.0011642878,0.00013492497,0.00027591438,0.0000017866747,0.00022560195,0.008318326],"genre_scores_gemma":[0.9489229,8.1438674e-7,0.04930655,0.00032066173,0.00017071681,0.000025687466,0.000047787365,0.0000054107823,0.001199501],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899065,0.00003063023,0.00023746067,0.00012789479,0.00029626617,0.000317078],"domain_scores_gemma":[0.9993084,0.00014038563,0.00006059483,0.000319374,0.00012781435,0.00004340975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017166615,0.00009827107,0.000088203604,0.0002520285,0.00015751422,0.0003093906,0.0004271819,0.0000523148,0.000024604758],"category_scores_gemma":[0.000053552107,0.00008536167,0.0000724237,0.00028842443,0.000030132103,0.0006752312,0.00008729096,0.00007443849,0.00007205927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008660631,0.000012372439,0.00053120824,0.000023967845,0.000004336427,1.2097091e-7,0.000060183003,0.76376456,0.0002576734,0.22864005,0.0031737895,0.0035230634],"study_design_scores_gemma":[0.0005281519,0.00010842112,0.0036855224,0.0000056256513,0.0000022185793,7.1487085e-7,0.0000051774787,0.98481846,0.004562768,0.00025274904,0.0059191887,0.000111021036],"about_ca_topic_score_codex":0.00039411528,"about_ca_topic_score_gemma":0.000004682036,"teacher_disagreement_score":0.94561887,"about_ca_system_score_codex":0.00009485179,"about_ca_system_score_gemma":0.00018821447,"threshold_uncertainty_score":0.3480948},"labels":[],"label_agreement":null},{"id":"W2046578831","doi":"10.1109/iros.2005.1545097","title":"Active versus passive expression of preference in the control of multiple-robot decision-making","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Preference; Robot; Expression (computer science); Computer science; Mechanism (biology); Control (management); Quality (philosophy); Artificial intelligence; Human–computer interaction; Mathematics","score_opus":0.033262968542642296,"score_gpt":0.28840695881588035,"score_spread":0.2551439902732381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2046578831","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":[0.03262247,0.000014179652,0.9644201,0.00011671917,0.00010820366,0.00023817539,7.4948963e-7,0.00001900508,0.0024604194],"genre_scores_gemma":[0.90764165,0.000005157271,0.092242956,0.00006469482,0.000016184678,0.000009273262,3.0098158e-7,0.000003354651,0.000016435808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871886,0.00011025817,0.0003474865,0.0001961908,0.00045125833,0.00017594504],"domain_scores_gemma":[0.9964495,0.0026292114,0.00027564014,0.00051285635,0.000111693495,0.000021126873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023546796,0.0001008101,0.00017537562,0.000097790115,0.00003969383,0.000025825688,0.0010757479,0.000053255764,0.000026941017],"category_scores_gemma":[0.00070483313,0.000064315,0.000051470124,0.00025704002,0.000051442817,0.0003841259,0.00018340074,0.00015454946,0.0000072335647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019250897,0.000051841118,0.00082609884,0.000006002172,0.000008943653,0.0000014337136,0.0024439502,0.90044725,0.0030374497,0.004482159,0.000050514394,0.08845184],"study_design_scores_gemma":[0.002245666,0.00022776448,0.01735253,0.00020759398,0.0000060943507,0.0000010577828,0.0004398562,0.9567127,0.022385975,0.00016508497,0.00013844922,0.00011722193],"about_ca_topic_score_codex":0.000012099709,"about_ca_topic_score_gemma":0.000017831351,"teacher_disagreement_score":0.8750192,"about_ca_system_score_codex":0.000037369493,"about_ca_system_score_gemma":0.00004646044,"threshold_uncertainty_score":0.26226896},"labels":[],"label_agreement":null},{"id":"W2047918528","doi":"10.1145/1329125.1329174","title":"Multiagent learning in adaptive dynamic systems","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Laval","funders":"","keywords":"Computer science; Class (philosophy); Set (abstract data type); Interdependence; Reinforcement learning; Artificial intelligence; Exploit; Adaptive learning; Mathematical optimization; Mathematics","score_opus":0.015793344502379895,"score_gpt":0.2588840668079719,"score_spread":0.24309072230559198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047918528","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":[0.004754084,0.00005498611,0.9747266,0.000048501584,0.00035991927,0.00015801638,2.4435419e-8,0.00023818189,0.01965965],"genre_scores_gemma":[0.9599838,0.0000057557168,0.033656854,0.000052188116,0.000013825592,0.0000032840114,7.36563e-7,0.0000072539888,0.0062763044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987996,0.000053504722,0.0002774767,0.00024276758,0.00027342708,0.00035318104],"domain_scores_gemma":[0.99939966,0.00015510038,0.0000817029,0.00025624476,0.000041438976,0.00006587088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008063124,0.00010166907,0.00011534412,0.0001864977,0.000058504076,0.00009354184,0.000454534,0.00005259679,0.0000075432117],"category_scores_gemma":[0.000054073244,0.00009376536,0.000028348972,0.0003591385,0.00001790236,0.0002569644,0.00017884333,0.0002554198,0.0001683449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022257664,0.000009686715,0.0027308841,0.0000049929304,0.0000048416614,0.00003417172,0.0004668577,0.9741478,0.0001431371,0.019146482,0.000027033908,0.0032819023],"study_design_scores_gemma":[0.00020801218,0.000076420416,0.007818366,0.000023288021,8.455562e-7,0.000006440709,0.00031708565,0.99023265,0.00009225381,0.000013036385,0.0010902619,0.000121345816],"about_ca_topic_score_codex":0.00013200441,"about_ca_topic_score_gemma":0.000038267302,"teacher_disagreement_score":0.9552297,"about_ca_system_score_codex":0.00016114922,"about_ca_system_score_gemma":0.00002805624,"threshold_uncertainty_score":0.38236406},"labels":[],"label_agreement":null},{"id":"W2050992779","doi":"10.1103/physreve.67.026706","title":"Convergence of reinforcement learning algorithms and acceleration of learning","year":2003,"lang":"en","type":"article","venue":"Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Acceleration; Reinforcement learning; Convergence (economics); Rate of convergence; Computer science; Conjecture; Algorithm; Relation (database); Popularity; Reinforcement; Mathematical optimization; Mathematics; Applied mathematics; Artificial intelligence; Physics; Discrete mathematics; Quantum mechanics","score_opus":0.01570648697182246,"score_gpt":0.3051240425009342,"score_spread":0.28941755552911175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050992779","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":[0.008035555,0.0014534871,0.9844699,0.0002089721,0.0003086018,0.0003751692,0.0000032253447,0.000059793176,0.0050852876],"genre_scores_gemma":[0.9814409,0.0059924307,0.011657395,0.000038775164,0.00006613887,0.000013856937,0.000041482737,0.000022726294,0.00072626944],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976511,0.0002624106,0.00084741897,0.00047819316,0.00043673557,0.0003241221],"domain_scores_gemma":[0.9984913,0.00044671362,0.0003975369,0.00031084594,0.00019467952,0.00015891195],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036275334,0.0002929064,0.0006938389,0.00005396434,0.00021673701,0.00004693511,0.00028326345,0.00008095045,0.00003084385],"category_scores_gemma":[0.00041190404,0.0002584663,0.00010954683,0.0002529806,0.00035679172,0.0004111167,0.000547247,0.0006453738,0.000012621768],"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":[0.000023153892,0.00019599908,0.0011068142,0.0022367705,0.00019845243,0.000013215798,0.0028169025,0.0794466,0.0020068556,0.87699884,0.0003513749,0.034605023],"study_design_scores_gemma":[0.00056111166,0.0011803805,0.0005753429,0.0011033796,0.00013247757,0.000016861371,0.0001326276,0.9551849,0.0033970333,0.036360133,0.000954773,0.000400983],"about_ca_topic_score_codex":0.0000044286817,"about_ca_topic_score_gemma":1.7477123e-7,"teacher_disagreement_score":0.97340536,"about_ca_system_score_codex":0.000035175333,"about_ca_system_score_gemma":0.00005459569,"threshold_uncertainty_score":0.99998677},"labels":[],"label_agreement":null},{"id":"W2051178751","doi":"10.1145/1160633.1160764","title":"Learning the required number of agents for complex tasks","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Task (project management); Computer science; Reinforcement learning; Perception; Artificial intelligence; Human–computer interaction; Machine learning; Psychology; Engineering","score_opus":0.044996304994496285,"score_gpt":0.3049986134090903,"score_spread":0.260002308414594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051178751","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":[0.0033735128,0.000003213828,0.9486691,0.00047535493,0.00011397001,0.0001800346,2.9900863e-7,0.000092336384,0.04709221],"genre_scores_gemma":[0.8790183,0.00000105187,0.09603672,0.00019391159,0.00004946344,0.0000097649145,0.000007532339,0.000008030548,0.024675192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991187,0.00004456715,0.00024358144,0.00015389203,0.00023191446,0.00020735057],"domain_scores_gemma":[0.9992212,0.00018807923,0.00014389088,0.0003417816,0.00008561549,0.000019441297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027999445,0.00008015691,0.00010653109,0.000022702528,0.00014913178,0.000074568474,0.00066396885,0.000030118854,0.00009723484],"category_scores_gemma":[0.000055438235,0.000055293436,0.00006870387,0.00016544768,0.000051463347,0.0001514691,0.0001677158,0.00007538159,0.000058123907],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000456924,0.00002106465,0.008392035,0.000019204299,0.000018915747,7.7840014e-7,0.00025927462,0.7156903,0.000987779,0.24981207,0.022677744,0.0021162508],"study_design_scores_gemma":[0.00031188194,0.000057331035,0.0070182686,0.000006943285,0.0000053843537,0.000003652237,0.000034918146,0.9269797,0.0005985149,0.0013982642,0.063489035,0.000096063566],"about_ca_topic_score_codex":0.0000743482,"about_ca_topic_score_gemma":0.0000023636871,"teacher_disagreement_score":0.8756448,"about_ca_system_score_codex":0.000016514727,"about_ca_system_score_gemma":0.000018740444,"threshold_uncertainty_score":0.2254801},"labels":[],"label_agreement":null},{"id":"W2055622634","doi":"10.1109/cig.2009.5286455","title":"Improving testing of multi-unit computer players for unwanted behavior using coordination macros","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Macro; Computer science; Unit testing; Competition (biology); Strengths and weaknesses; Limit (mathematics); Resource (disambiguation); Software; Operating system; Programming language","score_opus":0.07838992345998244,"score_gpt":0.3182366372027885,"score_spread":0.23984671374280606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055622634","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":[0.052627083,0.00000379474,0.9464927,0.00003406532,0.00018092556,0.00042391394,0.0000010861226,0.0001654498,0.00007103369],"genre_scores_gemma":[0.46595484,6.665537e-8,0.5338192,0.000070244816,0.000020845438,0.0000028915192,0.000002325287,0.0000054410575,0.00012413581],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99888575,0.00002313807,0.00035612943,0.0002544702,0.0002037139,0.00027681308],"domain_scores_gemma":[0.99891716,0.0001673269,0.00026981303,0.00028121093,0.00031301336,0.000051491057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026508345,0.00013249836,0.00016200307,0.00014433562,0.00015871946,0.00012408898,0.00045544872,0.00006043824,0.0000029669923],"category_scores_gemma":[0.00012715421,0.0001307354,0.000055518747,0.00035452272,0.00002646194,0.00043897147,0.00011100482,0.000093850125,0.0000018888244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005224498,0.00007766494,0.0052060666,0.000033157896,0.000009516209,0.0000033805152,0.00023427473,0.77055866,0.10992913,0.002032278,0.000026937867,0.11188369],"study_design_scores_gemma":[0.0006561194,0.000256076,0.0046861805,0.000033875243,0.000014714335,0.000008253082,0.000017199764,0.97949773,0.014649985,0.0000098552255,0.000017924838,0.0001520984],"about_ca_topic_score_codex":0.00003788487,"about_ca_topic_score_gemma":0.000001244163,"teacher_disagreement_score":0.41332775,"about_ca_system_score_codex":0.000049301576,"about_ca_system_score_gemma":0.00005831514,"threshold_uncertainty_score":0.5331235},"labels":[],"label_agreement":null},{"id":"W2055921164","doi":"10.1007/s10458-012-9200-2","title":"A survey of point-based POMDP solvers","year":2012,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":433,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Markov decision process; Computer science; Bellman equation; Function (biology); Observable; Value (mathematics); Point (geometry); State space; Mathematical optimization; Theoretical computer science; Space (punctuation); Scale (ratio); Markov chain; Markov process; Mathematics; Markov model; Machine learning","score_opus":0.06430470677447479,"score_gpt":0.28584377584545256,"score_spread":0.22153906907097776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055921164","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":[0.05566288,0.000502663,0.94075906,0.00004546454,0.0018558758,0.0005434519,0.000012730497,0.0001311061,0.00048676413],"genre_scores_gemma":[0.9934121,0.000017270515,0.0053309817,0.00013101747,0.0000355932,0.000018086454,0.00001985863,0.00001945481,0.0010156432],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99806863,0.00023435,0.0005365442,0.0003106401,0.0003368746,0.00051296566],"domain_scores_gemma":[0.9985338,0.00013642237,0.00036756974,0.0006006775,0.00011660068,0.0002449627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012161357,0.00022240492,0.0003408771,0.000140295,0.00012836228,0.0001267125,0.0005132077,0.00009352862,0.000014104096],"category_scores_gemma":[0.00007851667,0.00019794652,0.000072166775,0.00020902036,0.000059284397,0.0004050514,0.00020021645,0.00011148414,0.00006527548],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000132826835,0.000477245,0.7583708,0.00038785758,0.00024423888,0.000013375568,0.0037265634,0.22626781,0.00063388946,0.0026971267,0.0038552473,0.0033125666],"study_design_scores_gemma":[0.00076743105,0.00007488515,0.2529084,0.00005041674,0.0000140188995,0.0000051588654,0.00006118571,0.741416,0.00018933094,2.886011e-7,0.0042845504,0.00022836482],"about_ca_topic_score_codex":0.0018676431,"about_ca_topic_score_gemma":0.000012816754,"teacher_disagreement_score":0.9377492,"about_ca_system_score_codex":0.00008877759,"about_ca_system_score_gemma":0.000085583146,"threshold_uncertainty_score":0.80720246},"labels":[],"label_agreement":null},{"id":"W2060652090","doi":"10.1142/s0129183104006662","title":"REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES","year":2004,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Reinforcement Learning in Robotics","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 Lethbridge","funders":"","keywords":"Reinforcement learning; TRACE (psycholinguistics); Computer science; Reinforcement; Artificial intelligence; Mechanism (biology); Machine learning; Psychology","score_opus":0.014142522122078973,"score_gpt":0.27601330258619006,"score_spread":0.2618707804641111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060652090","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":[0.038393497,0.000035315225,0.9587401,0.000794095,0.00039093895,0.00006376076,2.6094514e-7,0.00007552104,0.0015064733],"genre_scores_gemma":[0.96365416,0.000028604976,0.035738736,0.00013478435,0.0002481162,0.000001538442,0.0000028553152,0.0000114601235,0.0001797684],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979337,0.000039249844,0.00046263807,0.0001809993,0.0011930648,0.0001903871],"domain_scores_gemma":[0.9980654,0.000072594645,0.00066270673,0.00021156736,0.00090130593,0.00008639698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030226377,0.0001499368,0.00018779778,0.000097316486,0.0000723499,0.00022789527,0.0011699712,0.000035866928,0.000006654746],"category_scores_gemma":[0.000078776815,0.000121061545,0.00010925271,0.0001535023,0.000049086786,0.0010109737,0.00014007826,0.00040259596,0.00001409244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050887873,0.00005814593,0.0007466875,0.000003840474,0.00014991467,0.00004197241,0.0009918751,0.9785616,0.0010042944,0.0071223434,0.000025449875,0.011242989],"study_design_scores_gemma":[0.0030087377,0.00076615805,0.0019133933,0.00025682044,0.000029778277,0.00021069242,0.000047388374,0.95138437,0.011764047,0.029276026,0.0009915489,0.00035102433],"about_ca_topic_score_codex":0.0000136998315,"about_ca_topic_score_gemma":0.0000015560812,"teacher_disagreement_score":0.92526066,"about_ca_system_score_codex":0.00024438332,"about_ca_system_score_gemma":0.00022138782,"threshold_uncertainty_score":0.49367464},"labels":[],"label_agreement":null},{"id":"W2064203730","doi":"10.5555/777092.777139","title":"Greedy linear value-approximation for factored Markov decision processes","year":2002,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Markov decision process; Bellman equation; Mathematical optimization; Linear programming; Computer science; Dynamic programming; Basis (linear algebra); Set (abstract data type); Linear approximation; Approximation error; Approximation algorithm; Function (biology); Value (mathematics); Function approximation; Markov process; Mathematics; Artificial intelligence; Nonlinear system; Artificial neural network","score_opus":0.03629519433379755,"score_gpt":0.266278795498935,"score_spread":0.22998360116513747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2064203730","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":[0.001101432,0.000035011763,0.9926317,0.00035524598,0.00022998727,0.0003870401,6.44676e-7,0.00027594517,0.0049830284],"genre_scores_gemma":[0.20399797,0.000025860963,0.7908021,0.0002441861,0.000075951524,0.00003152013,0.000006102603,0.000013652172,0.0048026177],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998827,0.000016988824,0.00026132472,0.00029322738,0.00035746302,0.00024403613],"domain_scores_gemma":[0.9988984,0.00032079316,0.000106728774,0.00040068038,0.00020887615,0.00006451199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000192358,0.0001258902,0.00012006607,0.00009667777,0.00013468346,0.00017816939,0.0006357001,0.00006442634,0.000091523514],"category_scores_gemma":[0.0005385348,0.00010341506,0.000047898317,0.0003608294,0.000018793082,0.0006798207,0.0001242405,0.00006974959,0.0001344098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031394025,0.00019278728,0.0014743964,0.00039906864,0.000051248364,0.0000038976777,0.0019959244,0.72201675,0.00047475472,0.044897348,0.023849938,0.20461248],"study_design_scores_gemma":[0.00035443637,0.00013405856,0.00017845003,0.000022546566,0.0000040625664,0.0000028261675,0.000011469815,0.98959297,0.0013217302,0.0008697044,0.0073636407,0.00014413072],"about_ca_topic_score_codex":0.000003864592,"about_ca_topic_score_gemma":0.0000010898051,"teacher_disagreement_score":0.2675762,"about_ca_system_score_codex":0.00003494412,"about_ca_system_score_gemma":0.000023211021,"threshold_uncertainty_score":0.4217144},"labels":[],"label_agreement":null},{"id":"W2066471519","doi":"10.3166/ria.21.9-33","title":"Apprentissage actif dans les processus décisionnels de Markov partiellement observables L'algorithme MEDUSA","year":2007,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Physics; Philosophy","score_opus":0.07443563189771293,"score_gpt":0.3055678652788824,"score_spread":0.23113223338116948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2066471519","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":[0.010591493,0.003929059,0.96425104,0.0029887974,0.0034318082,0.00081187434,0.000011392259,0.0002750314,0.013709523],"genre_scores_gemma":[0.75930065,0.0019928522,0.119316384,0.00030086713,0.00095568266,0.00006779921,0.000029901763,0.00012015925,0.11791569],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993311,0.0002947394,0.0018124386,0.0013423174,0.0009972706,0.0022422415],"domain_scores_gemma":[0.9954654,0.0010482585,0.0006799899,0.0016581081,0.00047923892,0.00066897995],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003868595,0.0007119694,0.000613683,0.00028414873,0.00091471075,0.00076863164,0.0025319923,0.00048019472,0.001548883],"category_scores_gemma":[0.0006981575,0.0007924455,0.000338113,0.0016802256,0.0005352345,0.0010211935,0.00093527435,0.0009816055,0.0011259345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037239748,0.00036183404,0.0020198477,0.00042130816,0.000067993686,0.00023120447,0.014378045,0.6118654,0.0027694516,0.009421881,0.0019111265,0.35651463],"study_design_scores_gemma":[0.00010377753,0.00033018112,0.00035044242,0.00073098176,0.00007517634,0.00015408394,0.0074016233,0.78467757,0.10175475,0.0009852335,0.10270273,0.00073345867],"about_ca_topic_score_codex":0.00036696217,"about_ca_topic_score_gemma":0.00015983576,"teacher_disagreement_score":0.84493464,"about_ca_system_score_codex":0.00057880586,"about_ca_system_score_gemma":0.00039525086,"threshold_uncertainty_score":0.9996518},"labels":[],"label_agreement":null},{"id":"W2067564749","doi":"10.1142/s0218213012500030","title":"STOCHASTIC RESOURCE ALLOCATION IN MULTIAGENT ENVIRONMENTS: AN APPROACH BASED ON DISTRIBUTED Q-VALUES AND BOUNDED REAL-TIME DYNAMIC PROGRAMMING","year":2012,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence Tools","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Computer science; Bounded function; A priori and a posteriori; Mathematical optimization; Heuristic; Convergence (economics); Set (abstract data type); Multi-agent system; Distributed computing; Resource allocation; Dynamic programming; Distributed algorithm; Resource (disambiguation); Reduction (mathematics); Algorithm; Artificial intelligence; Mathematics","score_opus":0.03907911182316321,"score_gpt":0.3112756167984046,"score_spread":0.2721965049752414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067564749","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":[0.054620292,0.000018646573,0.94443005,0.00037475812,0.00026997057,0.00019462919,0.000002973031,0.000022580074,0.00006608905],"genre_scores_gemma":[0.92714655,0.000010658786,0.072545186,0.0000945936,0.000121354526,0.000008305212,0.000037381615,0.0000119449505,0.000024027278],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770933,0.00016784712,0.0007573171,0.0002247794,0.0008439124,0.00029680578],"domain_scores_gemma":[0.9987251,0.000258652,0.00047466884,0.00023977182,0.00014493718,0.00015685978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012205832,0.00016718011,0.00018488576,0.0003198959,0.00007386302,0.00040462724,0.00082588615,0.00006923993,0.000015387397],"category_scores_gemma":[0.0005052697,0.0001580124,0.00006236262,0.00017900605,0.0000993965,0.0012149577,0.00010451143,0.00026880862,0.000021175538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009170237,0.00041247127,0.00018094333,0.000003488767,0.000028415961,0.000008793347,0.0009957398,0.8813365,0.0013052891,0.0030206938,0.0000048033526,0.11261116],"study_design_scores_gemma":[0.000106455984,0.00025061582,0.0024065396,0.00007362416,0.000009782869,0.000024442561,0.00035736422,0.99482,0.0010856488,0.0005928483,0.00011587523,0.00015680343],"about_ca_topic_score_codex":0.000012708785,"about_ca_topic_score_gemma":0.0000011787647,"teacher_disagreement_score":0.8725262,"about_ca_system_score_codex":0.00035706247,"about_ca_system_score_gemma":0.000056815355,"threshold_uncertainty_score":0.64435583},"labels":[],"label_agreement":null},{"id":"W2069891133","doi":"10.1109/ciisp.2007.369176","title":"Application of Opposition-Based Reinforcement Learning in Image Segmentation","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":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; Image segmentation; Artificial intelligence; Segmentation; Exploit; Computer vision; Image texture; Pattern recognition (psychology); Computer security","score_opus":0.009708222293382411,"score_gpt":0.26751706800371006,"score_spread":0.25780884571032764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069891133","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":[0.0032506997,0.000002883585,0.9876738,0.00013166161,0.000038361843,0.00023126396,3.1543355e-8,0.00009242961,0.008578823],"genre_scores_gemma":[0.8489859,0.0000011690848,0.15065052,0.0001267183,0.000008097576,0.000009063336,0.000014175533,0.0000042354245,0.00020012943],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989616,0.000026652675,0.00037510655,0.00016575937,0.00029407942,0.00017678112],"domain_scores_gemma":[0.99936646,0.000108096065,0.00017781288,0.0002318047,0.00007929585,0.00003652638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000658952,0.00007570636,0.0000854185,0.00021273429,0.00004214527,0.000033746004,0.00026244443,0.000035454166,0.00002069995],"category_scores_gemma":[0.000029169694,0.00007814835,0.000028007138,0.00040826632,0.0000225984,0.00031421953,0.000051855306,0.0001005777,0.000028836055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054003326,0.000015073443,0.0047627576,0.000016242864,0.000002374786,0.0000011126043,0.00016518458,0.9382103,0.040127337,0.009799284,0.000011234923,0.006883717],"study_design_scores_gemma":[0.00036257613,0.00008702958,0.00428788,0.000011974168,0.0000016257343,4.4831037e-7,0.000054585926,0.89599264,0.09898376,0.00004574405,0.00009430946,0.000077435165],"about_ca_topic_score_codex":0.00007552957,"about_ca_topic_score_gemma":0.000006976561,"teacher_disagreement_score":0.8457352,"about_ca_system_score_codex":0.00010143228,"about_ca_system_score_gemma":0.000036838053,"threshold_uncertainty_score":0.31867972},"labels":[],"label_agreement":null},{"id":"W2071814471","doi":"10.1145/1102351.1102472","title":"Bayesian sparse sampling for on-line reward optimization","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":122,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Machine learning; Bayesian probability; Sampling (signal processing); Action selection; Artificial intelligence; Bayesian optimization; Thompson sampling; Selection (genetic algorithm); Bayesian inference; Mathematical optimization; Mathematics","score_opus":0.06390024574608347,"score_gpt":0.30902289421512674,"score_spread":0.24512264846904327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071814471","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":[0.000022254706,0.000004492104,0.9897553,0.0025270595,0.00019195794,0.00020532985,2.935994e-7,0.00023931137,0.007054018],"genre_scores_gemma":[0.07929439,0.0000058868454,0.9159237,0.0012709338,0.00017486932,0.000010566899,0.0000071685477,0.0000103592665,0.00330213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991587,0.00001248374,0.00019998912,0.00023490479,0.00017518828,0.0002187774],"domain_scores_gemma":[0.9993139,0.00011593558,0.00006806522,0.0003744966,0.000067035355,0.00006054727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044868,0.00009482022,0.000089491834,0.00007857605,0.00010506554,0.00013084621,0.00040512942,0.000043167067,0.00006110704],"category_scores_gemma":[0.00009804495,0.00008619505,0.000044007556,0.0001499227,0.00001064408,0.00029951168,0.00007143758,0.000066790104,0.00006296292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038343014,0.0000115669245,0.00001825008,0.0000035351707,0.000004326756,1.7635195e-7,0.00006200455,0.96434784,0.000008761928,0.025228476,0.00067535276,0.009635856],"study_design_scores_gemma":[0.00026830434,0.00013549987,0.000007431322,0.000010678841,0.0000026029998,0.0000012944556,0.000004501995,0.98394537,0.00043381113,0.000117138254,0.01496264,0.00011073292],"about_ca_topic_score_codex":0.0000018029175,"about_ca_topic_score_gemma":0.0000012537653,"teacher_disagreement_score":0.079272136,"about_ca_system_score_codex":0.000047711274,"about_ca_system_score_gemma":0.00002682212,"threshold_uncertainty_score":0.35149318},"labels":[],"label_agreement":null},{"id":"W2073549596","doi":"10.1109/icsmc.2012.6378016","title":"Acquiring a broad range of empirical knowledge in real time by temporal-difference learning","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Generality; Robot; Computer science; Mobile robot; Set (abstract data type); Range (aeronautics); Artificial intelligence; Interface (matter); Robot learning; Human–computer interaction; Engineering","score_opus":0.036091105780360115,"score_gpt":0.31493739586074165,"score_spread":0.27884629008038153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073549596","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":[0.37865886,0.00018260164,0.5777215,0.00012366498,0.00016207117,0.00017050501,2.711407e-7,0.00026008254,0.042720474],"genre_scores_gemma":[0.9744076,0.000017872233,0.012981054,0.000036955516,0.000039705075,0.000006217104,0.0000028888753,0.000011967203,0.012495753],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843276,0.00017040173,0.00038971004,0.00024730898,0.00027555155,0.00048426434],"domain_scores_gemma":[0.99909854,0.00023458301,0.00013887018,0.00034654993,0.0000514276,0.0001300199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006072391,0.00015789871,0.0002610106,0.00014528396,0.000055249824,0.000050332328,0.0006611092,0.000095831354,0.00008863515],"category_scores_gemma":[0.000098068944,0.00014097337,0.000054203676,0.00047008428,0.000059410562,0.00047542359,0.000428144,0.0002538243,0.0002671576],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011174021,0.00017839014,0.9668031,0.00004929042,0.00001589129,0.0000023017096,0.005271791,0.009023541,0.006828182,0.0015527057,0.00232488,0.007938761],"study_design_scores_gemma":[0.00095482095,0.00023822158,0.1595374,0.00010591283,0.000007423093,0.000007945555,0.00011417719,0.83150584,0.002566717,0.00002985141,0.004451754,0.0004799392],"about_ca_topic_score_codex":0.00009343362,"about_ca_topic_score_gemma":0.0000031378142,"teacher_disagreement_score":0.8224823,"about_ca_system_score_codex":0.000071221446,"about_ca_system_score_gemma":0.00004713416,"threshold_uncertainty_score":0.57487273},"labels":[],"label_agreement":null},{"id":"W2074304756","doi":"10.1109/ssrr.2013.6719367","title":"Learning to cooperate together: A semi-autonomous control architecture for multi-robot teams in urban search and rescue","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Urban search and rescue; Search and rescue; Rescue robot; Robot; Reinforcement learning; Task (project management); Computer science; Identification (biology); Architecture; Human–computer interaction; Control (management); Collision avoidance; Artificial intelligence; Mobile robot; Computer security; Engineering; Collision; Systems engineering","score_opus":0.01678453592790917,"score_gpt":0.263294230890312,"score_spread":0.24650969496240283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074304756","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":[0.08955602,0.00003367937,0.90690506,0.0016369063,0.00007279567,0.0013372368,6.0901834e-7,0.00016809432,0.00028958748],"genre_scores_gemma":[0.8288156,0.000004046691,0.16239332,0.001079955,0.00004012966,0.00015890124,0.0000020871364,0.000023840023,0.0074821236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998172,0.00016184193,0.00032013556,0.00052159623,0.00021268781,0.0006117454],"domain_scores_gemma":[0.9989946,0.00022964865,0.000030232231,0.0003874289,0.00014807105,0.00021003898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057751336,0.00021320996,0.00027568743,0.00021431476,0.00016241138,0.0004367284,0.0006050741,0.000099956786,0.00003072241],"category_scores_gemma":[0.0002448589,0.00017821483,0.00004445114,0.0003156467,0.00004692336,0.00026712514,0.00028034323,0.0004379972,0.000093095434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012768543,0.000018335462,0.0039217025,0.0000193357,0.000014018344,0.0000026005923,0.0038552738,0.9750481,0.0032219838,0.00069374335,0.00015131867,0.013040803],"study_design_scores_gemma":[0.0014981199,0.00044837108,0.0039686994,0.000032711512,0.0000027982603,0.000007534356,0.0002040206,0.99139804,0.0005970503,0.000013715805,0.0015785678,0.00025040007],"about_ca_topic_score_codex":0.0007758273,"about_ca_topic_score_gemma":0.00015697839,"teacher_disagreement_score":0.7445117,"about_ca_system_score_codex":0.00007661319,"about_ca_system_score_gemma":0.000076500495,"threshold_uncertainty_score":0.726739},"labels":[],"label_agreement":null},{"id":"W2074458475","doi":"10.1016/j.engappai.2007.05.006","title":"A machine-learning approach to multi-robot coordination","year":2007,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":81,"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":"Computer science; Reinforcement learning; Robot; Probabilistic logic; Scheme (mathematics); Task (project management); Object (grammar); Artificial intelligence; Robot learning; Genetic algorithm; Distributed computing; Mobile robot; Machine learning","score_opus":0.03084198381141881,"score_gpt":0.280624133256297,"score_spread":0.24978214944487817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2074458475","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":[0.00025380924,0.00003944448,0.99817234,0.00008368377,0.00008943698,0.00041046645,6.591159e-7,0.0002920957,0.0006580834],"genre_scores_gemma":[0.54080886,0.0000023095242,0.45898083,0.000011192362,0.00003030447,0.00004479603,0.0000041116828,0.00001039532,0.00010716414],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986209,0.000013391072,0.00048638647,0.00032143714,0.0002682117,0.00028964467],"domain_scores_gemma":[0.99894595,0.00015345092,0.0001225927,0.0004829246,0.00017557196,0.000119479715],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068883906,0.00014283066,0.0001440209,0.00035419376,0.00010841279,0.000070258466,0.0008503233,0.00006252024,0.0000035499845],"category_scores_gemma":[0.00021922578,0.00016250808,0.000052364263,0.001266065,0.00002733408,0.0001707022,0.00016832854,0.00023206306,0.00009075386],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016150043,0.000050669594,0.000034249777,0.00001586123,0.000006450026,2.0268055e-7,0.00042737392,0.81719273,0.0063394993,0.14605589,0.0000029992857,0.029872471],"study_design_scores_gemma":[0.000014104402,0.00003713151,0.00014593654,0.000011316379,0.000003584992,0.0000025844015,0.00006196194,0.962454,0.0349944,0.00014322659,0.0019723617,0.00015938557],"about_ca_topic_score_codex":0.000032400385,"about_ca_topic_score_gemma":0.0000015349258,"teacher_disagreement_score":0.54055506,"about_ca_system_score_codex":0.00006155588,"about_ca_system_score_gemma":0.000020561622,"threshold_uncertainty_score":0.6626887},"labels":[],"label_agreement":null},{"id":"W2077559824","doi":"10.1287/opre.1090.0705","title":"Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes","year":2009,"lang":"en","type":"article","venue":"Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"GAVI Alliance","keywords":"Markov decision process; Monotone polygon; Mathematical optimization; Algorithm; Convergence (economics); Markov chain; Operator (biology); Mathematics; Computer science; Dynamic programming; Contraction (grammar); Acceleration; Linear programming; Markov process","score_opus":0.10822638641660903,"score_gpt":0.42880517446279043,"score_spread":0.3205787880461814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2077559824","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":[0.009757719,0.0000673095,0.9818187,0.0057702656,0.000105772706,0.0012870256,0.0000015119882,0.0000402798,0.0011514447],"genre_scores_gemma":[0.8128249,0.00008020664,0.18509606,0.0007144877,0.00016124222,0.00033018296,0.00004814017,0.000008973081,0.00073583465],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977187,0.0003241357,0.0003447509,0.0003712643,0.00086636865,0.00037476543],"domain_scores_gemma":[0.9979531,0.00059941225,0.000019266816,0.0005584999,0.00082908035,0.0000406373],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0028564443,0.00011280189,0.000102523554,0.00036786147,0.0009367064,0.0022530328,0.0011440108,0.000076192664,0.000013433677],"category_scores_gemma":[0.0014550589,0.000081646765,0.00002917321,0.0017628096,0.00003673348,0.0015463609,0.00008199775,0.00031495857,0.00003683981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012026436,0.00009530191,0.00006697046,0.000013169794,0.0000030627004,0.000002884918,0.0026387835,0.89757675,0.00085499056,0.046758115,0.0023390495,0.049638905],"study_design_scores_gemma":[0.0003521733,0.00035640004,0.0011136219,0.000036246125,0.0000012755589,0.000005072714,0.00015705412,0.9922379,0.0012685873,0.00077928597,0.0035832785,0.000109095046],"about_ca_topic_score_codex":0.000028891267,"about_ca_topic_score_gemma":0.00007713408,"teacher_disagreement_score":0.80306715,"about_ca_system_score_codex":0.00011348617,"about_ca_system_score_gemma":0.0003894376,"threshold_uncertainty_score":0.9987827},"labels":[],"label_agreement":null},{"id":"W2081102656","doi":"10.1007/s00186-013-0432-y","title":"Accelerated modified policy iteration algorithms for Markov decision processes","year":2013,"lang":"en","type":"article","venue":"Mathematical Methods of Operations Research","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Markov decision process; Convergence (economics); Markov chain; Operator (biology); Mathematical optimization; Computer science; Markov process; Algorithm; Markov model; Partially observable Markov decision process; Mathematics; Machine learning; Statistics","score_opus":0.2714919902690478,"score_gpt":0.5351392337457531,"score_spread":0.2636472434767053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081102656","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":[0.0014791632,0.000025748588,0.9927419,0.001796239,0.000052774907,0.0016468198,0.0000023069788,0.0000715109,0.002183577],"genre_scores_gemma":[0.037627295,0.000015015855,0.95979697,0.000056565084,0.000070086295,0.0007448823,0.000008815873,0.000018634812,0.0016617294],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99712586,0.0005769469,0.00067787257,0.00037550673,0.00078388804,0.0004598962],"domain_scores_gemma":[0.9920178,0.0041485275,0.000054266446,0.00073254615,0.0028973897,0.00014946715],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0038549218,0.0001494421,0.0002891806,0.00058721454,0.0004163149,0.00096454273,0.0009913023,0.00011873237,0.00014851733],"category_scores_gemma":[0.016072698,0.00011818085,0.00006259329,0.0017486213,0.00013839558,0.0010838667,0.00037060236,0.00025756643,0.00009018952],"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":[0.000017232156,0.0003090999,0.000005713352,0.0005840243,0.000049197868,6.835875e-7,0.0017689595,0.25402,0.015944267,0.48225287,0.0011529389,0.243895],"study_design_scores_gemma":[0.00027037752,0.00019787096,0.00003067011,0.00007225565,0.0000030672943,0.000003448513,0.00005790544,0.92052853,0.014937962,0.06361915,0.00016644322,0.00011231133],"about_ca_topic_score_codex":0.000043680604,"about_ca_topic_score_gemma":0.0000014491599,"teacher_disagreement_score":0.66650856,"about_ca_system_score_codex":0.000082107465,"about_ca_system_score_gemma":0.00046786544,"threshold_uncertainty_score":0.99221534},"labels":[],"label_agreement":null},{"id":"W2081239738","doi":"10.1109/adprl.2007.368191","title":"Opposition-Based Reinforcement Learning in the Management of Water Resources","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Exploit; Bellman equation; Opposition (politics); Artificial intelligence; Action learning; Operations research; Mathematical optimization; Engineering; Computer security; Mathematics; Law; Political science; Cooperative learning","score_opus":0.014481531006971042,"score_gpt":0.24468272489647908,"score_spread":0.23020119388950802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2081239738","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":[0.016029067,0.00000623655,0.92316794,0.000597233,0.000055643257,0.0001957093,1.2616124e-8,0.000061373874,0.059886776],"genre_scores_gemma":[0.9754455,0.0000030838441,0.02235682,0.00052788865,0.000011320277,0.000006694106,0.0000033187484,0.0000046663877,0.0016407048],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856895,0.000058612462,0.00036411374,0.00017182564,0.00051821425,0.0003182952],"domain_scores_gemma":[0.9993427,0.0001058604,0.00007520435,0.0004123402,0.00003548228,0.000028425142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016990468,0.00009792598,0.00009168841,0.0001557685,0.00009052708,0.000076278964,0.00083158567,0.000031136016,0.00005163805],"category_scores_gemma":[0.000004667862,0.000057499332,0.000045547276,0.00027782386,0.000034814806,0.00013926964,0.00016411612,0.00015049237,0.00003761972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072047387,0.00001682899,0.00077639986,0.00003490867,0.000012849025,0.000022386575,0.0018176291,0.9774881,0.00027653368,0.017699093,0.000035540423,0.0018125332],"study_design_scores_gemma":[0.0009884123,0.00035322606,0.0069597573,0.00013080408,0.000015128141,0.0000039751662,0.0013477452,0.9486541,0.026443172,0.00017544333,0.014659108,0.0002690987],"about_ca_topic_score_codex":0.000029737714,"about_ca_topic_score_gemma":0.0000026632208,"teacher_disagreement_score":0.95941645,"about_ca_system_score_codex":0.000038294587,"about_ca_system_score_gemma":0.0000062498807,"threshold_uncertainty_score":0.23447546},"labels":[],"label_agreement":null},{"id":"W2082315153","doi":"10.1109/acii.2013.43","title":"Event-Driven Fuzzy Automata for Tracking Changes in the Emotional Behavior of Affective Agents","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Windsor","funders":"","keywords":"Automaton; Transition (genetics); Fuzzy logic; Arousal; Event (particle physics); Computer science; Pleasure; Dominance (genetics); Finite-state machine; Transition system; Artificial intelligence; Psychology; Cognitive psychology; Theoretical computer science; Social psychology; Algorithm; Physics","score_opus":0.04215215203548606,"score_gpt":0.3034167299870698,"score_spread":0.26126457795158375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082315153","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":[0.15790915,0.000004493707,0.8380144,0.0011738911,0.00021239385,0.0012112042,0.0000017389318,0.00005031691,0.0014223973],"genre_scores_gemma":[0.97984743,0.000001971917,0.01949981,0.00019388091,0.000026882506,0.0001793122,0.000004330202,0.0000052120213,0.00024115837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991516,0.000063710846,0.00015880195,0.00016646711,0.00027297405,0.00018647301],"domain_scores_gemma":[0.99932194,0.00019688737,0.00010102306,0.00026894148,0.00008929712,0.000021923574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026007538,0.00008303709,0.00009995764,0.00008602332,0.00005581116,0.00008232031,0.0007055572,0.00003767743,0.000045543595],"category_scores_gemma":[0.00005494336,0.00005830323,0.000042365806,0.00019938129,0.000026667909,0.00025274628,0.0001130655,0.00007435594,0.000020376556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012933976,0.0010673922,0.09882424,0.00023583713,0.00012309483,0.000014452633,0.018075312,0.5201497,0.014191309,0.17073984,0.011480695,0.16508521],"study_design_scores_gemma":[0.00045849316,0.00022707488,0.34905097,0.000035893845,0.0000080309155,0.000004542677,0.00019674037,0.6479697,0.0013742963,0.00042678014,0.00013618554,0.00011130429],"about_ca_topic_score_codex":0.000050127015,"about_ca_topic_score_gemma":0.000029211158,"teacher_disagreement_score":0.8219383,"about_ca_system_score_codex":0.000030125157,"about_ca_system_score_gemma":0.00002344816,"threshold_uncertainty_score":0.23775367},"labels":[],"label_agreement":null},{"id":"W2085404981","doi":"10.3166/ria.20.311-344","title":"Étude de différentes combinaisons de comportements adaptatives","year":2006,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","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":"Psychology","score_opus":0.05580141030256195,"score_gpt":0.2918191637190429,"score_spread":0.23601775341648093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085404981","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":[0.011587038,0.0032998559,0.9670631,0.0053280997,0.0013936033,0.00039782203,0.00000862007,0.00019990977,0.010721903],"genre_scores_gemma":[0.9156862,0.00049057754,0.034149077,0.0004846662,0.00029300456,0.000034432644,0.000020991365,0.000050322895,0.048790723],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960577,0.00034507283,0.0010141126,0.0007344182,0.00045099074,0.0013977193],"domain_scores_gemma":[0.99759054,0.00049946934,0.00045447957,0.00094645674,0.00022842427,0.00028062265],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009539189,0.00044896992,0.00043683755,0.00018262753,0.00048766172,0.0005371415,0.0014417279,0.0002070093,0.00039946876],"category_scores_gemma":[0.00019708302,0.0005349417,0.00024679233,0.0007969647,0.0005100424,0.0008186465,0.00045622696,0.0005827378,0.0012150576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008484623,0.0004757811,0.0057902774,0.00013778487,0.000043344295,0.00010269526,0.002408427,0.8119689,0.0018708565,0.16655472,0.003440724,0.007197978],"study_design_scores_gemma":[0.00011058768,0.00028381223,0.0020781655,0.0004940374,0.000047340513,0.00009593569,0.0008275317,0.93428767,0.029407483,0.006055489,0.025806906,0.00050507346],"about_ca_topic_score_codex":0.001434185,"about_ca_topic_score_gemma":0.0000887726,"teacher_disagreement_score":0.9329141,"about_ca_system_score_codex":0.00036456838,"about_ca_system_score_gemma":0.0002536002,"threshold_uncertainty_score":0.9997102},"labels":[],"label_agreement":null},{"id":"W2086608109","doi":"10.1109/tnn.2011.2168422","title":"Hierarchical Approximate Policy Iteration With Binary-Tree State Space Decomposition","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Markov decision process; Reinforcement learning; Kernel (algebra); State space; Mathematical optimization; Tree (set theory); Algorithm; Markov process; Artificial intelligence; Mathematics","score_opus":0.018154263890840724,"score_gpt":0.24563729892052735,"score_spread":0.22748303502968664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086608109","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":[0.011307326,0.0000067701776,0.9861984,0.00059807824,0.0004364973,0.00029801493,0.0000015643078,0.00037446644,0.00077886414],"genre_scores_gemma":[0.9660975,0.000026066087,0.032928232,0.00039583107,0.00007619476,0.000035290654,0.000004774608,0.000026969643,0.00040918338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840635,0.0001340119,0.0002711058,0.00041957572,0.00030972285,0.00045924113],"domain_scores_gemma":[0.9990567,0.00007790827,0.000115409755,0.00051743595,0.00006817144,0.00016436483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011360829,0.0002494207,0.00017322184,0.0002620808,0.00033139376,0.00019035288,0.0004452183,0.000087625376,0.00002012242],"category_scores_gemma":[0.0000015492614,0.00021445715,0.000081816346,0.00068679545,0.00008787551,0.000758876,0.0000058666446,0.0005506611,0.000022338669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011996233,0.0000817185,0.00002619478,0.000006725684,0.000024578121,0.000024216919,0.00051212084,0.98001635,0.00016235177,0.0011179372,0.000033714266,0.017874144],"study_design_scores_gemma":[0.00044707026,0.0008184926,0.00045851863,0.00003313038,0.000013974233,0.00005217161,0.000005336851,0.995848,0.0018894908,0.00015453226,0.00003334471,0.00024596116],"about_ca_topic_score_codex":0.000047067464,"about_ca_topic_score_gemma":0.00002393523,"teacher_disagreement_score":0.9547901,"about_ca_system_score_codex":0.000079822814,"about_ca_system_score_gemma":0.000039158516,"threshold_uncertainty_score":0.87453085},"labels":[],"label_agreement":null},{"id":"W2086813915","doi":"10.1007/s10846-009-9380-4","title":"A Reinforcement Learning Adaptive Fuzzy Controller for Differential Games","year":2009,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"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; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Differential game; Computer science; Fuzzy logic; Differential (mechanical device); Reinforcement; Controller (irrigation); Control theory (sociology); Function (biology); Artificial intelligence; Control (management); Mathematical optimization; Engineering; Mathematics","score_opus":0.027291887146544194,"score_gpt":0.2659808781805624,"score_spread":0.2386889910340182,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086813915","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":[0.00034281047,0.0006961531,0.99410903,0.00035771637,0.0026063784,0.0007001523,1.8745374e-7,0.00006343046,0.0011241104],"genre_scores_gemma":[0.9840815,0.00010538201,0.012070211,0.00014140605,0.0007047076,0.0000126210925,0.0000015742721,0.000020356849,0.002862247],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630356,0.00019991865,0.0016615371,0.0002984374,0.0009650979,0.0005714247],"domain_scores_gemma":[0.9964383,0.00045313325,0.0016895764,0.00034379232,0.0008287816,0.00024638162],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001037098,0.00033938803,0.00083372655,0.0003958233,0.00019429853,0.00046153096,0.0011387457,0.00013039683,0.00001138975],"category_scores_gemma":[0.0003519859,0.0002653446,0.00048366142,0.00026447713,0.00003969663,0.00050518813,0.000090587026,0.00047804075,0.00003266169],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012174964,0.000057208566,0.000060616036,0.000031908065,0.00022121347,0.000016598811,0.0007236625,0.9634044,0.00042046525,0.029556751,0.0011890584,0.0041963398],"study_design_scores_gemma":[0.0013148492,0.0035928693,0.0001400526,0.00044553343,0.00009043595,0.00017741349,0.00047133988,0.9900827,0.00057558436,0.00046343348,0.0023397566,0.0003060727],"about_ca_topic_score_codex":0.000008719746,"about_ca_topic_score_gemma":2.2746973e-7,"teacher_disagreement_score":0.98373866,"about_ca_system_score_codex":0.00029683337,"about_ca_system_score_gemma":0.00014355242,"threshold_uncertainty_score":0.99997985},"labels":[],"label_agreement":null},{"id":"W2094387729","doi":"10.1016/j.automatica.2009.07.008","title":"Natural actor–critic algorithms","year":2009,"lang":"en","type":"article","venue":"Automatica","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":569,"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":"Temporal difference learning; Reinforcement learning; Computer science; Function approximation; Convergence (economics); Bellman equation; Mathematical proof; Function (biology); Stochastic gradient descent; Variance (accounting); Mathematics; Mathematical optimization; Artificial intelligence; Applied mathematics; Algorithm; Artificial neural network","score_opus":0.009214446772915929,"score_gpt":0.2557505181836024,"score_spread":0.24653607141068645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094387729","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":[0.0023711189,0.00006220524,0.9814356,0.0032122817,0.0005603607,0.00012281671,1.5195396e-7,0.0008934062,0.0113420505],"genre_scores_gemma":[0.83104223,0.0000028621178,0.16664626,0.0012337404,0.000054895376,0.0000023127207,0.0000016502354,0.0000053399094,0.0010107324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988358,0.000036111505,0.00022270111,0.00021650214,0.00035699812,0.000331858],"domain_scores_gemma":[0.99914205,0.00010272868,0.00005806637,0.00056557637,0.000048423997,0.000083146544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014024298,0.00012599808,0.00013923105,0.00007468036,0.00010260199,0.00022038666,0.0008319107,0.000044548455,0.000034268014],"category_scores_gemma":[0.00013325365,0.00011187862,0.000056373454,0.00026885647,0.000028449207,0.00047641914,0.00009320102,0.00017423935,0.0004491799],"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":[0.000004362511,0.00020607813,0.00023406623,0.000080083504,0.00009036154,0.00020836384,0.0037290934,0.03878931,0.0041530626,0.5334502,0.019073036,0.399982],"study_design_scores_gemma":[0.00015699204,0.00010337984,0.007838191,0.000023524564,0.0000048947595,0.000023176273,0.000008011419,0.9865984,0.00041230573,0.0028612358,0.0018039888,0.00016590129],"about_ca_topic_score_codex":0.0000015975597,"about_ca_topic_score_gemma":9.4318054e-8,"teacher_disagreement_score":0.9478091,"about_ca_system_score_codex":0.000042108557,"about_ca_system_score_gemma":0.000038568312,"threshold_uncertainty_score":0.57734483},"labels":[],"label_agreement":null},{"id":"W2095564494","doi":"10.1142/s0219525911002998","title":"AN EMPIRICAL STUDY OF POTENTIAL-BASED REWARD SHAPING AND ADVICE IN COMPLEX, MULTI-AGENT SYSTEMS","year":2011,"lang":"en","type":"article","venue":"Advances in Complex Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":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; Context (archaeology); Reward system; Nash equilibrium; Domain (mathematical analysis); Artificial intelligence; Machine learning; Psychology; Mathematical optimization; Mathematics","score_opus":0.1324506532271785,"score_gpt":0.3578127690604147,"score_spread":0.2253621158332362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095564494","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":[0.15649755,0.0012198306,0.83931196,0.000016515272,0.0007874885,0.0014838282,0.000003316151,0.0001905181,0.0004889802],"genre_scores_gemma":[0.9781694,0.000022675287,0.021599362,0.00004245591,0.000037893395,0.00007763507,0.000008129164,0.000023409073,0.000019056499],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99616057,0.00077050034,0.0012331611,0.00073085324,0.0006142443,0.0004906777],"domain_scores_gemma":[0.99804765,0.00016719481,0.0005286206,0.0009674509,0.00014850583,0.00014055624],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010150728,0.00030443052,0.0007055748,0.000437252,0.00010769545,0.00013433221,0.0012167655,0.00008585678,0.0000052232444],"category_scores_gemma":[0.00004786845,0.00029609702,0.00004246966,0.00068637973,0.00010886158,0.0008622232,0.00026756083,0.00025095357,0.0000068935324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024348457,0.00048017688,0.19728002,0.00030027342,0.0000143998095,0.000058218684,0.003976537,0.7968854,0.00021685987,0.00053092564,0.000018013858,0.00021487725],"study_design_scores_gemma":[0.0017469006,0.0006825228,0.101435095,0.00020156392,0.000007591191,0.000016067255,0.0029932456,0.8920888,0.000007462443,0.000011762947,0.00052152475,0.00028747006],"about_ca_topic_score_codex":0.001750264,"about_ca_topic_score_gemma":0.00033322422,"teacher_disagreement_score":0.82167184,"about_ca_system_score_codex":0.00013668528,"about_ca_system_score_gemma":0.000048295748,"threshold_uncertainty_score":0.9999491},"labels":[],"label_agreement":null},{"id":"W2096976789","doi":"","title":"Theoretical Analysis of Heuristic Search Methods for Online POMDPs.","year":2008,"lang":"en","type":"article","venue":"PubMed","topic":"Reinforcement Learning in Robotics","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":"Université Laval; McGill University; McGill University Health Centre","funders":"","keywords":"Heuristics; Scalability; Computer science; Heuristic; Online search; Mathematical optimization; Online algorithm; Artificial intelligence; Algorithm; Mathematics; Information retrieval","score_opus":0.07173965773491928,"score_gpt":0.35214968483620557,"score_spread":0.28041002710128626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096976789","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":[0.0045999447,0.00004319556,0.9935057,0.0003570261,0.0001374454,0.0003664295,0.0000034445516,0.000085170315,0.00090164924],"genre_scores_gemma":[0.5238741,0.000015642014,0.475703,0.00008035774,0.000028595307,0.00009236952,0.0000083068335,0.000005888087,0.00019176329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861336,0.00017714103,0.000303741,0.00026023653,0.0002710897,0.00037443286],"domain_scores_gemma":[0.99817157,0.00092966424,0.00008331914,0.0005416652,0.00015836726,0.00011542966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011090444,0.00009339859,0.00029199148,0.00032013084,0.00007187769,0.000025902138,0.00073506124,0.00004995065,0.000016245616],"category_scores_gemma":[0.00068273715,0.000081355654,0.00018460861,0.001153069,0.00016362563,0.000091950875,0.00019586386,0.00010810191,0.0000017087731],"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":[0.000024296338,0.00018717033,0.0032198988,0.000044256725,0.0010739005,0.0000068053055,0.0006373684,0.27456212,0.000028955847,0.5435675,0.00018610434,0.17646167],"study_design_scores_gemma":[0.0001883927,0.000036082707,0.08284106,0.0000010526479,0.00016160015,0.0000029732407,0.000004244961,0.91461855,0.00038681936,0.0009733664,0.00069477345,0.00009109372],"about_ca_topic_score_codex":0.0000044421777,"about_ca_topic_score_gemma":2.850704e-7,"teacher_disagreement_score":0.64005643,"about_ca_system_score_codex":0.00003871485,"about_ca_system_score_gemma":0.000041367806,"threshold_uncertainty_score":0.33175874},"labels":[],"label_agreement":null},{"id":"W2097113539","doi":"10.1613/jair.898","title":"Accelerating Reinforcement Learning through Implicit Imitation","year":2003,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":176,"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; University of British Columbia","funders":"Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Natural Sciences and Engineering Research Council of Canada","keywords":"Imitation; Reinforcement learning; Observability; Computer science; Convergence (economics); Action (physics); Space (punctuation); Artificial intelligence; State space; Reinforcement; Value (mathematics); Human–computer interaction; Machine learning; Psychology; Mathematics; Social psychology","score_opus":0.25418857368125086,"score_gpt":0.4324161648659641,"score_spread":0.17822759118471326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097113539","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":[0.007117496,0.00010141247,0.98067695,0.0005295918,0.00044074922,0.0001755816,4.1658787e-8,0.00002476661,0.010933403],"genre_scores_gemma":[0.9279053,0.00015945954,0.071227595,0.000058206067,0.00018186531,0.000004634013,5.2587745e-7,0.000014943611,0.00044743367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954541,0.00067831064,0.0011706825,0.00025708045,0.001750634,0.0006891928],"domain_scores_gemma":[0.9964403,0.00091068936,0.00052192976,0.00036312515,0.0016039745,0.00015999562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063111703,0.00015364416,0.0002507791,0.00044312954,0.0005890947,0.0007183951,0.0011119016,0.000095398,0.0001312823],"category_scores_gemma":[0.0037495503,0.00013679282,0.00013677683,0.0012795978,0.00012245461,0.0015018588,0.00019080279,0.0013969052,0.0001742293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013584984,0.000027925622,0.00009031263,0.000012111173,0.000021879088,0.000023482815,0.0025490578,0.7210429,0.0060994555,0.24787572,0.00011911896,0.022124454],"study_design_scores_gemma":[0.00009995599,0.001855639,0.000045278695,0.00016541872,0.000009800402,0.00014024976,0.006143613,0.7771646,0.15092716,0.056452412,0.006663742,0.0003321527],"about_ca_topic_score_codex":0.000026208209,"about_ca_topic_score_gemma":0.0000023467896,"teacher_disagreement_score":0.9207879,"about_ca_system_score_codex":0.00025324826,"about_ca_system_score_gemma":0.00041100124,"threshold_uncertainty_score":0.69275004},"labels":[],"label_agreement":null},{"id":"W2097575529","doi":"","title":"Reinforcement Learning using Kernel-Based Stochastic Factorization","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Kernel (algebra); Factorization; Markov decision process; Scalability; Matrix decomposition; Artificial intelligence; Machine learning; Algorithm; Markov process; Mathematics; Eigenvalues and eigenvectors","score_opus":0.0600288240839159,"score_gpt":0.2556550448293221,"score_spread":0.1956262207454062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2097575529","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":[0.0014210369,0.000004203093,0.98998165,0.000014118675,0.0003426088,0.00015923855,3.0016853e-8,0.0003755287,0.0077015585],"genre_scores_gemma":[0.9080668,4.6852335e-7,0.09060805,0.000120897326,0.000027442295,0.0000038429075,0.0000037117377,0.000013146231,0.0011556533],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987099,0.00004840248,0.00028341202,0.00027538836,0.00036344578,0.00031943605],"domain_scores_gemma":[0.99918854,0.00004869661,0.00016719462,0.0003944622,0.00010591288,0.00009518894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001995523,0.00015561022,0.000121909325,0.00014908893,0.00018300445,0.00011110705,0.0005282627,0.000059662434,0.00025287608],"category_scores_gemma":[0.00009629982,0.00014682554,0.00005110684,0.00032174346,0.000029506255,0.00048620213,0.00016266813,0.00016997404,0.000115199815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032580049,0.000008426178,0.0008515889,0.000006468392,0.000008391076,0.0000019091515,0.00050448196,0.9853175,0.00033394105,0.012601696,0.000009289567,0.00035300234],"study_design_scores_gemma":[0.00025286758,0.00013104966,0.00036569443,0.000019675475,0.000007392981,0.0000018627804,0.000027878143,0.9969632,0.001826725,0.00010170576,0.00011176786,0.00019017585],"about_ca_topic_score_codex":0.000063442814,"about_ca_topic_score_gemma":5.1652256e-7,"teacher_disagreement_score":0.9066458,"about_ca_system_score_codex":0.00010230933,"about_ca_system_score_gemma":0.00009330278,"threshold_uncertainty_score":0.5987371},"labels":[],"label_agreement":null},{"id":"W2098152875","doi":"10.1145/1390156.1390199","title":"Reinforcement learning in the presence of rare events","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":45,"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; Canada Research Chairs","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology","score_opus":0.029295139754644966,"score_gpt":0.25547336988383174,"score_spread":0.22617823012918678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2098152875","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":[0.019321224,0.00001884029,0.9548401,0.00039065842,0.00008585793,0.00018699087,1.9759948e-8,0.000055123863,0.025101189],"genre_scores_gemma":[0.98862374,0.00003458071,0.0060929665,0.00017942564,0.000010632573,0.000008112236,9.291272e-7,0.00000319771,0.005046399],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987512,0.00010639365,0.00027616924,0.00015364491,0.0005059528,0.00020659737],"domain_scores_gemma":[0.9991943,0.00017796131,0.00011125569,0.00044776156,0.000044946333,0.000023758837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040498067,0.00008079305,0.00010119195,0.00007866624,0.000095706026,0.000016237353,0.001144111,0.00002847652,0.000035736306],"category_scores_gemma":[0.00015726576,0.00005500599,0.00003862513,0.0003967098,0.00003985817,0.00030150908,0.00023779506,0.00019049308,0.000033648932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019271984,0.0000109408875,0.018652737,0.0000074132795,0.0000035477594,0.000009798431,0.002760735,0.9675706,0.000042985783,0.010153654,0.00039071846,0.00039493397],"study_design_scores_gemma":[0.00036695937,0.00018930814,0.028483411,0.00003639524,0.0000016120209,0.000029179606,0.00022143197,0.9664241,0.00071181706,0.00012381832,0.003281791,0.00013016557],"about_ca_topic_score_codex":0.00005211842,"about_ca_topic_score_gemma":0.0000017240684,"teacher_disagreement_score":0.96930254,"about_ca_system_score_codex":0.000019517953,"about_ca_system_score_gemma":0.000050306768,"threshold_uncertainty_score":0.22430791},"labels":[],"label_agreement":null},{"id":"W2099089474","doi":"","title":"PAC-Bayesian Model Selection for Reinforcement Learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Bayesian probability; Correctness; Selection (genetic algorithm); Artificial intelligence; Machine learning; Bayesian inference; Model selection; Algorithm","score_opus":0.014450719471556406,"score_gpt":0.25735404762560055,"score_spread":0.24290332815404414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099089474","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":[0.0006150215,9.791919e-7,0.97984535,0.00040506767,0.00032784746,0.0002815245,4.8230778e-8,0.00042858755,0.018095579],"genre_scores_gemma":[0.6564732,0.0000014289845,0.32532164,0.00021261766,0.000063148225,0.00001941819,0.0000035566873,0.000011111292,0.017893858],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988416,0.000013857959,0.00023831888,0.00029081997,0.00025873736,0.00035665254],"domain_scores_gemma":[0.99928457,0.00006964755,0.00010730605,0.00031287022,0.00013035658,0.000095281575],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036011968,0.00013499649,0.00011077514,0.00010517147,0.00028184627,0.00020935504,0.0004923083,0.0000888504,0.00005339315],"category_scores_gemma":[0.00012754025,0.00012569592,0.00007218219,0.00019728862,0.000020656875,0.00047993142,0.00012267263,0.00034344065,0.00004027718],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027728481,0.0000048169945,0.00023878228,0.0000069123175,0.000007126034,9.675186e-8,0.00016353361,0.8490474,0.003870246,0.1436312,0.00058641366,0.0024406451],"study_design_scores_gemma":[0.0002664686,0.00014381343,0.000021516089,0.0000033512622,0.0000044530016,0.000004018362,0.000011111905,0.9880684,0.003921894,0.0010696921,0.0063155196,0.00016973198],"about_ca_topic_score_codex":0.00001379146,"about_ca_topic_score_gemma":0.000012137798,"teacher_disagreement_score":0.6558582,"about_ca_system_score_codex":0.000034429206,"about_ca_system_score_gemma":0.000081379934,"threshold_uncertainty_score":0.51257306},"labels":[],"label_agreement":null},{"id":"W2099765827","doi":"10.1109/icsmc.2007.4414257","title":"Active exploratory q-learning for large problems","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Curse of dimensionality; Computer science; Artificial intelligence; Bellman equation; Machine learning; Robot; Action (physics); Mathematical optimization; Mathematics","score_opus":0.026113218419187033,"score_gpt":0.2715003364265079,"score_spread":0.24538711800732085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2099765827","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":[0.00072734413,0.000012237949,0.97998166,0.00012781336,0.00025540023,0.00029097663,1.477786e-7,0.0003659015,0.018238513],"genre_scores_gemma":[0.86650807,0.0000050897506,0.1246372,0.00050908886,0.00010968149,0.000034033656,0.0000055804553,0.000020493992,0.008170759],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988446,0.000023079307,0.00019799385,0.0002559489,0.00022035911,0.00045798044],"domain_scores_gemma":[0.999215,0.00021605189,0.00009808869,0.0002660155,0.000119024655,0.00008581326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085255806,0.00010626341,0.00010246036,0.00009861725,0.00019354052,0.00009438156,0.00047270695,0.000056318946,0.000026621688],"category_scores_gemma":[0.00012789661,0.00009690683,0.000054791024,0.00023296163,0.00001222,0.0005699599,0.00018289711,0.00017279628,0.00009410146],"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":[0.0000306051,0.00009562882,0.0025300928,0.00007574375,0.00007162293,0.000010260085,0.007948869,0.43967807,0.0022278214,0.5128891,0.0031030527,0.03133913],"study_design_scores_gemma":[0.00091866375,0.0003626321,0.0011032098,0.000023429553,0.0000057776065,0.0000035598064,0.0007376408,0.7675694,0.009016837,0.00086278917,0.21904048,0.00035555116],"about_ca_topic_score_codex":0.0000017001893,"about_ca_topic_score_gemma":0.0000049497207,"teacher_disagreement_score":0.8657807,"about_ca_system_score_codex":0.000052522555,"about_ca_system_score_gemma":0.000038087273,"threshold_uncertainty_score":0.39517456},"labels":[],"label_agreement":null},{"id":"W2100785108","doi":"10.7551/mitpress/7503.003.0062","title":"Bayesian Policy Gradient Algorithms","year":2007,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Bayesian probability; Computer science; Algorithm; Artificial intelligence","score_opus":0.053027897781275965,"score_gpt":0.27853266809186156,"score_spread":0.22550477031058558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100785108","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":[9.136226e-8,0.00017697393,0.45815894,0.000101929385,0.00036128014,0.00029013513,0.0000023519194,0.00018357117,0.54072475],"genre_scores_gemma":[0.00033202127,0.000050624727,0.009191939,0.0007925344,0.0008218131,0.000014913753,0.0000059956183,0.00008095475,0.9887092],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974422,0.00004420739,0.0005094109,0.00056839746,0.0008086952,0.0006271177],"domain_scores_gemma":[0.99705714,0.00016891994,0.00039823953,0.002086051,0.000107983244,0.0001816704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00049775676,0.0005007695,0.0003743336,0.00024642432,0.00026442675,0.000313839,0.0030592037,0.00031486954,0.000021700065],"category_scores_gemma":[0.000024224211,0.0003748428,0.0002445533,0.000019556794,0.0002535039,0.00008483228,0.0011285684,0.0008554027,0.00013689652],"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":[0.0000039503598,0.0000032156424,1.9611431e-7,0.000023316219,0.00011466435,0.00004273781,0.0008429682,0.005700462,0.000002843327,0.93516433,0.0014137586,0.05668754],"study_design_scores_gemma":[0.00021361002,0.00010366048,0.0000030595672,0.00013871948,0.00005927646,0.000049886345,0.0000020980672,0.054549154,0.00017326437,0.018379228,0.9257846,0.0005434372],"about_ca_topic_score_codex":0.00018787404,"about_ca_topic_score_gemma":0.0000072843627,"teacher_disagreement_score":0.9243708,"about_ca_system_score_codex":0.0001605906,"about_ca_system_score_gemma":0.00014242277,"threshold_uncertainty_score":0.99987036},"labels":[],"label_agreement":null},{"id":"W2101911972","doi":"10.1109/robot.2010.5509717","title":"Apprenticeship learning via soft local homomorphisms","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Markov decision process; Computer science; Reinforcement learning; State space; Artificial intelligence; Robot; Process (computing); Markov process; Space (punctuation); Homomorphism; Apprenticeship; Machine learning; Mathematics; Discrete mathematics; Statistics","score_opus":0.008005428190261192,"score_gpt":0.21867840387644316,"score_spread":0.21067297568618196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101911972","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":[0.0027479706,0.0000056914964,0.9695766,0.00027512506,0.00089375407,0.00008530913,3.3974228e-8,0.0005606486,0.02585485],"genre_scores_gemma":[0.9160135,0.0000010569019,0.07709538,0.00022544403,0.00008426502,0.000005159722,0.0000023707635,0.000012609843,0.0065602153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986342,0.00004422705,0.00022096807,0.00033502304,0.0003866034,0.00037893772],"domain_scores_gemma":[0.9989648,0.00013483407,0.000101186364,0.00058321405,0.00007458306,0.00014140549],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036751747,0.00014712787,0.00013009629,0.00008969117,0.00019372319,0.00027953717,0.0011231696,0.000101347505,0.00037079336],"category_scores_gemma":[0.00009686065,0.00013293518,0.00006355924,0.0002741345,0.00011278647,0.0005038374,0.00039412818,0.0007343192,0.0011107057],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037365994,0.000045883076,0.00419049,0.000020829772,0.000026575763,0.00002529642,0.00045160457,0.69667387,0.0052808654,0.18274018,0.0007310185,0.10980967],"study_design_scores_gemma":[0.00018208352,0.000069609596,0.0007618583,0.0000042051015,0.0000044936937,0.000027684946,0.000021008274,0.98153704,0.0017785465,0.00078519067,0.014627928,0.00020033274],"about_ca_topic_score_codex":0.000019860207,"about_ca_topic_score_gemma":0.000006761793,"teacher_disagreement_score":0.9132655,"about_ca_system_score_codex":0.000014726193,"about_ca_system_score_gemma":0.00003889029,"threshold_uncertainty_score":0.99966705},"labels":[],"label_agreement":null},{"id":"W2101984404","doi":"","title":"VDCBPI: an Approximate Scalable Algorithm for Large POMDPs","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":65,"is_retracted":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":"Scalability; Markov decision process; Curse of dimensionality; Computer science; Bounded function; Markov process; Mathematical optimization; Observable; Algorithm; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.018618968701239788,"score_gpt":0.26621215775492185,"score_spread":0.24759318905368205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101984404","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":[0.00018242303,0.000011507763,0.9914038,0.00033187735,0.00028088893,0.00032335403,0.0000017932277,0.0006567004,0.00680764],"genre_scores_gemma":[0.014752798,0.0000040859395,0.9812412,0.0006494197,0.00008023324,0.000031370753,0.000011625715,0.00001664916,0.0032125663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998662,0.000016718097,0.00020546648,0.00035780368,0.00025257492,0.00050544646],"domain_scores_gemma":[0.9990644,0.000030391668,0.000064749256,0.00061659876,0.000092632545,0.00013121834],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035930323,0.00013793456,0.00013615047,0.000073378484,0.00019908506,0.0002690145,0.0008424533,0.0000652018,0.000027527183],"category_scores_gemma":[0.000019167479,0.00012266007,0.00005933441,0.00022487022,0.00001294208,0.00081388786,0.00020101828,0.000092372524,0.00012194625],"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":[0.0000023157836,0.00023464023,0.00007276627,0.000029467092,0.000030080817,0.000007448249,0.00073004974,0.20249355,0.00018616806,0.771414,0.00080725574,0.023992272],"study_design_scores_gemma":[0.00093807763,0.00022580891,0.000044759785,0.0000071235313,0.000004447545,0.0000072745497,0.00002677084,0.98071617,0.0023802044,0.004385432,0.011071483,0.00019246688],"about_ca_topic_score_codex":0.000017586735,"about_ca_topic_score_gemma":0.00000243705,"teacher_disagreement_score":0.7782226,"about_ca_system_score_codex":0.000068461595,"about_ca_system_score_gemma":0.000077149445,"threshold_uncertainty_score":0.5001933},"labels":[],"label_agreement":null},{"id":"W2102847492","doi":"10.1145/1390156.1390286","title":"Apprenticeship learning using linear programming","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":194,"is_retracted":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":"Apprenticeship; Markov decision process; Computer science; Linear programming; Solver; Frame (networking); Markov process; Mathematical optimization; Process (computing); Markov chain; Artificial intelligence; Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.06668564856124883,"score_gpt":0.2809145654987666,"score_spread":0.21422891693751778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102847492","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":[0.025274852,0.000021288333,0.9683531,0.000062561114,0.00018925322,0.000104322724,1.0363493e-8,0.00052394957,0.0054706796],"genre_scores_gemma":[0.54708534,0.00000504924,0.4498993,0.00007084916,0.00006273286,0.0000021213575,8.50477e-7,0.000009465325,0.0028643021],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987568,0.00005713522,0.00021361187,0.00027303214,0.00034400492,0.00035538673],"domain_scores_gemma":[0.999343,0.00006244618,0.000105171144,0.00033391814,0.00006871622,0.0000867997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021903675,0.00012014801,0.00011749465,0.00009438318,0.00036777995,0.00010913852,0.00059812836,0.00005029282,0.000030302894],"category_scores_gemma":[0.00010032052,0.00011229623,0.00005762203,0.0004000482,0.000052202642,0.00054368866,0.00028817527,0.00025653848,0.00012972599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011288546,0.000014792265,0.01391528,0.000011242995,0.000011433516,0.000025600935,0.0007192069,0.97626925,0.00021058552,0.0038728707,0.000042509782,0.004906121],"study_design_scores_gemma":[0.00014206624,0.000052973497,0.00042085856,0.000011491916,0.0000034556388,0.00006403509,0.00003248982,0.9878993,0.0004858464,0.000012888178,0.010719626,0.00015498482],"about_ca_topic_score_codex":0.000025771542,"about_ca_topic_score_gemma":4.463867e-7,"teacher_disagreement_score":0.5218105,"about_ca_system_score_codex":0.000032844884,"about_ca_system_score_gemma":0.000054014592,"threshold_uncertainty_score":0.45793074},"labels":[],"label_agreement":null},{"id":"W2103568863","doi":"10.48550/arxiv.1407.0449","title":"Classification-based Approximate Policy Iteration: Experiments and Extended Discussions","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Exploit; Estimator; Computer science; Reinforcement learning; Bellman equation; Classifier (UML); Nonparametric statistics; Function (biology); Temporal difference learning; Mathematical optimization; Machine learning; Artificial intelligence; Algorithm; Mathematics; Econometrics; Statistics","score_opus":0.08066957996727817,"score_gpt":0.23344313061038263,"score_spread":0.15277355064310447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2103568863","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":[0.009655893,0.000014048266,0.9860879,0.0006279668,0.00027805837,0.00031312797,0.000003491848,0.00025498244,0.0027645375],"genre_scores_gemma":[0.9887046,0.000028673345,0.008698927,0.00021577328,0.00008669002,0.0000039070887,0.00004329838,0.000017817023,0.0022003106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982202,0.00017674289,0.00023492107,0.0009313857,0.00013403074,0.0003026931],"domain_scores_gemma":[0.9979127,0.00009284835,0.00031843988,0.0013625614,0.00011584746,0.00019757015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001837513,0.00029636943,0.00025230242,0.00034927274,0.000292699,0.0003406569,0.0011670282,0.00021420846,0.000017511824],"category_scores_gemma":[0.000064709384,0.00029635316,0.000103436854,0.00039125417,0.00013470234,0.0003175031,0.00113583,0.00037348524,0.000040118928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065569766,0.000039688253,0.0006990739,0.00004476217,0.00002420597,0.0000108618815,0.00020085044,0.7614193,0.00007173058,0.23711683,0.000100158635,0.00026598174],"study_design_scores_gemma":[0.00040444225,0.000042074946,0.002140626,0.00007688242,0.000021200347,0.0000011654963,0.00003862477,0.9920532,0.000107816035,0.0043334407,0.00045041103,0.0003300945],"about_ca_topic_score_codex":0.000028883807,"about_ca_topic_score_gemma":0.0000014279949,"teacher_disagreement_score":0.9790487,"about_ca_system_score_codex":0.00019378212,"about_ca_system_score_gemma":0.00023302519,"threshold_uncertainty_score":0.99994886},"labels":[],"label_agreement":null},{"id":"W2104641222","doi":"10.1177/105971230501300301","title":"Reinforcement Learning for RoboCup Soccer Keepaway","year":2005,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":390,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Generality; Computer science; Artificial intelligence; Learning classifier system; Benchmark (surveying); Machine learning; Task (project management); Psychology","score_opus":0.03632614507992138,"score_gpt":0.28627491977920116,"score_spread":0.24994877469927979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104641222","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":[0.002160611,0.000044193854,0.9916484,0.0003521383,0.0002968804,0.0007363658,5.4896697e-7,0.00032215874,0.0044387234],"genre_scores_gemma":[0.84988976,0.000009882785,0.13217655,0.00036756703,0.00019766422,0.00032397898,0.000012674953,0.000031574225,0.016990365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809307,0.000047674275,0.00039666164,0.00046791247,0.00042574637,0.0005689494],"domain_scores_gemma":[0.99881214,0.00012939276,0.00021171609,0.00050688593,0.00020022973,0.0001396327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032400645,0.0002483064,0.0002247243,0.00012965924,0.00032512788,0.00016623373,0.00078783405,0.000102043094,0.00010925853],"category_scores_gemma":[0.000063784726,0.00024610586,0.00016640939,0.00021218455,0.0000566728,0.00077130954,0.0002897343,0.00028967182,0.00030700903],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016029426,0.000046964287,0.0009961713,0.000005166805,0.0000240261,0.00000489849,0.0004977155,0.92134935,0.0006962757,0.03408218,0.0008843093,0.041396916],"study_design_scores_gemma":[0.0011062564,0.0007734715,0.0043173735,0.000027669576,0.00006573344,0.000011393846,0.00008802991,0.91034013,0.0036982915,0.000058592566,0.07897341,0.000539645],"about_ca_topic_score_codex":0.0000149999605,"about_ca_topic_score_gemma":0.0000041859284,"teacher_disagreement_score":0.85947186,"about_ca_system_score_codex":0.00020955273,"about_ca_system_score_gemma":0.000081012986,"threshold_uncertainty_score":0.9999991},"labels":[],"label_agreement":null},{"id":"W2105114545","doi":"","title":"Interval Estimation for Reinforcement-Learning Algorithms in Continuous-State Domains","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Bootstrapping (finance); Markov decision process; Computer science; Machine learning; Artificial intelligence; Confidence interval; Value (mathematics); Algorithm; Markov process; Statistics; Mathematics; Econometrics","score_opus":0.012292104332855507,"score_gpt":0.2686448487087605,"score_spread":0.256352744375905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105114545","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":[0.00974362,0.0000017917639,0.9836797,0.0003096307,0.0006215293,0.00043250283,2.1820888e-7,0.00025202887,0.004958996],"genre_scores_gemma":[0.62392455,0.0000021328597,0.37021747,0.00016770583,0.000035350364,0.000043558448,0.000012218259,0.000013192525,0.005583813],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985442,0.00003313496,0.00043698165,0.00031439308,0.00026046863,0.00041080939],"domain_scores_gemma":[0.99907595,0.00020230988,0.00017122355,0.0003714172,0.000099335164,0.00007974451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070528465,0.000158719,0.0001874911,0.0001933644,0.00011716431,0.00027081012,0.0006519499,0.000058287,0.000047101665],"category_scores_gemma":[0.00032918726,0.00015100834,0.000069462054,0.0002527537,0.00004121259,0.0007084053,0.0002216048,0.00040033064,0.00006597177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008166896,0.000013322393,0.0011217343,0.000015543197,0.000009968058,0.0000035491391,0.00076548365,0.93316567,0.0008692686,0.028607283,0.00019821191,0.03522178],"study_design_scores_gemma":[0.00081627304,0.00016757204,0.00068522437,0.000017498342,0.0000026847667,0.000005648065,0.000036785106,0.99109524,0.001584015,0.00084252504,0.004554767,0.00019174584],"about_ca_topic_score_codex":0.000052994837,"about_ca_topic_score_gemma":0.000038790204,"teacher_disagreement_score":0.6141809,"about_ca_system_score_codex":0.00004491041,"about_ca_system_score_gemma":0.00004822283,"threshold_uncertainty_score":0.6157941},"labels":[],"label_agreement":null},{"id":"W2105127884","doi":"10.1109/ia.2009.4927496","title":"How emotional mechanism helps episodic learning in a cognitive agent","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université du Québec à Montréal","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Episodic memory; Mechanism (biology); Computer science; Cognition; Memory consolidation; TRACE (psycholinguistics); Engram; Encoding (memory); Cognitive architecture; Cognitive science; Cognitive psychology; Cognitive model; Artificial intelligence; Psychology; Neuroscience; Hippocampus","score_opus":0.02740953433025567,"score_gpt":0.25763938789719043,"score_spread":0.23022985356693476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105127884","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":[0.004715689,0.000015207735,0.9806599,0.003682891,0.00013851307,0.00015163783,1.15180065e-7,0.00022374616,0.0104122795],"genre_scores_gemma":[0.9615323,0.000011161596,0.024083208,0.0009568949,0.000037186735,0.0000045226834,0.0000046415057,0.000005151435,0.013364951],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986942,0.00008716662,0.00017162388,0.00032021184,0.0003959063,0.00033088092],"domain_scores_gemma":[0.9995043,0.00009679189,0.00008192624,0.0001672224,0.000071013936,0.000078723635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002943626,0.00013439613,0.00013439047,0.00018470024,0.000100009755,0.00028133276,0.0003923124,0.000060532722,0.000074405616],"category_scores_gemma":[0.00018443125,0.00012845853,0.000052098378,0.00036261303,0.00001823599,0.0004930071,0.000120858764,0.00030111644,0.00013644894],"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":[0.000011729158,0.00013932782,0.0019271479,0.000012427186,0.000027576034,0.00016111285,0.0016752942,0.2588711,0.0011968717,0.67648864,0.00039131942,0.059097465],"study_design_scores_gemma":[0.0008871142,0.00054337387,0.013096384,0.000098858705,0.0000047700523,0.000028511738,0.00026187918,0.9716465,0.0017306181,0.010334999,0.0010187469,0.00034826278],"about_ca_topic_score_codex":0.000007019634,"about_ca_topic_score_gemma":0.0000026922523,"teacher_disagreement_score":0.9568166,"about_ca_system_score_codex":0.00006826539,"about_ca_system_score_gemma":0.000050840314,"threshold_uncertainty_score":0.5238387},"labels":[],"label_agreement":null},{"id":"W2105148789","doi":"10.1145/545056.545107","title":"Being the new guy in an experienced team","year":2002,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of Calgary","funders":"","keywords":"Flexibility (engineering); Computer science; Process (computing); Action (physics); Focus (optics); Artificial intelligence; Scratch; Human–computer interaction; Knowledge management; Management","score_opus":0.02793981256670081,"score_gpt":0.26034342719760006,"score_spread":0.23240361463089926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105148789","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":[0.014742778,0.000015043737,0.924322,0.0013757766,0.0001687347,0.00009640967,6.377329e-9,0.00013849452,0.059140727],"genre_scores_gemma":[0.95661306,0.0000051362003,0.031752404,0.00095348625,0.000047333677,0.000004430762,1.5413337e-7,0.00000441069,0.010619588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920213,0.000037373546,0.0001465115,0.0001854339,0.00020982017,0.00021870987],"domain_scores_gemma":[0.99931747,0.000044327648,0.000024430477,0.00053743477,0.000013395841,0.000062928724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013282416,0.00007116172,0.00006168961,0.000047788486,0.00008284958,0.00020841049,0.0010388334,0.000026107635,0.00022384292],"category_scores_gemma":[0.000039890732,0.000047247824,0.000018771014,0.00030603187,0.00002531567,0.00059394975,0.000168655,0.00011471368,0.00013921237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012042775,0.00004176884,0.006074464,0.0000024057165,0.0000042316046,0.000010988508,0.04733834,0.7492261,0.0006862495,0.1344832,0.010386664,0.051744398],"study_design_scores_gemma":[0.00012938467,0.00005895653,0.0012392151,0.0000046916666,4.209818e-7,0.0000029531361,0.00027383972,0.9925093,0.0004727162,0.0002511459,0.004968747,0.00008859837],"about_ca_topic_score_codex":0.000046209956,"about_ca_topic_score_gemma":0.000017007524,"teacher_disagreement_score":0.9418703,"about_ca_system_score_codex":0.000024132605,"about_ca_system_score_gemma":0.000012415325,"threshold_uncertainty_score":0.24509229},"labels":[],"label_agreement":null},{"id":"W2106919681","doi":"10.1109/noms.2010.5488472","title":"Towards adaptive policy-based management","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science","score_opus":0.012975108101956432,"score_gpt":0.25474589984564394,"score_spread":0.2417707917436875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106919681","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":[0.00015401962,9.266821e-7,0.7400609,0.0016607187,0.00027369615,0.000094379844,1.1434699e-7,0.00022251668,0.2575327],"genre_scores_gemma":[0.49893618,0.0000010720561,0.49414065,0.0014036165,0.00006025225,0.000008574191,7.434231e-7,0.0000059201825,0.0054430086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907357,0.000015337035,0.00012690036,0.00022586173,0.00030572803,0.0002525793],"domain_scores_gemma":[0.9991683,0.000023586517,0.000044103428,0.00063171505,0.000046463858,0.00008586213],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016397923,0.000101130674,0.00007441779,0.00015764782,0.00007240323,0.00012882786,0.00091158255,0.000041157302,0.00010582672],"category_scores_gemma":[0.00002109091,0.00008657181,0.00004521968,0.0003411378,0.00003684193,0.00018556834,0.00027905087,0.00017007667,0.00033958364],"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":[0.0000016261511,0.000012783659,0.000063408166,0.0000041337776,0.000010964795,0.000008061418,0.000049125625,0.06475228,0.00011002672,0.911839,0.0009416313,0.02220695],"study_design_scores_gemma":[0.00032282565,0.000085089036,0.0023263383,0.0000064280616,0.0000036531153,0.0000023095579,0.000013702275,0.9664032,0.0021389993,0.0022290659,0.02628365,0.00018473613],"about_ca_topic_score_codex":0.00005471933,"about_ca_topic_score_gemma":0.0000058179735,"teacher_disagreement_score":0.9096099,"about_ca_system_score_codex":0.000028428083,"about_ca_system_score_gemma":0.00008799571,"threshold_uncertainty_score":0.4364774},"labels":[],"label_agreement":null},{"id":"W2107479312","doi":"10.1109/noms.2008.4575242","title":"Reinforcement learning in policy-driven autonomic management","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Autonomic computing; Computer science; Context (archaeology); Set (abstract data type); Order (exchange); Risk analysis (engineering); Work (physics); Knowledge management; Process management; Artificial intelligence; Engineering; Business; Cloud computing","score_opus":0.01849947260282962,"score_gpt":0.24430428134269927,"score_spread":0.22580480873986966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107479312","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":[0.003397285,0.0000065477902,0.83516335,0.0006810008,0.00011233776,0.00019855694,1.5342868e-8,0.00031790358,0.160123],"genre_scores_gemma":[0.9170278,0.00010669603,0.043250024,0.000549543,0.00003897802,0.000019694124,0.0000024153494,0.000011521073,0.038993333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984651,0.000045454486,0.00037138836,0.00033802819,0.00032068236,0.00045931505],"domain_scores_gemma":[0.9992554,0.000035236997,0.00009806976,0.0005024128,0.0000223262,0.000086507614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018621032,0.00015968313,0.00015956836,0.0004532762,0.00015883979,0.00006943596,0.0008576919,0.00004655275,0.000062684514],"category_scores_gemma":[0.000023144758,0.00015931894,0.000055878216,0.0005519696,0.000042667565,0.000409684,0.0006147469,0.0002233676,0.000505082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016837628,0.000009255095,0.0038977389,0.0000060826387,0.00001181151,0.000047602396,0.00048964814,0.90343827,0.000018432138,0.0901928,0.000366522,0.0015201292],"study_design_scores_gemma":[0.0005217715,0.00008167719,0.013064863,0.000017724804,0.0000015984369,0.000017811313,0.000035698722,0.9696301,0.00011010981,0.00007617152,0.016234057,0.00020838183],"about_ca_topic_score_codex":0.000117446005,"about_ca_topic_score_gemma":0.00000382516,"teacher_disagreement_score":0.9136305,"about_ca_system_score_codex":0.00031306036,"about_ca_system_score_gemma":0.000100469726,"threshold_uncertainty_score":0.6496838},"labels":[],"label_agreement":null},{"id":"W2107741520","doi":"","title":"Weighted importance sampling for off-policy learning with linear function approximation","year":2014,"lang":"en","type":"article","venue":"neural information processing systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":100,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Weighting; Computer science; Importance sampling; Sampling (signal processing); Convergence (economics); Function (biology); Bridging (networking); Artificial intelligence; Mathematical optimization; Machine learning; Function approximation; Mathematics; Statistics; Artificial neural network","score_opus":0.020501250815071665,"score_gpt":0.2586979979424325,"score_spread":0.2381967471273608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107741520","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":[0.0033595155,0.000045288176,0.9933459,0.00023464818,0.0003094954,0.0005470256,5.696735e-7,0.00059286586,0.0015647032],"genre_scores_gemma":[0.95991045,0.0000033912622,0.038832296,0.0003278566,0.0003431948,0.00012906449,0.00010619396,0.00001915083,0.00032840695],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827385,0.00005976248,0.0006617876,0.00021165861,0.00046202572,0.00033094527],"domain_scores_gemma":[0.99812853,0.00009550097,0.00089897047,0.00027142873,0.00052995037,0.00007563071],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006400385,0.00019961092,0.00020964738,0.00028363036,0.0005195138,0.0009234643,0.00034519413,0.00009606953,8.6488166e-7],"category_scores_gemma":[0.00022276708,0.00016527154,0.000040303163,0.0006244434,0.000028170496,0.005227198,0.000047061432,0.00021901003,0.000023733455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023031113,0.0000045732645,0.0005843919,0.00048437336,0.000008453634,5.330334e-8,0.0007866694,0.9183554,0.00007266143,0.011711123,0.000064083186,0.06790516],"study_design_scores_gemma":[0.000516156,0.0002619887,0.00022865848,0.00012893789,0.00000884387,0.000016681855,0.00012112899,0.96898276,0.00009761469,0.000068498426,0.029362008,0.0002067],"about_ca_topic_score_codex":0.00001019537,"about_ca_topic_score_gemma":4.99597e-7,"teacher_disagreement_score":0.95655096,"about_ca_system_score_codex":0.00010056349,"about_ca_system_score_gemma":0.00011495646,"threshold_uncertainty_score":0.89049876},"labels":[],"label_agreement":null},{"id":"W2108005621","doi":"10.1609/aaai.v26i1.8260","title":"Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Computer science; Partially observable Markov decision process; Benchmark (surveying); Markov decision process; Bounded function; Mathematical optimization; Sample (material); Sample complexity; Computation; Set (abstract data type); Artificial intelligence; Markov process; Markov chain; Machine learning; Mathematics; Markov model; Algorithm","score_opus":0.07689906790923026,"score_gpt":0.3054622507888089,"score_spread":0.22856318287957864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108005621","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":[0.0060702707,0.000018058085,0.9882203,0.0023464987,0.00048090503,0.00053468504,0.0000040357727,0.00018177002,0.0021434838],"genre_scores_gemma":[0.9669596,0.00007698834,0.032171108,0.0001947182,0.000047442656,0.00005281055,0.000012496213,0.000017749673,0.00046707652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745965,0.000028723636,0.00074776117,0.0005498042,0.0006409391,0.0005730993],"domain_scores_gemma":[0.99721503,0.00035369574,0.00055661943,0.0003901932,0.0013615978,0.00012284503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004417754,0.0002667707,0.0003327017,0.00008325469,0.0004338198,0.0005647899,0.0017016034,0.000106322565,0.00010753934],"category_scores_gemma":[0.0025442878,0.00022482863,0.00021559293,0.0007464603,0.00014129808,0.00039648192,0.0005447251,0.00034956975,0.000033988854],"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":[0.00005459266,0.00007596238,0.00025092677,0.00006753147,0.00004460881,5.188746e-7,0.0007218686,0.055493444,0.01185003,0.9256324,0.0001665229,0.0056415778],"study_design_scores_gemma":[0.00008339699,0.00020363118,0.00006518222,0.00013376033,0.000021801296,0.000003331666,0.0002993447,0.6149811,0.33021727,0.051248576,0.0025119088,0.00023069732],"about_ca_topic_score_codex":0.000021069003,"about_ca_topic_score_gemma":0.0000026841765,"teacher_disagreement_score":0.96088934,"about_ca_system_score_codex":0.00012766548,"about_ca_system_score_gemma":0.00026695346,"threshold_uncertainty_score":0.9168246},"labels":[],"label_agreement":null},{"id":"W2109592579","doi":"10.1109/ccece.2003.1226121","title":"Using reinforcement learning for image thresholding","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":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; Reinforcement learning; Thresholding; Artificial intelligence; Image (mathematics); Machine learning; Computer vision","score_opus":0.05225257102805825,"score_gpt":0.30919521182997206,"score_spread":0.2569426408019138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109592579","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":[0.001543468,0.000011676007,0.98599094,0.00024024022,0.00024971314,0.0002886298,3.335706e-8,0.0003255259,0.011349793],"genre_scores_gemma":[0.47783524,0.0000027422602,0.5209246,0.0003365667,0.000054392,0.00000925246,0.0000015926752,0.000013083311,0.0008225337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870205,0.000012765885,0.00028024736,0.00029621524,0.0002840106,0.00042468918],"domain_scores_gemma":[0.99928963,0.000058378424,0.000121239485,0.00035846894,0.00010050025,0.00007179898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032916354,0.00014753881,0.0001367579,0.00011408518,0.00032284486,0.00030604732,0.0005793848,0.00004857025,0.000021144004],"category_scores_gemma":[0.00010686334,0.00013969404,0.0000892115,0.00023258409,0.000030194076,0.0007876058,0.00026797559,0.00015182197,0.000044080727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019212941,0.0000042529223,0.000056586032,0.000012250797,0.000009768747,0.0000029022463,0.0002036456,0.88031405,0.0038739499,0.115152895,0.000029770436,0.00033803016],"study_design_scores_gemma":[0.0006705893,0.0001289578,0.000018452582,0.000031203563,0.0000064005694,0.000011807065,0.000047732632,0.9832692,0.011434409,0.0015655626,0.002609106,0.00020655492],"about_ca_topic_score_codex":0.000030431287,"about_ca_topic_score_gemma":6.0293223e-7,"teacher_disagreement_score":0.47629178,"about_ca_system_score_codex":0.00017328975,"about_ca_system_score_gemma":0.00008658038,"threshold_uncertainty_score":0.5696558},"labels":[],"label_agreement":null},{"id":"W2109909644","doi":"","title":"Cost-Sensitive Exploration in Bayesian Reinforcement Learning","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; ENCODE; Artificial intelligence; Total cost; Bayesian probability; Machine learning; Partially observable Markov decision process; Mathematical optimization; Bayesian optimization; Markov process; Markov chain; Markov model; Mathematics; Economics","score_opus":0.04822342128543226,"score_gpt":0.28527178582256785,"score_spread":0.2370483645371356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109909644","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":[0.000544893,0.000008537426,0.9610342,0.0003755208,0.00026296216,0.0002455518,1.5675269e-8,0.00016722573,0.037361108],"genre_scores_gemma":[0.96913224,0.000012712618,0.027280008,0.00031548933,0.00006317903,0.000022272656,0.0000059666368,0.000008358189,0.0031597852],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987021,0.00009898369,0.00027070686,0.00017858662,0.00030466318,0.00044495708],"domain_scores_gemma":[0.999391,0.000083148065,0.000095572475,0.00027189392,0.00005053561,0.00010786014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005557345,0.00012172965,0.00011627912,0.00016484539,0.00008903704,0.00010292972,0.00025284532,0.00005189593,0.000048652728],"category_scores_gemma":[0.000101031175,0.00011689846,0.000031117175,0.00035716008,0.00001834032,0.0020868767,0.00018724379,0.00022252776,0.000289873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002716354,0.00001192562,0.0047697877,0.0000036546178,0.000004573115,0.0000025843203,0.0035485763,0.9380254,0.00011398471,0.048021115,0.00012307159,0.0053726085],"study_design_scores_gemma":[0.00027592242,0.00006972748,0.0024678812,0.000016825248,0.0000018884344,0.000004019049,0.00048740764,0.9900811,0.0023499688,0.000064310145,0.00399806,0.0001829176],"about_ca_topic_score_codex":0.000033338765,"about_ca_topic_score_gemma":0.0000049585406,"teacher_disagreement_score":0.96858734,"about_ca_system_score_codex":0.0001281924,"about_ca_system_score_gemma":0.00002724995,"threshold_uncertainty_score":0.47669807},"labels":[],"label_agreement":null},{"id":"W2111625536","doi":"","title":"Value Pursuit Iteration","year":2012,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Bellman equation; Reinforcement learning; Value (mathematics); Function (biology); Set (abstract data type); Mathematics; Algorithm; Power iteration; Mathematical optimization; Representation (politics); Approximation error; Computer science; Iterative method; Approximation algorithm; Artificial intelligence; Statistics","score_opus":0.013020207704836174,"score_gpt":0.23781960109386333,"score_spread":0.22479939338902716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111625536","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":[0.0063663726,0.00058981543,0.9855387,0.0032285685,0.00051214476,0.0005412074,0.0000018405493,0.0011886677,0.0020326807],"genre_scores_gemma":[0.7013289,0.000047211168,0.29325825,0.003694384,0.000336475,0.0002409449,0.0000109321,0.00003328179,0.0010496553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974764,0.00015868936,0.00042870583,0.00035010232,0.0006078966,0.0009781865],"domain_scores_gemma":[0.9979965,0.000107962565,0.00022103701,0.0011978182,0.000092628004,0.0003840226],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010236775,0.00028841235,0.00023531479,0.00033672134,0.0002714601,0.000553911,0.0013211444,0.00021174188,0.000027426262],"category_scores_gemma":[0.00018442555,0.0002925817,0.00013073882,0.0006245667,0.000046434165,0.0025864597,0.0005028097,0.00039176136,0.00016657652],"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":[0.000012679005,0.0001745557,0.080691576,0.000029529023,0.000042999967,0.000016682541,0.0015917389,0.09819986,0.0047724424,0.7774394,0.0040563163,0.032972183],"study_design_scores_gemma":[0.00028928,0.00012016065,0.06547137,0.00003418754,0.000016446967,0.000101844795,0.000020718588,0.9081851,0.0066537494,0.0011486934,0.017472435,0.00048595452],"about_ca_topic_score_codex":0.00087338337,"about_ca_topic_score_gemma":0.000025846064,"teacher_disagreement_score":0.8099853,"about_ca_system_score_codex":0.00037701588,"about_ca_system_score_gemma":0.0000934204,"threshold_uncertainty_score":0.9999526},"labels":[],"label_agreement":null},{"id":"W2111680853","doi":"","title":"A planning algorithm for predictive state representations","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Observable; Representation (politics); Markov decision process; Computer science; State (computer science); Sequence (biology); Mathematical optimization; Markov process; Process (computing); Algorithm; Mathematics; Statistics","score_opus":0.027297718444463843,"score_gpt":0.3026270110575934,"score_spread":0.27532929261312955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111680853","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":[0.000042246644,0.00001156432,0.9689895,0.00007835319,0.00022672133,0.00024959212,0.0000014380615,0.00018086341,0.030219724],"genre_scores_gemma":[0.020469077,0.000002057111,0.9685926,0.00018798522,0.000018370316,0.000055479617,0.0000038681083,0.000007802761,0.010662792],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992413,0.000032608146,0.00014776646,0.00021635217,0.00015590125,0.00020610017],"domain_scores_gemma":[0.9993379,0.00018249564,0.00005727893,0.00028324826,0.00008477518,0.000054273063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018783128,0.000069945294,0.00006969636,0.00006154244,0.00012735762,0.000113714035,0.00025798063,0.000019763838,0.000018242741],"category_scores_gemma":[0.00011970804,0.00006500852,0.000035628545,0.00017965295,0.000017941918,0.00034004383,0.00004809861,0.0000613558,0.0000191888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010249856,0.000010493978,0.00044049876,0.0000029410394,0.000024502304,0.0000029748014,0.0010494892,0.94948846,0.000016180942,0.03832512,0.0026306766,0.008007609],"study_design_scores_gemma":[0.0002693316,0.00009420678,0.00024127615,0.000005197305,0.0000030741885,0.0000046157093,0.00009374023,0.98805434,0.0008790237,0.0035625119,0.006708436,0.00008426569],"about_ca_topic_score_codex":0.000004313828,"about_ca_topic_score_gemma":1.7376634e-7,"teacher_disagreement_score":0.038565833,"about_ca_system_score_codex":0.000024255707,"about_ca_system_score_gemma":0.000051162504,"threshold_uncertainty_score":0.26509705},"labels":[],"label_agreement":null},{"id":"W2111833414","doi":"10.1109/robot.2008.4543641","title":"Bayesian reinforcement learning in continuous POMDPs with application to robot navigation","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Markov decision process; Particle filter; Partially observable Markov decision process; Robot; Artificial intelligence; Trajectory; Optimal control; Posterior probability; Bayesian probability; Mathematical optimization; Observable; Machine learning; Markov process; Markov chain; Kalman filter; Markov model; Mathematics","score_opus":0.009732780240815567,"score_gpt":0.23108885917368907,"score_spread":0.2213560789328735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111833414","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":[0.007573664,0.0000037331681,0.98085976,0.0005037441,0.000041014744,0.0004931939,1.7730564e-8,0.00038424705,0.010140602],"genre_scores_gemma":[0.87727064,0.0000041082617,0.11997201,0.00030933422,0.000021350741,0.000058368365,0.000008065602,0.00001125889,0.002344871],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985559,0.000041998897,0.00031294132,0.00035678953,0.00041557063,0.00031677412],"domain_scores_gemma":[0.9992138,0.00004273611,0.00011940765,0.00042676722,0.00009003174,0.00010722421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022911359,0.00014691279,0.00015572371,0.0001677423,0.00015338196,0.00007331377,0.00045961217,0.000050083236,0.000011485308],"category_scores_gemma":[0.000023385264,0.00013140506,0.000022726554,0.0006729921,0.00002072008,0.00041630433,0.00013457792,0.00020365289,0.00014607345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007082816,0.000014129159,0.0106501775,0.0000058922687,0.000005275956,0.000012066177,0.0012144161,0.9797261,0.00032773375,0.005538478,0.000059068843,0.0024396062],"study_design_scores_gemma":[0.0004411508,0.0003644296,0.007221822,0.000034118235,0.0000022306237,0.000036089594,0.000057187943,0.9878868,0.0010962313,0.000023681207,0.0026103167,0.00022593873],"about_ca_topic_score_codex":0.00012864685,"about_ca_topic_score_gemma":0.000010800434,"teacher_disagreement_score":0.869697,"about_ca_system_score_codex":0.00014125237,"about_ca_system_score_gemma":0.00006977919,"threshold_uncertainty_score":0.5358543},"labels":[],"label_agreement":null},{"id":"W2111836691","doi":"10.1109/iros.2009.5354126","title":"Robot task switching under diminishing returns","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Robot; Work (physics); Computer science; Term (time); Rate of return; Task (project management); Foraging; Econometrics; Mathematical optimization; Variety (cybernetics); Economics; Mathematics; Artificial intelligence; Engineering; Finance","score_opus":0.015211187821304775,"score_gpt":0.25029447934549937,"score_spread":0.2350832915241946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111836691","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":[0.0015905158,0.000016547503,0.9570611,0.0047103046,0.00029619568,0.00007570767,3.1827657e-8,0.00044438842,0.035805188],"genre_scores_gemma":[0.8625967,0.0000051329407,0.13163374,0.0034965219,0.0000679612,8.1329034e-7,8.9056005e-7,0.000006189471,0.002192056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869555,0.00003606157,0.00024099689,0.00031306705,0.00035708694,0.00035723048],"domain_scores_gemma":[0.999085,0.00008385615,0.000087562315,0.00060407305,0.000038776314,0.00010070668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027801268,0.00013893236,0.00012939786,0.000081032194,0.00016396826,0.0005013397,0.0009625295,0.00006184973,0.000029977013],"category_scores_gemma":[0.000058085032,0.00012100298,0.000059396156,0.00027410313,0.000009946932,0.00087177724,0.00017613199,0.00025639674,0.00012576045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013891615,0.00001756267,0.0001793009,0.0000030448105,0.000010225342,0.000012244072,0.00081656396,0.76451886,0.0052740774,0.2162031,0.0011041586,0.011859478],"study_design_scores_gemma":[0.00026090062,0.00016730405,0.008357577,0.0000301647,0.0000061676624,0.000023327115,0.00009429091,0.97897166,0.0015639301,0.008165844,0.002015075,0.00034373143],"about_ca_topic_score_codex":0.00001068935,"about_ca_topic_score_gemma":0.0000020984844,"teacher_disagreement_score":0.8610062,"about_ca_system_score_codex":0.000050706967,"about_ca_system_score_gemma":0.000037859583,"threshold_uncertainty_score":0.49343583},"labels":[],"label_agreement":null},{"id":"W2113710263","doi":"10.1109/icca.2003.1595047","title":"A Reinfrocement Learning Approach to Online Learning in Control","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Control (management); Online learning; Artificial intelligence; Multimedia","score_opus":0.01819162284227271,"score_gpt":0.24589915820550085,"score_spread":0.22770753536322813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113710263","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":[0.004952986,0.000021003649,0.91719234,0.0002640324,0.00009781752,0.00029415378,5.9387446e-8,0.00029679004,0.07688082],"genre_scores_gemma":[0.82002854,0.000005584158,0.1671893,0.00081763003,0.00002130253,0.000023494866,0.000003430002,0.000015772399,0.011894933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978509,0.0002646606,0.00040868245,0.0004942559,0.0004313515,0.00055018096],"domain_scores_gemma":[0.9991852,0.00011720257,0.00010158081,0.00036612496,0.00007204783,0.00015785581],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008429115,0.00019726915,0.00024839252,0.00028017972,0.00013253432,0.00017333643,0.0006097209,0.000068912406,0.000041284537],"category_scores_gemma":[0.0006242898,0.0001879409,0.000054287942,0.00076966645,0.000016565202,0.0002809492,0.00015248617,0.00058203546,0.00014361637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038784106,0.00005626019,0.008072795,0.0000081111275,0.000009474701,0.0000043546797,0.00061510544,0.9510173,0.00015886845,0.038383827,0.00009815115,0.0015718817],"study_design_scores_gemma":[0.00097460655,0.00023274995,0.0017880296,0.000019697785,0.0000033493043,0.000008521991,0.00026894556,0.96692085,0.00011330199,0.00005570611,0.029342752,0.00027147477],"about_ca_topic_score_codex":0.000024870269,"about_ca_topic_score_gemma":0.00000326418,"teacher_disagreement_score":0.8150756,"about_ca_system_score_codex":0.000122029836,"about_ca_system_score_gemma":0.00006980276,"threshold_uncertainty_score":0.7664007},"labels":[],"label_agreement":null},{"id":"W2114500662","doi":"10.1142/s0129183101002851","title":"DEEP-SARSA: A REINFORCEMENT LEARNING ALGORITHM FOR AUTONOMOUS NAVIGATION","year":2001,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Algorithm; Artificial intelligence; Q-learning; Learning classifier system; Robot; Graph; Theoretical computer science","score_opus":0.019940586004140722,"score_gpt":0.2823315718161346,"score_spread":0.2623909858119939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114500662","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":[0.0010402397,0.00005024949,0.9965208,0.00045311588,0.0010976177,0.00011522305,5.052745e-7,0.000041537318,0.0006807032],"genre_scores_gemma":[0.79895097,0.000052596242,0.19897564,0.00022799674,0.0009643347,0.000007886013,0.00002225184,0.000020524343,0.0007778116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822265,0.00003356324,0.000548294,0.00016669148,0.0008120139,0.00021678174],"domain_scores_gemma":[0.99788207,0.00012603724,0.00076400186,0.00016504405,0.0009855969,0.00007726871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036028595,0.00014276408,0.00017786855,0.000114826435,0.00009506625,0.0002485373,0.001106094,0.000047527374,0.000006892701],"category_scores_gemma":[0.000059995986,0.00014062232,0.00018958005,0.000114726274,0.000025247104,0.0009921149,0.00015733115,0.0002826525,0.000013631835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012140981,0.000025606081,0.00009628655,0.0000022245877,0.00009820267,0.00002030011,0.0004353164,0.6839582,0.00025350624,0.0042549944,0.0000527715,0.31079048],"study_design_scores_gemma":[0.0008868439,0.00022299103,0.000052765452,0.000058137673,0.000014323855,0.00013579003,0.000016247297,0.9802066,0.0007314762,0.012843929,0.004693277,0.00013762976],"about_ca_topic_score_codex":0.0000036289307,"about_ca_topic_score_gemma":1.6292887e-7,"teacher_disagreement_score":0.79791075,"about_ca_system_score_codex":0.00023683262,"about_ca_system_score_gemma":0.00011707342,"threshold_uncertainty_score":0.57344115},"labels":[],"label_agreement":null},{"id":"W2114819182","doi":"","title":"Optimal Robot Recharging Strategies For Time Discounted Labour","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Work (physics); Robot; Computer science; Energy (signal processing); Selection (genetic algorithm); Value (mathematics); Action (physics); Class (philosophy); Simulation; Artificial intelligence; Mathematics; Engineering; Machine learning","score_opus":0.025938479480937058,"score_gpt":0.26250877982827586,"score_spread":0.2365703003473388,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114819182","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":[0.006227769,0.000012935801,0.9835527,0.0005350134,0.00016271452,0.00019624685,9.017653e-7,0.00037502314,0.008936683],"genre_scores_gemma":[0.31659988,0.000009961833,0.6443601,0.00031447088,0.00008553797,0.000021057112,0.000007283414,0.00001634192,0.03858534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989382,0.000021493304,0.00020304101,0.00027063492,0.00022871631,0.00033788924],"domain_scores_gemma":[0.99927926,0.00010534864,0.00007485088,0.00038205547,0.00009805109,0.000060444527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017658176,0.00013230414,0.0001416118,0.000073676456,0.0002370348,0.00021493238,0.0006667495,0.000048588165,0.0000970571],"category_scores_gemma":[0.000039108123,0.00011506716,0.000060562616,0.00021517827,0.00004360826,0.000942047,0.0001474642,0.00010048513,0.00021335634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042602046,0.000010286414,0.000045444536,0.0000088746265,0.00001319972,0.000006393045,0.00046737868,0.9071958,0.0011177823,0.088934004,0.0020223174,0.00017426437],"study_design_scores_gemma":[0.0002939977,0.00011581023,0.00021916519,0.00001077953,0.0000026153746,0.000025137808,0.00009732029,0.9931946,0.00126871,0.00032343256,0.004255034,0.00019342665],"about_ca_topic_score_codex":0.000014628514,"about_ca_topic_score_gemma":5.310267e-7,"teacher_disagreement_score":0.33919257,"about_ca_system_score_codex":0.00003488322,"about_ca_system_score_gemma":0.00013108949,"threshold_uncertainty_score":0.46923026},"labels":[],"label_agreement":null},{"id":"W2115083386","doi":"10.1007/978-3-642-04174-7_43","title":"Learning the Difference between Partially Observable Dynamical Systems","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Université Laval; McGill University","funders":"","keywords":"Observable; Computer science; Markov decision process; Divergence (linguistics); Reinforcement learning; Dynamical systems theory; Key (lock); Temporal difference learning; Markov process; Markov chain; Artificial intelligence; Process (computing); Mathematical optimization; Machine learning; Mathematics; Statistics","score_opus":0.025984326590315347,"score_gpt":0.24446419850116202,"score_spread":0.21847987191084667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115083386","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":[0.00014150594,0.0002265295,0.99348754,0.0009140753,0.001452988,0.0005261107,0.0000011793255,0.0003156711,0.002934418],"genre_scores_gemma":[0.84237427,0.00010100458,0.14619431,0.0012669245,0.0015131441,0.000020691332,0.000019405437,0.00008553213,0.008424706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946228,0.00014622869,0.0008253494,0.0015223915,0.0018043113,0.0010788921],"domain_scores_gemma":[0.9957723,0.0013237508,0.00054820854,0.0018735129,0.000261457,0.00022076404],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015442092,0.00067783793,0.00073717016,0.0004261674,0.0006857551,0.0018057395,0.0066374615,0.0004276863,0.0000079946585],"category_scores_gemma":[0.00025739,0.00049913954,0.00016625208,0.00070923095,0.00075079245,0.0004879945,0.0017675812,0.0023191255,0.00008773235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014584929,0.000005022452,0.0006869675,0.00002012132,0.000011245604,0.000026708314,0.00029295354,0.7779467,0.000023109358,0.009256474,0.000004698606,0.21172452],"study_design_scores_gemma":[0.00014976619,0.00033325967,0.0023875276,0.00042227717,0.000016038844,0.000029461497,2.5182618e-7,0.982404,0.00006466273,0.011425955,0.0021464652,0.0006203508],"about_ca_topic_score_codex":0.000047726237,"about_ca_topic_score_gemma":0.000020156313,"teacher_disagreement_score":0.8472932,"about_ca_system_score_codex":0.00041109047,"about_ca_system_score_gemma":0.0005561899,"threshold_uncertainty_score":0.99998254},"labels":[],"label_agreement":null},{"id":"W2115253045","doi":"","title":"Off-policy Learning with Options and Recognizers","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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; McGill University","funders":"","keywords":"Variance (accounting); Computer science; Convergence (economics); Function (biology); Temporal difference learning; Reinforcement learning; Sampling (signal processing); Filter (signal processing); Function approximation; State (computer science); Importance sampling; Artificial intelligence; Policy learning; Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics; Artificial neural network","score_opus":0.012605854074279685,"score_gpt":0.24240306836910663,"score_spread":0.22979721429482694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115253045","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":[0.009853139,0.00027497616,0.9760786,0.0017163832,0.00015179915,0.00029161098,4.689744e-7,0.0005965691,0.011036415],"genre_scores_gemma":[0.98758024,0.000031052597,0.010622482,0.00036900313,0.00012225177,0.000023146391,0.000008981962,0.000007942617,0.0012348937],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889547,0.0000449528,0.0003727642,0.00012940656,0.00031883531,0.00023860266],"domain_scores_gemma":[0.9991945,0.000033627366,0.00033084405,0.00016074826,0.00019391,0.00008636154],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00024765666,0.00013313605,0.0001278034,0.00024974634,0.00036900103,0.0012367069,0.00025216883,0.000053680804,0.0000014413766],"category_scores_gemma":[0.000076670505,0.000109072666,0.000015711865,0.00047545662,0.000044276792,0.0062357234,0.000073164505,0.00021733782,0.000059608934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028911961,0.0000024733367,0.00036794718,0.00009469855,0.000004680024,2.7692812e-7,0.001984689,0.86476344,0.00001762239,0.003146747,0.00010648888,0.12950803],"study_design_scores_gemma":[0.00027736792,0.000078030534,0.00024277843,0.000092991875,0.0000037237066,0.0000817227,0.0002672425,0.95159733,0.00004167815,0.0000030846193,0.04716873,0.00014531905],"about_ca_topic_score_codex":0.00002074562,"about_ca_topic_score_gemma":9.826948e-7,"teacher_disagreement_score":0.9777271,"about_ca_system_score_codex":0.00007165846,"about_ca_system_score_gemma":0.00010365218,"threshold_uncertainty_score":0.9998001},"labels":[],"label_agreement":null},{"id":"W2115318338","doi":"","title":"Bootstrapping Apprenticeship Learning","year":2010,"lang":"en","type":"article","venue":"Max Planck Digital Library","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Bootstrapping (finance); Reinforcement learning; Feature (linguistics); Machine learning; Artificial intelligence; Monte Carlo method; Quality (philosophy); State space; Feature engineering; Feature vector; Apprenticeship; Mathematical optimization; Mathematics; Econometrics; Statistics","score_opus":0.006204349322123965,"score_gpt":0.18233502947085264,"score_spread":0.17613068014872868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115318338","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05010309,0.000035704506,0.45112243,0.00054567284,0.0013829184,0.00017496466,0.000008686338,0.0018958639,0.49473068],"genre_scores_gemma":[0.98568696,0.0000020753014,0.0055434434,0.00022178251,0.00022957657,0.000004864027,0.00008589189,0.000025890968,0.008199534],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986847,0.00001884898,0.00025020356,0.00035378846,0.00029538665,0.00039703975],"domain_scores_gemma":[0.9991012,0.00014850397,0.00012262899,0.00046526807,0.000011813616,0.00015058462],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00006994176,0.00017897511,0.00014553977,0.00011814269,0.00013793449,0.0021670482,0.0011373116,0.000096972086,0.00012023634],"category_scores_gemma":[0.0000786972,0.00017553856,0.000072935996,0.00029729004,0.000053411513,0.005198796,0.0005706085,0.00068120094,0.00073770393],"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":[0.00003717352,0.00016062232,0.50283074,0.00020889641,0.00012097579,0.00029874357,0.00087144825,0.13941365,0.002155126,0.26904142,0.022355475,0.062505685],"study_design_scores_gemma":[0.00052632287,0.00016239096,0.01874356,0.0000675092,0.000006779905,0.0000967852,0.000050374147,0.34290648,0.0012198145,0.0052315732,0.63015014,0.000838285],"about_ca_topic_score_codex":4.4754023e-7,"about_ca_topic_score_gemma":7.996207e-8,"teacher_disagreement_score":0.93558383,"about_ca_system_score_codex":0.0000041198327,"about_ca_system_score_gemma":0.000051763313,"threshold_uncertainty_score":0.9988688},"labels":[],"label_agreement":null},{"id":"W2115615930","doi":"10.1109/ijcnn.2006.247204","title":"Extend Single-agent Reinforcement Learning Approach to a Multi-robot Cooperative Task in an Unknown Dynamic Environment","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Robot; Markov decision process; Robustness (evolution); Robot learning; Artificial intelligence; Q-learning; Obstacle; Mobile robot; Markov process; Task (project management); Machine learning; Engineering; Mathematics","score_opus":0.052808010837956824,"score_gpt":0.26725047299880855,"score_spread":0.21444246216085172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2115615930","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":[0.067667834,0.000019686711,0.9159742,0.002201477,0.00074060523,0.0011018761,0.0000015936059,0.00021534521,0.012077357],"genre_scores_gemma":[0.9810828,0.000021954529,0.013600375,0.0007853197,0.00025805205,0.00014972907,0.000033589116,0.000032892076,0.004035269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666405,0.00008569179,0.0007584609,0.0008330412,0.00094199117,0.0007167914],"domain_scores_gemma":[0.9988455,0.00005687819,0.00037880847,0.0003196872,0.0002503576,0.00014873884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005769551,0.00044344392,0.00032439447,0.00023291873,0.0002863924,0.00074229547,0.0015815032,0.00009628271,0.000028377763],"category_scores_gemma":[0.000042386102,0.00035561388,0.00009152617,0.00039810373,0.00012006726,0.00070896605,0.0004049499,0.000708204,0.00011136324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004735575,0.00018848953,0.00027097235,0.000006588221,0.0000189907,0.0000060970806,0.00073517265,0.96673936,0.0053500235,0.024646673,0.00033655262,0.0016537299],"study_design_scores_gemma":[0.0005874382,0.00057527435,0.0023105403,0.000110238885,0.000007925537,0.000019597792,0.00008739922,0.99426544,0.0004431905,0.0002070225,0.00097357837,0.00041237785],"about_ca_topic_score_codex":0.000066733104,"about_ca_topic_score_gemma":0.000018231536,"teacher_disagreement_score":0.91341496,"about_ca_system_score_codex":0.000523723,"about_ca_system_score_gemma":0.000044570632,"threshold_uncertainty_score":0.9998896},"labels":[],"label_agreement":null},{"id":"W2117723247","doi":"","title":"An on-line decision-theoretic Golog interpreter","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpreter; Computer science; Prolog; Programming language; Representation (politics); Artificial intelligence","score_opus":0.019679629969391682,"score_gpt":0.2986808653297143,"score_spread":0.2790012353603226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117723247","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":[0.012448792,0.0000039219453,0.9236905,0.00038517424,0.0003945155,0.0000744896,8.4962394e-8,0.00025796355,0.06274456],"genre_scores_gemma":[0.9001523,0.000010497557,0.09520642,0.00219619,0.000051637795,0.0000033289512,0.0000012912833,0.000008888148,0.0023694464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887425,0.00004880225,0.00021492083,0.0003246464,0.00027579363,0.00026160304],"domain_scores_gemma":[0.9986043,0.00024106086,0.000047293193,0.00094440643,0.000050220653,0.00011272322],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00024921828,0.000124344,0.00011097797,0.000109228975,0.000065609405,0.00018203018,0.0012069454,0.00005632766,0.00039084296],"category_scores_gemma":[0.00010726551,0.000094150295,0.000046390316,0.00022195817,0.000052002917,0.00033954767,0.00018766086,0.00014783336,0.0009820319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025472882,0.000049948725,0.0012587324,0.0000017622431,0.000008829968,0.00004431612,0.00025535325,0.64828,0.000055173565,0.29964146,0.0012093197,0.049169634],"study_design_scores_gemma":[0.00018852677,0.00067487126,0.00030999226,0.000018522274,0.0000018660377,0.000026710557,0.000008726793,0.9880111,0.00023596971,0.0067550885,0.0036258216,0.00014275702],"about_ca_topic_score_codex":0.0000037647421,"about_ca_topic_score_gemma":0.0000013672621,"teacher_disagreement_score":0.88770354,"about_ca_system_score_codex":0.000031864765,"about_ca_system_score_gemma":0.000018336692,"threshold_uncertainty_score":0.9997958},"labels":[],"label_agreement":null},{"id":"W2119076930","doi":"10.1007/978-3-540-30217-9_100","title":"A Neuroevolutionary Approach to Emergent Task Decomposition","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Decomposition; Task (project management); Modular design; Artificial neural network; Artificial intelligence; Scalability; Reinforcement learning; Exploit; Function (biology); Distributed computing; Programming language","score_opus":0.016081137430461346,"score_gpt":0.24822591734682667,"score_spread":0.2321447799163653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119076930","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":[0.000018178367,0.00012463536,0.9848951,0.0009104295,0.0020102728,0.0006632082,0.0000025309555,0.00026270517,0.011112948],"genre_scores_gemma":[0.1257305,0.000028014256,0.8702475,0.0029543752,0.00044431063,0.000022936754,0.000019509382,0.000051151233,0.0005017096],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99522054,0.00003804792,0.00063633913,0.0018079936,0.0014829434,0.0008141252],"domain_scores_gemma":[0.99741024,0.0001394356,0.00027071915,0.0016065412,0.00024902655,0.00032403838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053961115,0.00059218425,0.0004630359,0.0011282647,0.00035318942,0.00046247148,0.0038622431,0.00025992963,0.000018638357],"category_scores_gemma":[0.00006739463,0.00059450784,0.00016122866,0.0009270606,0.00033205788,0.00059258,0.0020190687,0.00087967014,0.00018565955],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035813032,0.000030444413,0.000011868687,0.000027080101,0.00000761441,0.000030220384,0.0003973612,0.92113465,0.000110938076,0.04339438,0.000049823208,0.034802053],"study_design_scores_gemma":[0.00022918716,0.00028334497,0.00020999576,0.00024934445,0.000008299182,0.00010170738,8.743978e-8,0.9530215,0.00016687185,0.043356635,0.0016454477,0.0007275522],"about_ca_topic_score_codex":0.000018442657,"about_ca_topic_score_gemma":0.000003948244,"teacher_disagreement_score":0.12571232,"about_ca_system_score_codex":0.0008545126,"about_ca_system_score_gemma":0.000676734,"threshold_uncertainty_score":0.99965066},"labels":[],"label_agreement":null},{"id":"W2119778140","doi":"10.11575/prism/31038","title":"Spidey: a Robotic Tabletop Assistant","year":2012,"lang":"en","type":"article","venue":"Open MIND","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Human–computer interaction; Computer science; Visualization; Robot; Task (project management); Rapid prototyping; Artificial intelligence; Systems engineering; Engineering","score_opus":0.06420558674325796,"score_gpt":0.31618562482708984,"score_spread":0.25198003808383185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119778140","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":[0.0032600719,0.00006882048,0.89761263,0.00044245142,0.00061415066,0.00023316035,3.1561746e-7,0.00000772405,0.097760685],"genre_scores_gemma":[0.6325719,0.0000033396173,0.3489646,0.0001890126,0.00010734794,0.000009080116,0.0000030670299,0.000011119592,0.018140549],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987452,0.000056245928,0.00022355835,0.00024035088,0.00026375533,0.00047090917],"domain_scores_gemma":[0.99893975,0.00006713492,0.00011485185,0.0006754917,0.000035789064,0.00016697895],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006470562,0.00012167103,0.0001647315,0.000052574032,0.00012285732,0.00060759275,0.0016628343,0.000048009,0.000967283],"category_scores_gemma":[0.00008448209,0.00010851009,0.000037045163,0.00028252506,0.00002749749,0.0014244783,0.0009552881,0.00013617188,0.0031764195],"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":[0.000023153692,0.0003984174,0.03180841,0.000032123276,0.00016797542,0.00007565263,0.006936861,0.54199785,0.002907206,0.045605034,0.01262246,0.35742486],"study_design_scores_gemma":[0.0006340199,0.00014706145,0.008811913,0.00006723082,0.000029859097,0.00005168107,0.00010106155,0.27555385,0.0034634438,0.00010287632,0.71043545,0.0006015731],"about_ca_topic_score_codex":0.00001648524,"about_ca_topic_score_gemma":0.0000020138384,"teacher_disagreement_score":0.697813,"about_ca_system_score_codex":0.000062814834,"about_ca_system_score_gemma":0.00007397208,"threshold_uncertainty_score":0.99994594},"labels":[],"label_agreement":null},{"id":"W2119785746","doi":"10.1007/s10994-009-5110-1","title":"Training parsers by inverse reinforcement learning","year":2009,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":70,"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":"Treebank; Parsing; Computer science; Generalization; Artificial intelligence; Set (abstract data type); Reinforcement learning; Function (biology); Machine learning; Training set; Inverse; Algorithm; Mathematics","score_opus":0.02311423201309188,"score_gpt":0.2528785846531024,"score_spread":0.22976435264001055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119785746","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":[0.0053719906,0.00014025996,0.95776445,0.0011481398,0.00026125895,0.00020554055,2.0077422e-7,0.0010942443,0.03401393],"genre_scores_gemma":[0.9683691,0.000065382985,0.015494074,0.0015293333,0.00008932386,0.000008185975,0.000053488497,0.000032920125,0.014358181],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969763,0.00026363137,0.00054705027,0.00062130915,0.0007161278,0.0008755513],"domain_scores_gemma":[0.99866337,0.00014646107,0.00036231475,0.00050234626,0.00006959905,0.0002559408],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008953355,0.0003839408,0.00036077978,0.00023496346,0.00066871895,0.00039596218,0.0010499478,0.0001285741,0.00014964138],"category_scores_gemma":[0.0004570929,0.00039516378,0.00014618738,0.00061835296,0.000051472995,0.0007917808,0.0002581384,0.0012406264,0.0002110276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008422765,0.000012736875,0.0020073855,0.0000075747525,0.000023590985,0.0000211593,0.0028737956,0.9460119,0.0014554831,0.002259953,0.0010955204,0.0442225],"study_design_scores_gemma":[0.0005922793,0.00054548593,0.0002844098,0.000038545113,0.000011440844,0.000017910532,0.00020421341,0.873429,0.00027419408,0.000092262635,0.12408241,0.0004278263],"about_ca_topic_score_codex":0.000047158337,"about_ca_topic_score_gemma":0.0000023433117,"teacher_disagreement_score":0.96299714,"about_ca_system_score_codex":0.0001395637,"about_ca_system_score_gemma":0.00006895386,"threshold_uncertainty_score":0.99985003},"labels":[],"label_agreement":null},{"id":"W2120045945","doi":"10.1287/moor.2016.0832","title":"On the Asymptotic Optimality of Finite Approximations to Markov Decision Processes with Borel Spaces","year":2017,"lang":"en","type":"preprint","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Mathematics; State space; Convergence (economics); Applied mathematics; Mathematical optimization; Action (physics); Markov chain; Space (punctuation); Finite state; Markov process; Class (philosophy); Q-learning; State (computer science); Average cost; Reinforcement learning; Computer science; Algorithm; Statistics","score_opus":0.11485889613744056,"score_gpt":0.3944555419249472,"score_spread":0.27959664578750665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120045945","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":[0.027809277,0.00002795787,0.9619757,0.0022935949,0.000057104156,0.001723886,0.000023305392,0.000031834574,0.00605736],"genre_scores_gemma":[0.48764536,0.00004192169,0.51119643,0.000013374241,0.00001625764,0.0002441033,0.000010751268,0.000019819112,0.00081199897],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963108,0.0002126725,0.0006637246,0.000459486,0.0020188629,0.00033445487],"domain_scores_gemma":[0.9892951,0.004460787,0.0002822295,0.0032239757,0.0026403572,0.00009752711],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0032582833,0.00023775273,0.00042573042,0.0005130506,0.0006890981,0.0011338663,0.003825783,0.00013688157,0.000036218436],"category_scores_gemma":[0.014389807,0.00014990625,0.00007118355,0.0006598789,0.00036338318,0.0002568683,0.002433891,0.0007571104,0.00004305261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010118178,0.00017875254,0.00001894738,0.0009360077,0.000048563736,0.0000010917297,0.0029006165,0.8835837,0.000039474904,0.11173988,0.000353363,0.00018946399],"study_design_scores_gemma":[0.00013997202,0.00035842953,0.00013593948,0.002429406,0.000016125648,0.0000020485256,0.00027485806,0.98162425,0.0017507711,0.0130485315,0.000031280368,0.0001884222],"about_ca_topic_score_codex":0.000059823953,"about_ca_topic_score_gemma":0.00006126883,"teacher_disagreement_score":0.45983607,"about_ca_system_score_codex":0.00007494747,"about_ca_system_score_gemma":0.0012833445,"threshold_uncertainty_score":0.999903},"labels":[],"label_agreement":null},{"id":"W2121943493","doi":"","title":"Exact Dynamic Programming for decentralized POMDPs with lossless policy compression","year":2008,"lang":"en","type":"article","venue":"MPG.PuRe (Max Planck Society)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Benchmark (surveying); Curse of dimensionality; Dynamic programming; Mathematical optimization; State space; Reinforcement learning; Lossless compression; Partially observable Markov decision process; Markov decision process; Computation; Compression (physics); State (computer science); Theoretical computer science; Artificial intelligence; Data compression; Algorithm; Machine learning; Mathematics; Markov process; Markov chain; Markov model","score_opus":0.016323954191927535,"score_gpt":0.26402618162316643,"score_spread":0.2477022274312389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121943493","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":[0.021671556,0.0001655338,0.9747264,0.00081946136,0.0003072151,0.00097656035,0.0000073428228,0.00073372264,0.0005922179],"genre_scores_gemma":[0.5255514,0.00021646416,0.471502,0.000601685,0.00023386147,0.00012520941,0.00010077262,0.00007586934,0.0015927439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99733835,0.000061337334,0.00038222343,0.0006303875,0.0006315403,0.0009561507],"domain_scores_gemma":[0.9983924,0.00020100093,0.00029435058,0.0007301154,0.00015891048,0.00022319518],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001747386,0.0003844582,0.00041398866,0.000093481314,0.000669032,0.0002340428,0.0011014999,0.00021415632,0.000009704749],"category_scores_gemma":[0.000042918553,0.0003194084,0.00025888556,0.00070273306,0.00013967136,0.00051192695,0.00023242157,0.00036617665,0.00002370606],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006372794,0.0015835892,0.07198678,0.0020855851,0.0019512045,0.00041579388,0.045988094,0.7179612,0.0085453065,0.053577505,0.060932986,0.034334682],"study_design_scores_gemma":[0.0063078455,0.0007625503,0.0068682767,0.00036507248,0.00007643607,0.00029447477,0.00028278903,0.8307979,0.0009330115,0.00033310513,0.15154135,0.0014371816],"about_ca_topic_score_codex":0.000028891034,"about_ca_topic_score_gemma":0.000006200873,"teacher_disagreement_score":0.50387985,"about_ca_system_score_codex":0.00025712,"about_ca_system_score_gemma":0.00034459864,"threshold_uncertainty_score":0.9999258},"labels":[],"label_agreement":null},{"id":"W2122372591","doi":"","title":"Sketch-Based Linear Value Function Approximation","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Hash function; Computer science; Estimator; Reinforcement learning; Universal hashing; Function approximation; Dynamic perfect hashing; Function (biology); Bellman equation; Hash table; Artificial intelligence; Algorithm; Mathematics; Mathematical optimization; Statistics; Double hashing; Artificial neural network","score_opus":0.02141704514927115,"score_gpt":0.24769549645635106,"score_spread":0.2262784513070799,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122372591","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":[0.0010267652,0.000012315966,0.9823925,0.00030086012,0.00062852533,0.00010663427,4.6539842e-8,0.00033089935,0.015201444],"genre_scores_gemma":[0.7009897,5.828298e-7,0.29665247,0.0007200141,0.00014780526,0.0000072274674,0.0000055117516,0.0000064686133,0.0014701661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991817,0.00004416882,0.00014555105,0.00012711641,0.00026418577,0.00023727544],"domain_scores_gemma":[0.99940836,0.00005104312,0.00006519293,0.00035516385,0.00004547541,0.00007475005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003534133,0.00008039075,0.0000631605,0.00007110959,0.00007886826,0.00006184925,0.00025505095,0.00004714622,0.00006944839],"category_scores_gemma":[0.000045444394,0.000069783964,0.000036117217,0.00022727149,0.000014034312,0.00074892165,0.000062683896,0.00008616862,0.00058284326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034483032,0.000040092513,0.002832972,0.000014609964,0.000007565838,1.5808197e-7,0.00013556177,0.8079687,0.0003228223,0.1809852,0.0008463667,0.006842533],"study_design_scores_gemma":[0.0001576462,0.000051557483,0.002610826,0.000004028433,0.0000043663867,8.659815e-7,0.000006592004,0.98657435,0.0020152049,0.00014726781,0.008332275,0.0000950292],"about_ca_topic_score_codex":0.0000062111003,"about_ca_topic_score_gemma":1.3272903e-7,"teacher_disagreement_score":0.699963,"about_ca_system_score_codex":0.000037118,"about_ca_system_score_gemma":0.000025505358,"threshold_uncertainty_score":0.7491465},"labels":[],"label_agreement":null},{"id":"W2122633037","doi":"10.1109/cdc.1989.70344","title":"Computationally efficient adaptive control algorithms for Markov chains","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; McGill University","funders":"","keywords":"Markov chain; A priori and a posteriori; Computer science; Computation; Optimal control; Markov decision process; Algorithm; Mathematical optimization; State (computer science); Markov process; Theoretical computer science; Mathematics; Machine learning","score_opus":0.02201706201798436,"score_gpt":0.2565755941705012,"score_spread":0.23455853215251682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122633037","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":[0.00009969076,0.000016894306,0.9862167,0.00036818717,0.00035633787,0.0005055025,0.0000022245522,0.0001537701,0.012280639],"genre_scores_gemma":[0.43333137,5.9273293e-7,0.5630177,0.0008122992,0.000030235522,0.00003452395,0.0000028762452,0.0000086585405,0.0027616872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987866,0.00006323284,0.00022942173,0.00029671035,0.0003176035,0.00030641464],"domain_scores_gemma":[0.9989253,0.00041989656,0.00009470746,0.00025874443,0.00021574018,0.00008558474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042521174,0.00012931802,0.00014389333,0.00007905825,0.00014852462,0.00010725353,0.00039983852,0.000042602303,0.00002481007],"category_scores_gemma":[0.00012076152,0.000115500094,0.00007977774,0.00018852798,0.000034033284,0.00010128454,0.000040758267,0.00007636708,0.00004255534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032233809,0.000017958055,0.000020386567,0.00000225355,0.000016788788,0.0000010014938,0.00008337567,0.64595586,0.000011995847,0.35176077,0.00036957898,0.0017568145],"study_design_scores_gemma":[0.0011072828,0.00017894244,0.0003450191,0.0000051454745,0.0000054030133,0.00000530934,0.00004274041,0.99503523,0.000104925806,0.0005098706,0.0025063497,0.00015379718],"about_ca_topic_score_codex":0.000002480258,"about_ca_topic_score_gemma":4.85525e-7,"teacher_disagreement_score":0.43323168,"about_ca_system_score_codex":0.000059896953,"about_ca_system_score_gemma":0.00010601295,"threshold_uncertainty_score":0.4709957},"labels":[],"label_agreement":null},{"id":"W2123975568","doi":"10.1109/ictai.2001.974465","title":"Developing collaborative Golog agents by reinforcement learning","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Reinforcement learning; Scalability; Human–computer interaction; Plan (archaeology); Knowledge management; Artificial intelligence; Database","score_opus":0.02568505897910089,"score_gpt":0.27940363886921765,"score_spread":0.25371857989011676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2123975568","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":[0.0014484327,0.000033328044,0.91244584,0.0011064662,0.00023653415,0.00018572478,7.3143845e-8,0.00034210752,0.08420149],"genre_scores_gemma":[0.7710415,0.00030919668,0.12104524,0.0026230393,0.000056074245,0.000034171186,0.00002555904,0.000024579464,0.10484064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983412,0.000084325904,0.00033613728,0.00035399062,0.00042795387,0.0004563977],"domain_scores_gemma":[0.99913806,0.000087498964,0.000162835,0.000345713,0.00016558898,0.00010032449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029722904,0.00018555937,0.00016681736,0.000097039236,0.0002851222,0.0002497525,0.0007742486,0.000070977876,0.00015268299],"category_scores_gemma":[0.00012398943,0.00017256677,0.00003574762,0.0007875606,0.0000382269,0.00059033226,0.00040431245,0.00021539157,0.00042399068],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054001976,0.000009293003,0.004289231,0.0000067132073,0.000042374086,0.000021463095,0.00081520336,0.906433,0.00013139291,0.06452534,0.020393733,0.003326849],"study_design_scores_gemma":[0.00041803558,0.0001641742,0.00041443575,0.000021310427,0.000003833117,0.000010599364,0.00018896889,0.6184616,0.0010927053,0.00013739381,0.37875944,0.00032752464],"about_ca_topic_score_codex":0.00001942615,"about_ca_topic_score_gemma":0.0000018158141,"teacher_disagreement_score":0.7914006,"about_ca_system_score_codex":0.00018377713,"about_ca_system_score_gemma":0.00014043904,"threshold_uncertainty_score":0.70370686},"labels":[],"label_agreement":null},{"id":"W2124520701","doi":"10.3233/mgs-2010-0153","title":"Task allocation learning in a multiagent environment: Application to the RoboCupRescue simulation","year":2010,"lang":"en","type":"article","venue":"Multiagent and Grid Systems","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Computer science; Reinforcement learning; Task (project management); Perception; Human–computer interaction; Artificial intelligence; Multi-agent system; Distributed computing; Machine learning; Systems engineering","score_opus":0.01073146175779477,"score_gpt":0.23421884923192984,"score_spread":0.22348738747413507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124520701","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":[0.04455509,0.00008102547,0.9528694,0.00060911314,0.00064832903,0.0010671652,6.396584e-7,0.00008748241,0.00008173393],"genre_scores_gemma":[0.99654996,0.000018759152,0.0025157558,0.000070318536,0.00022540723,0.00017440147,0.000016272592,0.0000123564,0.00041678775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985427,0.00013430916,0.0003542511,0.00039487213,0.00033078206,0.00024305875],"domain_scores_gemma":[0.99906754,0.00014982425,0.00014661819,0.0005111206,0.000034045228,0.00009082697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075022184,0.00015294297,0.00013579911,0.00011377712,0.00021706725,0.0002358963,0.00042493222,0.0000818091,0.0000031252375],"category_scores_gemma":[0.00008533685,0.00012025097,0.000030263796,0.00019521583,0.000022833727,0.00024975993,0.00019756627,0.00030454472,0.00015710469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028504935,0.000017227561,0.005304854,0.000015094561,0.0000059082868,8.265248e-7,0.00189939,0.97891545,0.0064317374,0.00059018505,0.00005103553,0.0067654545],"study_design_scores_gemma":[0.00025471995,0.000032543634,0.016687557,0.00001588011,0.000004257877,0.0000021936928,0.00008468455,0.9326715,0.00018649765,0.00000270784,0.0499195,0.00013798082],"about_ca_topic_score_codex":0.00027805907,"about_ca_topic_score_gemma":0.00005085073,"teacher_disagreement_score":0.95199484,"about_ca_system_score_codex":0.000054431493,"about_ca_system_score_gemma":0.000013066089,"threshold_uncertainty_score":0.4903692},"labels":[],"label_agreement":null},{"id":"W2126410641","doi":"10.7551/mitpress/7503.003.0060","title":"iLSTD: Eligibility Traces and Convergence Analysis","year":2007,"lang":"en","type":"book-chapter","venue":"The MIT Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":42,"is_retracted":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":"Convergence (economics); Computer science; Economics; Macroeconomics","score_opus":0.060792911913390306,"score_gpt":0.29606644664909776,"score_spread":0.23527353473570745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126410641","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005077076,0.0008211417,0.38801482,0.000032085896,0.00019351374,0.00028070432,0.0000039164056,0.00013273963,0.6104703],"genre_scores_gemma":[0.02601076,0.0002166795,0.0035385815,0.00027319317,0.00011749503,0.000010146238,0.000005625938,0.00003306624,0.96979445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99790466,0.000054344342,0.00047860757,0.0006387073,0.00058736,0.00033632442],"domain_scores_gemma":[0.99738026,0.00033212942,0.00037778806,0.0016758646,0.00011855287,0.00011542037],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008290454,0.00036083424,0.00046389672,0.00016808721,0.00019855112,0.0002561667,0.0016475313,0.0002402943,0.000040217976],"category_scores_gemma":[0.000027512227,0.00026609757,0.00022815942,0.00003059088,0.00036860432,0.00010213667,0.00070751976,0.00053592556,0.000025701589],"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":[0.000023786533,0.000007820696,0.00009585773,0.000111087254,0.0019585318,0.000038911126,0.0024756691,0.024753563,0.000024328292,0.9438749,0.00060739595,0.02602815],"study_design_scores_gemma":[0.0005123584,0.00022480366,0.00064898876,0.00017815572,0.0030567187,0.000031061394,0.00001725367,0.30299523,0.0011415803,0.020746889,0.6686499,0.0017970175],"about_ca_topic_score_codex":0.00011933861,"about_ca_topic_score_gemma":0.00003338265,"teacher_disagreement_score":0.923128,"about_ca_system_score_codex":0.00003883267,"about_ca_system_score_gemma":0.00004287613,"threshold_uncertainty_score":0.99997914},"labels":[],"label_agreement":null},{"id":"W2126848223","doi":"10.1007/978-3-642-15880-3_19","title":"Smarter Sampling in Model-Based Bayesian Reinforcement Learning","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Markov decision process; Approximate Bayesian computation; Bellman equation; Bayesian probability; Computation; Sample (material); Sampling (signal processing); Artificial intelligence; Posterior probability; Bayesian inference; Machine learning; Markov process; Algorithm; Mathematical optimization; Mathematics; Statistics","score_opus":0.02126356525934251,"score_gpt":0.25524624714224586,"score_spread":0.23398268188290336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126848223","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":[0.000034298635,0.000047537542,0.9923826,0.0004938528,0.0013164951,0.00051608036,4.3980066e-7,0.00023590017,0.0049728104],"genre_scores_gemma":[0.3473456,0.000011772472,0.650213,0.0013711911,0.00021672419,0.000014728171,0.000010496958,0.000058603127,0.0007578643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448234,0.000046772795,0.0009898845,0.0017751429,0.0015228656,0.001183013],"domain_scores_gemma":[0.9967131,0.0005229942,0.0005077651,0.0017808495,0.00022836245,0.0002469418],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015962399,0.00076419435,0.0006829386,0.0017028496,0.00037199218,0.0008467562,0.0039786873,0.00061715726,0.00004512102],"category_scores_gemma":[0.00020551318,0.00076775573,0.00017790808,0.0007412648,0.00057637854,0.0007211351,0.0013756398,0.003283526,0.000052896346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004929658,0.00000959629,0.00015789234,0.000035889174,0.0000045313527,0.00003427021,0.00049203873,0.938483,0.00019075563,0.0043004416,0.0000014030261,0.056285277],"study_design_scores_gemma":[0.0004266744,0.0001690756,0.000041959924,0.00047422774,0.0000056995946,0.000012080403,1.3621082e-7,0.98244566,0.0006365157,0.014246306,0.00072947965,0.0008121651],"about_ca_topic_score_codex":0.00002459677,"about_ca_topic_score_gemma":0.00007887761,"teacher_disagreement_score":0.3473113,"about_ca_system_score_codex":0.00056319265,"about_ca_system_score_gemma":0.0010054327,"threshold_uncertainty_score":0.9994773},"labels":[],"label_agreement":null},{"id":"W2127186087","doi":"10.7282/t3zw1qcr","title":"Exploring compact reinforcement-learning representations with linear regression","year":2009,"lang":"en","type":"article","venue":"View","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Linear regression; Artificial intelligence; Function (biology); Regression; Object (grammar); Machine learning; Mathematical optimization; Mathematics; Statistics","score_opus":0.10293541427455874,"score_gpt":0.31457327685415964,"score_spread":0.2116378625796009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127186087","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":[0.0027597402,0.00011628203,0.97736865,0.0013908683,0.00013402807,0.00020850963,5.2382738e-8,0.00041146742,0.017610407],"genre_scores_gemma":[0.9655827,0.0004488093,0.030914718,0.0004265178,0.000087706394,0.000009689689,0.000010304811,0.000014153171,0.0025053644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985718,0.0000758605,0.00027989346,0.00031117137,0.00044492155,0.00031631716],"domain_scores_gemma":[0.9989289,0.00008176845,0.00018016223,0.0006100362,0.000084974316,0.0001141827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022966342,0.00016612731,0.00018878715,0.00012505929,0.00028565936,0.00015354721,0.0005251482,0.000026915377,0.000034448673],"category_scores_gemma":[0.000091559734,0.00012545168,0.000052444793,0.00056914,0.000024101266,0.0011957914,0.00007881909,0.00028174036,0.00013813387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063645634,0.000011474271,0.00056753744,0.000014694683,0.000011541235,0.000017196991,0.00063774193,0.9761029,0.00017506281,0.0073442543,0.00024233622,0.01486888],"study_design_scores_gemma":[0.00075921975,0.00090594124,0.0073350826,0.0007592884,0.000022597105,0.00003820064,0.00013650974,0.93908787,0.002081612,0.00011245818,0.04828841,0.00047280948],"about_ca_topic_score_codex":0.000012307368,"about_ca_topic_score_gemma":3.9621406e-7,"teacher_disagreement_score":0.962823,"about_ca_system_score_codex":0.00005368153,"about_ca_system_score_gemma":0.00004645443,"threshold_uncertainty_score":0.5115771},"labels":[],"label_agreement":null},{"id":"W2128371572","doi":"10.65109/yget7348","title":"Point-based incremental pruning heuristic for solving finite-horizon DEC-POMDPs","year":2009,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Partially observable Markov decision process; Computer science; Backup; Pruning; Heuristics; Mathematical optimization; Heuristic; Computation; Markov decision process; Bounded function; Markov process; Algorithm; Artificial intelligence; Markov chain; Machine learning; Mathematics; Markov model","score_opus":0.028466300042394005,"score_gpt":0.27550534672508825,"score_spread":0.24703904668269425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128371572","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":[0.00055865536,0.00007117758,0.98874366,0.000589151,0.0012666573,0.001592791,0.000004600843,0.0011197587,0.00605357],"genre_scores_gemma":[0.25934422,0.000014183654,0.73852044,0.0008120839,0.00024492602,0.00015065206,0.000116813426,0.000052108746,0.0007445632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964677,0.00009941914,0.0008271506,0.0010933911,0.00071074226,0.00080161553],"domain_scores_gemma":[0.9966046,0.00088851055,0.0005684485,0.0015019652,0.00023933595,0.00019709354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010735055,0.0005758944,0.0005437541,0.00038647512,0.0003296732,0.00095010333,0.002482903,0.0003589476,0.000048548252],"category_scores_gemma":[0.00060842326,0.00059493695,0.00031937097,0.00024655065,0.0000424419,0.00032546738,0.001705885,0.00072921574,0.000052759246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014404656,0.00006486859,0.00015336915,0.00026924614,0.000058170415,0.000014614511,0.00019901796,0.977072,0.00013719231,0.014747185,0.001985409,0.0052845064],"study_design_scores_gemma":[0.00067561783,0.000550002,0.00007015347,0.00034924934,0.000046691774,0.0000028782515,0.000027057586,0.99160796,0.001577894,0.002165022,0.002239647,0.00068782165],"about_ca_topic_score_codex":0.000039717634,"about_ca_topic_score_gemma":0.000007989752,"teacher_disagreement_score":0.25878558,"about_ca_system_score_codex":0.00040229072,"about_ca_system_score_gemma":0.0005312963,"threshold_uncertainty_score":0.9996502},"labels":[],"label_agreement":null},{"id":"W2128619633","doi":"10.1007/978-3-540-30115-8_53","title":"Batch Reinforcement Learning with State Importance","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Classifier (UML); Machine learning; Process (computing); State (computer science); Learning classifier system; Q-learning; Quality (philosophy); Function (biology); Bellman equation; Mathematical optimization; Algorithm; Mathematics","score_opus":0.011927894267546134,"score_gpt":0.22735911585792695,"score_spread":0.2154312215903808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128619633","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":[0.00005766123,0.00012926805,0.98587114,0.00031817157,0.0007775887,0.00054299686,4.169292e-7,0.00034104256,0.011961722],"genre_scores_gemma":[0.38506132,0.0001074161,0.60779387,0.0017528741,0.00032593694,0.000013671009,0.000014587543,0.000112114125,0.00481819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939482,0.000025809344,0.0008582748,0.0017651628,0.0021741556,0.0012283571],"domain_scores_gemma":[0.9965327,0.00032219614,0.00074993115,0.0017255169,0.00038420572,0.00028544798],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013401614,0.00079653965,0.00064138544,0.0009480439,0.00040712,0.00078858493,0.0036373322,0.00027491577,0.00006062409],"category_scores_gemma":[0.0000909408,0.00068681303,0.00011929984,0.0009145606,0.0007949428,0.00091556716,0.0014388798,0.0018702453,0.00009383797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010045333,0.0000066507173,0.00032597355,0.000040815157,0.000017587749,0.00022289492,0.00075287063,0.92624664,0.000018041266,0.0138167525,0.0000034559903,0.058538288],"study_design_scores_gemma":[0.0007391184,0.0009466191,0.00018650081,0.0009189286,0.000012852641,0.00010609002,4.0768919e-7,0.9636414,0.0008875637,0.029268,0.0019521518,0.0013403333],"about_ca_topic_score_codex":0.0000339424,"about_ca_topic_score_gemma":0.000052381798,"teacher_disagreement_score":0.38500366,"about_ca_system_score_codex":0.001017343,"about_ca_system_score_gemma":0.0012791196,"threshold_uncertainty_score":0.9995583},"labels":[],"label_agreement":null},{"id":"W2128812357","doi":"","title":"Error Propagation for Approximate Policy and Value Iteration","year":2010,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":135,"is_retracted":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":"Value (mathematics); Computer science; Mathematical optimization; Algorithm; Mathematics; Machine learning","score_opus":0.016255203649768592,"score_gpt":0.2649227238120397,"score_spread":0.2486675201622711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128812357","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":[0.004994018,0.00018013144,0.98249924,0.007239315,0.00048635557,0.0030348347,0.000036222682,0.0011708281,0.00035903222],"genre_scores_gemma":[0.25229108,0.00010512369,0.7420113,0.0017631005,0.00054862903,0.0019528291,0.00021925988,0.000094717776,0.001013918],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683243,0.00015505578,0.0007271074,0.0009951039,0.00050701946,0.0007832728],"domain_scores_gemma":[0.99681133,0.00019527793,0.0007259752,0.0016972737,0.00028482638,0.0002853187],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012071626,0.00056942395,0.0005052505,0.0008113928,0.00039113557,0.0014688311,0.0013943685,0.0009979499,0.0000029663133],"category_scores_gemma":[0.0007681039,0.00059027853,0.00017558521,0.00036841098,0.000106233485,0.00068982784,0.0016185682,0.0013737193,0.00000531463],"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":[0.000034799865,0.000078944664,0.00065459294,0.0004670693,0.00006154795,0.0000072373346,0.000842873,0.42243767,0.0062860874,0.55070657,0.00067682174,0.017745776],"study_design_scores_gemma":[0.00036871218,0.00014120417,0.0011838253,0.00011365622,0.00003189916,0.00004191695,0.000008990271,0.9719033,0.005304757,0.017936293,0.0023944585,0.00057095435],"about_ca_topic_score_codex":0.0018384923,"about_ca_topic_score_gemma":0.00018809464,"teacher_disagreement_score":0.54946566,"about_ca_system_score_codex":0.0004895136,"about_ca_system_score_gemma":0.00080552755,"threshold_uncertainty_score":0.9996549},"labels":[],"label_agreement":null},{"id":"W2128862550","doi":"10.65109/mphg3605","title":"Multi-Agent Patrolling with Reinforcement Learning","year":2004,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"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":"Patrolling; Reinforcement learning; Computer science; Task (project management); Adaptation (eye); Domain (mathematical analysis); Variety (cybernetics); Artificial intelligence; Distributed computing; Machine learning; Engineering","score_opus":0.029312571230412754,"score_gpt":0.2582969557574918,"score_spread":0.22898438452707903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128862550","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":[0.00047541296,0.00008169117,0.9896591,0.00027900617,0.00068634487,0.0006863187,1.886088e-7,0.0009766743,0.0071552703],"genre_scores_gemma":[0.5661249,0.000080765065,0.42532545,0.00025221825,0.00008807553,0.000063090934,0.000028062548,0.000044966968,0.007992481],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996508,0.00008747569,0.0006598637,0.0010287696,0.0010025632,0.00071331335],"domain_scores_gemma":[0.99748856,0.000063318854,0.00057022733,0.0014485954,0.00021523579,0.00021405604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047843345,0.00058359175,0.00049234077,0.0002649472,0.00027379429,0.00075742044,0.0019651225,0.00028361887,0.000078217956],"category_scores_gemma":[0.00005989656,0.00047715768,0.00018890554,0.00025672006,0.00006192465,0.00029975534,0.0029464446,0.0017110328,0.0002464719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000067991714,0.00002231977,0.00052848633,0.0001158143,0.00010893087,0.00004320408,0.00075744645,0.9946941,0.000028428736,0.0030009376,0.000027046306,0.0006664811],"study_design_scores_gemma":[0.0009510854,0.0002643519,0.00020826474,0.00038916452,0.000032112504,0.0000111559575,0.00005260465,0.99524164,0.00032728098,0.00008203669,0.0017673804,0.00067289436],"about_ca_topic_score_codex":0.00017393468,"about_ca_topic_score_gemma":0.000007924238,"teacher_disagreement_score":0.5656495,"about_ca_system_score_codex":0.00050532725,"about_ca_system_score_gemma":0.0005529025,"threshold_uncertainty_score":0.999768},"labels":[],"label_agreement":null},{"id":"W2129479396","doi":"10.1109/tsmcb.2003.821869","title":"Modular Fuzzy-Reinforcement Learning Approach With Internal Model Capabilities for Multiagent Systems","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Modular design; Computer science; Reinforcement learning; Robustness (evolution); Fuzzy logic; Artificial intelligence; Multi-agent system; Architecture; State space; Domain (mathematical analysis); Internal model; Control (management); Mathematics","score_opus":0.022985664478799343,"score_gpt":0.22860031637009612,"score_spread":0.20561465189129677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129479396","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":[0.011611183,0.000242008,0.98190403,0.0000815844,0.0010023615,0.0018922453,0.000012094433,0.0003299237,0.0029245638],"genre_scores_gemma":[0.97258747,0.00017030978,0.013473711,0.00007537338,0.00012327501,0.00059538084,0.000013405689,0.00009172617,0.012869325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960208,0.00013927446,0.0009821616,0.0010007038,0.0009887255,0.00086833775],"domain_scores_gemma":[0.9978079,0.0001437841,0.00039662104,0.00095559616,0.00031067443,0.0003853839],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054876786,0.0006566834,0.00064981816,0.0003050717,0.0005121333,0.00081734976,0.0007891958,0.00024618214,0.000003699137],"category_scores_gemma":[0.000010862858,0.00059426506,0.00018948948,0.00025729043,0.00024214218,0.00034656998,0.000024458297,0.00061125064,0.000032992353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058375714,0.0001477561,0.000023194678,0.0003701575,0.00020269105,0.00000581543,0.0028780329,0.97586185,0.00010331255,0.019928047,0.000053497508,0.00036726557],"study_design_scores_gemma":[0.0024063613,0.0011457461,0.000016502698,0.00041887403,0.00011598695,0.00008833452,0.000906787,0.9911903,0.0006193156,0.00010781062,0.0022709002,0.00071308366],"about_ca_topic_score_codex":0.00040855765,"about_ca_topic_score_gemma":0.000019540379,"teacher_disagreement_score":0.96843034,"about_ca_system_score_codex":0.00034291745,"about_ca_system_score_gemma":0.00014411687,"threshold_uncertainty_score":0.9996509},"labels":[],"label_agreement":null},{"id":"W2129578296","doi":"10.1109/cccrv.2004.1301489","title":"A reinforcement learning framework for parameter control in computer vision applications","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Entropy (arrow of time); Selection (genetic algorithm); Fuzzy logic; Principle of maximum entropy; Function approximation; Machine learning; Artificial neural network","score_opus":0.013490645539640269,"score_gpt":0.28086394825622957,"score_spread":0.2673733027165893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129578296","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":[0.00016102611,0.000011488934,0.9967619,0.0011957804,0.0001285971,0.0010449466,1.3653789e-7,0.00021318096,0.00048292673],"genre_scores_gemma":[0.48818412,0.0000036621232,0.510339,0.0010605614,0.000051289393,0.00020388722,0.0000035508588,0.000008515293,0.00014539028],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985722,0.00003130762,0.00038873393,0.0003746533,0.00025392775,0.0003792216],"domain_scores_gemma":[0.99876684,0.00047179247,0.00012845776,0.0004787168,0.00007431751,0.00007987217],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032997987,0.00015472363,0.0001896401,0.00015183023,0.0001411036,0.00020864757,0.0005876354,0.000103410624,0.000014976803],"category_scores_gemma":[0.00007455532,0.00014212256,0.00008481415,0.00033139222,0.000031045773,0.00033882557,0.00014455414,0.00027816146,0.00009286773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064856467,0.000019349865,0.00017128665,0.000009472581,0.00000767819,9.345988e-7,0.00013224484,0.75669014,0.000021718444,0.23656623,0.000024400175,0.0063500367],"study_design_scores_gemma":[0.0013086449,0.0004201088,0.00023607325,0.000051361327,0.0000042668785,0.0000028678107,0.000009102624,0.9743223,0.00008768919,0.018466635,0.004902431,0.0001884733],"about_ca_topic_score_codex":0.00001479283,"about_ca_topic_score_gemma":0.0000019555207,"teacher_disagreement_score":0.4880231,"about_ca_system_score_codex":0.00012836904,"about_ca_system_score_gemma":0.000051047555,"threshold_uncertainty_score":0.57955897},"labels":[],"label_agreement":null},{"id":"W2132622533","doi":"10.5555/2031678.2031726","title":"Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":305,"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; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Function (biology); Scalability; Temporal difference learning; Modular design; Architecture; Robot; Robot learning; Robotics; Machine learning; Unsupervised learning; Mobile robot","score_opus":0.032686465502922035,"score_gpt":0.25832884638991926,"score_spread":0.22564238088699723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132622533","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":[0.014385351,0.000015133608,0.9193181,0.00008789951,0.00044758496,0.00035255527,0.000001177627,0.00059958757,0.0647926],"genre_scores_gemma":[0.26695955,0.000027393116,0.70311636,0.00012584179,0.00030454327,0.00006440374,0.00003903906,0.000056873712,0.029306008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985661,0.00011300163,0.00029221733,0.00047172644,0.00017350852,0.0003834594],"domain_scores_gemma":[0.99874794,0.0003474203,0.00012387353,0.000507862,0.0001525395,0.00012035707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023633908,0.00020871818,0.00022113603,0.00014347301,0.00019308222,0.00015329802,0.00064703054,0.000109031476,0.00044827512],"category_scores_gemma":[0.00014575488,0.00018653297,0.000114129565,0.0002492749,0.000031248877,0.00041701758,0.00023405714,0.00028369235,0.0006485887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070936076,0.00075325527,0.008014528,0.00029946762,0.00075054955,0.00003762201,0.05778679,0.52343965,0.11838705,0.03280865,0.021317828,0.23569526],"study_design_scores_gemma":[0.0006285246,0.000380699,0.0009631351,0.000047121524,0.000019215731,0.0000048334578,0.00010572921,0.9648424,0.0074173626,0.0006224482,0.024644231,0.00032430148],"about_ca_topic_score_codex":0.0002822767,"about_ca_topic_score_gemma":0.000009845169,"teacher_disagreement_score":0.44140276,"about_ca_system_score_codex":0.0000677533,"about_ca_system_score_gemma":0.000058282574,"threshold_uncertainty_score":0.8336512},"labels":[],"label_agreement":null},{"id":"W2133342902","doi":"10.1109/ijcnn.2006.246687","title":"Learning to Coordinate Behaviors in Soft Behavior-Based Systems Using Reinforcement Learning","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Architecture; Task (project management); Mobile robot; Robot; Behavior-based robotics; Robotics; Mechanism (biology); Reinforcement; Engineering","score_opus":0.0449721869003996,"score_gpt":0.28035691451561023,"score_spread":0.23538472761521062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133342902","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":[0.60850996,0.000020200696,0.38212213,0.001478751,0.0020560694,0.0010870618,8.660849e-7,0.00042756856,0.0042974087],"genre_scores_gemma":[0.9957201,0.0000042225893,0.0016256125,0.00041980314,0.00042051586,0.00009573413,0.000011790662,0.000038867496,0.0016633424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966092,0.00007781665,0.0007966138,0.0006403277,0.001082846,0.0007932135],"domain_scores_gemma":[0.99849343,0.00009693786,0.00055626256,0.00023972776,0.00049855496,0.00011507882],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088409544,0.0004044279,0.0003501753,0.00031264973,0.00043955058,0.0010028386,0.0014355679,0.00012957778,0.00004034036],"category_scores_gemma":[0.00007388968,0.00035950713,0.000120159566,0.00060092215,0.0000890719,0.00052328315,0.00028513177,0.0010825408,0.00009511965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004045046,0.000034719622,0.012552298,0.000010290267,0.000009000175,0.00001817085,0.00023968115,0.9772554,0.0034025714,0.005308124,0.0004295179,0.00069976953],"study_design_scores_gemma":[0.0004740586,0.00041619135,0.0038167387,0.00034020448,0.000016984979,0.00002749665,0.00012268618,0.99317753,0.00035277224,0.000085324944,0.000763271,0.0004067659],"about_ca_topic_score_codex":0.00076224963,"about_ca_topic_score_gemma":0.000015518597,"teacher_disagreement_score":0.38721016,"about_ca_system_score_codex":0.0003602024,"about_ca_system_score_gemma":0.000088063854,"threshold_uncertainty_score":0.9998857},"labels":[],"label_agreement":null},{"id":"W2133552775","doi":"","title":"Learning from Limited Demonstrations","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Task (project management); Key (lock); Path (computing); Artificial intelligence; Machine learning; Mathematical optimization; Temporal difference learning; Mathematics","score_opus":0.01983794697850236,"score_gpt":0.22507605906335879,"score_spread":0.20523811208485643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133552775","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":[0.013337124,0.0000697689,0.97600037,0.0004689774,0.0005264495,0.00032851714,4.7615495e-7,0.00071104115,0.0085572535],"genre_scores_gemma":[0.9931545,0.0000036235213,0.0057827546,0.00029487308,0.00007321599,0.00006198107,0.000049268467,0.0000066556786,0.0005730748],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855167,0.00007156991,0.0005813006,0.0001402922,0.00040131685,0.000253846],"domain_scores_gemma":[0.9988053,0.00007767429,0.0004257515,0.00025445776,0.00034565965,0.00009114947],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00014591245,0.00014461976,0.0001391362,0.00015932781,0.00038891882,0.0026836635,0.0005030924,0.00008430407,0.000020143767],"category_scores_gemma":[0.00012265227,0.00013072099,0.00003507361,0.0004300872,0.000028397819,0.009905141,0.00009446697,0.00026924637,0.00082338986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.565448e-7,0.0000046622768,0.0014272155,0.00006763845,0.000007914984,4.025693e-7,0.0021737805,0.9477512,0.0002316718,0.0012354378,0.0016288587,0.045470513],"study_design_scores_gemma":[0.00015669451,0.00004010701,0.0015992495,0.000055359433,0.0000033131932,0.000009655053,0.00038651977,0.99199134,0.000092372386,0.000034484572,0.005478017,0.00015287839],"about_ca_topic_score_codex":0.00018141768,"about_ca_topic_score_gemma":4.5504657e-7,"teacher_disagreement_score":0.97981745,"about_ca_system_score_codex":0.000048863283,"about_ca_system_score_gemma":0.00006543627,"threshold_uncertainty_score":0.9999546},"labels":[],"label_agreement":null},{"id":"W2134042548","doi":"","title":"Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation","year":2009,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":168,"is_retracted":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; McGill University","funders":"","keywords":"Temporal difference learning; Function approximation; Stochastic approximation; Markov decision process; Mathematics; Function (biology); Stochastic gradient descent; Bellman equation; Mathematical optimization; Convergence (economics); Nonlinear system; Approximation algorithm; Artificial neural network; Gradient descent; Approximation error; Markov process; Rate of convergence; Algorithm; Applied mathematics; Reinforcement learning; Computer science; Artificial intelligence; Key (lock)","score_opus":0.014547591731831377,"score_gpt":0.22033568944607174,"score_spread":0.20578809771424036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134042548","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":[0.014030971,0.000066003995,0.98026335,0.00029328323,0.0003826908,0.0003897695,2.9524543e-7,0.00073911034,0.0038345181],"genre_scores_gemma":[0.9948147,0.0000036058846,0.004097127,0.00048790328,0.000063171705,0.000024623847,0.00005705701,0.000007337842,0.00044449922],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811894,0.00007744353,0.0006156633,0.00021243721,0.00067048863,0.0003050246],"domain_scores_gemma":[0.99859214,0.00002447851,0.0007143242,0.00027076117,0.0003032678,0.00009501889],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00030861658,0.0002223608,0.00020097774,0.00022021255,0.00038045464,0.001254692,0.00039402695,0.000091192676,0.0000029558971],"category_scores_gemma":[0.00003746253,0.00017817388,0.000034208504,0.00057143037,0.000029080295,0.0058340267,0.00003667051,0.0003370327,0.000058035308],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038115042,0.000021407272,0.0020646635,0.0003278746,0.000010719106,0.0000019786874,0.0025885662,0.8960687,0.0002584095,0.007980965,0.00019803701,0.09044057],"study_design_scores_gemma":[0.00038423904,0.00043890125,0.004044361,0.00015669859,0.000007907748,0.0000324485,0.00027609308,0.9909536,0.00014832344,0.00005426573,0.0032596048,0.0002435369],"about_ca_topic_score_codex":0.000016645883,"about_ca_topic_score_gemma":2.6021738e-7,"teacher_disagreement_score":0.9807837,"about_ca_system_score_codex":0.00008591708,"about_ca_system_score_gemma":0.0001059508,"threshold_uncertainty_score":0.9997821},"labels":[],"label_agreement":null},{"id":"W2135097260","doi":"10.1007/3-540-44886-1_26","title":"Model-Based Least-Squares Policy Evaluation","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Estimator; Computation; Least-squares function approximation; Basis (linear algebra); Algorithm; Set (abstract data type); Markov decision process; Mathematical optimization; Markov process; Mathematics; Statistics","score_opus":0.03695932473739669,"score_gpt":0.29243450260143466,"score_spread":0.25547517786403795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135097260","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":[0.0000110338015,0.00018908687,0.98508745,0.001661354,0.0011105081,0.0006380625,0.0000018422096,0.00019100704,0.011109643],"genre_scores_gemma":[0.2200319,0.000020859612,0.77082604,0.007254215,0.0004949348,0.000028471572,0.000015297794,0.00007542592,0.0012528233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943141,0.000091597656,0.0006386798,0.0015845979,0.0025217948,0.00084927987],"domain_scores_gemma":[0.996359,0.00033456247,0.0004353857,0.002028227,0.0006291032,0.00021375946],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019038559,0.0006310703,0.00049312215,0.0016122299,0.00033148125,0.0007679187,0.0035801984,0.00038749023,0.00003834118],"category_scores_gemma":[0.0004337212,0.00061547616,0.00016851905,0.0009622765,0.0006028542,0.000673201,0.0006955024,0.0009059838,0.00009933289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018977635,0.000009470249,0.000013133174,0.000019432775,0.0000048605707,0.0000072208354,0.00017441862,0.8183084,0.000024876012,0.02077237,0.000027851378,0.16063608],"study_design_scores_gemma":[0.00033366526,0.00013151082,0.000015575866,0.00019789688,0.000011331803,0.000012518207,4.71722e-8,0.91552335,0.00033941906,0.08215408,0.00069786125,0.00058275514],"about_ca_topic_score_codex":0.00001418567,"about_ca_topic_score_gemma":0.000013522307,"teacher_disagreement_score":0.22002088,"about_ca_system_score_codex":0.0010470893,"about_ca_system_score_gemma":0.00297138,"threshold_uncertainty_score":0.9996297},"labels":[],"label_agreement":null},{"id":"W2136602922","doi":"","title":"Incremental Natural Actor-Critic Algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":157,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; Convergence (economics); Bellman equation; Mathematical proof; Function approximation; Algorithm; Variance (accounting); Stochastic gradient descent; Function (biology); Rate of convergence; Gradient descent; Artificial intelligence; Mathematical optimization; Mathematics; Artificial neural network","score_opus":0.013354005743277607,"score_gpt":0.2696630519567899,"score_spread":0.2563090462135123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136602922","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":[0.005854929,0.000032090866,0.96692485,0.00022263624,0.0009490399,0.000086059874,9.1292776e-8,0.00030072627,0.025629563],"genre_scores_gemma":[0.84441173,0.0000019095235,0.15202905,0.00072867685,0.00009362788,9.0497343e-7,0.0000017913533,0.000006404874,0.0027259146],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874014,0.00001686526,0.00021412653,0.0002287741,0.00040479985,0.000395323],"domain_scores_gemma":[0.9993472,0.000102336235,0.000041228977,0.00035870826,0.00005410389,0.00009643325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004145986,0.00011299199,0.00008987168,0.00009757355,0.00010145941,0.00014941148,0.0007321856,0.000040529034,0.00008062309],"category_scores_gemma":[0.000046998066,0.00009893506,0.000047400044,0.00025523469,0.000037304457,0.00051944045,0.00029011542,0.00018748005,0.00025601697],"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":[0.000029958777,0.00022558417,0.015429227,0.00007409385,0.00018850784,0.00044399357,0.0025906959,0.019735428,0.034061894,0.6049364,0.013895603,0.3083886],"study_design_scores_gemma":[0.0009711609,0.00024461056,0.026801206,0.000026002537,0.000009391599,0.000096413394,0.00023913679,0.9171981,0.037343893,0.00051309966,0.015843451,0.00071352685],"about_ca_topic_score_codex":0.000028575862,"about_ca_topic_score_gemma":0.0000049319747,"teacher_disagreement_score":0.89746267,"about_ca_system_score_codex":0.00008389457,"about_ca_system_score_gemma":0.000024572924,"threshold_uncertainty_score":0.40344548},"labels":[],"label_agreement":null},{"id":"W2136617285","doi":"10.1109/icsmc.2007.4414024","title":"Aggregation of tiling-based reinforcement learning algorithms","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Aggregate (composite); Architecture; Artificial intelligence; Function (biology); Stability (learning theory); Instance-based learning; Competitive learning; Algorithm; Machine learning; Unsupervised learning","score_opus":0.01789302460037047,"score_gpt":0.2669956302511332,"score_spread":0.24910260565076275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136617285","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":[0.001523536,0.000012955984,0.9783222,0.000079363665,0.00019253176,0.000121890116,2.179286e-8,0.00019203198,0.019555442],"genre_scores_gemma":[0.8447554,0.0000024914068,0.15249391,0.00013753322,0.000028316828,0.0000015587317,0.000004294239,0.000007019686,0.0025694408],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985826,0.000025770954,0.0004188665,0.00020126761,0.00049226097,0.00027922672],"domain_scores_gemma":[0.9990154,0.00016368144,0.00023634202,0.00036031174,0.00015422424,0.000070048845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009306904,0.00010918601,0.00012559857,0.00018415097,0.000084680796,0.000046855774,0.0004576277,0.00005680079,0.00005733439],"category_scores_gemma":[0.00012724886,0.00010231802,0.0000608145,0.00039531957,0.000036466437,0.00025018983,0.00010730863,0.00015513603,0.000045417055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004329246,0.000008883448,0.0010176164,0.000013286187,0.000007256532,0.0000027651822,0.00014817373,0.96471846,0.00043791527,0.011000486,0.000033283268,0.022607528],"study_design_scores_gemma":[0.00030796952,0.00019107673,0.0005768627,0.000025744243,0.0000032727007,0.0000012381183,0.000029722987,0.94374603,0.052989077,0.00004199617,0.001974605,0.0001124066],"about_ca_topic_score_codex":0.000025552143,"about_ca_topic_score_gemma":0.0000019515905,"teacher_disagreement_score":0.8432319,"about_ca_system_score_codex":0.0000565135,"about_ca_system_score_gemma":0.000058655834,"threshold_uncertainty_score":0.4172408},"labels":[],"label_agreement":null},{"id":"W2136895343","doi":"","title":"Brain Inspired Reinforcement Learning","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Neurophysiology; Machine learning; Adaptation (eye); Task (project management); Convergence (economics); Learning classifier system; Feature (linguistics); Neuroscience; Psychology; Engineering","score_opus":0.016273083672864667,"score_gpt":0.24571917080806616,"score_spread":0.22944608713520148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136895343","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":[0.0010647513,0.00000868488,0.9303194,0.003845582,0.00018823083,0.00011742091,1.0614408e-8,0.0005549909,0.06390088],"genre_scores_gemma":[0.9137373,0.0000059428767,0.06758471,0.0022408788,0.000042835065,0.000008158676,0.0000029240473,0.000011100427,0.016366186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870867,0.00002849884,0.00025872563,0.00027019618,0.00038698004,0.00034694799],"domain_scores_gemma":[0.9992487,0.00005399418,0.00009077429,0.000453133,0.000051767634,0.00010165483],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027536965,0.00013395694,0.000114799965,0.00010799365,0.00017716341,0.000193045,0.00073179824,0.000051054503,0.00007968766],"category_scores_gemma":[0.00015049645,0.00012305475,0.00005704175,0.00034398295,0.000029828392,0.00052728754,0.00033023112,0.0002132646,0.000625175],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.35515e-7,0.0000052188025,0.00011681806,0.0000034815855,0.0000071049863,0.0000063684506,0.00033491646,0.8180172,0.00028850418,0.17934069,0.00028728164,0.0015914667],"study_design_scores_gemma":[0.0017921117,0.00059197034,0.00093322725,0.000046477875,0.000004865861,0.000024081482,0.0000806767,0.91086197,0.0061515844,0.0025570432,0.07641027,0.00054571964],"about_ca_topic_score_codex":0.000046360004,"about_ca_topic_score_gemma":0.0000020786244,"teacher_disagreement_score":0.9126725,"about_ca_system_score_codex":0.00011679201,"about_ca_system_score_gemma":0.000086173335,"threshold_uncertainty_score":0.80355686},"labels":[],"label_agreement":null},{"id":"W2136937392","doi":"10.1287/moor.1050.0148","title":"On the Empirical State-Action Frequencies in Markov Decision Processes Under General Policies","year":2005,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"National Science Foundation","keywords":"Polytope; Mathematics; Markov decision process; Markov chain; State (computer science); Element (criminal law); Action (physics); Limit (mathematics); Empirical research; Finite state; Markov process; Mathematical optimization; Mathematical economics; Combinatorics; Statistics; Algorithm; Mathematical analysis; Law","score_opus":0.31700725284698666,"score_gpt":0.46017316569362243,"score_spread":0.14316591284663577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136937392","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":[0.4734502,0.000017106668,0.5207565,0.0038803574,0.000023155148,0.00026127926,9.588447e-7,0.000021908769,0.0015885619],"genre_scores_gemma":[0.8651178,0.000059984046,0.13301925,0.0001355698,0.000028467906,0.000053696753,0.0000017119186,0.00001040591,0.0015730911],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798477,0.00015938221,0.00039182254,0.00018349785,0.0009886674,0.00029185112],"domain_scores_gemma":[0.9974459,0.001434012,0.00003567263,0.0005692786,0.0004732678,0.000041914816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015212226,0.0000974379,0.00013163086,0.0003734744,0.00028733554,0.00035753424,0.0008273652,0.0000463698,0.00005916406],"category_scores_gemma":[0.0014595042,0.000064306885,0.000026679158,0.0010578135,0.0001493979,0.0004203297,0.0002328607,0.00032490777,0.000084029016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033862268,0.00011356565,0.000055131895,0.000025646223,0.0000064638903,4.8413455e-7,0.0045435177,0.8931477,0.00063377095,0.09974442,0.0006279575,0.0010979779],"study_design_scores_gemma":[0.00012969297,0.0001498061,0.0005286004,0.000089523295,0.0000011992325,0.000003996066,0.00068473036,0.97970426,0.0049614115,0.013463232,0.00019496701,0.000088579],"about_ca_topic_score_codex":0.000067231136,"about_ca_topic_score_gemma":0.00031001063,"teacher_disagreement_score":0.3916676,"about_ca_system_score_codex":0.00015775175,"about_ca_system_score_gemma":0.0002975253,"threshold_uncertainty_score":0.3447711},"labels":[],"label_agreement":null},{"id":"W2137312721","doi":"","title":"On-line Reinforcement Learning Using Incremental Kernel-Based Stochastic Factorization","year":2012,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Kernel (algebra); Factorization; Q-learning; Markov process; Algorithm; State space; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.045062490513218506,"score_gpt":0.28652545567702453,"score_spread":0.24146296516380603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137312721","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":[0.0111564975,0.00004103796,0.98591006,0.00003984713,0.0013205545,0.00043502895,6.2035593e-7,0.0004168892,0.0006794616],"genre_scores_gemma":[0.9974749,4.81468e-7,0.0018030494,0.0003163316,0.00016789374,0.000025158213,0.00007863174,0.000016418619,0.00011715381],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99748516,0.000096430274,0.00081333116,0.00016650763,0.00090924295,0.0005293011],"domain_scores_gemma":[0.99839085,0.000084819716,0.00081923313,0.00028816628,0.00025277745,0.00016417031],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055918505,0.00026867833,0.00021556683,0.0003423405,0.00052190595,0.0008869543,0.00043112304,0.00010397096,0.000009272318],"category_scores_gemma":[0.00019521559,0.0002490108,0.000053854117,0.00052763615,0.000032064636,0.0063838596,0.000110318906,0.0003180756,0.00011277619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009596092,0.000012722172,0.00038309905,0.00014785453,0.0000069172324,2.0677555e-7,0.0010044669,0.99468833,0.00019223262,0.0020749348,0.000038222686,0.0014414442],"study_design_scores_gemma":[0.00051475153,0.00016924372,0.0000588558,0.00019085279,0.000010182851,0.000012683555,0.00016360318,0.997706,0.000524611,0.000004546228,0.0003742172,0.00027046047],"about_ca_topic_score_codex":0.000026937532,"about_ca_topic_score_gemma":6.808772e-8,"teacher_disagreement_score":0.9863184,"about_ca_system_score_codex":0.00036527507,"about_ca_system_score_gemma":0.00011438056,"threshold_uncertainty_score":0.9999962},"labels":[],"label_agreement":null},{"id":"W2138781282","doi":"10.1613/jair.3384","title":"Policy Invariance under Reward Transformations for General-Sum Stochastic Games","year":2011,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada; Carleton University","funders":"","keywords":"Convergence (economics); Nash equilibrium; Mathematical economics; Property (philosophy); Markov chain; Computer science; Markov decision process; Mathematical optimization; Mathematics; Markov process; Economics; Machine learning","score_opus":0.28393678730286626,"score_gpt":0.42748179026709787,"score_spread":0.14354500296423162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138781282","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":[0.0017137027,0.000059105732,0.9933514,0.0029133954,0.00040612227,0.00032744906,0.0000014810025,0.000024543868,0.0012028277],"genre_scores_gemma":[0.8490356,0.00016556735,0.14950973,0.00016414956,0.0006205224,0.000021478872,8.4914547e-7,0.000020888121,0.00046119752],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99697876,0.00021568459,0.00093936257,0.00021038689,0.000995241,0.00066059385],"domain_scores_gemma":[0.99699354,0.00056284445,0.00028935153,0.00042026973,0.0014890822,0.00024492186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033249191,0.00013895474,0.00024298855,0.00091712363,0.00034515143,0.00029324242,0.0016801326,0.00009809709,0.000053871107],"category_scores_gemma":[0.0011736267,0.00012060578,0.00017199354,0.0011926246,0.00022672358,0.0010410234,0.00013368396,0.00064882694,0.00009125513],"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":[0.00007928378,0.000091658694,0.000007100266,0.000022165028,0.000043933705,0.0000074087566,0.0042349542,0.28906798,0.0011459973,0.6682715,0.00033040036,0.036697663],"study_design_scores_gemma":[0.00008218078,0.0010966856,0.000116986186,0.00010333325,0.000009370399,0.00006430957,0.0009837464,0.5628976,0.020910177,0.41296214,0.00056213146,0.00021129072],"about_ca_topic_score_codex":0.00007209532,"about_ca_topic_score_gemma":0.000014912487,"teacher_disagreement_score":0.8473219,"about_ca_system_score_codex":0.00018663582,"about_ca_system_score_gemma":0.00089623313,"threshold_uncertainty_score":0.49181607},"labels":[],"label_agreement":null},{"id":"W2139555052","doi":"10.1287/opre.2014.1332","title":"Myopic Bounds for Optimal Policy of POMDPs: An Extension of Lovejoy’s Structural Results","year":2015,"lang":"en","type":"article","venue":"Operations Research","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Extension (predicate logic); Bounded function; Markov decision process; Mathematical optimization; Computer science; Relaxation (psychology); Upper and lower bounds; Mathematical economics; Mathematics; Markov process","score_opus":0.22538392064775611,"score_gpt":0.47345286381946544,"score_spread":0.24806894317170933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139555052","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":[0.35155785,0.000045869347,0.6426114,0.0019603523,0.00019427043,0.00077761454,0.000021515898,0.000056300294,0.0027748474],"genre_scores_gemma":[0.8164722,0.0000056317026,0.1817744,0.000016289281,0.00009303717,0.000013030871,0.000027968128,0.00000797837,0.0015895204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803525,0.00020155763,0.0003895742,0.0002817723,0.000770644,0.00032119613],"domain_scores_gemma":[0.9969363,0.00014591678,0.000047913716,0.00084684795,0.0018756775,0.00014731154],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015850494,0.00008202928,0.00015006775,0.00040140335,0.00020188751,0.00018801016,0.0008478619,0.000065078144,0.0000044512167],"category_scores_gemma":[0.0015480008,0.00007193426,0.000037802183,0.00073332636,0.00014361851,0.00068477285,0.000313355,0.00017022263,0.000009357213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048999478,0.000037606707,0.00006086512,0.000018864104,0.000011383851,8.352151e-7,0.0030300743,0.9080865,0.0045536864,0.08211383,0.000715836,0.0013215297],"study_design_scores_gemma":[0.00077128527,0.0011727145,0.00088449137,0.000016975971,0.0000019608628,0.0000037888638,0.00023100305,0.99052596,0.005063875,0.00032107084,0.000931294,0.00007560825],"about_ca_topic_score_codex":0.00048948854,"about_ca_topic_score_gemma":0.00003302232,"teacher_disagreement_score":0.4649143,"about_ca_system_score_codex":0.000111585374,"about_ca_system_score_gemma":0.0010154218,"threshold_uncertainty_score":0.29333937},"labels":[],"label_agreement":null},{"id":"W2140035747","doi":"","title":"Action selection in Bayesian reinforcement learning","year":2006,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Action selection; Machine learning; Computer science; Artificial intelligence; Bayesian probability; Markov decision process; Selection (genetic algorithm); Variable-order Bayesian network; Action (physics); Perspective (graphical); Bayesian inference; Markov process; Mathematics","score_opus":0.014056294869686356,"score_gpt":0.24991752923176236,"score_spread":0.235861234362076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140035747","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":[0.0026613828,0.0000034867428,0.9464512,0.0001792144,0.00011703459,0.0001015382,3.4477932e-9,0.00027441402,0.05021176],"genre_scores_gemma":[0.9660203,0.00000407678,0.0196898,0.00006859368,0.000056765337,0.000008202712,0.0000025754875,0.0000063786597,0.014143311],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989795,0.00004803714,0.00024927038,0.00021531558,0.0002505094,0.00025735056],"domain_scores_gemma":[0.9997022,0.00003113079,0.0000836799,0.0001222711,0.000033465014,0.000027250979],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023580476,0.000095477226,0.000082386716,0.00020046032,0.000099760924,0.000131758,0.00022401739,0.00005246604,0.00007640277],"category_scores_gemma":[0.000021793467,0.00009600167,0.000028862118,0.00050863606,0.0000096121585,0.0005628166,0.00007192036,0.00021139992,0.00008444098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017087194,0.000007359141,0.008639298,0.000004048924,0.0000016529923,0.0000014299468,0.00004153633,0.9586403,0.00089436263,0.029300006,0.00025946117,0.00220888],"study_design_scores_gemma":[0.00021617571,0.00007686849,0.009835611,0.0000082830775,0.0000010721061,0.000005050223,0.000016989074,0.9831927,0.0021549948,0.00029450186,0.0040802946,0.00011745835],"about_ca_topic_score_codex":0.00044365216,"about_ca_topic_score_gemma":0.00009680985,"teacher_disagreement_score":0.96335894,"about_ca_system_score_codex":0.00016673394,"about_ca_system_score_gemma":0.000030284678,"threshold_uncertainty_score":0.39148346},"labels":[],"label_agreement":null},{"id":"W2141050197","doi":"10.4304/jcp.2.1.12-19","title":"Noisy K Best-Paths for Approximate Dynamic Programming with Application to Portfolio Optimization","year":2007,"lang":"en","type":"article","venue":"Journal of Computers","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Dynamic programming; Computer science; Sharpe ratio; Reinforcement learning; Mathematical optimization; Portfolio; Markov decision process; Kernel (algebra); Controller (irrigation); Artificial intelligence; Markov process; Mathematics; Algorithm; Finance","score_opus":0.007554112725446023,"score_gpt":0.26092508528742103,"score_spread":0.253370972561975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141050197","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":[0.0018746416,0.000015372952,0.99678856,0.00035860424,0.0003375121,0.0004915721,1.7277402e-7,0.000047985173,0.0000855879],"genre_scores_gemma":[0.14120418,0.0000037033121,0.8584443,0.00019633694,0.00008789266,0.0000062287863,0.0000023925188,0.000014385401,0.000040634433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861336,0.000015102686,0.0004990953,0.00017892533,0.00040316713,0.00029035824],"domain_scores_gemma":[0.9984619,0.00009822647,0.00060683466,0.00025540587,0.00041900197,0.00015860384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007874601,0.00013138729,0.00019376993,0.00031165496,0.00009142764,0.00018553279,0.00064480305,0.00004413921,5.8687834e-7],"category_scores_gemma":[0.000025791169,0.00011064209,0.00007191102,0.00045676844,0.000019573175,0.00046646097,0.000075622855,0.00012991115,0.0000024839196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038993483,0.000033896173,0.00015866989,0.000019101883,0.000024454448,0.000008661911,0.0002492124,0.92359316,0.000070635084,0.0009410754,0.00007381345,0.074788325],"study_design_scores_gemma":[0.00052266865,0.00089756784,0.00022084684,0.00007888707,0.000018203957,0.00012256391,0.000037832866,0.9949246,0.00014718204,0.000041815994,0.0028452245,0.0001425778],"about_ca_topic_score_codex":0.0000014454464,"about_ca_topic_score_gemma":8.166475e-7,"teacher_disagreement_score":0.13932954,"about_ca_system_score_codex":0.00012700599,"about_ca_system_score_gemma":0.00007467023,"threshold_uncertainty_score":0.45118535},"labels":[],"label_agreement":null},{"id":"W2141650360","doi":"10.1109/icsmc.2004.1399805","title":"Reinforcement learning and aggregation","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Robustness (evolution); Artificial intelligence; Q-learning; Machine learning; Computation; Learning classifier system; Algorithm","score_opus":0.011181410940896828,"score_gpt":0.24484486953103568,"score_spread":0.23366345859013885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141650360","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":[0.0012185012,0.000033728007,0.94742215,0.0009037108,0.00004784879,0.00006100342,3.4853842e-9,0.00019350041,0.050119538],"genre_scores_gemma":[0.8951714,0.000045939993,0.086586766,0.00033514845,0.00004620094,0.0000029643027,9.370198e-7,0.000003848038,0.017806785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993676,0.000017686949,0.00013676875,0.00014957355,0.0001789615,0.00014939516],"domain_scores_gemma":[0.9996885,0.000034991288,0.00005332338,0.00014307606,0.00002940472,0.00005071993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016111284,0.00006666707,0.000055265307,0.000056222263,0.00010592486,0.00013589257,0.00016936338,0.00002538786,0.00007106165],"category_scores_gemma":[0.00003990146,0.00006029788,0.000014264852,0.000104535735,0.00001615191,0.00049236906,0.00015577192,0.000095334835,0.00014060835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.5250435e-7,0.0000020755765,0.0008910019,0.0000030764552,0.0000042192723,5.4793696e-7,0.00026507964,0.8565001,0.00011588191,0.06642469,0.0002237499,0.07556893],"study_design_scores_gemma":[0.00015044388,0.000052494357,0.00024200683,0.000006188204,0.0000013209041,0.0000051416037,0.0000141064575,0.93439424,0.0012168804,0.000056988505,0.063777946,0.000082220824],"about_ca_topic_score_codex":0.000004403381,"about_ca_topic_score_gemma":9.2374887e-7,"teacher_disagreement_score":0.8939529,"about_ca_system_score_codex":0.000028719729,"about_ca_system_score_gemma":0.000012147134,"threshold_uncertainty_score":0.24588762},"labels":[],"label_agreement":null},{"id":"W2141690016","doi":"10.1145/1553374.1553383","title":"Predictive representations for policy gradient in POMDPs","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université Laval","funders":"","keywords":"Computer science; Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.02090219095413405,"score_gpt":0.3127686912663465,"score_spread":0.29186650031221245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141690016","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":[0.00053516467,0.0000048475963,0.96375555,0.0060904985,0.00008065532,0.00030488576,4.092985e-7,0.00016927264,0.029058693],"genre_scores_gemma":[0.84627473,0.0000064485002,0.15036455,0.00092903455,0.00006565108,0.000024546538,0.0000031015065,0.000003390592,0.002328554],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992646,0.000018654186,0.00016741802,0.00020206238,0.00013372838,0.00021351977],"domain_scores_gemma":[0.9994634,0.00008116577,0.000042488224,0.00031769538,0.000046291567,0.000048958722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011757092,0.00006357427,0.00007152678,0.00019153603,0.000052957937,0.00006625759,0.00037580795,0.000025886453,0.0000027473418],"category_scores_gemma":[0.00012504883,0.00005908623,0.000035987727,0.0004139658,0.000011342566,0.00029631786,0.000050573526,0.000058042184,0.000012619719],"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":[0.0000031494358,0.00003925431,0.0006984597,0.0000018945016,0.000004637631,0.0000014481183,0.0010075811,0.33499494,0.00003886255,0.6593247,0.0013978882,0.0024871794],"study_design_scores_gemma":[0.0004157851,0.00029496796,0.026651382,0.0000064778023,0.0000018507067,0.0000026826913,0.000034964785,0.9517042,0.0002760719,0.018644972,0.0018755666,0.0000910574],"about_ca_topic_score_codex":0.000044339544,"about_ca_topic_score_gemma":0.0000041518883,"teacher_disagreement_score":0.84573954,"about_ca_system_score_codex":0.00009488997,"about_ca_system_score_gemma":0.000072027826,"threshold_uncertainty_score":0.24094665},"labels":[],"label_agreement":null},{"id":"W2142394576","doi":"10.1109/tmech.2009.2024681","title":"Sequential $Q$-Learning With Kalman Filtering for Multirobot Cooperative Transportation","year":2009,"lang":"en","type":"article","venue":"IEEE/ASME Transactions on Mechatronics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Robot; Kalman filter; Artificial intelligence; Reinforcement learning; Sequence (biology); Table (database); Q-learning; Process (computing); Domain (mathematical analysis); Algorithm; Extended Kalman filter; Machine learning; Data mining; Mathematics","score_opus":0.018342717479080454,"score_gpt":0.25790694029586303,"score_spread":0.23956422281678258,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142394576","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":[0.004290824,0.000014036688,0.9936252,0.0005005139,0.0003878388,0.000614823,0.000010095857,0.0004301499,0.00012648826],"genre_scores_gemma":[0.8364522,0.000028860522,0.16236721,0.00019122635,0.0000461803,0.00006590415,0.000027155867,0.000029953744,0.00079131126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981296,0.00006861021,0.00036286272,0.0005307709,0.00040025683,0.0005078639],"domain_scores_gemma":[0.9990377,0.00010684891,0.00015544651,0.0004076492,0.00016953716,0.00012284447],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022130994,0.00030549598,0.00025785263,0.00019120786,0.0005675035,0.00019437306,0.00046804966,0.00012483407,0.000029620362],"category_scores_gemma":[0.0000068280633,0.00029137882,0.00014713273,0.00037397243,0.000035887188,0.000720717,0.0000013586604,0.0005238146,0.000025911379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081218,0.00006634031,0.000002751907,0.000015776674,0.000049403945,0.000004479863,0.0009214664,0.9775047,0.0048312503,0.0066499324,0.000014035015,0.009858701],"study_design_scores_gemma":[0.0016707894,0.0024912339,0.000051090094,0.00007750811,0.000063985026,0.000009394436,0.00013956883,0.9591595,0.033714373,0.00014208573,0.0020180945,0.0004624124],"about_ca_topic_score_codex":0.000010044977,"about_ca_topic_score_gemma":0.00002878702,"teacher_disagreement_score":0.83216137,"about_ca_system_score_codex":0.00017089635,"about_ca_system_score_gemma":0.00012937267,"threshold_uncertainty_score":0.9999538},"labels":[],"label_agreement":null},{"id":"W2143680741","doi":"10.1109/ijcnn.2006.246661","title":"Aggregation of Reinforcement Learning Algorithms","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","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; Artificial intelligence; Learning classifier system; Instance-based learning; Machine learning; Robustness (evolution); Robot learning; Online machine learning; Unsupervised learning; Algorithm; Proactive learning; Computational learning theory; Robot","score_opus":0.036895722843877536,"score_gpt":0.2604671221146379,"score_spread":0.22357139927076036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143680741","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":[0.049716312,0.000036774738,0.8484924,0.0061775516,0.0026239974,0.0006552082,0.000001426797,0.00041113418,0.09188523],"genre_scores_gemma":[0.99110377,0.000034237986,0.0032452012,0.00032554189,0.00065769954,0.000024228499,0.000011354395,0.000015620122,0.00458232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768275,0.000029492874,0.0006294886,0.0003500003,0.00092555146,0.00038273496],"domain_scores_gemma":[0.9984043,0.000085741856,0.00066753506,0.00020430614,0.0005890745,0.000049022787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049041276,0.00023734091,0.00021681201,0.0001323221,0.00020442689,0.00030435913,0.0011973488,0.000071207505,0.000054143627],"category_scores_gemma":[0.000059877733,0.00018217634,0.00011189255,0.00034906348,0.00011276374,0.00053710106,0.00019811337,0.0004310876,0.000053676704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017510598,0.00001557444,0.00047587266,0.000007445853,0.000020591255,0.0000017095564,0.00010403849,0.8216796,0.0009959466,0.16973372,0.0033513186,0.0035966951],"study_design_scores_gemma":[0.00030718718,0.00022563328,0.0011962372,0.00013543834,0.000008588564,0.00001684128,0.000024905827,0.9881991,0.0042676604,0.0037824446,0.0016386384,0.00019733423],"about_ca_topic_score_codex":0.00006982416,"about_ca_topic_score_gemma":0.0000019158256,"teacher_disagreement_score":0.9413875,"about_ca_system_score_codex":0.00009312642,"about_ca_system_score_gemma":0.00004103505,"threshold_uncertainty_score":0.7428936},"labels":[],"label_agreement":null},{"id":"W2144283793","doi":"","title":"Bounded Finite State Controllers","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":162,"is_retracted":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":"Bounded function; Mathematical optimization; Observable; Controller (irrigation); State space; Computer science; Mathematics; State (computer science); Vulnerability (computing); Applied mathematics; Control theory (sociology); Algorithm; Control (management); Artificial intelligence; Mathematical analysis","score_opus":0.012154928724894355,"score_gpt":0.22102379852353382,"score_spread":0.20886886979863947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144283793","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":[0.00041247322,0.000008785731,0.85224074,0.00020425727,0.00025376526,0.0000800361,7.395096e-8,0.00016465232,0.14663522],"genre_scores_gemma":[0.83441085,0.000010941847,0.12185605,0.0015312276,0.000009143572,0.0000056566096,5.8818046e-7,0.000008372285,0.042167187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991403,0.000058396723,0.00015959659,0.00017926162,0.00020765582,0.00025475342],"domain_scores_gemma":[0.9992953,0.00014267609,0.000052798463,0.00039336743,0.000044314158,0.00007157396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024656623,0.00008550496,0.00009775798,0.00005526246,0.00008536689,0.0002135307,0.0003859705,0.000022157345,0.00012632195],"category_scores_gemma":[0.00015617556,0.00007308829,0.000039762963,0.00019258574,0.000026280064,0.00026774278,0.000051053248,0.00008489822,0.00043228146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017318642,0.000008968382,0.00025688743,0.000002456966,0.000018622884,0.000015541287,0.00026334927,0.6475833,0.000040527724,0.3494916,0.0014017649,0.00091522734],"study_design_scores_gemma":[0.0010096744,0.00008927753,0.00015243134,0.0000041236763,0.0000026813552,0.000008498228,0.000022574886,0.8950768,0.0008418866,0.0064775706,0.096102044,0.00021244424],"about_ca_topic_score_codex":0.000005952946,"about_ca_topic_score_gemma":0.0000015875964,"teacher_disagreement_score":0.8339984,"about_ca_system_score_codex":0.000026106316,"about_ca_system_score_gemma":0.000061874794,"threshold_uncertainty_score":0.5556248},"labels":[],"label_agreement":null},{"id":"W2144794447","doi":"","title":"Bayes-Adaptive POMDPs","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Bellman equation; Artificial intelligence; Bayesian probability; Machine learning; Bayes' theorem; Markov process; Markov chain; Mathematical optimization; Markov model; Mathematics","score_opus":0.016486388323310792,"score_gpt":0.2496534226924639,"score_spread":0.23316703436915312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144794447","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":[0.00019380926,0.000006522531,0.76025885,0.00013805066,0.00019992284,0.00004703738,1.6998529e-8,0.00031638172,0.23883939],"genre_scores_gemma":[0.52557397,0.0000017105806,0.46906033,0.0005419122,0.00004357845,6.0939396e-7,2.0792427e-7,0.000004321103,0.0047733537],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991756,0.000011874461,0.00014059778,0.00017690554,0.00023444701,0.00026054468],"domain_scores_gemma":[0.9993888,0.00009925981,0.00004017972,0.00035145573,0.000046223715,0.0000740461],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004021169,0.000072065406,0.000062717896,0.000070138114,0.000061010123,0.00006755251,0.0005549037,0.000033703265,0.000053900374],"category_scores_gemma":[0.000023692339,0.00006167231,0.000031834046,0.0002348636,0.000014925261,0.00027689637,0.00012477246,0.00009398271,0.00047512577],"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":[0.000004483453,0.000027266204,0.0013067166,0.000003115499,0.000024089743,0.000030695384,0.0007057164,0.023835994,0.00060309155,0.9552886,0.0024814354,0.015688788],"study_design_scores_gemma":[0.0007123906,0.0005751841,0.01946405,0.000017607761,0.000008943068,0.000046442132,0.00017218277,0.8578063,0.02553957,0.0036922803,0.09126528,0.00069972087],"about_ca_topic_score_codex":0.000010615431,"about_ca_topic_score_gemma":0.0000023730715,"teacher_disagreement_score":0.9515963,"about_ca_system_score_codex":0.00003904704,"about_ca_system_score_gemma":0.000024123623,"threshold_uncertainty_score":0.6106939},"labels":[],"label_agreement":null},{"id":"W2144913588","doi":"10.1613/jair.2567","title":"Online Planning Algorithms for POMDPs","year":2008,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":515,"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 Laval; McGill University","funders":"National Institute of Mental Health; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Partially observable Markov decision process; Computer science; Heuristic; Markov decision process; Mathematical optimization; Upper and lower bounds; Reduction (mathematics); Observable; Focus (optics); Computational complexity theory; Action (physics); Artificial intelligence; Machine learning; Markov process; Markov chain; Algorithm; Markov model; Mathematics","score_opus":0.4539481331437369,"score_gpt":0.4870388551056944,"score_spread":0.0330907219619575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144913588","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":[0.014141948,0.00019750088,0.98346865,0.001156918,0.0005757028,0.00019062005,9.831576e-7,0.000033475888,0.00023417981],"genre_scores_gemma":[0.5305747,0.00027932672,0.4673403,0.00009028836,0.0012374645,0.0000060515017,0.0000016241368,0.000023364328,0.00044691318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968257,0.00017088499,0.00084091205,0.00021818551,0.0013412748,0.00060307694],"domain_scores_gemma":[0.9963918,0.0010729071,0.00028978774,0.00034839587,0.0016823207,0.00021481626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003161627,0.00011930691,0.0002483997,0.0006251191,0.00046261854,0.00018137993,0.0016435031,0.00008752154,0.000018699146],"category_scores_gemma":[0.0012905208,0.00010218367,0.00015777712,0.0008386896,0.00017337737,0.0006108243,0.00023077229,0.00081630726,0.00004755243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016748704,0.0007302961,0.00048194945,0.000058903086,0.0001337133,0.00063445343,0.008394283,0.7665037,0.0038627347,0.043660197,0.004426053,0.17094626],"study_design_scores_gemma":[0.000070068,0.0015353994,0.00016696563,0.00009343179,0.000004972575,0.0003390118,0.00077266357,0.9612532,0.018687967,0.0097106695,0.007198069,0.00016753326],"about_ca_topic_score_codex":0.000008837411,"about_ca_topic_score_gemma":8.872053e-7,"teacher_disagreement_score":0.5164327,"about_ca_system_score_codex":0.00014248613,"about_ca_system_score_gemma":0.0005033809,"threshold_uncertainty_score":0.4166929},"labels":[],"label_agreement":null},{"id":"W2149347537","doi":"10.1109/icsmc.2009.5346111","title":"A novel hybrid learning technique applied to a self-learning multi-robot system","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Robot; Robot learning; Convergence (economics); Controller (irrigation); Fuzzy logic; Fuzzy control system; Artificial intelligence; Genetic algorithm; Robot control; Mobile robot; Control theory (sociology); Control (management); Machine learning","score_opus":0.01447734765549332,"score_gpt":0.2397579619282721,"score_spread":0.22528061427277876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149347537","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":[0.00036287642,0.0000063673733,0.97300464,0.00025505663,0.00012630568,0.0008400039,1.07441686e-7,0.0040722596,0.021332407],"genre_scores_gemma":[0.51080924,0.0000011141092,0.48718116,0.00029758087,0.00003849074,0.000049079066,0.0000016676445,0.000017721677,0.0016039453],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99742365,0.00008238984,0.00049915595,0.0007337205,0.00055328454,0.0007078079],"domain_scores_gemma":[0.9986384,0.000084183615,0.00021220614,0.0006677501,0.00012970694,0.00026774965],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007959013,0.0003390298,0.00035881044,0.0003344386,0.00039377366,0.00042184265,0.0012798489,0.00010298428,0.0000104351675],"category_scores_gemma":[0.00012208971,0.000328956,0.00009816957,0.0007524138,0.000015288817,0.00031008784,0.0004222257,0.00073220656,0.00045557573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054508614,0.00005537595,0.000077987264,0.000031915082,0.000018359055,0.000017009805,0.0005835861,0.938746,0.03414165,0.021007556,0.00007554933,0.005239609],"study_design_scores_gemma":[0.0005820469,0.00038924694,0.0006870045,0.000100404424,0.000011082562,0.00013091089,0.0001695251,0.9814542,0.010871104,0.000007876262,0.005052177,0.0005444566],"about_ca_topic_score_codex":0.000024725316,"about_ca_topic_score_gemma":5.8041184e-7,"teacher_disagreement_score":0.51044637,"about_ca_system_score_codex":0.00025789556,"about_ca_system_score_gemma":0.00008089656,"threshold_uncertainty_score":0.99991626},"labels":[],"label_agreement":null},{"id":"W2149385746","doi":"","title":"Direct value-approximation for factored MDPs","year":2001,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":69,"is_retracted":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":"Markov decision process; Bellman equation; Mathematical optimization; Linear programming; Linear approximation; Computation; Approximation error; Computer science; Approximation algorithm; Dynamic programming; Function (biology); Reduction (mathematics); Value (mathematics); Constraint (computer-aided design); Mathematics; Simple (philosophy); Applied mathematics; Markov process; Algorithm; Nonlinear system","score_opus":0.028321800899337682,"score_gpt":0.2669645503386068,"score_spread":0.2386427494392691,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149385746","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":[0.0009417756,0.000006879396,0.9439813,0.00038337708,0.00023889166,0.00023492645,2.1457721e-7,0.0003015996,0.053911064],"genre_scores_gemma":[0.6180343,0.000010896939,0.3667979,0.0004037589,0.00007817559,0.000033486478,0.000009311402,0.000011514368,0.01462064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992463,0.000019580433,0.00015083734,0.00019460382,0.00018490884,0.00020374861],"domain_scores_gemma":[0.9993972,0.0001102209,0.00005943455,0.00033052271,0.00005748336,0.0000451398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018552491,0.00008115468,0.000087621636,0.000056661353,0.000087469,0.00014138204,0.00041680833,0.00003696137,0.000028539453],"category_scores_gemma":[0.0000892672,0.00006905665,0.00005014611,0.00017899934,0.000011505265,0.00039725157,0.000072676405,0.000039245027,0.000065173415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011647133,0.000043613596,0.0020173574,0.000028633896,0.00003471562,0.0000026245102,0.0006989564,0.62709475,0.0014494117,0.33681443,0.0067924745,0.025011402],"study_design_scores_gemma":[0.0002321998,0.00007171811,0.0008479306,0.0000046417404,0.0000028579368,0.0000025071702,0.000008841869,0.96611464,0.0026413745,0.00083010807,0.029132117,0.00011104657],"about_ca_topic_score_codex":0.000010085775,"about_ca_topic_score_gemma":7.5868024e-7,"teacher_disagreement_score":0.61709255,"about_ca_system_score_codex":0.000034435277,"about_ca_system_score_gemma":0.000020900929,"threshold_uncertainty_score":0.28160486},"labels":[],"label_agreement":null},{"id":"W2149418961","doi":"10.1109/adprl.2007.368168","title":"Dual Representations for Dynamic Programming and Reinforcement Learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Bellman equation; Dual (grammatical number); Dynamic programming; Computer science; Mathematical optimization; Divergence (linguistics); Representation (politics); Function (biology); Linear programming; Function approximation; Markov decision process; Exploit; Artificial intelligence; Mathematics; Artificial neural network; Markov process","score_opus":0.017369933620148447,"score_gpt":0.3033845091280638,"score_spread":0.28601457550791537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149418961","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":[0.0018235635,0.000015829728,0.9918555,0.00033336692,0.00015885389,0.00039971693,3.9510912e-8,0.00025162255,0.0051614786],"genre_scores_gemma":[0.674433,0.000006436754,0.31583792,0.00008958503,0.000024286659,0.00002037652,0.0000071806016,0.000008287421,0.00957293],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988951,0.000013563767,0.00026842128,0.00026470158,0.00021186135,0.00034631457],"domain_scores_gemma":[0.99925035,0.00024272634,0.000097360215,0.00024015542,0.00008317241,0.00008624316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065216725,0.000098356526,0.000089670924,0.00011295283,0.00026450737,0.00020226232,0.0001931864,0.0000392725,0.000009304144],"category_scores_gemma":[0.00013534915,0.00009390506,0.000036843277,0.00019823696,0.000035959627,0.00035175605,0.0001865789,0.00011526617,0.000008880188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010901234,0.000014072673,0.0035009945,0.00003769438,0.000035289464,0.000007386043,0.0015487077,0.7898555,0.0004496053,0.11344747,0.00018202516,0.09091039],"study_design_scores_gemma":[0.00039864765,0.00021247382,0.0021570749,0.000010125713,0.000006922416,0.0000140962065,0.00036286053,0.98388493,0.0003406441,0.00017457697,0.012283044,0.00015460035],"about_ca_topic_score_codex":0.000013414241,"about_ca_topic_score_gemma":0.0000070127207,"teacher_disagreement_score":0.67601764,"about_ca_system_score_codex":0.000040700947,"about_ca_system_score_gemma":0.000022623188,"threshold_uncertainty_score":0.38293374},"labels":[],"label_agreement":null},{"id":"W2149586740","doi":"10.1613/jair.4117","title":"Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based on Monte-Carlo Tree Search","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":79,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Gatsby Charitable Foundation; Royal Society","keywords":"Computer science; Monte Carlo tree search; Machine learning; Reinforcement learning; Tree (set theory); Scalability; Bayesian probability; Artificial intelligence; Benchmark (surveying); Monte Carlo method; Mathematical optimization; Mathematics; Statistics","score_opus":0.1097453708321637,"score_gpt":0.354419875162297,"score_spread":0.24467450433013332,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149586740","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":[0.043451983,0.00008065807,0.9511471,0.0017067122,0.0002475839,0.00048758672,1.4752037e-7,0.000034584733,0.0028436657],"genre_scores_gemma":[0.98701805,0.00006693841,0.01195211,0.00006725278,0.00016149945,0.00001319237,2.6672038e-7,0.0000210606,0.00069964316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940898,0.00072085793,0.0009819152,0.0004229187,0.0028253356,0.0009591772],"domain_scores_gemma":[0.9952742,0.0015215272,0.0002982956,0.00051376724,0.0019376157,0.00045460858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005920767,0.0002316583,0.00035576223,0.0011152879,0.0005681771,0.00092271855,0.0013308496,0.00012302946,0.00021028398],"category_scores_gemma":[0.0012135223,0.00018946931,0.00014309991,0.0012354389,0.00035299687,0.00058064726,0.00045913667,0.0018962253,0.0003977752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000963148,0.00009252336,0.00015361364,0.00001775933,0.00002373833,0.000035000918,0.00084574043,0.9359654,0.0012066419,0.005470461,0.00020986355,0.055882897],"study_design_scores_gemma":[0.000095660325,0.0028826725,0.00022859564,0.00018114461,0.000004763602,0.000014970659,0.0012098339,0.982104,0.012364112,0.00055153307,0.00018498194,0.00017774856],"about_ca_topic_score_codex":0.0001783437,"about_ca_topic_score_gemma":0.0000034722525,"teacher_disagreement_score":0.943566,"about_ca_system_score_codex":0.00035023602,"about_ca_system_score_gemma":0.0004203224,"threshold_uncertainty_score":0.8897796},"labels":[],"label_agreement":null},{"id":"W2150468603","doi":"10.1613/jair.3912","title":"The Arcade Learning Environment: An Evaluation Platform for General Agents","year":2013,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1060,"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":"Alberta Innovates; University of Alberta; Compute Canada","keywords":"Testbed; Benchmarking; Reinforcement learning; Benchmark (surveying); Imitation; Interface (matter)","score_opus":0.29025970311617355,"score_gpt":0.4427010381262976,"score_spread":0.15244133501012402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150468603","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":[0.0776395,0.00011415057,0.9195682,0.0012941144,0.0004011518,0.00063313515,1.5214343e-7,0.000012665434,0.00033696866],"genre_scores_gemma":[0.9676027,0.00033821454,0.030571409,0.000040153758,0.0006171849,0.000060222785,0.000001990808,0.000019037963,0.00074904086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958612,0.0004719288,0.0007582436,0.00021820032,0.0020757867,0.0006146715],"domain_scores_gemma":[0.99687946,0.0009411229,0.00035926767,0.0003876486,0.0012249118,0.00020760397],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010364811,0.00011473528,0.00014583132,0.00026284528,0.00094491115,0.0010069141,0.001638236,0.00007871621,0.00014900157],"category_scores_gemma":[0.001593545,0.00007997811,0.00011056025,0.0003240265,0.00018970013,0.0013434042,0.00021957389,0.0008387021,0.0002262879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002452238,0.000038752758,0.00006165066,0.0000045992624,0.000023130397,0.00000178245,0.0011417979,0.56498045,0.0025405593,0.017244529,0.00031156326,0.4136267],"study_design_scores_gemma":[0.00004503443,0.00085899216,0.00022363587,0.0000164548,0.0000057532498,0.000010975389,0.0008975657,0.9479652,0.008820786,0.03571634,0.005351497,0.00008775616],"about_ca_topic_score_codex":0.000029253295,"about_ca_topic_score_gemma":0.0000033937415,"teacher_disagreement_score":0.88996327,"about_ca_system_score_codex":0.0002630366,"about_ca_system_score_gemma":0.00022404343,"threshold_uncertainty_score":0.97096956},"labels":[],"label_agreement":null},{"id":"W2150526575","doi":"10.1109/tai.2002.1180840","title":"Reinforcement learning in multiagent systems: a modular fuzzy approach with internal model capabilities","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Modular design; Computer science; Robustness (evolution); Fuzzy logic; Artificial intelligence; Multi-agent system; Fuzzy rule; Fuzzy control system; State space; Mathematics","score_opus":0.019054210749540022,"score_gpt":0.22208761357715973,"score_spread":0.2030334028276197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2150526575","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":[0.007244702,0.000042404954,0.9221721,0.000030799958,0.000097496915,0.00043685516,6.503842e-8,0.00020503576,0.06977054],"genre_scores_gemma":[0.8720467,0.000008460594,0.11547912,0.000079470425,0.000009086956,0.000077224286,0.0000022170773,0.000017931194,0.01227978],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768084,0.00016732253,0.00049199385,0.0005030522,0.00062954944,0.00052723417],"domain_scores_gemma":[0.9989549,0.000057485715,0.00015165766,0.0006201662,0.00009896279,0.000116839525],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007159676,0.00026050297,0.00027640528,0.00022547926,0.000107188025,0.00028143742,0.0006536544,0.000072856936,0.000010218609],"category_scores_gemma":[0.00009024979,0.00020730577,0.00005368659,0.0003136465,0.000060982085,0.00056470605,0.00017750722,0.0003922088,0.00002291255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006541833,0.00002837447,0.0017470546,0.000058285605,0.000020278481,0.000006923266,0.0019789184,0.8729959,0.000023876828,0.12303875,0.000022278948,0.00007277916],"study_design_scores_gemma":[0.0007301567,0.00017164368,0.00006270754,0.00006539327,0.0000046196883,0.000025738611,0.0010785313,0.9970807,0.00009836602,0.00008548034,0.00031446636,0.00028223734],"about_ca_topic_score_codex":0.00022107754,"about_ca_topic_score_gemma":0.0000042839797,"teacher_disagreement_score":0.864802,"about_ca_system_score_codex":0.00025916964,"about_ca_system_score_gemma":0.00013667512,"threshold_uncertainty_score":0.8453684},"labels":[],"label_agreement":null},{"id":"W2151416233","doi":"","title":"Fitted Q-iteration in continuous action-space MDPs","year":2007,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Action (physics); Q-learning; Bellman equation; Trajectory; Set (abstract data type); Mathematical optimization; Action selection; Markov decision process; State space; Computer science; State (computer science); Function (biology); Value (mathematics); Space (punctuation); Selection (genetic algorithm); Mathematics; Algorithm; Artificial intelligence; Markov process; Machine learning; Statistics","score_opus":0.013775759560532399,"score_gpt":0.24041286006998908,"score_spread":0.22663710050945668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151416233","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":[0.052954167,0.00007786212,0.9087112,0.00454998,0.0001914444,0.00020670198,6.722555e-7,0.00024336486,0.0330646],"genre_scores_gemma":[0.899999,0.000048846818,0.09045593,0.00015985244,0.000015592172,0.000009687915,0.000031450832,0.000015845708,0.009263756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703264,0.0013137775,0.00043666075,0.00043581027,0.00039654717,0.00038453497],"domain_scores_gemma":[0.9964423,0.0011599986,0.0002689856,0.001188625,0.00081986526,0.00012019787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005217011,0.00016775221,0.00017498493,0.00027398963,0.00022689122,0.00041984583,0.0009865747,0.000113380585,0.000042010106],"category_scores_gemma":[0.0010148891,0.00018595389,0.000066434186,0.0008924998,0.00007896763,0.0005789692,0.00030281782,0.00031247298,0.000079019366],"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":[0.0000260956,0.0005725659,0.034028843,0.0000694524,0.000049012273,0.00004200169,0.02678034,0.017818432,0.023424525,0.74420875,0.0019803434,0.15099965],"study_design_scores_gemma":[0.0016640387,0.0000022740526,0.071185835,0.0006460989,0.0000117688105,0.000034634522,0.00031723664,0.7491357,0.13085824,0.0016020631,0.04381804,0.0007240969],"about_ca_topic_score_codex":0.00032203557,"about_ca_topic_score_gemma":0.0009546096,"teacher_disagreement_score":0.8470449,"about_ca_system_score_codex":0.00013591554,"about_ca_system_score_gemma":0.00008343826,"threshold_uncertainty_score":0.758298},"labels":[],"label_agreement":null},{"id":"W2151620419","doi":"10.1111/coin.12016","title":"EFFICIENT ABSTRACTION SELECTION IN REINFORCEMENT LEARNING","year":2013,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Abstraction; Markov decision process; Action selection; Selection (genetic algorithm); Context (archaeology); Artificial intelligence; Set (abstract data type); Machine learning; State space; Class (philosophy); Theoretical computer science; Markov process; Programming language; Mathematics; Agency (philosophy)","score_opus":0.02106858788774564,"score_gpt":0.2715625062281282,"score_spread":0.2504939183403826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151620419","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":[0.017015945,0.000014732059,0.9795288,0.00023318437,0.00019903114,0.00025835732,2.6028712e-8,0.00015434122,0.0025956016],"genre_scores_gemma":[0.9560931,0.0000041222024,0.043203153,0.0001177766,0.00003062712,0.00003614579,0.000004971205,0.0000072158296,0.000502901],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985027,0.00005782307,0.00042412456,0.00030916452,0.0004336165,0.00027260988],"domain_scores_gemma":[0.9992269,0.00022014594,0.00015544891,0.00010966671,0.00022116599,0.00006666577],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00026281676,0.00013118706,0.00010518414,0.000248718,0.00013348745,0.00020684632,0.00037780567,0.00005319104,0.0001949292],"category_scores_gemma":[0.00011124552,0.0001389468,0.00003319366,0.00059951254,0.000032741096,0.0003306111,0.000114515584,0.00031459137,0.0011878206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014567343,0.000019250036,0.000683996,0.000006718573,0.000004422254,0.0000012016732,0.00030005278,0.9697675,0.00011724386,0.020181313,0.000049691705,0.008867132],"study_design_scores_gemma":[0.000057477566,0.00008520791,0.013368005,0.000024552535,0.0000010162044,0.000010493158,0.000047573707,0.9829576,0.00035338156,0.0027991335,0.00015075426,0.00014478194],"about_ca_topic_score_codex":0.00010060251,"about_ca_topic_score_gemma":0.0000018792991,"teacher_disagreement_score":0.93907714,"about_ca_system_score_codex":0.00020360241,"about_ca_system_score_gemma":0.00006746529,"threshold_uncertainty_score":0.99958986},"labels":[],"label_agreement":null},{"id":"W2152469292","doi":"10.3166/ria.27.171-194","title":"Stratégies d’échantillonnage pour l’apprentissage par renforcement batch","year":2013,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.051993114263749474,"score_gpt":0.2708318065741388,"score_spread":0.21883869231038933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152469292","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":[0.004526824,0.0026941597,0.9339709,0.012170918,0.004648232,0.0011850325,0.0000075088697,0.0003016531,0.04049472],"genre_scores_gemma":[0.7318645,0.0011520997,0.024097096,0.00038624572,0.00048105355,0.000109912056,0.000019357254,0.000070915805,0.24181882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944025,0.0002697365,0.001570048,0.0012641192,0.00077011506,0.0017234237],"domain_scores_gemma":[0.9959149,0.0004050531,0.0005817779,0.0020931796,0.0005334381,0.00047168377],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00086283445,0.00071525155,0.0006311896,0.0002628387,0.00058534846,0.0016680141,0.0022951746,0.0003614101,0.009798909],"category_scores_gemma":[0.0002925218,0.0007848802,0.00037985068,0.0011306929,0.00048532023,0.0019573057,0.0009970115,0.0008239154,0.026839873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005541291,0.00022715557,0.00038975765,0.00036946373,0.00009687133,0.000078787045,0.0040553357,0.80125374,0.0031206575,0.076459974,0.025156904,0.08878583],"study_design_scores_gemma":[0.0000893791,0.0003252882,0.00020096658,0.000638481,0.000048565413,0.00007590153,0.002350319,0.900871,0.03250007,0.0035728714,0.058534916,0.00079228234],"about_ca_topic_score_codex":0.0007460593,"about_ca_topic_score_gemma":0.00002070306,"teacher_disagreement_score":0.90987384,"about_ca_system_score_codex":0.00019580513,"about_ca_system_score_gemma":0.00021666026,"threshold_uncertainty_score":0.9994602},"labels":[],"label_agreement":null},{"id":"W2152711271","doi":"10.1109/acc.2011.5990832","title":"Decentralized learning in two-player zero-sum games: A L&lt;inf&gt;R-I&lt;/inf&gt; lagging anchor algorithm","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Lagging; Zero (linguistics); Algorithm; Action (physics); Computer science; Zero-sum game; Matrix (chemical analysis); Nash equilibrium; Artificial intelligence; Mathematics; Discrete mathematics; Mathematical optimization; Statistics; Physics; Philosophy","score_opus":0.025089321999201167,"score_gpt":0.26151948006262016,"score_spread":0.236430158063419,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152711271","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":[0.010561513,0.00019686745,0.9586629,0.00019774074,0.00079815224,0.00049330667,7.968735e-7,0.00096385996,0.028124828],"genre_scores_gemma":[0.54560304,0.00020011523,0.44379428,0.0009724773,0.0001278884,0.000058126767,0.000013571686,0.00008730453,0.009143195],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99522686,0.00031799785,0.0009791482,0.0010262134,0.0009170486,0.0015327553],"domain_scores_gemma":[0.99767333,0.0002654094,0.00039531992,0.0011126075,0.00018761995,0.00036573628],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011466916,0.0005647627,0.0006183231,0.00052363717,0.00027981226,0.00045894776,0.0018325921,0.00018930291,0.0006724515],"category_scores_gemma":[0.00029421496,0.00053995964,0.00020359336,0.0011527243,0.00011949359,0.0014154621,0.00077379117,0.0008435529,0.0007453297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118036536,0.00052743446,0.059192494,0.00015874783,0.00033540837,0.0008058413,0.022648653,0.6368428,0.0069433707,0.06740467,0.008341985,0.19668059],"study_design_scores_gemma":[0.002504537,0.00023027386,0.0051527494,0.00016961571,0.000024785233,0.00005097678,0.0001358959,0.955119,0.0019868815,0.0005215102,0.03319576,0.0009080011],"about_ca_topic_score_codex":0.00021783607,"about_ca_topic_score_gemma":0.000054956854,"teacher_disagreement_score":0.5350415,"about_ca_system_score_codex":0.00024099981,"about_ca_system_score_gemma":0.00017791778,"threshold_uncertainty_score":0.9997052},"labels":[],"label_agreement":null},{"id":"W2153516274","doi":"10.5555/2772879.2773311","title":"Incremental Policy Iteration with Guaranteed Escape from Local Optima in POMDP Planning","year":2015,"lang":"en","type":"article","venue":"Kent Academic Repository (University of Kent)","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Partially observable Markov decision process; Mathematical optimization; Markov decision process; Local optimum; Bounded function; Controller (irrigation); Local search (optimization); State (computer science); Markov chain; Markov process; Artificial intelligence; Markov model; Algorithm; Mathematics; Machine learning","score_opus":0.019518381185233375,"score_gpt":0.22832623942463323,"score_spread":0.20880785823939985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2153516274","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":[0.5112414,0.00009686719,0.48542482,0.0003034094,0.00014807694,0.00016038869,0.0000010703591,0.00007555215,0.002548419],"genre_scores_gemma":[0.9871295,0.0000099856225,0.0122183915,0.00009016383,0.000076836666,3.7924138e-7,0.000012522146,0.0000087863145,0.00045343844],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983536,0.00012564159,0.000265118,0.00037734734,0.0006018508,0.000276449],"domain_scores_gemma":[0.9990684,0.00005334439,0.0003069815,0.00034027762,0.000080177735,0.00015082688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025400263,0.00016571012,0.00022855442,0.0002707051,0.00013190147,0.000049198436,0.00096045417,0.00016631775,0.000005499678],"category_scores_gemma":[0.00001946257,0.00018749107,0.00004942969,0.00041948646,0.00013942219,0.0009912037,0.00030736247,0.00045247568,0.000016307564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026905804,0.000055242777,0.1633542,0.000021621967,0.00007560067,0.0002504766,0.017834703,0.8083981,0.0058566993,0.0014881786,0.0015642673,0.0008317937],"study_design_scores_gemma":[0.0034124814,0.00044895356,0.044042923,0.0004166347,0.000035538935,0.00006398937,0.005528101,0.9411195,0.0031103776,0.00014112076,0.0012383215,0.00044206838],"about_ca_topic_score_codex":0.0012767875,"about_ca_topic_score_gemma":0.000008401803,"teacher_disagreement_score":0.4758881,"about_ca_system_score_codex":0.0005038314,"about_ca_system_score_gemma":0.0002587375,"threshold_uncertainty_score":0.76456636},"labels":[],"label_agreement":null},{"id":"W2156760524","doi":"10.1109/ijcnn.1999.833417","title":"Adaptive exploration in reinforcement learning","year":2003,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Implementation; Artificial intelligence; Connectionism; Machine learning; Reinforcement; Learning classifier system; Artificial neural network; Engineering; Software engineering","score_opus":0.036640872771695775,"score_gpt":0.2510125592442868,"score_spread":0.214371686472591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156760524","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":[0.00025769754,0.000008717811,0.8748337,0.000100932986,0.000115001196,0.00011281525,3.2234484e-9,0.00010992328,0.12446118],"genre_scores_gemma":[0.9425653,0.000013148552,0.05075844,0.00014474719,0.000007485241,0.000014791253,9.546239e-7,0.000005259278,0.006489839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900603,0.00009740243,0.0002239208,0.00020201609,0.00024212095,0.00022851606],"domain_scores_gemma":[0.99955887,0.00005297191,0.00006911222,0.00023611466,0.00004068462,0.000042243482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037251815,0.000091103306,0.00008608391,0.0001286319,0.00006593943,0.00008711098,0.0002473037,0.000035570654,0.00007313519],"category_scores_gemma":[0.00009589735,0.000087237226,0.000018888575,0.0003735603,0.00001245517,0.0009163018,0.00006769198,0.0001712351,0.00019220698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.828794e-7,0.0000038106482,0.00037263142,0.0000010416989,0.0000018656267,0.0000024072717,0.00044034477,0.7372749,0.00003744638,0.26094577,0.000049057442,0.0008698417],"study_design_scores_gemma":[0.00028280134,0.0001788445,0.00016005391,0.0000107331025,8.2414e-7,0.000001877192,0.0002474098,0.9912731,0.0011903738,0.0009822652,0.0055352803,0.00013644707],"about_ca_topic_score_codex":0.000014994307,"about_ca_topic_score_gemma":0.0000044833264,"teacher_disagreement_score":0.94230765,"about_ca_system_score_codex":0.000080402264,"about_ca_system_score_gemma":0.000044518416,"threshold_uncertainty_score":0.35574308},"labels":[],"label_agreement":null},{"id":"W2157544132","doi":"10.48550/arxiv.1207.5554","title":"Bellman Error Based Feature Generation using Random Projections on Sparse Spaces","year":2012,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Bellman equation; Computer science; Logarithm; Dimension (graph theory); Sparse approximation; Contraction (grammar); Representation (politics); Mathematical optimization; Algorithm; Feature (linguistics); Convergence (economics); Mathematics; Artificial intelligence","score_opus":0.03420690341322675,"score_gpt":0.2673350574748708,"score_spread":0.23312815406164406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157544132","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":[0.031162454,0.00023995482,0.962495,0.0031228187,0.00058562803,0.00089088734,0.00000454453,0.0008384292,0.0006602691],"genre_scores_gemma":[0.657027,0.000012389325,0.33974057,0.0016474725,0.0003896601,0.00014702175,0.000019884597,0.00004147752,0.0009744765],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751955,0.00025504536,0.00034657415,0.00044680096,0.0005648201,0.0008671949],"domain_scores_gemma":[0.99805397,0.00012131051,0.00029629908,0.0011034003,0.00011888692,0.00030615204],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008672715,0.00036371098,0.00029911214,0.00056932436,0.0006104972,0.0004725306,0.00070058176,0.00028031142,0.000015657559],"category_scores_gemma":[0.00020536625,0.00034733248,0.00016800956,0.00082558935,0.00005964483,0.0010519784,0.00019021564,0.0005427556,0.000032874643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004159927,0.00018218915,0.011096627,0.000018134511,0.000033572145,0.000009378728,0.000390941,0.9509068,0.012816982,0.018900793,0.0038832084,0.0017197508],"study_design_scores_gemma":[0.00073191983,0.00014173152,0.002877176,0.000041636646,0.000029400218,0.00004093179,0.000027025877,0.97485816,0.01678564,0.000051099745,0.00403326,0.00038198795],"about_ca_topic_score_codex":0.00095934037,"about_ca_topic_score_gemma":0.0002076844,"teacher_disagreement_score":0.62586457,"about_ca_system_score_codex":0.0005215196,"about_ca_system_score_gemma":0.00023735562,"threshold_uncertainty_score":0.9998979},"labels":[],"label_agreement":null},{"id":"W2157864803","doi":"","title":"Action-Gap Phenomenon in Reinforcement Learning","year":2011,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Action (physics); Phenomenon; Bounded function; Q-learning; Bellman equation; Function (biology); Value (mathematics); Mathematics; Reinforcement; Computer science; Mathematical optimization; Artificial intelligence; Statistics; Mathematical analysis; Physics; Engineering; Structural engineering","score_opus":0.03411165688407607,"score_gpt":0.24838523452784825,"score_spread":0.21427357764377217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157864803","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":[0.009943073,0.00013183661,0.97055715,0.00044118267,0.00022567662,0.0005303891,3.1975e-7,0.0009728189,0.017197566],"genre_scores_gemma":[0.86109287,0.00014739441,0.13438202,0.00080157485,0.000059266236,0.00022632175,0.000006906329,0.000043018103,0.0032406128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971056,0.00017447493,0.00067108206,0.0005699246,0.00052026444,0.000958628],"domain_scores_gemma":[0.99814206,0.00008716878,0.00034156526,0.0010758783,0.00009302535,0.00026031496],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092849927,0.00035668846,0.00033323388,0.00073422334,0.00025025048,0.00022245021,0.0013675743,0.0002211498,0.00011613244],"category_scores_gemma":[0.00017632986,0.00038343805,0.00010428421,0.0009577348,0.00006362168,0.0010846172,0.00057751616,0.0008173765,0.00011260571],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004558981,0.000120350654,0.038923424,0.000035598536,0.000038044494,0.00008261863,0.0028704728,0.8165485,0.0020665396,0.12330357,0.0003105552,0.015654722],"study_design_scores_gemma":[0.0005910658,0.0004264032,0.023685878,0.000060293038,0.0000099796225,0.000041702257,0.00018168024,0.96468496,0.004902469,0.0018654328,0.0030021218,0.0005480355],"about_ca_topic_score_codex":0.004657289,"about_ca_topic_score_gemma":0.00043570288,"teacher_disagreement_score":0.8511498,"about_ca_system_score_codex":0.0007129125,"about_ca_system_score_gemma":0.00019198334,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W2158304715","doi":"10.1109/tsmcb.2007.899419","title":"Positive Impact of State Similarity on Reinforcement Learning Performance","year":2007,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Reinforcement learning; Similarity (geometry); Artificial intelligence; Context (archaeology); Computer science; Reinforcement; Function (biology); Bellman equation; Tree (set theory); State (computer science); Action (physics); Machine learning; Value (mathematics); Mathematics; Mathematical optimization; Algorithm; Engineering","score_opus":0.01715931351416537,"score_gpt":0.2565818502936981,"score_spread":0.23942253677953276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158304715","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":[0.20742388,0.00005768205,0.7840869,0.000030090334,0.00067135406,0.00053758384,0.000007870045,0.00013743987,0.0070472136],"genre_scores_gemma":[0.992153,0.00036241993,0.0005845778,0.0000690491,0.000058702874,0.000016811991,0.0000060931848,0.00004396878,0.0067053903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655855,0.00016737368,0.00097631355,0.00061644823,0.00091843423,0.000762912],"domain_scores_gemma":[0.9977781,0.00036500508,0.00048599034,0.0007690185,0.00026446892,0.00033738976],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094304513,0.00048649887,0.0005156912,0.00038989342,0.00033920258,0.00022362823,0.00055810815,0.00019083895,0.000029648145],"category_scores_gemma":[0.000014486233,0.00045659931,0.00021667809,0.00045097212,0.00019975491,0.00025415682,0.000019960024,0.0007678471,0.000084932966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010933079,0.000116505544,0.0007265596,0.000079477904,0.00016527086,0.00001284012,0.001455078,0.99016947,0.0003239034,0.00097603403,0.00009522978,0.00577028],"study_design_scores_gemma":[0.0016666735,0.005781939,0.011061025,0.0006560808,0.00009112738,0.000060212704,0.00018623593,0.9583239,0.0195062,0.000034954028,0.0017099087,0.0009217653],"about_ca_topic_score_codex":0.00025176344,"about_ca_topic_score_gemma":0.000017646467,"teacher_disagreement_score":0.7847291,"about_ca_system_score_codex":0.00026192263,"about_ca_system_score_gemma":0.000090390924,"threshold_uncertainty_score":0.9997886},"labels":[],"label_agreement":null},{"id":"W2158738729","doi":"","title":"Regularized Policy Iteration","year":2008,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":108,"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; University of Alberta","funders":"","keywords":"Reinforcement learning; Mathematical optimization; Regularization (linguistics); Reproducing kernel Hilbert space; Temporal difference learning; Computer science; Bellman equation; Markov decision process; Kernel (algebra); Residual; Hilbert space; Parametric statistics; Convergence (economics); Function approximation; Rate of convergence; Algorithm; Mathematics; Artificial intelligence; Markov process; Artificial neural network","score_opus":0.013613790347172965,"score_gpt":0.2341841148069613,"score_spread":0.22057032445978833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158738729","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":[0.011901583,0.00013044248,0.9768935,0.006540798,0.00015332786,0.00044970468,0.0000020499663,0.001467012,0.0024616253],"genre_scores_gemma":[0.5925515,0.000128722,0.39845273,0.003250908,0.00020978611,0.0001312214,0.000014646185,0.00003765041,0.005222841],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974926,0.00015663238,0.0005062401,0.0005044159,0.00058752747,0.0007525987],"domain_scores_gemma":[0.9977376,0.000095015836,0.00025186143,0.001471461,0.00015633038,0.0002877525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047077463,0.0003094737,0.00029984827,0.00065957225,0.00050606194,0.00031372032,0.001314647,0.0002315038,0.000018611088],"category_scores_gemma":[0.0003584282,0.00031975712,0.00016120702,0.0011502436,0.00010277832,0.0010569087,0.0004395104,0.000400826,0.00009018645],"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":[0.000045630124,0.00017170607,0.016749352,0.000031313983,0.00007035593,0.00026275025,0.0017662332,0.30870065,0.021356078,0.6291784,0.008296905,0.013370605],"study_design_scores_gemma":[0.0005910139,0.00015412865,0.019934306,0.000025183566,0.000007102347,0.0004419751,0.000009519779,0.9604462,0.008672397,0.0023802028,0.0068974486,0.00044053793],"about_ca_topic_score_codex":0.0019717677,"about_ca_topic_score_gemma":0.00006714044,"teacher_disagreement_score":0.65174556,"about_ca_system_score_codex":0.000498026,"about_ca_system_score_gemma":0.00050437363,"threshold_uncertainty_score":0.99992543},"labels":[],"label_agreement":null},{"id":"W2159008857","doi":"","title":"Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods","year":2005,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"octopus (software); Gaussian process; Robotic arm; Reinforcement learning; Temporal difference learning; Computer science; Artificial intelligence; Process (computing); Domain (mathematical analysis); Bayesian optimization; Bayesian probability; State space; Trajectory; Machine learning; Computer vision; Gaussian; Mathematics","score_opus":0.020160526124716367,"score_gpt":0.3137583755310238,"score_spread":0.29359784940630745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159008857","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":[0.028591136,0.000030065037,0.96767163,0.000600391,0.00025002274,0.00058658246,7.5801387e-7,0.0006732757,0.0015961657],"genre_scores_gemma":[0.94615877,5.590228e-7,0.052372146,0.0007577442,0.00013476291,0.00009679658,0.000014835605,0.00001683829,0.00044757282],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744964,0.00022205863,0.00078269496,0.000317184,0.0007189612,0.00050944585],"domain_scores_gemma":[0.99811417,0.00006351039,0.0006660353,0.00041267503,0.00046254767,0.00028104457],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007647283,0.00030568658,0.00034127093,0.00030612486,0.00046906632,0.0020997173,0.0009455087,0.00010140648,0.0000038117846],"category_scores_gemma":[0.000120636876,0.00023576156,0.00003447767,0.0007447276,0.000042756958,0.0071433196,0.00007197191,0.00040925303,0.00006452866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002128273,0.000016529884,0.0012754579,0.00018089627,0.00000758873,0.0000011393112,0.0072933836,0.8867991,0.000106216445,0.0005555853,0.000018979754,0.10372387],"study_design_scores_gemma":[0.00058863056,0.0006137023,0.00076435175,0.00016700663,0.000008962836,0.00008004194,0.00089896703,0.99288934,0.00043356416,0.000008906447,0.003192978,0.00035355703],"about_ca_topic_score_codex":0.000030212756,"about_ca_topic_score_gemma":0.0000028099473,"teacher_disagreement_score":0.9175676,"about_ca_system_score_codex":0.00011191508,"about_ca_system_score_gemma":0.0001716455,"threshold_uncertainty_score":0.9989362},"labels":[],"label_agreement":null},{"id":"W2159136633","doi":"10.5555/2627435.2750354","title":"Efficient learning and planning with compressed predictive states","year":2014,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","score_opus":0.0249183959460578,"score_gpt":0.331304983517485,"score_spread":0.30638658757142717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159136633","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":[0.18937214,0.0003850899,0.80815166,0.00047339028,0.00008708872,0.000105578954,1.394694e-7,0.000062026964,0.0013628802],"genre_scores_gemma":[0.9846391,0.000052986285,0.014525572,0.000024906052,0.00014870182,0.000002234473,0.0000015108037,0.000025651465,0.0005793448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957034,0.001343142,0.00044258544,0.00029488566,0.0016455492,0.000570457],"domain_scores_gemma":[0.9959605,0.0022366897,0.00045583717,0.00021064423,0.00088193244,0.00025442013],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0058949534,0.00018196643,0.00034164297,0.0006333191,0.00062055833,0.0004457496,0.00073786924,0.00006792065,0.000013938108],"category_scores_gemma":[0.0021851074,0.00013327216,0.00005125783,0.00058615755,0.00020476486,0.00022323005,0.00047032477,0.0031186072,0.000009896463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013151037,0.000027168242,0.056979213,0.0000376587,0.0000519098,0.00005595272,0.0025308647,0.9361988,0.00026034296,0.00047113342,0.00006811733,0.0031873756],"study_design_scores_gemma":[0.0010115352,0.0029844635,0.007667805,0.0002789267,0.00000966031,0.00015179154,0.00046110046,0.9808924,0.0001317663,0.00008085598,0.0061861984,0.00014349236],"about_ca_topic_score_codex":0.000022216396,"about_ca_topic_score_gemma":4.2095107e-7,"teacher_disagreement_score":0.795267,"about_ca_system_score_codex":0.000080681,"about_ca_system_score_gemma":0.00010767062,"threshold_uncertainty_score":0.9991812},"labels":[],"label_agreement":null},{"id":"W2159272820","doi":"10.1613/jair.3175","title":"Non-Deterministic Policies in Markovian Decision Processes","year":2011,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"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":"National Institutes of Health; Duke-NUS Medical School; Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Reinforcement learning; Computer science; Flexibility (engineering); Markov decision process; Set (abstract data type); Task (project management); Action selection; Markov process; Construct (python library); Process (computing); Action (physics); Decision problem; Artificial intelligence; Selection (genetic algorithm); Decision support system; Machine learning; Operations research; Algorithm; Mathematics; Engineering","score_opus":0.23871200327016803,"score_gpt":0.42671615641768834,"score_spread":0.1880041531475203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159272820","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":[0.083281286,0.00007090092,0.91266733,0.00022231613,0.00036898375,0.0001577288,1.9183761e-7,0.000012367402,0.0032188948],"genre_scores_gemma":[0.9673474,0.00017806583,0.03220369,0.000027752356,0.0001334822,0.0000034305906,8.985341e-8,0.000010730807,0.00009538501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967707,0.00015409087,0.0009914415,0.0002211468,0.0012708976,0.0005917335],"domain_scores_gemma":[0.99711394,0.0008335555,0.00027633947,0.00037497774,0.0012106369,0.00019053374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038191376,0.00012722067,0.00024954896,0.0012199546,0.00015356898,0.00029138298,0.0020780328,0.00008744935,0.00007762185],"category_scores_gemma":[0.0027555989,0.00010503458,0.00007118322,0.0019182384,0.0002285508,0.0007699018,0.00037409685,0.0007933617,0.0001521819],"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":[0.0008799643,0.0011040197,0.012893447,0.00034154524,0.000068877445,0.0018762836,0.048470978,0.08950875,0.005101085,0.055215433,0.0008626198,0.783677],"study_design_scores_gemma":[0.00024320355,0.00621681,0.015602529,0.0018849899,0.000015886624,0.00048969703,0.007659744,0.5799738,0.15763931,0.22816664,0.0012300133,0.0008773938],"about_ca_topic_score_codex":0.00009503392,"about_ca_topic_score_gemma":0.000063946834,"teacher_disagreement_score":0.8840661,"about_ca_system_score_codex":0.0001350784,"about_ca_system_score_gemma":0.00067231985,"threshold_uncertainty_score":0.4283186},"labels":[],"label_agreement":null},{"id":"W2159666783","doi":"10.5555/1838206.1838251","title":"Using spatial hints to improve policy reuse in a reinforcement learning agent","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Reinforcement learning; Reuse; Computer science; Exploit; Robustness (evolution); Task (project management); Domain (mathematical analysis); Artificial intelligence; Human–computer interaction; Machine learning; Data science; Computer security; Engineering; Systems engineering","score_opus":0.02532803722935456,"score_gpt":0.3020450763178422,"score_spread":0.27671703908848766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159666783","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":[0.07614447,9.101863e-7,0.91446203,0.0008018592,0.00069513347,0.00033060432,7.870811e-8,0.0001588681,0.0074060587],"genre_scores_gemma":[0.8621309,0.0000016415098,0.13325812,0.00074029074,0.00017749365,0.000011407057,0.000001196725,0.000015917185,0.0036630773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980642,0.000048920883,0.00043290737,0.0004311276,0.00045483073,0.0005679854],"domain_scores_gemma":[0.99844676,0.00005388235,0.00013154016,0.0010739708,0.00007915369,0.00021472006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005037087,0.00019395092,0.0001832133,0.00045419895,0.00012536482,0.00025557514,0.0013537531,0.00009246491,0.0001062146],"category_scores_gemma":[0.0009272161,0.00018574121,0.000046664798,0.0006063385,0.000025866879,0.00040314262,0.0014877517,0.00055934774,0.00027528833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058733326,0.000012868276,0.0013729852,0.0000069286657,0.0000064240903,0.000011469754,0.0010927645,0.94296795,0.041087586,0.008100243,0.00008306024,0.005251816],"study_design_scores_gemma":[0.00040100657,0.00019429026,0.0014742689,0.000019280935,0.000002287066,0.000006467149,0.000024243358,0.98594856,0.0060331714,0.0001284243,0.0055052764,0.00026272834],"about_ca_topic_score_codex":0.0031645594,"about_ca_topic_score_gemma":0.00015172972,"teacher_disagreement_score":0.78598636,"about_ca_system_score_codex":0.00021208769,"about_ca_system_score_gemma":0.00021139595,"threshold_uncertainty_score":0.7574307},"labels":[],"label_agreement":null},{"id":"W2159849946","doi":"","title":"Universal Option Models","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Function (biology); Consistency (knowledge bases); Domain (mathematical analysis); Task (project management); Relevance (law); Preference; Construct (python library); Mathematical optimization; Computation; Mathematics; Artificial intelligence; Algorithm; Economics","score_opus":0.015026671304967964,"score_gpt":0.20617425160361055,"score_spread":0.1911475802986426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159849946","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":[0.00028946603,8.818433e-7,0.8667594,0.00025939356,0.0001113414,0.000022901562,8.753784e-9,0.00017124164,0.13238537],"genre_scores_gemma":[0.82721597,0.0000016133197,0.16721374,0.00021844203,0.000021106618,4.1331086e-7,4.478233e-7,0.0000023116183,0.0053259833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995859,0.000020045594,0.000058203543,0.000108902175,0.00012515651,0.000101773825],"domain_scores_gemma":[0.99964195,0.00002444636,0.000021700522,0.0002536426,0.000025137437,0.000033102817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010868106,0.000039718823,0.00003745064,0.000035337835,0.000039222363,0.00006346341,0.0003552014,0.000020483993,0.000014510759],"category_scores_gemma":[0.000008957973,0.00003566397,0.000016527578,0.00008632094,0.000009751057,0.00049413147,0.00010685829,0.000042198437,0.0001592591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.3380102e-7,9.545846e-7,0.000008932583,4.3544256e-7,7.0348534e-7,1.18043715e-7,0.00003134576,0.5130403,0.000019792402,0.48510993,0.00014378392,0.0016435474],"study_design_scores_gemma":[0.00008242006,0.000030805404,0.00005427653,0.0000016277368,6.887912e-7,9.476649e-7,0.000004545911,0.989227,0.00011276181,0.006534628,0.003899739,0.00005057077],"about_ca_topic_score_codex":0.000008342619,"about_ca_topic_score_gemma":3.5182688e-7,"teacher_disagreement_score":0.82692647,"about_ca_system_score_codex":0.000016738066,"about_ca_system_score_gemma":0.000009360574,"threshold_uncertainty_score":0.20470066},"labels":[],"label_agreement":null},{"id":"W2161677453","doi":"10.1109/ical.2008.4636228","title":"Q-learning based multi-robot box-pushing with minimal switching of actions","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Robot; Computer science; Reinforcement learning; Action (physics); Robot learning; Artificial intelligence; Mobile robot","score_opus":0.04728716757252466,"score_gpt":0.26318817795017335,"score_spread":0.2159010103776487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161677453","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":[0.04408523,0.0000058056785,0.95224553,0.00020754953,0.000106441184,0.000105592335,6.992807e-8,0.00027955478,0.002964236],"genre_scores_gemma":[0.61618525,0.0000020235734,0.38300636,0.000084140396,0.000013917445,0.000003278259,8.0060124e-7,0.000010327496,0.00069391815],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986134,0.00006970988,0.00029374257,0.00030012784,0.00041215596,0.00031084774],"domain_scores_gemma":[0.9989334,0.00023429218,0.0002136076,0.00041108683,0.00011649112,0.00009112303],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021961684,0.0001580314,0.00019262494,0.00017444511,0.00036567188,0.00007141663,0.00055895094,0.00005429448,0.000032886946],"category_scores_gemma":[0.00013098134,0.00013231073,0.00006550545,0.00042956462,0.00004238225,0.00062053645,0.00013947894,0.00035399947,0.000026335256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007502169,0.000035078512,0.013927347,0.000012746103,0.000017998358,0.000016064716,0.0009659271,0.97827697,0.0057184007,0.0005094582,0.00003281499,0.0004796936],"study_design_scores_gemma":[0.0006238437,0.0002755726,0.012167263,0.00005082899,0.000007412925,0.000036967067,0.00014687893,0.9787438,0.00726043,0.0000017187145,0.0004912786,0.00019402934],"about_ca_topic_score_codex":0.00009331562,"about_ca_topic_score_gemma":0.000010757115,"teacher_disagreement_score":0.5721,"about_ca_system_score_codex":0.000041295516,"about_ca_system_score_gemma":0.00014072114,"threshold_uncertainty_score":0.5395475},"labels":[],"label_agreement":null},{"id":"W2161717678","doi":"","title":"MDPs with Non-Deterministic Policies.","year":2009,"lang":"en","type":"article","venue":"PubMed","topic":"Reinforcement Learning in Robotics","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":"Computer science; Markov decision process; Flexibility (engineering); Context (archaeology); Mathematical optimization; Optimal decision; Integer (computer science); Markov process; Operations research; Artificial intelligence; Decision tree; Mathematics","score_opus":0.014300349578223721,"score_gpt":0.21057131257444645,"score_spread":0.19627096299622274,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2161717678","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":[0.0057403976,0.000011290733,0.93674815,0.0016118189,0.00024735212,0.00039522728,2.1864292e-7,0.00024040784,0.055005122],"genre_scores_gemma":[0.98858434,0.0000028486509,0.0071493974,0.001373365,0.000092060225,0.00008355017,7.7099975e-7,0.000006411393,0.002707256],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99889106,0.000015107014,0.00014266,0.00022223199,0.00027627975,0.0004526954],"domain_scores_gemma":[0.99920076,0.000036005917,0.000075158205,0.0005208779,0.000036622074,0.00013055543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014808605,0.00011424303,0.00011657303,0.00008376527,0.000079137564,0.00019789516,0.0007047174,0.000033184486,0.0000024422661],"category_scores_gemma":[0.000043989916,0.00009181644,0.000027682652,0.00029869558,0.000035330107,0.00025626612,0.00007272774,0.00010974723,0.000044432363],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031736545,0.00012064997,0.0048215683,0.000029653575,0.000056509733,0.00017341487,0.0015606472,0.19295065,0.000047868994,0.04473144,0.007147038,0.7483288],"study_design_scores_gemma":[0.000735433,0.00028190727,0.8630112,0.000013805073,0.000014973937,0.000062707455,0.000012214739,0.1220713,0.0003507805,0.000665763,0.01234196,0.0004379735],"about_ca_topic_score_codex":0.0000058659916,"about_ca_topic_score_gemma":6.0762653e-7,"teacher_disagreement_score":0.98284394,"about_ca_system_score_codex":0.00004143189,"about_ca_system_score_gemma":0.000029187722,"threshold_uncertainty_score":0.37441656},"labels":[],"label_agreement":null},{"id":"W2162664081","doi":"","title":"Dual Temporal Difference Learning","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Dual (grammatical number); Convergence (economics); Temporal difference learning; Reinforcement learning; Computer science; Artificial intelligence; Dynamic programming; Basis (linear algebra); Machine learning; Algorithm; Mathematical optimization; Mathematics","score_opus":0.016511148029155924,"score_gpt":0.2444750998830643,"score_spread":0.22796395185390836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162664081","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":[0.00809576,0.0000095665255,0.9513201,0.00094176765,0.00012189823,0.000048156962,1.5904435e-8,0.00044979833,0.039012935],"genre_scores_gemma":[0.9310511,0.0000031564452,0.050898507,0.00053528557,0.00004102203,7.8033355e-7,0.0000012188473,0.0000029633384,0.017465984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908143,0.00003682174,0.00015234339,0.00021701374,0.0002628483,0.00024956884],"domain_scores_gemma":[0.9994984,0.000041717034,0.000056387446,0.00029690133,0.000034540462,0.00007204224],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000136605,0.000097734584,0.000094440635,0.000058093396,0.00011382466,0.0001879417,0.00046912834,0.000037336096,0.000046968038],"category_scores_gemma":[0.00005880922,0.00008263969,0.000034786142,0.00020477967,0.000016472555,0.00025496993,0.000110314526,0.0002042291,0.00019984832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004824521,0.000054196335,0.023242733,0.0000060644243,0.000013228594,0.000054894932,0.0009723413,0.4279094,0.0022273392,0.4007896,0.0013729983,0.14335239],"study_design_scores_gemma":[0.00022587554,0.00038773642,0.0491012,0.000010388363,0.000001945253,0.000017032076,0.000022458295,0.9418923,0.00062437356,0.0013758858,0.0060997773,0.00024102436],"about_ca_topic_score_codex":0.0000073389374,"about_ca_topic_score_gemma":4.577239e-7,"teacher_disagreement_score":0.92295533,"about_ca_system_score_codex":0.000019136638,"about_ca_system_score_gemma":0.000027187123,"threshold_uncertainty_score":0.3369949},"labels":[],"label_agreement":null},{"id":"W2162926979","doi":"10.1109/cdc.2009.5400662","title":"Arbitrarily modulated Markov decision processes","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Transition (genetics); Computer science; Markov chain; Markov process; Markov model; Partially observable Markov decision process; Decision theory; Artificial intelligence; Mathematical optimization; Machine learning; Algorithm; Mathematics; Statistics","score_opus":0.009695192704821434,"score_gpt":0.24127695218328302,"score_spread":0.23158175947846157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162926979","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":[0.0045442674,0.000033134955,0.9521947,0.00059335656,0.00013096997,0.00009137448,5.038069e-8,0.00040294457,0.04200919],"genre_scores_gemma":[0.72821504,0.000014271533,0.26856083,0.0011392866,0.000022392021,0.0000010262116,0.0000010967213,0.0000037270283,0.002042336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896795,0.000012814406,0.0001962385,0.00026030178,0.00032959465,0.00023309128],"domain_scores_gemma":[0.9992174,0.00008434383,0.000054614233,0.0004517823,0.000118770484,0.000073088304],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012547775,0.00010726619,0.000099348974,0.00008693699,0.00008069781,0.00022393618,0.0007604908,0.00005135753,0.00004795396],"category_scores_gemma":[0.00015779353,0.000086981156,0.000027856044,0.0005776967,0.000011961376,0.00054456317,0.00008345286,0.00010236543,0.00015361923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022394255,0.00009252623,0.0005599572,0.000022255403,0.000016497506,0.00003655406,0.0003516479,0.719919,0.0012041647,0.04563451,0.008465862,0.22367458],"study_design_scores_gemma":[0.000310619,0.0002149455,0.007778431,0.000034284825,0.0000029350629,0.000014770154,0.0000049601545,0.9770653,0.0024092514,0.008024156,0.0039091413,0.00023120237],"about_ca_topic_score_codex":0.0000032912028,"about_ca_topic_score_gemma":7.1711304e-7,"teacher_disagreement_score":0.7236708,"about_ca_system_score_codex":0.000021243519,"about_ca_system_score_gemma":0.00007102646,"threshold_uncertainty_score":0.35469887},"labels":[],"label_agreement":null},{"id":"W2163126463","doi":"","title":"Online Discovery and Learning of Predictive State Representations","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Machine learning; Outcome (game theory); Artificial intelligence; Gradient descent; State (computer science); Current (fluid); Algorithm; Monte Carlo method; Data mining; Artificial neural network; Mathematics","score_opus":0.013972898074078937,"score_gpt":0.27080232391216796,"score_spread":0.25682942583808904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2163126463","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":[0.05878504,0.00002033414,0.9357699,0.00042354333,0.000031146286,0.00006111545,0.0000010246565,0.00006903531,0.0048388634],"genre_scores_gemma":[0.891873,0.00003969964,0.0971875,0.00006714182,0.000020976977,0.0000014431217,0.0000039807796,0.000003700029,0.010802544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937165,0.000043056367,0.00016811113,0.0001527578,0.0001596411,0.000104797284],"domain_scores_gemma":[0.9995152,0.00013513296,0.00008414299,0.00018613004,0.00004690843,0.00003253492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000116019844,0.000054058713,0.00007572986,0.00005921766,0.000059533217,0.00006525414,0.00017808609,0.000014145628,0.000011064566],"category_scores_gemma":[0.00009919722,0.000047390102,0.000018070748,0.00013595301,0.00004482288,0.0008338679,0.00019269959,0.00012310912,0.0000044613653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021847284,0.000020259731,0.006863244,0.00000429709,0.000012565748,5.6663157e-7,0.0011152724,0.9788192,0.00017227685,0.007781702,0.00008096336,0.005127498],"study_design_scores_gemma":[0.00016414,0.00009678183,0.02388473,0.000009135845,0.0000033301496,0.0000024728488,0.00015812936,0.9739937,0.00077680976,0.00014590086,0.00070794584,0.000056924637],"about_ca_topic_score_codex":0.000029384479,"about_ca_topic_score_gemma":0.0000053319295,"teacher_disagreement_score":0.8385824,"about_ca_system_score_codex":0.000012498131,"about_ca_system_score_gemma":0.000023121243,"threshold_uncertainty_score":0.19325122},"labels":[],"label_agreement":null},{"id":"W2164065344","doi":"10.1109/iros.2007.4399526","title":"Decision theoretic task coordination for a visually-guided interactive mobile robot","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Partially observable Markov decision process; Heuristics; Computer science; Mobile robot; Robot; Markov decision process; Task (project management); Artificial intelligence; Social robot; Human–computer interaction; Planner; Process (computing); Markov process; Robot learning; Behavior-based robotics; Robot control; Machine learning; Markov chain; Markov model; Engineering","score_opus":0.014687924549861111,"score_gpt":0.3253183112698323,"score_spread":0.3106303867199712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164065344","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":[0.004399364,0.000009397224,0.9870367,0.00012118772,0.00058341963,0.00064608286,3.1174756e-7,0.00020402695,0.0069995164],"genre_scores_gemma":[0.76628745,0.00000229297,0.23147132,0.00026471887,0.000045039924,0.00003572014,0.0000049432215,0.0000113530405,0.0018771756],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863094,0.000029616207,0.0003626348,0.0003357745,0.0003182696,0.00032274966],"domain_scores_gemma":[0.9979193,0.0011534225,0.00015221132,0.00040489217,0.00028849245,0.00008163724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009936038,0.0001395656,0.00014161316,0.00018534003,0.00012661508,0.00018550982,0.00064222596,0.000068691195,0.000050745817],"category_scores_gemma":[0.0003899416,0.00011835346,0.00008259852,0.00031081558,0.00003875134,0.0005538737,0.00021541223,0.000108613465,0.0000839241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000103791936,0.00011636529,0.00027781457,0.000024252875,0.00004385582,0.000007971901,0.0019340056,0.4905042,0.0051921513,0.38921657,0.0052322964,0.10734672],"study_design_scores_gemma":[0.00073099387,0.0005191415,0.00048866955,0.00003362866,0.000008203527,0.000011239817,0.00014319841,0.97676486,0.009423866,0.0066698324,0.004990694,0.00021567903],"about_ca_topic_score_codex":0.0000060375373,"about_ca_topic_score_gemma":0.0000030666831,"teacher_disagreement_score":0.7618881,"about_ca_system_score_codex":0.00012956954,"about_ca_system_score_gemma":0.000038043836,"threshold_uncertainty_score":0.4826314},"labels":[],"label_agreement":null},{"id":"W2164327805","doi":"10.1115/1.2764516","title":"Decentralized Coordinated Motion Control of Two Hydraulic Actuators Handling a Common Object","year":2007,"lang":"en","type":"article","venue":"Journal of Dynamic Systems Measurement and Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Actuator; Trajectory; Computer science; Task (project management); Object (grammar); Control theory (sociology); Position (finance); Artificial intelligence; Control engineering; Control (management); Engineering","score_opus":0.013405342807333475,"score_gpt":0.2483025158322252,"score_spread":0.23489717302489174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164327805","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":[0.05582736,0.001986753,0.9403902,0.00015347564,0.0010354848,0.00047689685,9.436755e-7,0.0000321366,0.0000967116],"genre_scores_gemma":[0.9990497,0.000042168496,0.0007365683,0.00006581447,0.000070666094,0.000002987409,5.366892e-7,0.000014539798,0.000017018952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963765,0.00033556332,0.0014305116,0.0001948628,0.0012541175,0.000408456],"domain_scores_gemma":[0.99659604,0.00025315335,0.00176918,0.0002854431,0.0009035639,0.00019263636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058860816,0.00023521183,0.00078220555,0.00035743817,0.00011748508,0.00015820675,0.00050112297,0.00009291274,0.0000020730317],"category_scores_gemma":[0.00024323333,0.0001914944,0.00018823067,0.00027814417,0.000050729483,0.00040752135,0.000029075056,0.00027490966,0.0000014877863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019329034,0.00052656163,0.12492115,0.000659205,0.0036601957,0.00022738737,0.0024552974,0.62223375,0.1423076,0.0063108653,0.00010157306,0.09466351],"study_design_scores_gemma":[0.014525366,0.00058368576,0.007993772,0.0005697077,0.0002368599,0.00016045113,0.00015387706,0.9748341,0.0005020852,0.00007947768,0.00012709374,0.0002335338],"about_ca_topic_score_codex":0.00006912552,"about_ca_topic_score_gemma":0.000019193634,"teacher_disagreement_score":0.94322234,"about_ca_system_score_codex":0.00031574356,"about_ca_system_score_gemma":0.00012076584,"threshold_uncertainty_score":0.78089154},"labels":[],"label_agreement":null},{"id":"W2164750193","doi":"10.5430/air.v1n2p1","title":"Combining coordination mechanisms to improve performance in multi-robot teams","year":2012,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"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":"Computer science; Stigmergy; Negotiation; Robot; Artificial intelligence; Domain (mathematical analysis); Human–computer interaction; Mechanism (biology); Multi-agent system; Distributed computing","score_opus":0.17958176777957213,"score_gpt":0.4121311132034148,"score_spread":0.23254934542384265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164750193","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":[0.038333308,0.000020893782,0.95857495,0.00077534775,0.00066330744,0.0005589036,2.9721318e-7,0.000093606235,0.000979365],"genre_scores_gemma":[0.9387139,0.000011232774,0.060470413,0.00008088156,0.00007221506,0.0000866691,0.0000017430507,0.00001708785,0.00054585544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99654657,0.0002750537,0.00050580956,0.00043880497,0.0009790409,0.0012547285],"domain_scores_gemma":[0.9983124,0.00037154672,0.000069127695,0.00062579714,0.00033807143,0.00028303714],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.005057547,0.00016110267,0.00017872946,0.0006665781,0.00032336186,0.00029791187,0.0013010233,0.00010784157,0.000035969184],"category_scores_gemma":[0.0007491845,0.00016334631,0.000039639643,0.0019357102,0.000092421484,0.0011247571,0.0007490622,0.00068836956,0.0017337456],"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":[0.000031066014,0.00033365827,0.0039380877,0.000040350467,0.000010723518,0.0000067162296,0.0074516493,0.24939905,0.06716187,0.42042094,0.000045588502,0.2511603],"study_design_scores_gemma":[0.00003969122,0.00031217275,0.0014551558,0.000047621925,9.4020555e-7,0.0000022890329,0.0007618021,0.81302696,0.18160415,0.0023291847,0.0002147091,0.00020535233],"about_ca_topic_score_codex":0.00017181483,"about_ca_topic_score_gemma":0.00003352056,"teacher_disagreement_score":0.9003806,"about_ca_system_score_codex":0.00032474735,"about_ca_system_score_gemma":0.00011508633,"threshold_uncertainty_score":0.9990435},"labels":[],"label_agreement":null},{"id":"W2164941694","doi":"10.48550/arxiv.1206.6444","title":"Statistical Linear Estimation with Penalized Estimators: an Application to Reinforcement Learning","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Estimator; Reinforcement learning; Regularization (linguistics); Applied mathematics; Mathematics; Mathematical optimization; Computer science; Feature (linguistics); Inverse problem; Function (biology); Algorithm; Artificial intelligence; Statistics","score_opus":0.0385205685199137,"score_gpt":0.21785937348316717,"score_spread":0.17933880496325347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164941694","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":[0.02879861,0.0000017576991,0.9695939,0.000036672427,0.00005552426,0.0002881898,3.2458036e-7,0.0002660137,0.0009590442],"genre_scores_gemma":[0.8549479,0.0000017510226,0.14435221,0.000089722475,0.00003239314,0.0000023062792,0.000024785175,0.000012709644,0.00053620175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987952,0.00009148471,0.00016626874,0.00038455735,0.00016615646,0.00039633404],"domain_scores_gemma":[0.9987916,0.000091938404,0.00013462357,0.0005275502,0.00010814983,0.00034617068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003165767,0.00016618654,0.00014472665,0.00014957938,0.00022055132,0.000076885706,0.0005218622,0.000055470617,0.0000357291],"category_scores_gemma":[0.00007309887,0.00016840898,0.000024714836,0.00059429696,0.000046364363,0.0012976192,0.00018271305,0.0001800724,0.0003718492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030321595,0.000027003065,0.00615595,0.000009060115,0.000012006644,0.000005969366,0.00031674522,0.8412285,0.000039838756,0.15131885,0.000020973826,0.0008347869],"study_design_scores_gemma":[0.000406661,0.00030440392,0.0022517317,0.000015050736,0.00002377179,0.000005626165,0.00005511971,0.99556583,0.00012561215,0.00015637605,0.00085851,0.00023128392],"about_ca_topic_score_codex":0.00004691349,"about_ca_topic_score_gemma":0.0000022869008,"teacher_disagreement_score":0.8261493,"about_ca_system_score_codex":0.00015059311,"about_ca_system_score_gemma":0.000051880066,"threshold_uncertainty_score":0.6867519},"labels":[],"label_agreement":null},{"id":"W2165044515","doi":"","title":"Symbolic Dynamic Programming for Continuous State and Observation POMDPs","year":2012,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Markov decision process; Dynamic programming; Computer science; Observable; Mathematical optimization; State (computer science); Partially observable Markov decision process; Set (abstract data type); Discrete time and continuous time; Theoretical computer science; Markov process; Algorithm; Mathematics","score_opus":0.020659966466638514,"score_gpt":0.2658637831583126,"score_spread":0.2452038166916741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165044515","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":[0.061028987,0.000057015513,0.93757653,0.00021811466,0.00019342348,0.00034803216,1.9034437e-7,0.00018195866,0.00039574195],"genre_scores_gemma":[0.62244564,0.000008106251,0.37470615,0.00014890148,0.000019970463,0.000026767078,0.0000029007454,0.0000070401975,0.002634497],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926746,0.000015539687,0.00014880986,0.00013486508,0.00011490741,0.0003184015],"domain_scores_gemma":[0.999532,0.00007870012,0.00007110182,0.00019056811,0.000055188484,0.00007247555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027880815,0.000081216516,0.00009109952,0.000041510397,0.00008485445,0.00015770723,0.0001906072,0.000026699408,0.0000024702474],"category_scores_gemma":[0.000041142433,0.0000720412,0.00002116705,0.00010649,0.000014175239,0.0006417445,0.0000950785,0.00004776013,0.00001537963],"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":[0.000013452538,0.00015468404,0.16299094,0.00024219346,0.00011112416,0.0000016102008,0.009442949,0.020456975,0.0013183098,0.22292033,0.000675954,0.5816715],"study_design_scores_gemma":[0.00035778043,0.00012598964,0.03415174,0.000011197523,0.000008368208,0.00000633879,0.00004957573,0.94364685,0.00021454565,0.0003410328,0.020900855,0.00018572467],"about_ca_topic_score_codex":0.000007577168,"about_ca_topic_score_gemma":0.0000015421444,"teacher_disagreement_score":0.9231899,"about_ca_system_score_codex":0.000026624486,"about_ca_system_score_gemma":0.000013732135,"threshold_uncertainty_score":0.2937755},"labels":[],"label_agreement":null},{"id":"W2165235114","doi":"","title":"Using Free Energies to Represent Q-values in a Multiagent Reinforcement Learning Task","year":2000,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Q-learning; Markov decision process; Computer science; Task (project management); Artificial intelligence; Markov chain; Sampling (signal processing); Markov process; Machine learning; State (computer science); Representation (politics); Gibbs sampling; Table (database); Action (physics); Algorithm; Data mining; Mathematics; Statistics; Engineering","score_opus":0.035425327012383365,"score_gpt":0.293271296584887,"score_spread":0.2578459695725036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165235114","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":[0.07346973,0.000034539473,0.9013764,0.00042492445,0.0001625849,0.0003278399,9.7885625e-8,0.00029330922,0.023910573],"genre_scores_gemma":[0.8093965,0.000042075295,0.16789263,0.0006181944,0.00006273037,0.000024398501,0.000002283021,0.000020449308,0.021940717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975814,0.000121728546,0.0005309973,0.00055213453,0.00063290965,0.0005808025],"domain_scores_gemma":[0.9984858,0.000093568065,0.00008380191,0.001122595,0.00005565708,0.00015857627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047113418,0.00022469851,0.00023221671,0.00027797386,0.00016976758,0.00026549975,0.0012698397,0.00006329607,0.0004913087],"category_scores_gemma":[0.0001986226,0.00021337197,0.000076938086,0.0006346844,0.000032123167,0.0005153877,0.0007772203,0.00024371868,0.0002328577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008731976,0.000016505557,0.0010637457,0.000007055649,0.00001212199,0.000023024768,0.001821774,0.98808426,0.0009817386,0.0020327908,0.00050873926,0.00543953],"study_design_scores_gemma":[0.00045677973,0.00012987317,0.0008915282,0.000058144997,0.0000039433203,0.000006817335,0.00012659168,0.9876698,0.0022067984,0.00009568056,0.008069373,0.00028463593],"about_ca_topic_score_codex":0.00095854356,"about_ca_topic_score_gemma":0.000024929268,"teacher_disagreement_score":0.7359268,"about_ca_system_score_codex":0.00020558148,"about_ca_system_score_gemma":0.00006138317,"threshold_uncertainty_score":0.8701056},"labels":[],"label_agreement":null},{"id":"W2167748058","doi":"","title":"Average Reward Optimization Objective In Partially Observable Domains","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Observability; Dimension (graph theory); Observable; Representation (politics); Function (biology); Mathematics; Process (computing); Mathematical optimization; Bellman equation; Computer science; Computation; Key (lock); Applied mathematics; Algorithm","score_opus":0.012999340964716806,"score_gpt":0.22070248817275684,"score_spread":0.20770314720804003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167748058","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":[0.0023407165,0.0000046416435,0.9637617,0.0005445865,0.00016895709,0.0002736231,5.9368173e-8,0.00016554397,0.032740198],"genre_scores_gemma":[0.64580375,0.000011733617,0.34861702,0.0005631411,0.00002375586,0.000035053417,0.0000027054202,0.000008645811,0.0049342117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989292,0.00006722971,0.00023147416,0.0002573265,0.00022780383,0.00028697413],"domain_scores_gemma":[0.9993126,0.00007198829,0.0000674529,0.0003995298,0.00008631862,0.00006213768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019285141,0.00010251888,0.00011318692,0.00008799058,0.000062136365,0.00024335118,0.0004985115,0.00005549202,0.00032658872],"category_scores_gemma":[0.00007942965,0.00009362606,0.000029051149,0.00040072962,0.000018876612,0.0011301229,0.0001975307,0.00011866972,0.0003696237],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.7689756e-7,0.000012428045,0.0031491572,0.0000028243408,0.0000040065647,0.0000031233403,0.0003865356,0.9851594,0.00004770237,0.010397451,0.00047725457,0.0003592547],"study_design_scores_gemma":[0.00025173294,0.00005382023,0.0063816677,0.000009563641,7.958191e-7,0.0000014498123,0.000026247586,0.9919391,0.0002812502,0.0005960382,0.00033309657,0.00012519433],"about_ca_topic_score_codex":0.00026018062,"about_ca_topic_score_gemma":0.00003333913,"teacher_disagreement_score":0.643463,"about_ca_system_score_codex":0.000088089204,"about_ca_system_score_gemma":0.00005600605,"threshold_uncertainty_score":0.4750888},"labels":[],"label_agreement":null},{"id":"W2169183587","doi":"10.1109/ijcnn.2006.246689","title":"Opposition-Based Q(&amp;amp;#955;) Algorithm","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":48,"is_retracted":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":"Opposition (politics); Reinforcement learning; Computer science; Lambda; Algorithm; Artificial intelligence; Law; Political science; Physics","score_opus":0.053300843179456,"score_gpt":0.27574545304177817,"score_spread":0.22244460986232217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169183587","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":[0.010230401,0.00001825438,0.9393387,0.014087876,0.0024104894,0.0004209532,0.000009088803,0.00048055607,0.033003684],"genre_scores_gemma":[0.9345991,0.000015801994,0.052198704,0.0037611006,0.001992154,0.00007740696,0.0000636151,0.000038748367,0.007253394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99720216,0.000038738915,0.0005726708,0.0005489487,0.0010506554,0.00058680214],"domain_scores_gemma":[0.998314,0.00014691848,0.00041301094,0.0003652552,0.00065961236,0.000101169106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045076004,0.00035442712,0.0002446093,0.00016192287,0.00036235148,0.00096860237,0.001863323,0.00010379084,0.00015914299],"category_scores_gemma":[0.00004268459,0.00027644544,0.00016133244,0.00042892818,0.00015648223,0.0005539669,0.00017998519,0.00053911534,0.0005508347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024371931,0.000072523035,0.00033683947,0.000008853822,0.000034920555,0.0000059843833,0.000071293834,0.7986826,0.0019313842,0.122110605,0.0715099,0.0052107307],"study_design_scores_gemma":[0.00039678745,0.000090233974,0.0007526577,0.00011810915,0.000012706832,0.000036811554,0.0000059250087,0.9732943,0.00080397347,0.0070708776,0.017053185,0.00036438464],"about_ca_topic_score_codex":0.00008342553,"about_ca_topic_score_gemma":0.000011568774,"teacher_disagreement_score":0.9243687,"about_ca_system_score_codex":0.00014832616,"about_ca_system_score_gemma":0.00008576233,"threshold_uncertainty_score":0.99996877},"labels":[],"label_agreement":null},{"id":"W2169190416","doi":"","title":"Using bisimulation for policy transfer in MDPs (Extended Abstract)","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Markov decision process; Bellman equation; Set (abstract data type); Function (biology); Action (physics); Value (mathematics); Computer science; State (computer science); Mathematical economics; Markov process; Artificial intelligence; Mathematics; Algorithm; Machine learning; Statistics","score_opus":0.048726002218220925,"score_gpt":0.3417722960033684,"score_spread":0.29304629378514746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169190416","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":[0.0973371,7.5253945e-7,0.89905995,0.00045695246,0.00020831969,0.00020691185,2.5786358e-7,0.00007694311,0.00265281],"genre_scores_gemma":[0.87742907,4.9847193e-7,0.12207424,0.00016571858,0.00007557668,0.0000036587805,0.000001489952,0.0000070480237,0.00024273175],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922323,0.000007611692,0.00021256277,0.00018418836,0.00014433441,0.00022807624],"domain_scores_gemma":[0.9995111,0.00009425154,0.000024309124,0.0002763485,0.000049253777,0.000044694858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022384465,0.000082459694,0.000085177104,0.0002048619,0.00005426785,0.00010781478,0.00032917515,0.00007304892,0.00002151545],"category_scores_gemma":[0.0000774635,0.00007699045,0.000041160685,0.00027425666,0.000019198153,0.00044633722,0.000030870047,0.00014890253,0.000011389431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041194676,0.000018480097,0.0005489699,0.000010125225,0.0000033333918,8.677884e-7,0.00026354232,0.7582277,0.019264884,0.21530232,0.000011476632,0.00634416],"study_design_scores_gemma":[0.00039735882,0.000029981977,0.008543811,0.000004812539,0.0000013603682,0.0000019114375,0.000003512461,0.9850253,0.0032840492,0.0018700742,0.0007336409,0.000104224644],"about_ca_topic_score_codex":0.00017173176,"about_ca_topic_score_gemma":0.00006491627,"teacher_disagreement_score":0.78009194,"about_ca_system_score_codex":0.000034857498,"about_ca_system_score_gemma":0.000098422395,"threshold_uncertainty_score":0.31395796},"labels":[],"label_agreement":null},{"id":"W2169375932","doi":"10.5555/2447556.2447651","title":"Integrating a robot in a tabletop reservoir engineering application","year":2013,"lang":"en","type":"article","venue":"OCAD University Open Research Repository (OCAD University)","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Computer science; Visualization; Human–computer interaction; Simple (philosophy); Robot; Data visualization; Artificial intelligence","score_opus":0.03200415483870318,"score_gpt":0.2613764750102883,"score_spread":0.22937232017158515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169375932","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":[0.029081708,0.000013632598,0.52770686,0.00070067425,0.000102777434,0.0011642033,7.3995153e-7,0.00015975007,0.44106963],"genre_scores_gemma":[0.86936533,0.000030202405,0.024404412,0.000025553707,0.000045811757,0.0000041656676,0.0000086809605,0.000024025041,0.106091835],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969544,0.0005539955,0.00023539121,0.00076625403,0.00070820894,0.0007817398],"domain_scores_gemma":[0.99768573,0.00029047782,0.00014058588,0.0010527308,0.00052692706,0.00030357117],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009765984,0.00022140307,0.0002785144,0.0010578871,0.0008054235,0.0007220945,0.0046408237,0.00019510333,0.0000019272309],"category_scores_gemma":[0.00012754844,0.00027141743,0.00007847302,0.0029402685,0.00016335533,0.0037870489,0.002031103,0.0010682269,0.00012098335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024701278,0.000048232498,0.0029294773,0.000025077794,0.000024634805,0.0002105007,0.0004981427,0.122199,0.0051624877,0.86797106,0.0002077126,0.0006989593],"study_design_scores_gemma":[0.0012595083,0.00022067841,0.0080758175,0.00018523035,0.000009525909,0.000019462621,0.0017914752,0.88592565,0.0010521587,0.00008552242,0.100883365,0.0004915985],"about_ca_topic_score_codex":0.0073775123,"about_ca_topic_score_gemma":0.00023908696,"teacher_disagreement_score":0.86788553,"about_ca_system_score_codex":0.0013407079,"about_ca_system_score_gemma":0.0004301453,"threshold_uncertainty_score":0.9999738},"labels":[],"label_agreement":null},{"id":"W2169619645","doi":"10.5555/2484920.2485084","title":"Smart exploration in reinforcement learning using absolute temporal difference errors","year":2013,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Temporal difference learning; Computer science; State (computer science); Function (biology); Artificial intelligence; Function approximation; Control (management); Machine learning; Algorithm; Artificial neural network","score_opus":0.10786902931368043,"score_gpt":0.29261669850862043,"score_spread":0.18474766919494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169619645","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":[0.19021417,0.00009192763,0.80751556,0.00004357572,0.00065648585,0.0010363704,5.4796874e-7,0.00009644435,0.00034494352],"genre_scores_gemma":[0.98867625,0.00006678287,0.0075289807,0.000087236214,0.000039929088,0.00010096997,0.000013319356,0.000025036648,0.0034614785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973987,0.00024853885,0.0006908059,0.000579794,0.00051942316,0.0005627802],"domain_scores_gemma":[0.99879235,0.00005292565,0.00041341243,0.0004035714,0.00014936985,0.00018839812],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040137747,0.00032611203,0.00034950432,0.0002562618,0.00028385973,0.00042298902,0.00047226055,0.00011409763,0.000018984176],"category_scores_gemma":[0.000053513948,0.00029877533,0.00004944437,0.0003205286,0.000058721984,0.00142779,0.00041003432,0.00029259428,0.00010844462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063530565,0.000053837342,0.03842801,0.00005249882,0.000057399055,0.00001976851,0.0036247906,0.95502543,0.00065677223,0.0008062542,0.00012522622,0.0011436484],"study_design_scores_gemma":[0.0008635098,0.00016043265,0.043647103,0.00019243409,0.000008756949,0.0000060316706,0.00079188094,0.95343333,0.000026982183,0.000012293648,0.0005362582,0.00032097168],"about_ca_topic_score_codex":0.00421482,"about_ca_topic_score_gemma":0.000032241234,"teacher_disagreement_score":0.79998654,"about_ca_system_score_codex":0.00019103264,"about_ca_system_score_gemma":0.000048797912,"threshold_uncertainty_score":0.9999464},"labels":[],"label_agreement":null},{"id":"W2172123610","doi":"10.1142/s0217979200002077","title":"SELF-ADAPTING REACTIVE AUTONOMOUS AGENTS","year":2000,"lang":"en","type":"article","venue":"International Journal of Modern Physics B","topic":"Reinforcement Learning in Robotics","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 Lethbridge","funders":"","keywords":"Computer science; Reinforcement learning; Autonomous agent; Adaptation (eye); Architecture; Distributed computing; Autonomous system (mathematics); Multi-agent system; Artificial intelligence; Human–computer interaction","score_opus":0.019786536530311302,"score_gpt":0.27127720933122484,"score_spread":0.25149067280091353,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2172123610","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":[0.022790702,0.000026944788,0.9641136,0.00048184063,0.0007482726,0.00004011415,8.0662335e-7,0.00004972942,0.0117479805],"genre_scores_gemma":[0.9461422,0.000035161007,0.05243323,0.0003030831,0.00052843353,7.489028e-7,0.0000012662981,0.000011231536,0.0005446491],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984919,0.000041184558,0.00037378308,0.00013752785,0.00079836673,0.0001572312],"domain_scores_gemma":[0.9988594,0.00007283212,0.00040538603,0.00018494877,0.00040676864,0.00007067522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020923199,0.000111230205,0.00013785707,0.00007172292,0.00004944598,0.00019754158,0.0013857903,0.000033015127,0.000041052852],"category_scores_gemma":[0.000021567652,0.00010656481,0.00012613482,0.00008510273,0.000016568667,0.0010587553,0.00011145406,0.00026392046,0.000075765594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019807834,0.00010488487,0.00022767791,0.0000024250016,0.00026069352,0.00008968097,0.0018736938,0.78461653,0.00028414725,0.007450631,0.0002486721,0.20482118],"study_design_scores_gemma":[0.00048326803,0.00007910917,0.00051066396,0.000039165734,0.000011592078,0.000117166106,0.000007764862,0.9783481,0.00094249507,0.012477604,0.006858473,0.0001246017],"about_ca_topic_score_codex":0.000003968833,"about_ca_topic_score_gemma":1.2685703e-7,"teacher_disagreement_score":0.92335147,"about_ca_system_score_codex":0.00019896706,"about_ca_system_score_gemma":0.00012625071,"threshold_uncertainty_score":0.4345587},"labels":[],"label_agreement":null},{"id":"W2174786457","doi":"10.48550/arxiv.1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":208,"is_retracted":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; Exploit; Artificial intelligence; Transfer of learning; Set (abstract data type); Task (project management); Machine learning; Engineering","score_opus":0.07661995159032055,"score_gpt":0.19594166404524566,"score_spread":0.11932171245492511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2174786457","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":[0.050566617,0.0000724946,0.94364375,0.000059094426,0.0005010002,0.00035992422,0.0000010856863,0.0003674588,0.0044285785],"genre_scores_gemma":[0.99307966,0.00031311682,0.0022932473,0.00008640963,0.00006315284,0.000001270768,0.000027061635,0.000030751282,0.00410533],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976581,0.00017639126,0.00031090577,0.0011032969,0.0002206087,0.0005307141],"domain_scores_gemma":[0.9980758,0.00011412968,0.00018069896,0.0010438031,0.00024196053,0.00034362188],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043931467,0.0004550408,0.00041963154,0.00030372557,0.00022677807,0.00027564328,0.0015560989,0.0003733191,0.000035232042],"category_scores_gemma":[0.00008195826,0.00052249833,0.00015965111,0.00035280635,0.0001470049,0.00057864503,0.0021372186,0.0011858229,0.00010624394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019896426,0.000015244187,0.0016443157,0.0000749872,0.000097715034,0.00009938002,0.00083837524,0.97281617,0.00002740382,0.023896774,0.00007999845,0.00038975765],"study_design_scores_gemma":[0.0007869599,0.0001416586,0.000284112,0.00008431375,0.00007446969,0.0000057613984,0.00014282347,0.9946031,0.000068475565,0.0010256834,0.002199968,0.00058269413],"about_ca_topic_score_codex":0.00009791936,"about_ca_topic_score_gemma":0.000015935148,"teacher_disagreement_score":0.94251305,"about_ca_system_score_codex":0.00033327547,"about_ca_system_score_gemma":0.00020789687,"threshold_uncertainty_score":0.99972266},"labels":[],"label_agreement":null},{"id":"W2181804636","doi":"","title":"Autonomous Navigation Through Crowds","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Crowds; Computer science; Presentation (obstetrics); Artificial intelligence; Reinforcement learning; Computer vision; Mobile robot; Human–computer interaction; Robot; Computer security","score_opus":0.04958624137517291,"score_gpt":0.254975453139823,"score_spread":0.20538921176465008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2181804636","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":[0.0013830351,0.0000049615915,0.7593146,0.00007225607,0.00022274499,0.00004699402,2.9236128e-8,0.00027451394,0.23868088],"genre_scores_gemma":[0.652974,0.0000013241249,0.34191164,0.00033221094,0.000020739151,0.0000034825061,0.0000011691518,0.0000046609566,0.0047507402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993912,0.000016372,0.00013379818,0.00016281774,0.00013745442,0.0001583445],"domain_scores_gemma":[0.99947757,0.00001543761,0.000049950715,0.00038849335,0.000037912614,0.000030633306],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0000898816,0.00006721451,0.000056962286,0.00002072938,0.0000639727,0.00006343096,0.0005179702,0.000035224013,0.00013471625],"category_scores_gemma":[0.000009451595,0.000059152768,0.00002738756,0.00014840487,0.000023662906,0.0006608739,0.00013939057,0.00007292844,0.00050981913],"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":[0.0000014648365,0.000024153967,0.0014217986,0.000007812305,0.000012979393,0.000012056618,0.0053538573,0.019283574,0.0001689645,0.9667406,0.0015034612,0.0054692575],"study_design_scores_gemma":[0.0004075435,0.00029879407,0.009244635,0.000024301871,0.000007968663,0.000036380934,0.00008366886,0.9208504,0.02439487,0.016039712,0.02813625,0.0004754946],"about_ca_topic_score_codex":0.000058759466,"about_ca_topic_score_gemma":6.66804e-7,"teacher_disagreement_score":0.9507009,"about_ca_system_score_codex":0.0000240704,"about_ca_system_score_gemma":0.000026976742,"threshold_uncertainty_score":0.6552864},"labels":[],"label_agreement":null},{"id":"W2182573229","doi":"10.1609/aaai.v29i1.9701","title":"Representation Discovery for MDPs Using Bisimulation Metrics","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Bisimulation; Metric (unit); Computer science; Representation (politics); Computation; Convergence (economics); Markov decision process; Sequence (biology); Theoretical computer science; State space; State (computer science); Metric space; Algorithm; Markov process; Mathematics; Discrete mathematics","score_opus":0.29689374545324165,"score_gpt":0.37833881418119636,"score_spread":0.0814450687279547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182573229","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":[0.054990172,0.000008686137,0.94126886,0.00068945653,0.00061159674,0.0004894096,0.0000015617344,0.000058908245,0.0018813659],"genre_scores_gemma":[0.96945256,0.000005864407,0.030074185,0.00008011826,0.000077339166,0.000012830501,0.0000010120003,0.000011096095,0.00028498514],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998232,0.000017284654,0.00050769903,0.0003694469,0.0006191741,0.00025438762],"domain_scores_gemma":[0.99779093,0.00018423669,0.0005254794,0.0002862069,0.0011380317,0.0000751349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071478885,0.0001562833,0.00019927837,0.00020806218,0.00014893265,0.00047549338,0.0012300739,0.00007364412,0.0000031650552],"category_scores_gemma":[0.0020714551,0.00012410196,0.00010397847,0.0011676466,0.00010873289,0.001216878,0.00029008507,0.00014839572,0.000013430606],"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":[0.000058756497,0.000045321147,0.0007461628,0.000026558117,0.000013960477,1.010846e-7,0.0010304861,0.23822124,0.011000048,0.7377622,0.00010029416,0.010994882],"study_design_scores_gemma":[0.000034605062,0.0001348189,0.000051727046,0.000055605255,0.000011996512,0.0000010788527,0.00032147107,0.7565469,0.17852639,0.064154975,0.00004332218,0.00011712018],"about_ca_topic_score_codex":0.00003318259,"about_ca_topic_score_gemma":0.0000011805158,"teacher_disagreement_score":0.9144624,"about_ca_system_score_codex":0.00010386655,"about_ca_system_score_gemma":0.00013395294,"threshold_uncertainty_score":0.5060731},"labels":[],"label_agreement":null},{"id":"W2182877511","doi":"10.82308/46241","title":"Optimal time scales for reinforcement learning behaviour strategies","year":2010,"lang":"en","type":"article","venue":"Open MIND","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Artificial intelligence; Temporal difference learning; Formalism (music); Gradient descent; Representation (politics); Q-learning; Scale (ratio); Machine learning; Mathematical optimization; Artificial neural network; Mathematics","score_opus":0.026822870449726807,"score_gpt":0.30606543534320313,"score_spread":0.2792425648934763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2182877511","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":[0.08491374,0.00000384285,0.8850424,0.00021053106,0.0003032976,0.00061980844,9.010674e-7,0.000018107932,0.02888734],"genre_scores_gemma":[0.60026634,0.0000010833292,0.37925354,0.00002258139,0.00006745963,0.0000358841,0.000022982344,0.0000139212425,0.020316213],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986631,0.00002652504,0.0002931438,0.00038243717,0.00025885753,0.0003759336],"domain_scores_gemma":[0.99902266,0.00010304829,0.00016923388,0.00049549167,0.000104666804,0.000104868945],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005758661,0.00016693892,0.00017870711,0.0000696505,0.00029197952,0.0016533029,0.0018021291,0.00009230382,0.00079281756],"category_scores_gemma":[0.00007931678,0.00016005762,0.00006580196,0.00012852604,0.000061957755,0.0012646302,0.00073264085,0.00032906365,0.00076955825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001270364,0.00001951833,0.00032404115,0.0000043991677,0.000018006003,0.000004969489,0.00066463026,0.9670671,0.005702648,0.0033404068,0.00036843942,0.02247314],"study_design_scores_gemma":[0.0006341233,0.0003907452,0.00043943114,0.000018844117,0.000015191017,0.000013005013,0.00019731944,0.92994475,0.006388408,0.00004712696,0.061569795,0.00034127207],"about_ca_topic_score_codex":0.000013569963,"about_ca_topic_score_gemma":0.0000073799056,"teacher_disagreement_score":0.5153526,"about_ca_system_score_codex":0.0000220582,"about_ca_system_score_gemma":0.00014898869,"threshold_uncertainty_score":0.9993831},"labels":[],"label_agreement":null},{"id":"W2184461682","doi":"10.82308/33420","title":"A Bayesian Framework for Online Parameter Learning in POMDPs","year":2011,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Computer science; Reinforcement learning; Artificial intelligence; Markov decision process; Machine learning; Ambiguity; Robotics; Bayesian probability; Robot; Markov process; Markov chain; Markov model","score_opus":0.043054267710654175,"score_gpt":0.26167763034968494,"score_spread":0.21862336263903076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2184461682","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":[0.47592115,0.00014070056,0.48363397,0.00025809783,0.002589985,0.002734829,0.00009124446,0.003137615,0.031492416],"genre_scores_gemma":[0.5812483,0.00002005775,0.41766548,0.00051221764,0.000024484429,0.000063355554,0.000011061961,0.000060122686,0.0003949364],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9961155,0.00034958025,0.0008439161,0.0010319471,0.00056758756,0.0010914407],"domain_scores_gemma":[0.9970821,0.00091311807,0.0003888752,0.0011109612,0.00018763143,0.0003172797],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011826539,0.00048712443,0.00050751824,0.0004429139,0.00059518067,0.0001492674,0.0018119591,0.00042872797,0.00008291841],"category_scores_gemma":[0.00242455,0.00051271624,0.00025605064,0.0009344034,0.00006418687,0.001381098,0.00063318136,0.0016870367,0.00015033859],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007701379,0.00040733936,0.0016960195,0.00010235405,0.000108735025,0.00009280372,0.000106065476,0.021490362,0.00073199504,0.8431109,0.0000024389424,0.13207394],"study_design_scores_gemma":[0.003902986,0.002376261,0.0095613375,0.0008500776,0.00011851229,0.00010610977,0.0002174026,0.40216827,0.01617329,0.47451216,0.08674499,0.0032685963],"about_ca_topic_score_codex":0.00008528476,"about_ca_topic_score_gemma":0.000049230996,"teacher_disagreement_score":0.3806779,"about_ca_system_score_codex":0.00036218835,"about_ca_system_score_gemma":0.000044158303,"threshold_uncertainty_score":0.99973243},"labels":[],"label_agreement":null},{"id":"W2185087676","doi":"10.13140/2.1.4274.3043","title":"Efficient Planning in MDPs by Small Backups","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Backup; Successor cardinal; Computer science; Reinforcement learning; Flexibility (engineering); Computation; Implementation; Process (computing); Distributed computing; Artificial intelligence; Algorithm; Mathematics; Operating system","score_opus":0.016645286899418594,"score_gpt":0.22778139205813944,"score_spread":0.21113610515872083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2185087676","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":[0.1017413,0.000024816436,0.8691801,0.0004224882,0.00014915438,0.00014778611,5.406833e-8,0.00013092846,0.028203378],"genre_scores_gemma":[0.9283842,0.0000011273764,0.06611116,0.00059513503,0.000014871881,0.000014604736,0.0000015031474,0.0000074777868,0.0048699174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903864,0.000030365494,0.00020179892,0.0002330424,0.00018334706,0.0003128031],"domain_scores_gemma":[0.9994282,0.000081880586,0.000047002923,0.00034186876,0.000030428473,0.00007059799],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016934251,0.000097204174,0.000094961695,0.000085435,0.000041981853,0.00018607794,0.0006357245,0.00004228853,0.00014055091],"category_scores_gemma":[0.00003370854,0.00008409137,0.000022555492,0.00025146242,0.000018161376,0.000106874606,0.00023810002,0.00014172132,0.0008618009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.3156695e-7,0.000015635183,0.0031736377,0.000003898509,0.0000022938061,0.0000030656893,0.00037694554,0.98441136,0.0006106107,0.0039994265,0.006077649,0.0013251391],"study_design_scores_gemma":[0.00017935362,0.000043944034,0.005279522,0.000015776484,4.6217684e-7,0.000001518752,0.000040900988,0.992485,0.00028192895,0.00005674694,0.0014907147,0.00012411879],"about_ca_topic_score_codex":0.000118520955,"about_ca_topic_score_gemma":0.0000012249623,"teacher_disagreement_score":0.8266429,"about_ca_system_score_codex":0.00004159041,"about_ca_system_score_gemma":0.000018730441,"threshold_uncertainty_score":0.99991614},"labels":[],"label_agreement":null},{"id":"W2188892596","doi":"10.13140/2.1.1456.2568","title":"True Online TD(λ)","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Equivalence (formal languages); Algorithm; TRACE (psycholinguistics); Function (biology); Simple (philosophy); Reinforcement learning; Online algorithm; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.011263924549713058,"score_gpt":0.2308848390242981,"score_spread":0.21962091447458504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2188892596","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":[0.0015800081,0.0000023160576,0.9459564,0.0009397116,0.00028320547,0.000029807328,5.123999e-8,0.00023775005,0.050970737],"genre_scores_gemma":[0.6865635,0.0000024366966,0.29517245,0.0019816407,0.000108359374,0.0000012399441,0.0000024811925,0.0000060885977,0.016161785],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940366,0.0000251311,0.00011063925,0.00014687296,0.0001611528,0.00015252289],"domain_scores_gemma":[0.9993813,0.00005881871,0.000031817548,0.0004494715,0.000027694461,0.00005087785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013705848,0.000059345482,0.00006548301,0.000038209073,0.000041772648,0.00007709277,0.0005980468,0.000024849474,0.00006351434],"category_scores_gemma":[0.000069307614,0.00004838962,0.000025321518,0.00012867808,0.000013873696,0.0001763597,0.0001633719,0.00007253074,0.00036722425],"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":[8.2781924e-7,0.000029270179,0.0010466669,0.0000069485186,0.0000083939685,0.0000017310933,0.00018048908,0.31084415,0.00025935535,0.63450676,0.0063709174,0.046744477],"study_design_scores_gemma":[0.00011601658,0.000057210636,0.0015355705,0.000002871259,8.861955e-7,0.0000019466104,0.0000044345325,0.9333718,0.00026935776,0.00059572596,0.06396655,0.00007766371],"about_ca_topic_score_codex":0.000008480736,"about_ca_topic_score_gemma":0.0000025662466,"teacher_disagreement_score":0.6849835,"about_ca_system_score_codex":0.000011393853,"about_ca_system_score_gemma":0.000011758135,"threshold_uncertainty_score":0.47200474},"labels":[],"label_agreement":null},{"id":"W2190606234","doi":"10.5555/2936924.2936996","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Benchmark (surveying); Representation (politics); Artificial intelligence; Set (abstract data type); Strengths and weaknesses; Simple (philosophy); Key (lock); Artificial neural network; Feature learning; Machine learning","score_opus":0.04777979186199204,"score_gpt":0.2658761195988801,"score_spread":0.21809632773688803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2190606234","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":[0.050363656,0.0001757146,0.9479423,0.000039669387,0.0005319819,0.0006639892,0.000005972487,0.000029415032,0.00024727706],"genre_scores_gemma":[0.9947135,0.00009203773,0.0016289494,0.00004644096,0.000019934329,0.000011730282,0.0000010307002,0.00001693143,0.003469455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779034,0.00025492578,0.0006700302,0.00034907128,0.00058349804,0.0003521264],"domain_scores_gemma":[0.9981955,0.00013612019,0.00081560365,0.0005317581,0.00022418995,0.00009679316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052271097,0.00022492904,0.00038640344,0.00009769399,0.00015125652,0.000059257316,0.0006308009,0.000054532775,0.0000082491515],"category_scores_gemma":[0.00009829664,0.00013250689,0.00011320847,0.00017235176,0.00014066712,0.00042951145,0.00039655645,0.00011814454,0.000013191845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002873874,0.00004502024,0.037428465,0.00008640031,0.00030138262,0.000005115685,0.0012895962,0.94823545,0.007769123,0.0011858004,0.00007662026,0.0035483064],"study_design_scores_gemma":[0.0018921403,0.00018039558,0.012169218,0.0006079295,0.00003565308,0.0000052535484,0.00011524757,0.98184663,0.0007525636,0.000006083937,0.002207422,0.00018147426],"about_ca_topic_score_codex":0.00024973557,"about_ca_topic_score_gemma":0.0000063140183,"teacher_disagreement_score":0.9463134,"about_ca_system_score_codex":0.00007828774,"about_ca_system_score_gemma":0.000060895745,"threshold_uncertainty_score":0.5403474},"labels":[],"label_agreement":null},{"id":"W2191938486","doi":"","title":"Basis refinement strategies for linear value function approximation in MDPs","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Markov decision process; Basis (linear algebra); Computer science; Bellman equation; Bisimulation; Basis function; Mathematical optimization; Function (biology); Value (mathematics); Markov process; Algorithm; Theoretical computer science; Mathematics; Machine learning","score_opus":0.05119097121540838,"score_gpt":0.2817875639405395,"score_spread":0.2305965927251311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2191938486","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":[0.0032420317,0.000047492547,0.99210453,0.00030090995,0.0008692886,0.00061647047,0.0000010637556,0.00025168314,0.0025665332],"genre_scores_gemma":[0.9829067,0.0000013754212,0.016311057,0.00025787862,0.00010584483,0.00018539165,0.00006331178,0.000008319791,0.0001601373],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834675,0.00005568737,0.00071499107,0.00015397869,0.00048272987,0.00024585327],"domain_scores_gemma":[0.99878865,0.00003490759,0.00045916814,0.00023153522,0.00041682052,0.000068902875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00083312445,0.00014798036,0.00016399966,0.00027073734,0.00012581836,0.001001448,0.00032097753,0.00008508768,5.734701e-7],"category_scores_gemma":[0.00011068262,0.00013459299,0.0000319232,0.0004698251,0.000016537208,0.007610477,0.000056325407,0.0001226392,0.000029149915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001549355,0.000008028811,0.00009126922,0.00035207614,0.0000032982953,1.4355727e-7,0.0021683578,0.9656221,0.000023405972,0.02006149,0.00057587324,0.011078453],"study_design_scores_gemma":[0.0006495622,0.00020450992,0.00009927128,0.000095893854,0.000004690836,0.000005945661,0.0015527067,0.9903277,0.000072495524,0.00030169706,0.006537361,0.00014812428],"about_ca_topic_score_codex":0.000047947928,"about_ca_topic_score_gemma":0.0000016247534,"teacher_disagreement_score":0.9796646,"about_ca_system_score_codex":0.00017127315,"about_ca_system_score_gemma":0.00022315278,"threshold_uncertainty_score":0.96569866},"labels":[],"label_agreement":null},{"id":"W2197326744","doi":"10.1017/s0269888910000354","title":"Robotics competitions as benchmarks for AI research","year":2011,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Robotics; Benchmark (surveying); Artificial intelligence; Computer science; Applications of artificial intelligence; Robot","score_opus":0.1069341295820813,"score_gpt":0.3609366505106727,"score_spread":0.2540025209285914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197326744","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":[0.000004729257,0.027464,0.9506235,0.0012608111,0.00053445,0.0007819554,6.369146e-7,0.00015990612,0.019170003],"genre_scores_gemma":[0.1588029,0.08110286,0.7326562,0.0031586292,0.0017136334,0.00222928,0.00009030831,0.00031827905,0.019927898],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986507,0.00010456524,0.00031713845,0.00024310919,0.00023734296,0.00044708652],"domain_scores_gemma":[0.9980001,0.00055234757,0.00005118678,0.00095105334,0.0003458033,0.00009950138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018837907,0.00015875894,0.00023921079,0.00010462736,0.0002326873,0.00007228665,0.0015749256,0.00004819043,0.00010211669],"category_scores_gemma":[0.00067417923,0.000118214935,0.00011965994,0.00069961045,0.000058509537,0.00017817054,0.00037543086,0.00044301146,0.0004887831],"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":[0.0000011699369,0.00004914116,0.000010085396,0.0023000916,0.000045832716,0.0000033426904,0.00092808576,0.0502697,0.000023643068,0.9254194,0.01521416,0.0057353717],"study_design_scores_gemma":[0.00016838756,0.00018950559,0.000107486725,0.0036518143,0.00004655369,0.000035954083,0.000010253506,0.59052986,0.00012916824,0.0018936889,0.402916,0.00032128385],"about_ca_topic_score_codex":0.000003649979,"about_ca_topic_score_gemma":9.1153186e-7,"teacher_disagreement_score":0.9235257,"about_ca_system_score_codex":0.00006536955,"about_ca_system_score_gemma":0.00009518593,"threshold_uncertainty_score":0.6282481},"labels":[],"label_agreement":null},{"id":"W2198357760","doi":"10.1609/aaai.v29i1.9702","title":"Reward Shaping for Model-Based Bayesian Reinforcement Learning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Agency for Defense Development; National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Reinforcement learning; Benchmark (surveying); Machine learning; Computer science; Artificial intelligence; Heuristic; Bayesian probability; Function (biology); Bayes' theorem; Domain (mathematical analysis); Bayesian inference; Mathematics","score_opus":0.16860257365642317,"score_gpt":0.32334944967993895,"score_spread":0.15474687602351578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2198357760","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":[0.001652961,0.000007817043,0.98364985,0.002458337,0.00033512758,0.00061710697,5.5802536e-7,0.00016181664,0.011116414],"genre_scores_gemma":[0.9567234,0.0000049799955,0.04183935,0.0003723585,0.00006031104,0.00006340562,0.0000012137282,0.000021644639,0.00091331924],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744815,0.000018910407,0.0007081486,0.0005191741,0.0007918,0.0005138134],"domain_scores_gemma":[0.99750865,0.00011968924,0.00059880456,0.00037133897,0.0012195746,0.00018196694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011407775,0.00027756486,0.00030814766,0.00017723496,0.00028092362,0.00036524967,0.0022783987,0.00011094609,0.000012923978],"category_scores_gemma":[0.001330522,0.00022674177,0.00016651495,0.00051733485,0.00018130215,0.00048576004,0.0003876268,0.00038030662,0.000037166603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049397702,0.000020737958,0.000059193917,0.00003630818,0.000008127585,1.01413804e-7,0.0008066869,0.6225054,0.0016720595,0.36964628,0.00014072654,0.005054983],"study_design_scores_gemma":[0.00006946929,0.00041138334,0.0000028541986,0.00019380383,0.000012049999,8.492195e-7,0.00027669495,0.8661893,0.095674284,0.036723588,0.00021485245,0.00023087031],"about_ca_topic_score_codex":0.000012876132,"about_ca_topic_score_gemma":0.0000013285528,"teacher_disagreement_score":0.95507044,"about_ca_system_score_codex":0.00013888977,"about_ca_system_score_gemma":0.0003417586,"threshold_uncertainty_score":0.9246262},"labels":[],"label_agreement":null},{"id":"W2201672140","doi":"10.1609/aaai.v25i1.7918","title":"Basis Function Discovery Using Spectral Clustering and Bisimulation Metrics","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"Office of Naval Research; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Adjacency list; Cluster analysis; Computer science; Basis (linear algebra); Graph; Function (biology); Theoretical computer science; Spectral clustering; State (computer science); Artificial intelligence; Data mining; Algorithm; Mathematics","score_opus":0.1564952070208593,"score_gpt":0.2914427844955239,"score_spread":0.1349475774746646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2201672140","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":[0.18439879,0.000008708654,0.81130373,0.00010690337,0.0003829674,0.00018303843,4.5739156e-7,0.000051880572,0.0035635123],"genre_scores_gemma":[0.9834474,0.000019136469,0.016316293,0.0000605978,0.00004126408,0.0000028625468,1.5457243e-7,0.000009603967,0.00010269845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986055,0.00001352067,0.0004044587,0.00034708477,0.00038047845,0.00024894997],"domain_scores_gemma":[0.9990512,0.00005866324,0.0003519016,0.0002077402,0.00027598115,0.00005449103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038277882,0.00016640303,0.0001678621,0.0002180476,0.00018727726,0.00031800996,0.0007489745,0.00006891793,0.000020298172],"category_scores_gemma":[0.00026180292,0.00013270894,0.00006400424,0.00074333465,0.00013749026,0.0011384096,0.00038602747,0.00020349835,0.000010053435],"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":[0.000108993416,0.00007414254,0.005148918,0.000071197166,0.000033910088,4.8505007e-7,0.002610425,0.037393425,0.026990753,0.8917172,0.0000076575925,0.035842914],"study_design_scores_gemma":[0.000019534771,0.00017502144,0.0017106273,0.00009155061,0.000018992809,0.000002958873,0.00023905654,0.8585604,0.11533246,0.023696113,0.000005637963,0.00014762896],"about_ca_topic_score_codex":0.00006076634,"about_ca_topic_score_gemma":0.0000036828333,"teacher_disagreement_score":0.8680211,"about_ca_system_score_codex":0.000052301435,"about_ca_system_score_gemma":0.000039555394,"threshold_uncertainty_score":0.5411713},"labels":[],"label_agreement":null},{"id":"W2205300805","doi":"10.1609/aiide.v9i1.12609","title":"Scythe AI: A Tool for Modular Reuse of Game AI","year":2013,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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":"Modular design; Reuse; Computer science; Software engineering; Process (computing); Artificial intelligence; Programming language; Human–computer interaction; Engineering","score_opus":0.0330847396573221,"score_gpt":0.2804623404342777,"score_spread":0.2473776007769556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2205300805","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":[0.38785532,0.000010572475,0.60047776,0.0061426316,0.0003314253,0.0015631993,0.000013526361,0.000048036243,0.0035575149],"genre_scores_gemma":[0.997977,0.000015460277,0.0008083609,0.00055627606,0.000025211582,0.000098580975,0.000001511298,0.000012664626,0.0005049312],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982425,0.000009726936,0.00062904845,0.00041013808,0.00040335392,0.00030521286],"domain_scores_gemma":[0.9980889,0.00014107021,0.0004501253,0.00036382256,0.00088430196,0.00007176497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017052877,0.00023850513,0.00029517044,0.00012379893,0.00007754293,0.0006167899,0.0014153612,0.00005995928,0.000037154587],"category_scores_gemma":[0.0006403157,0.0001714913,0.00016417682,0.00018744635,0.00022228777,0.001814823,0.000681883,0.00021952507,0.000029531997],"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":[0.00039004776,0.00071097957,0.0016191739,0.0002456416,0.00023405398,5.169686e-7,0.0087022325,0.0058999034,0.06908361,0.79061085,0.00089195324,0.121611044],"study_design_scores_gemma":[0.00010846038,0.0013207875,0.0003180082,0.0005195308,0.000017145849,0.000004195936,0.0012040945,0.52119875,0.3973899,0.07713406,0.00049261516,0.00029244885],"about_ca_topic_score_codex":0.000018508794,"about_ca_topic_score_gemma":3.2951058e-7,"teacher_disagreement_score":0.7134768,"about_ca_system_score_codex":0.000062986954,"about_ca_system_score_gemma":0.00004272407,"threshold_uncertainty_score":0.6993212},"labels":[],"label_agreement":null},{"id":"W2219400200","doi":"10.1609/aaai.v29i1.9655","title":"Approximate Linear Programming for Constrained Partially Observable Markov Decision Processes","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Institute for Information and Communications Technology Promotion; Natural Sciences and Engineering Research Council of Canada; Ministry of Science, ICT and Future Planning","keywords":"Observable; Partially observable Markov decision process; Markov decision process; Mathematical optimization; Benchmark (surveying); Computer science; Linear programming; Suite; Sequence (biology); Dynamic programming; Controller (irrigation); State (computer science); Markov process; Mathematics; Algorithm","score_opus":0.14263682547995002,"score_gpt":0.3262468132388472,"score_spread":0.18360998775889717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2219400200","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":[0.010173033,0.000022379627,0.9831963,0.0015565385,0.000535936,0.0012552221,0.0000034760117,0.00020951248,0.0030476116],"genre_scores_gemma":[0.8021566,0.000015157759,0.19711404,0.00013994858,0.00008968475,0.000120426135,0.0000015449926,0.000021432868,0.0003411271],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972799,0.000015718548,0.00078193017,0.000583825,0.0007772198,0.00056143664],"domain_scores_gemma":[0.99617153,0.00027961528,0.00060536375,0.00037996622,0.0023754323,0.00018811804],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001208441,0.0002930063,0.00034539288,0.00011630851,0.00023918606,0.0004943446,0.002442492,0.0001213989,0.000011362001],"category_scores_gemma":[0.0037626568,0.00022058144,0.00011755698,0.00087434537,0.00029699728,0.00069811003,0.00047201724,0.00025254107,0.00003550281],"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":[0.00044594257,0.00028950942,0.0005631301,0.00045768128,0.000048722846,0.0000011149698,0.0029468378,0.037162516,0.0060991626,0.7679531,0.0005354869,0.18349677],"study_design_scores_gemma":[0.000112991656,0.00062966376,0.0000110410765,0.00041432015,0.00002065934,0.000005686569,0.0006314941,0.74397933,0.19436891,0.05824236,0.0012632294,0.00032029752],"about_ca_topic_score_codex":0.000012285733,"about_ca_topic_score_gemma":0.000006280997,"teacher_disagreement_score":0.7919836,"about_ca_system_score_codex":0.00006259207,"about_ca_system_score_gemma":0.0005112284,"threshold_uncertainty_score":0.899505},"labels":[],"label_agreement":null},{"id":"W2232305727","doi":"10.1609/aaai.v29i1.9700","title":"Tighter Value Function Bounds for Bayesian Reinforcement Learning","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Agency for Defense Development; National Research Foundation of Korea; Ministry of Science, ICT and Future Planning; National Research Foundation","keywords":"Reinforcement learning; Bayesian probability; Computer science; Heuristic; Bellman equation; Bayes' theorem; Function (biology); Perspective (graphical); Value (mathematics); Artificial intelligence; Machine learning; Mathematical optimization; Focus (optics); Mathematics","score_opus":0.09005187973659068,"score_gpt":0.2974173093581666,"score_spread":0.20736542962157595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232305727","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":[0.0027183334,0.0000090677,0.97271335,0.001836529,0.0008908436,0.0005671081,3.6187146e-7,0.00013904391,0.021125387],"genre_scores_gemma":[0.9876659,0.000007756005,0.009073542,0.00029345823,0.00012609469,0.000055533696,0.0000014473269,0.000018299308,0.0027579544],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977155,0.00002227625,0.0006261173,0.00046275154,0.0007334446,0.00043995856],"domain_scores_gemma":[0.9979054,0.00010007942,0.0005235491,0.00031937793,0.0010010551,0.00015059367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000985991,0.00024841764,0.00025870668,0.00015213607,0.0002923829,0.00044350408,0.0016055387,0.000109096,0.000030912244],"category_scores_gemma":[0.0007631306,0.00019308597,0.00014284361,0.0004950477,0.0001664303,0.00062548363,0.00037567265,0.00034588893,0.000083347186],"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":[0.00009852436,0.00003183675,0.00015768607,0.00003464258,0.000021558102,1.1773948e-7,0.0012295392,0.14841889,0.0028659247,0.83515114,0.0005020636,0.011488109],"study_design_scores_gemma":[0.00006951249,0.00091218215,0.000029221575,0.00011984934,0.000020425487,0.000002113591,0.00041018368,0.85056454,0.0692981,0.07585861,0.0024806494,0.00023461798],"about_ca_topic_score_codex":0.000020046793,"about_ca_topic_score_gemma":0.0000012827753,"teacher_disagreement_score":0.98494756,"about_ca_system_score_codex":0.00011908141,"about_ca_system_score_gemma":0.00017450062,"threshold_uncertainty_score":0.78738177},"labels":[],"label_agreement":null},{"id":"W223326216","doi":"10.1613/jair.4301","title":"Policy Iteration Based on Stochastic Factorization","year":2014,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"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; National Institutes of Health; McGill University; Fonds Québécois de la Recherche sur la Nature et les Technologies; Compute Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Markov decision process; Factorization; Mathematical optimization; Factoring; Mathematics; Multiplication (music); Computer science; Markov process; Applied mathematics; Algorithm; Finance","score_opus":0.12763786672913804,"score_gpt":0.4165855694153244,"score_spread":0.2889477026861863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W223326216","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":[0.0009982113,0.0000033781837,0.9951997,0.002491475,0.0004031405,0.00010937478,1.772307e-7,0.000018992432,0.00077556906],"genre_scores_gemma":[0.98781073,0.0000041446892,0.011329444,0.00011922279,0.0006452555,0.0000017574177,8.1295195e-7,0.000008986704,0.00007964638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969166,0.00045629308,0.0005771903,0.00017353245,0.0015204474,0.00035596904],"domain_scores_gemma":[0.9971175,0.0009934565,0.00025279215,0.0003588338,0.0011208192,0.00015656797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034780137,0.000098442826,0.00014937867,0.0010993907,0.00022759885,0.0004986643,0.00090117037,0.00006964059,0.000027714445],"category_scores_gemma":[0.0042599346,0.00008301176,0.00007371903,0.001179662,0.00008377041,0.00049524574,0.00007894828,0.00058515696,0.00014448151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025887779,0.000042194257,0.00001801281,0.0000055901596,0.0000035671858,0.0000024587425,0.00026074136,0.8027494,0.001479438,0.12359322,0.000046410256,0.07177306],"study_design_scores_gemma":[0.000028271725,0.0010368568,0.00006314416,0.00006494281,0.0000014515289,0.0000042676993,0.000034382316,0.9617393,0.009555851,0.02721175,0.00018634435,0.000073428935],"about_ca_topic_score_codex":0.000011279856,"about_ca_topic_score_gemma":0.0000015301077,"teacher_disagreement_score":0.98681253,"about_ca_system_score_codex":0.00019560281,"about_ca_system_score_gemma":0.0003836134,"threshold_uncertainty_score":0.50998473},"labels":[],"label_agreement":null},{"id":"W2236244207","doi":"10.1561/2200000049","title":"Bayesian Reinforcement Learning: A Survey","year":2015,"lang":"en","type":"article","venue":"Foundations and Trends® in Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":223,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Reinforcement learning; Artificial intelligence; Bayesian inference; Bayesian probability; Variable-order Bayesian network; Prior probability; Inference; Bellman equation; Algorithm; Mathematical optimization; Mathematics","score_opus":0.0465390705497981,"score_gpt":0.3022379049415592,"score_spread":0.2556988343917611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2236244207","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":[0.00440627,0.00011028432,0.9754209,0.0005987748,0.00022329211,0.000092587085,4.754638e-7,0.00023374346,0.018913705],"genre_scores_gemma":[0.9800444,0.000028852834,0.008560605,0.00006780464,0.00003635856,0.000014360655,0.00020636294,0.000019538042,0.011021687],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794465,0.00042753274,0.00042014365,0.00042077948,0.00038617692,0.00040069432],"domain_scores_gemma":[0.99896246,0.00020768215,0.00019838277,0.00032764743,0.00010852845,0.00019528161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014795837,0.00021613146,0.00023206479,0.0006192418,0.00033161783,0.00045100154,0.00040078769,0.00007362461,0.00010708475],"category_scores_gemma":[0.0006175301,0.00021547904,0.00004370805,0.001155608,0.000057939593,0.0006242121,0.00034747372,0.0006992697,0.000064967775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000076084634,0.000016157433,0.15663686,0.000004218743,0.000013762654,0.000007336901,0.0010104881,0.81605583,0.0000028304014,0.0053211534,0.000092795286,0.020830955],"study_design_scores_gemma":[0.000790716,0.00020759102,0.04959874,0.000016744134,0.000005486397,0.000013071291,0.00006400618,0.92572916,0.0000024125188,0.00015542972,0.023179356,0.00023729484],"about_ca_topic_score_codex":0.0011316905,"about_ca_topic_score_gemma":0.00037160364,"teacher_disagreement_score":0.97563815,"about_ca_system_score_codex":0.000108018605,"about_ca_system_score_gemma":0.00006361707,"threshold_uncertainty_score":0.87869805},"labels":[],"label_agreement":null},{"id":"W2238086212","doi":"10.15307/fcj.25.185.2015","title":"FCJ-185 An Algorithmic Agartha: Post-App Approaches to Synarchic Regulation","year":2015,"lang":"en","type":"article","venue":"The Fibreculture Journal","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Computer science; World Wide Web; Internet privacy","score_opus":0.13523283284432092,"score_gpt":0.2589250793733536,"score_spread":0.12369224652903266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2238086212","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":[0.013757038,0.00010227541,0.9711993,0.010971124,0.0007249643,0.00028643588,0.0000012815163,0.00015313982,0.0028044959],"genre_scores_gemma":[0.75471836,0.000010603975,0.23543155,0.0015771798,0.0020088868,0.00001431332,0.00002198788,0.000041851916,0.0061752703],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799156,0.000301812,0.0003222708,0.0002541432,0.00074543565,0.00038478503],"domain_scores_gemma":[0.99847627,0.000044127122,0.00021976055,0.0006031284,0.00025095133,0.0004057421],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012656538,0.00019678552,0.00017171135,0.000107547035,0.0003941462,0.00072165293,0.0015165036,0.00009119031,0.000016033398],"category_scores_gemma":[0.00014695888,0.000119234275,0.00008465354,0.00039715902,0.000049644717,0.00093233626,0.00026335142,0.00059315667,0.00017060479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039701314,0.000034000186,0.00006725473,0.000006550068,0.00005046651,0.000017294331,0.017964214,0.9339195,0.001177177,0.008468535,0.009987759,0.028267538],"study_design_scores_gemma":[0.0010676532,0.001873685,0.0070067965,0.000119414384,0.000046772602,0.0030382723,0.001805238,0.92819524,0.0010162506,0.007162591,0.04795135,0.00071671116],"about_ca_topic_score_codex":0.0000062389904,"about_ca_topic_score_gemma":0.0000033330311,"teacher_disagreement_score":0.7409613,"about_ca_system_score_codex":0.00010725141,"about_ca_system_score_gemma":0.00015025331,"threshold_uncertainty_score":0.69589156},"labels":[],"label_agreement":null},{"id":"W2264982354","doi":"10.3166/ria.27.243-263","title":"Adaptation de la matrice de covariance pour l’apprentissage par renforcement direct","year":2013,"lang":"fr","type":"article","venue":"Revue d intelligence artificielle","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Adaptation (eye); Reinforcement learning; Covariance; Parameterized complexity; Humanities; Political science; Computer science; Psychology; Artificial intelligence; Mathematics; Philosophy; Algorithm; Neuroscience; Statistics","score_opus":0.04328650558652317,"score_gpt":0.278600095215143,"score_spread":0.23531358962861984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2264982354","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":[0.0015514955,0.0019521369,0.94047326,0.0031090467,0.001180157,0.0006306543,0.000003822562,0.00019086161,0.05090855],"genre_scores_gemma":[0.7516473,0.0014451682,0.1442313,0.00035408518,0.0003275668,0.00011945398,0.000010122411,0.00005261944,0.10181236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602914,0.00067590975,0.00092188036,0.0007414324,0.00043901996,0.0011926449],"domain_scores_gemma":[0.9967949,0.0010567362,0.000461151,0.0010552299,0.00028098392,0.00035103838],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0018069322,0.00040757487,0.00036804585,0.00016861346,0.0004006702,0.0010332742,0.0012519936,0.0003082248,0.0021586914],"category_scores_gemma":[0.0006684316,0.0004799337,0.00020049213,0.00091322657,0.0003039573,0.00089862035,0.00035019103,0.00059961923,0.0051646824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007986405,0.00013301182,0.00035839193,0.00018946923,0.00004393337,0.0000475619,0.004809656,0.87684715,0.0015731337,0.03947332,0.007094546,0.06942185],"study_design_scores_gemma":[0.000080114856,0.00015349934,0.00034037232,0.0004150487,0.000048097823,0.00011362384,0.0009354578,0.9254158,0.0136877075,0.0027382667,0.055611882,0.00046008854],"about_ca_topic_score_codex":0.0011075208,"about_ca_topic_score_gemma":0.000007976217,"teacher_disagreement_score":0.79624194,"about_ca_system_score_codex":0.00046231423,"about_ca_system_score_gemma":0.00042032351,"threshold_uncertainty_score":0.9997652},"labels":[],"label_agreement":null},{"id":"W2269274350","doi":"10.48550/arxiv.1512.04087","title":"True Online Temporal-Difference Learning","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":56,"is_retracted":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":"Temporal difference learning; Computer science; Artificial intelligence; Equivalence (formal languages); Lambda; Reinforcement learning; Domain (mathematical analysis); Online learning; Machine learning; Binary number; Online algorithm; Simple (philosophy); Algorithm; Theoretical computer science; Mathematics; Discrete mathematics; Arithmetic; Mathematical analysis","score_opus":0.12191799175305862,"score_gpt":0.2099222055253362,"score_spread":0.08800421377227757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269274350","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":[0.12345245,0.00004121028,0.87144846,0.0001061001,0.0007169494,0.00022039468,0.0000049285172,0.00061138143,0.0033981153],"genre_scores_gemma":[0.9719549,0.000101536985,0.007016428,0.00008260691,0.000115659335,5.301028e-7,0.00008622509,0.000028838236,0.020613303],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747646,0.00026397136,0.00030891615,0.0012197198,0.00022319288,0.00050776143],"domain_scores_gemma":[0.99719006,0.00012195069,0.00049971964,0.001534038,0.00034651064,0.00030773002],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038591874,0.00044114966,0.0004578537,0.00031770088,0.00018323885,0.00024230377,0.0031017219,0.00039054285,0.000030314322],"category_scores_gemma":[0.00019169776,0.0005050108,0.0001920367,0.00062615034,0.00012500524,0.00034623462,0.0039762263,0.0016674246,0.00021075994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010019728,0.000043504446,0.009164898,0.000046388304,0.0000504024,0.0001913153,0.00026062495,0.9731921,0.000010529718,0.016209839,0.0002463851,0.0005739789],"study_design_scores_gemma":[0.00042717575,0.00011442654,0.0015546599,0.0001137072,0.000038619935,0.0000042789375,0.000089406145,0.9891911,0.000016206715,0.005512863,0.0023772963,0.00056026556],"about_ca_topic_score_codex":0.00017142625,"about_ca_topic_score_gemma":0.000021522137,"teacher_disagreement_score":0.86443204,"about_ca_system_score_codex":0.00035185786,"about_ca_system_score_gemma":0.00047539794,"threshold_uncertainty_score":0.9997401},"labels":[],"label_agreement":null},{"id":"W2272644799","doi":"10.1609/aaai.v29i1.9659","title":"Information Gathering and Reward Exploitation of Subgoals for POMDPs","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"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; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Partially observable Markov decision process; Computer science; Benchmark (surveying); Solver; Time horizon; Markov decision process; Space (punctuation); State (computer science); Artificial intelligence; Machine learning; Markov chain; Markov process; Markov model; Mathematical optimization; Mathematics; Algorithm","score_opus":0.1196532880799096,"score_gpt":0.3033813658153713,"score_spread":0.18372807773546168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2272644799","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":[0.13853109,0.000011290899,0.85518944,0.0011836198,0.0003053932,0.0005758414,0.0000017814656,0.00007557668,0.0041259923],"genre_scores_gemma":[0.97769004,0.000015562853,0.022141838,0.00006088208,0.000018554647,0.000020907668,4.3861672e-7,0.0000048667257,0.00004689153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886733,0.000008127411,0.00047699673,0.0001341648,0.00035047185,0.00016289024],"domain_scores_gemma":[0.9982347,0.00008725259,0.00049082946,0.00015443648,0.0009733203,0.000059484606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006553527,0.0001108877,0.00015994343,0.000107991145,0.00006630219,0.00014764615,0.0007156919,0.000052012576,0.0000024131086],"category_scores_gemma":[0.0008787372,0.00008853296,0.000045148896,0.00026583084,0.00009424186,0.0010252941,0.00018506279,0.000090708985,0.000008641525],"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":[0.00005606384,0.000026863594,0.00031732366,0.00011540536,0.000012242303,1.827589e-8,0.01207865,0.005980539,0.0067431927,0.9480742,0.00008898383,0.026506491],"study_design_scores_gemma":[0.000077787656,0.00054148794,0.00017317613,0.00021225221,0.00001329692,0.0000019831673,0.003100561,0.5186226,0.37611198,0.100685604,0.00027981988,0.0001794471],"about_ca_topic_score_codex":0.000012262567,"about_ca_topic_score_gemma":6.792297e-7,"teacher_disagreement_score":0.8473886,"about_ca_system_score_codex":0.00003061865,"about_ca_system_score_gemma":0.00007329838,"threshold_uncertainty_score":0.3610269},"labels":[],"label_agreement":null},{"id":"W2276615213","doi":"","title":"Two perspectives on learning rich representations from robot experience","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Robot; Artificial intelligence; Computer science; Space (punctuation); Robot learning; Position (finance); Social robot; Human–computer interaction; Mobile robot; Robot control","score_opus":0.021885736796746522,"score_gpt":0.29417326471106175,"score_spread":0.2722875279143152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2276615213","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":[0.05691765,0.000021868753,0.87576455,0.0007321624,0.00017355684,0.00015985357,7.809998e-8,0.0003579782,0.065872304],"genre_scores_gemma":[0.87460977,0.000010753755,0.11661562,0.00020811791,0.00006364075,0.000043528744,0.000002167261,0.000008753337,0.008437634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985935,0.000091029804,0.00019558039,0.00048669224,0.0003672892,0.00026588156],"domain_scores_gemma":[0.9987664,0.00029735736,0.00008986133,0.0006306382,0.00012429386,0.000091412854],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00007481891,0.00013176579,0.00011195087,0.00009328877,0.00024773253,0.0004495427,0.0007557216,0.000031713593,0.0009538542],"category_scores_gemma":[0.00024377264,0.00011611693,0.000044471253,0.00033271872,0.000059057787,0.0008965994,0.00025754693,0.0002462112,0.0016532332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000112497,0.000028881079,0.0068736444,7.3779245e-7,0.000015411428,0.0000029624093,0.022004426,0.91362673,0.0019597742,0.05331903,0.000623364,0.0015439175],"study_design_scores_gemma":[0.00034087803,0.00012880591,0.023895489,0.000014457359,0.0000033214742,0.000002268454,0.015505024,0.95544666,0.0030327146,0.000835702,0.00050168164,0.00029300232],"about_ca_topic_score_codex":0.0008407542,"about_ca_topic_score_gemma":0.0000030133806,"teacher_disagreement_score":0.81769216,"about_ca_system_score_codex":0.000055230368,"about_ca_system_score_gemma":0.000023196453,"threshold_uncertainty_score":0.9999594},"labels":[],"label_agreement":null},{"id":"W2284456400","doi":"10.1007/978-3-642-29946-9_21","title":"A Framework for Computing Bounds for the Return of a Policy","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Lipschitz continuity; Computer science; Piecewise; Bounding overwatch; Bounded function; Constant (computer programming); Context (archaeology); Markov decision process; Representation (politics); State (computer science); Theoretical computer science; Mathematical optimization; Markov process; Algorithm; Mathematics; Artificial intelligence; Pure mathematics","score_opus":0.03357722234187318,"score_gpt":0.3053615565312778,"score_spread":0.2717843341894046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2284456400","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":[0.000004956733,0.0007150493,0.9935616,0.0018644698,0.0020868732,0.0012439163,0.0000066709013,0.00009602338,0.00042041508],"genre_scores_gemma":[0.09419462,0.00003345757,0.90240896,0.0014149362,0.0016519736,0.000022807782,0.0000038284397,0.000046859124,0.00022255031],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99655825,0.000025270348,0.0007199116,0.0009008084,0.00084310316,0.00095262966],"domain_scores_gemma":[0.99082845,0.006154732,0.00076499075,0.0016735432,0.0004483095,0.00012994702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018824564,0.00047766126,0.0005886213,0.000615978,0.00051372644,0.00047183968,0.0046794997,0.00039446654,0.0000044120093],"category_scores_gemma":[0.001152334,0.0003618047,0.00029833996,0.000665191,0.0008485154,0.00035164243,0.0013629169,0.00076602853,0.000004005563],"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":[0.000008801038,0.0000100618445,0.000032901684,0.00010962783,0.000026487132,7.823688e-7,0.0016486,0.34897676,0.000020814474,0.3580954,0.000022616543,0.29104716],"study_design_scores_gemma":[0.00020433334,0.00021511907,0.000035216795,0.00039543517,0.000017894188,0.000013925654,3.956111e-7,0.7913996,0.00032149002,0.20310535,0.003945569,0.0003457066],"about_ca_topic_score_codex":0.000019060055,"about_ca_topic_score_gemma":0.00000686421,"teacher_disagreement_score":0.4424228,"about_ca_system_score_codex":0.00029591174,"about_ca_system_score_gemma":0.00084211916,"threshold_uncertainty_score":0.9998834},"labels":[],"label_agreement":null},{"id":"W2286609364","doi":"10.5555/2034396.2034427","title":"Basis function discovery using spectral clustering and bisimulation metrics","year":2011,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","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":"Computer science; Markov decision process; Cluster analysis; Set (abstract data type); Bellman equation; State space; Feature (linguistics); Function (biology); Artificial intelligence; State (computer science); Markov process; Feature vector; Basis (linear algebra); Markov chain; Focus (optics); Machine learning; Quality (philosophy); Mathematical optimization; Algorithm; Mathematics","score_opus":0.14918220564433027,"score_gpt":0.28652763876973,"score_spread":0.1373454331253997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286609364","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":[0.12833378,0.00026557516,0.8696133,0.0000036020547,0.0009960233,0.00037077474,0.0000026693733,0.000063598425,0.00035067543],"genre_scores_gemma":[0.9788097,0.00009338306,0.020390544,0.000048505346,0.000063030864,0.000006573576,0.00000332187,0.000018997582,0.0005659135],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984564,0.00011411441,0.00034914282,0.00045685412,0.00031192502,0.0003115565],"domain_scores_gemma":[0.9992169,0.000048668433,0.00024215119,0.00029133083,0.00007817714,0.00012274449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030954406,0.00021770186,0.00022460305,0.00025203536,0.000253276,0.00033366322,0.00020691496,0.00008396067,0.0000046092073],"category_scores_gemma":[0.00003305678,0.00019780599,0.000045355846,0.00031790385,0.00004314338,0.0013424325,0.0003038566,0.000115363444,0.000008150586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012404373,0.00026796898,0.19966733,0.00031111191,0.0007124136,0.00008396649,0.009321653,0.7661524,0.0013734722,0.0076108496,0.00014433397,0.01423049],"study_design_scores_gemma":[0.00059911836,0.00013990465,0.0693329,0.000066407985,0.000041888412,0.000012732263,0.00025071614,0.92907757,0.000054034397,0.000011110762,0.00020019917,0.0002134316],"about_ca_topic_score_codex":0.0006761878,"about_ca_topic_score_gemma":0.000008371321,"teacher_disagreement_score":0.85047597,"about_ca_system_score_codex":0.00008098525,"about_ca_system_score_gemma":0.000018259052,"threshold_uncertainty_score":0.8066294},"labels":[],"label_agreement":null},{"id":"W2295665692","doi":"10.5555/2034396.2034406","title":"Efficient planning in R-max","year":2011,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","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; Mathematical optimization; Markov decision process; Value (mathematics); Artificial intelligence; Algorithm; Machine learning; Mathematics; Markov process","score_opus":0.12420306409074311,"score_gpt":0.2922210493630056,"score_spread":0.16801798527226247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295665692","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":[0.12270224,0.00041306223,0.8687607,0.000011317719,0.0012011789,0.0006809322,0.000002480599,0.00012166927,0.0061064237],"genre_scores_gemma":[0.98909694,0.00001631232,0.009579816,0.00009156671,0.000028606688,0.000033327186,0.0000019193765,0.000017700742,0.0011338238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810076,0.00014237272,0.0004327447,0.000508761,0.00034721775,0.00046816777],"domain_scores_gemma":[0.9991097,0.000046265293,0.0002006228,0.0004206666,0.00006413563,0.00015863072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042251803,0.00023463389,0.00026968287,0.00020774035,0.00013801084,0.000114041955,0.0005529722,0.00008858023,0.000011621731],"category_scores_gemma":[0.00003259089,0.00020878576,0.000046026882,0.00026052014,0.00005130504,0.00017912613,0.0003597204,0.00018314294,0.00009271448],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030323103,0.00034852253,0.09871728,0.000088483765,0.00014194654,0.00040542154,0.028145386,0.85856813,0.00012663633,0.011050082,0.0006090404,0.0017687627],"study_design_scores_gemma":[0.0008460768,0.000105486295,0.082523204,0.00015895507,0.000006765047,0.000012160609,0.0006013604,0.91456467,0.000031554224,0.0000055886926,0.00090606976,0.0002381151],"about_ca_topic_score_codex":0.0005488077,"about_ca_topic_score_gemma":0.000003993842,"teacher_disagreement_score":0.8663947,"about_ca_system_score_codex":0.000078637466,"about_ca_system_score_gemma":0.000027432681,"threshold_uncertainty_score":0.8514036},"labels":[],"label_agreement":null},{"id":"W233883780","doi":"10.1609/icaps.v21i1.13468","title":"Distributed Control of Situated Assistance in Large Domains with Many Tasks","year":2011,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Situated; Partially observable Markov decision process; Computer science; Task (project management); Scalability; Affordance; Domain (mathematical analysis); Set (abstract data type); Process (computing); Population; Markov decision process; Artificial intelligence; Human–computer interaction; Controller (irrigation); Control (management); Machine learning; Distributed computing; Markov process; Markov chain; Markov model; Engineering; Mathematics","score_opus":0.029838982046658497,"score_gpt":0.25990372975629306,"score_spread":0.23006474770963456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W233883780","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":[0.83405495,0.000017258164,0.16114819,0.0002748168,0.00009493108,0.00013603417,0.00001267018,0.0001476917,0.004113434],"genre_scores_gemma":[0.9895632,0.0000038754656,0.0103332875,0.000052108146,0.0000057019215,0.0000058237556,0.0000032253959,0.0000061054434,0.00002667178],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988818,0.000010321873,0.0003241741,0.00022065474,0.00037798155,0.00018505914],"domain_scores_gemma":[0.9990369,0.00005212491,0.0004300161,0.000100025536,0.00034441444,0.000036520145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036514326,0.00012999581,0.00019459294,0.00011389227,0.00006089384,0.00008872887,0.0008031152,0.000059488917,0.000006796332],"category_scores_gemma":[0.00014600519,0.0000939373,0.000028128863,0.0002472273,0.00006868883,0.0002544033,0.00012560615,0.0002207078,8.366731e-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":[0.0003884929,0.00014630645,0.47712302,0.00009474195,0.00018132462,0.0000104392,0.0035394097,0.053931758,0.018631691,0.44581178,0.000033692988,0.000107328626],"study_design_scores_gemma":[0.00086317165,0.00010124546,0.06763539,0.00072483433,0.000008366619,0.0000077136365,0.00031517528,0.9241989,0.0056076404,0.00042485044,0.0000064320834,0.00010623773],"about_ca_topic_score_codex":0.00001630684,"about_ca_topic_score_gemma":0.0000010344784,"teacher_disagreement_score":0.8702672,"about_ca_system_score_codex":0.000032040116,"about_ca_system_score_gemma":0.000044939057,"threshold_uncertainty_score":0.3830652},"labels":[],"label_agreement":null},{"id":"W2342981176","doi":"10.1007/978-3-319-57969-6_1","title":"NeuroHex: A Deep Q-learning Hex Agent","year":2017,"lang":"en","type":"preprint","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Olympiad; Reinforcement learning; Computer science; Q-learning; Champion; Artificial intelligence; Initialization; State (computer science); Convolutional neural network; Action (physics); Algorithm; Mathematics; Political science; Law; Mathematics education","score_opus":0.05352251106668458,"score_gpt":0.32683744967227296,"score_spread":0.27331493860558836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342981176","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":[0.00082196726,0.00020294395,0.9816179,0.0015354126,0.0008663356,0.00036503968,9.770782e-7,0.00018307565,0.014406336],"genre_scores_gemma":[0.7364022,0.002363465,0.26044562,0.0006339923,0.00003457424,0.00005068153,0.000028326167,0.000006525275,0.00003461298],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976854,0.00015088872,0.0007303031,0.00040076097,0.00064719527,0.00038549415],"domain_scores_gemma":[0.9938077,0.00020368317,0.00074099825,0.004723398,0.00037983365,0.00014438933],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0018433142,0.00024699335,0.00026927327,0.00090851734,0.0013580042,0.003815184,0.010279684,0.00013072869,0.0000025514582],"category_scores_gemma":[0.00037911063,0.0002580405,0.00005878957,0.0005801287,0.00082725985,0.007079501,0.020437043,0.0012617006,0.00006198742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001266403,0.000019993047,0.0014720523,0.00006117141,0.000006168578,0.0000010139414,0.0056246966,0.66592765,0.0000038618837,0.039742194,0.0000641004,0.28707582],"study_design_scores_gemma":[0.00017483212,0.000035542012,0.013776762,0.00012993002,0.0000030178303,0.000011996596,0.00002597636,0.96082646,0.000008117184,0.0007671694,0.02398334,0.00025685545],"about_ca_topic_score_codex":0.00003911544,"about_ca_topic_score_gemma":0.0000042197776,"teacher_disagreement_score":0.7355802,"about_ca_system_score_codex":0.00017100736,"about_ca_system_score_gemma":0.00035773075,"threshold_uncertainty_score":0.9999872},"labels":[],"label_agreement":null},{"id":"W2394540668","doi":"10.1609/aaai.v25i1.8032","title":"Provoking Opponents to Facilitate the Recognition of their Intentions","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds Québécois de la Recherche sur la Nature et les Technologies","keywords":"Adversary; Plan (archaeology); Contrast (vision); Observer (physics); Computer science; State (computer science); Psychology; Cognitive psychology; Artificial intelligence; Social psychology; Human–computer interaction; Computer security; Algorithm","score_opus":0.3161080705411999,"score_gpt":0.29375630951558374,"score_spread":0.022351761025616146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2394540668","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":[0.18650822,0.000008956674,0.75613725,0.0030566656,0.0008507403,0.001352056,0.000010064482,0.0001324087,0.05194363],"genre_scores_gemma":[0.99391645,0.000012487829,0.005539654,0.00014075321,0.000017554952,0.000038305127,3.721628e-7,0.000008461903,0.00032598583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99826133,0.000028638713,0.0005956435,0.00032820817,0.00050384505,0.00028236173],"domain_scores_gemma":[0.99805975,0.00008896946,0.00044613777,0.00037317394,0.00096488686,0.00006706784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074001896,0.0001766907,0.0001928909,0.00013174812,0.0001948449,0.0001098478,0.0023595537,0.000053899374,0.00006200723],"category_scores_gemma":[0.0005916113,0.00010793279,0.00012456505,0.0006113436,0.00024925996,0.000365405,0.00056395534,0.00025811387,0.00010857425],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012741295,0.00024365683,0.00056590734,0.00009835433,0.00007011541,3.2173608e-7,0.032726455,0.001437542,0.101253144,0.6912452,0.0002044294,0.17202748],"study_design_scores_gemma":[0.00002830307,0.0004660663,0.0007623904,0.00048783515,0.000018650331,0.0000034311938,0.0025532215,0.07005692,0.81681734,0.10843803,0.00013009759,0.00023773308],"about_ca_topic_score_codex":0.00006263695,"about_ca_topic_score_gemma":0.0000065444083,"teacher_disagreement_score":0.8074082,"about_ca_system_score_codex":0.000030769297,"about_ca_system_score_gemma":0.00006437275,"threshold_uncertainty_score":0.44013715},"labels":[],"label_agreement":null},{"id":"W2395526823","doi":"","title":"An empirical analysis of reinforcement learning using design of experiments","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Convergence (economics); Computer science; Reinforcement learning; Artificial neural network; Subspace topology; Design of experiments; Logistic regression; Regression; Artificial intelligence; Machine learning; Mathematical optimization; Algorithm; Statistics; Mathematics","score_opus":0.08287195625593569,"score_gpt":0.3503770929916817,"score_spread":0.267505136735746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2395526823","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":[0.06471152,0.000008031025,0.93413657,0.000013043531,0.00003943599,0.00016777229,3.0917448e-8,0.000052640138,0.0008709454],"genre_scores_gemma":[0.74068004,0.0000020822235,0.25902995,0.000043825665,0.000004724482,0.0000040950945,0.000002020506,0.0000050942563,0.000228158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983603,0.00014969026,0.000532706,0.0002409562,0.00048335618,0.0002330231],"domain_scores_gemma":[0.9987155,0.00009779438,0.0003195656,0.00058144185,0.00019521175,0.00009047021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033804608,0.00012343231,0.0003169288,0.00042661454,0.000060042228,0.00006530138,0.0006618947,0.000053414595,0.00039618695],"category_scores_gemma":[0.000046571306,0.000108074055,0.00010386742,0.0010995618,0.00004930901,0.00063015224,0.00018399952,0.0000903087,0.000012313734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022791198,0.000027968106,0.011093884,0.000004732099,0.00022318219,3.4259818e-7,0.00092890527,0.96195793,0.024829315,0.0005648407,0.000020902491,0.00034571814],"study_design_scores_gemma":[0.00013732794,0.00028013965,0.0023343503,0.0000073659216,0.00007901366,3.5593894e-7,0.0001487402,0.9751415,0.021737164,0.00001314523,0.000010397778,0.00011046505],"about_ca_topic_score_codex":0.00020645357,"about_ca_topic_score_gemma":2.1502785e-7,"teacher_disagreement_score":0.6759685,"about_ca_system_score_codex":0.000046336914,"about_ca_system_score_gemma":0.00005110035,"threshold_uncertainty_score":0.4407132},"labels":[],"label_agreement":null},{"id":"W2396459401","doi":"","title":"SmartWheeler: A Robotic Wheelchair Test-Bed for Investigating New Models of Human-Robot Interaction.","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Wheelchair; Robot; Human–computer interaction; Computer science; Human–robot interaction; Mobile robot; Autonomy; Scale (ratio); Robotics; Interface (matter); Control (management); Test (biology); Artificial intelligence; Simulation; Engineering","score_opus":0.0721783322261814,"score_gpt":0.31582696792387427,"score_spread":0.24364863569769285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2396459401","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":[0.002174435,0.000021784303,0.9895304,0.0004352091,0.00035518996,0.00040853448,2.3327217e-7,0.00028093095,0.0067932694],"genre_scores_gemma":[0.567803,0.0000014658511,0.42795244,0.00034358393,0.0000974564,0.0000070391616,0.0000036518404,0.000019343559,0.003771995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979355,0.00002451932,0.00075676164,0.00040494255,0.00038444396,0.00049384456],"domain_scores_gemma":[0.99771595,0.0008061677,0.00039328737,0.0006348483,0.00022795619,0.00022177097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006778481,0.0002197386,0.0003036497,0.0002454311,0.00019474352,0.00013502417,0.00086862023,0.00009738978,0.000025627356],"category_scores_gemma":[0.0004169553,0.00021248992,0.00013533571,0.00044814986,0.00006510753,0.0009932453,0.00026865216,0.00021632093,0.000017696664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003080279,0.00003348535,0.00066679344,0.000045809884,0.00002396792,0.0000012219127,0.000991707,0.90695846,0.011167225,0.07607369,0.0014465668,0.002587986],"study_design_scores_gemma":[0.0005891647,0.00036501972,0.00029933508,0.00009141688,0.000013862007,0.0000080316,0.00011872599,0.97251236,0.017244905,0.008319462,0.0001872454,0.00025049428],"about_ca_topic_score_codex":0.00019136305,"about_ca_topic_score_gemma":0.000048934315,"teacher_disagreement_score":0.5656286,"about_ca_system_score_codex":0.00009278983,"about_ca_system_score_gemma":0.00014026987,"threshold_uncertainty_score":0.8665087},"labels":[],"label_agreement":null},{"id":"W2401626140","doi":"","title":"Treating Epilepsy by Reinforcement Learning Via Manifold-Based Simulation.","year":2010,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Epilepsy; Artificial intelligence; Manifold (fluid mechanics); Psychology; Neuroscience; Engineering; Mechanical engineering","score_opus":0.06475144094737749,"score_gpt":0.32914766654567496,"score_spread":0.26439622559829745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401626140","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":[0.0011898357,0.0000031161176,0.9760644,0.0008867456,0.000465106,0.00025037333,0.000001690162,0.00024971034,0.020889044],"genre_scores_gemma":[0.98133606,0.000002214366,0.016857017,0.0005673563,0.00012363004,0.000030709856,0.000046125813,0.000017056142,0.0010198596],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969639,0.00009761232,0.0006666725,0.0005633356,0.0012971067,0.00041136885],"domain_scores_gemma":[0.99756646,0.00072091544,0.00034660258,0.00038125025,0.0008337622,0.00015101554],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007579415,0.00027156936,0.00019704692,0.00024779156,0.00047320547,0.00047452273,0.00094247994,0.00015549417,0.00076110224],"category_scores_gemma":[0.0009908922,0.0002805198,0.00008948896,0.00048182768,0.00009118084,0.00048525239,0.0001113641,0.0007824169,0.0008180082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011314731,0.000035153986,0.000073352145,0.0000038603675,0.0000064632877,0.0000014787377,0.0000917878,0.6794477,0.0041758637,0.29405144,0.00005248095,0.022049097],"study_design_scores_gemma":[0.00005110957,0.00020467308,0.00007042657,0.000023939947,0.000003803688,0.0000013059034,0.000026545267,0.96706754,0.020210104,0.010200332,0.0018435668,0.0002966253],"about_ca_topic_score_codex":0.000031103486,"about_ca_topic_score_gemma":0.00001315474,"teacher_disagreement_score":0.98014617,"about_ca_system_score_codex":0.000117304364,"about_ca_system_score_gemma":0.0002719135,"threshold_uncertainty_score":0.9999647},"labels":[],"label_agreement":null},{"id":"W2403918565","doi":"","title":"Online Robot Task Switching Under Diminishing Returns.","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Foraging; Computer science; Task (project management); Robot; Variety (cybernetics); Work (physics); Artificial intelligence; Mathematical optimization; Mathematics; Ecology; Engineering","score_opus":0.01661103039644213,"score_gpt":0.260694048774749,"score_spread":0.24408301837830687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403918565","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":[0.024260165,0.0000060216007,0.96146554,0.0029532923,0.0012343585,0.00008488718,2.1412608e-7,0.00043523812,0.009560285],"genre_scores_gemma":[0.7314019,0.0000028633824,0.26503068,0.0013935659,0.00015059303,0.0000014535889,0.0000036201895,0.000012566214,0.0020027405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857634,0.000029058954,0.0002823404,0.00036001482,0.00038382108,0.00036841774],"domain_scores_gemma":[0.9987099,0.00015353978,0.00011286904,0.0008295062,0.000064339525,0.00012984769],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034120455,0.00015947255,0.00014357938,0.0000902324,0.0001753466,0.00047588337,0.0012658677,0.000102698694,0.00008831235],"category_scores_gemma":[0.00014434753,0.0001359331,0.00006289192,0.00025523314,0.000026440934,0.0008155249,0.00051205116,0.0007232276,0.00012005525],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031871937,0.00011710935,0.0022372375,0.000020405925,0.000045614135,0.000027007021,0.0014582998,0.60732853,0.077031314,0.29293758,0.0017954685,0.01699823],"study_design_scores_gemma":[0.00025290277,0.00005459409,0.0054307636,0.000015828466,0.0000062541353,0.000029971243,0.000089238325,0.9852576,0.0016014029,0.0018992056,0.005049257,0.00031294522],"about_ca_topic_score_codex":0.000042891712,"about_ca_topic_score_gemma":0.00007133682,"teacher_disagreement_score":0.70714176,"about_ca_system_score_codex":0.000022572178,"about_ca_system_score_gemma":0.00006226048,"threshold_uncertainty_score":0.55431914},"labels":[],"label_agreement":null},{"id":"W2406813038","doi":"","title":"Learning and planning with timing information in Markov decision processes","year":2015,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Computer science; Markov decision process; Representation (politics); Artificial intelligence; Machine learning; Markov chain; Markov process; Set (abstract data type); State (computer science); Robot; Duration (music); Algorithm; Mathematics","score_opus":0.05173460047726749,"score_gpt":0.3098116824769045,"score_spread":0.258077081999637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2406813038","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":[0.10940781,0.000050370443,0.8889863,0.00012520383,0.00012159586,0.00018277067,1.3539157e-7,0.00007260119,0.0010532015],"genre_scores_gemma":[0.9677154,0.000020715872,0.032123044,0.00007469608,0.0000216857,0.00001393381,0.000003606943,0.000005936438,0.000021007725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848247,0.000063480365,0.00048734288,0.00024973182,0.0003948413,0.00032213907],"domain_scores_gemma":[0.99897486,0.0003967999,0.00015302948,0.00016821835,0.0002135283,0.00009356726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008575333,0.00015042385,0.00016487144,0.00039162193,0.00007908745,0.0003292659,0.00036671959,0.000069037094,0.000004253252],"category_scores_gemma":[0.0018781758,0.0001337627,0.000010136366,0.0010183012,0.00006914234,0.0013847154,0.00017654337,0.0003398868,0.000030311314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000064154796,0.000010150669,0.0079688635,0.000020662595,0.0000015134314,0.000014319075,0.009325266,0.8806962,0.0000052000546,0.0015630256,0.0000069829675,0.100323655],"study_design_scores_gemma":[0.000084535335,0.0002094069,0.0002645901,0.0003148289,0.0000014145398,0.000010540587,0.0046955217,0.99036974,0.00036375716,0.0030242866,0.00046684375,0.00019456647],"about_ca_topic_score_codex":0.00016792207,"about_ca_topic_score_gemma":0.0001431985,"teacher_disagreement_score":0.85830754,"about_ca_system_score_codex":0.00013310387,"about_ca_system_score_gemma":0.0001864715,"threshold_uncertainty_score":0.54546845},"labels":[],"label_agreement":null},{"id":"W2407045295","doi":"10.13140/2.1.3356.8002","title":"Efficient Abstraction Selection in Reinforcement Learning --- Extended Abstract","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Abstraction; Reinforcement learning; Computer science; Markov decision process; Selection (genetic algorithm); Set (abstract data type); Artificial intelligence; State (computer science); Markov process; Machine learning; Theoretical computer science; Programming language; Mathematics","score_opus":0.012565001163403085,"score_gpt":0.24342780531320649,"score_spread":0.2308628041498034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407045295","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":[0.09150583,0.000005512936,0.87188673,0.00023323165,0.0002111275,0.000350722,8.16699e-9,0.00033468494,0.035472143],"genre_scores_gemma":[0.98523766,0.0000051955067,0.010388798,0.00009645941,0.00003390215,0.000040282986,0.0000018283249,0.000010090493,0.004185783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983565,0.00003524236,0.00043470028,0.00033763552,0.00042510577,0.00041078858],"domain_scores_gemma":[0.9993588,0.00007842756,0.00017107422,0.00020619028,0.00010051083,0.00008500492],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00036779695,0.0001585324,0.0001305419,0.00026323093,0.00012973782,0.00027400735,0.00034468688,0.00008250534,0.00069463684],"category_scores_gemma":[0.00007685857,0.00014943586,0.000040871004,0.00045881193,0.000017792438,0.00048328945,0.00010814485,0.00041412096,0.0012556413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018224569,0.000026655356,0.00062912266,0.000007695493,0.0000052224723,0.0000016608979,0.00019531511,0.9853791,0.003957551,0.0029278272,0.00014929258,0.0067187105],"study_design_scores_gemma":[0.0002506776,0.00010692929,0.09019968,0.000015769048,0.0000013580907,0.0000068111226,0.000059391434,0.90745836,0.0011723243,0.00007127957,0.0004931538,0.00016426547],"about_ca_topic_score_codex":0.00041209723,"about_ca_topic_score_gemma":0.0000087024055,"teacher_disagreement_score":0.89373183,"about_ca_system_score_codex":0.00022147562,"about_ca_system_score_gemma":0.00004566469,"threshold_uncertainty_score":0.999522},"labels":[],"label_agreement":null},{"id":"W2407441816","doi":"","title":"Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs.","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Planner; Markov decision process; Artificial intelligence; Automated planning and scheduling; Machine learning; Bayesian probability; Domain (mathematical analysis); Markov process; Markov chain; Markov model; Mathematics","score_opus":0.029598965353824374,"score_gpt":0.2529070386760443,"score_spread":0.22330807332221994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2407441816","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":[0.043512724,0.000022908867,0.9464915,0.00008232318,0.00012682732,0.00090001425,2.4617097e-7,0.0006372234,0.008226237],"genre_scores_gemma":[0.8723774,0.0001411458,0.122464314,0.00015653153,0.00006323873,0.00006779461,0.00002092824,0.00005091591,0.0046577486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965789,0.00017765396,0.0007383585,0.000744827,0.0007660514,0.0009942356],"domain_scores_gemma":[0.9978518,0.0004609108,0.0006431661,0.00058626954,0.0002762021,0.00018165141],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006468582,0.00045046725,0.00046151903,0.0005681796,0.00092680426,0.00018578989,0.00081433414,0.00015401744,0.000056375135],"category_scores_gemma":[0.0003922782,0.00040104205,0.00013430987,0.0010301332,0.0000984135,0.0013860821,0.00039455944,0.0008761111,0.00003255242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010773336,0.000025632191,0.011892276,0.000028964392,0.00008849469,0.000023320792,0.0033390564,0.97990716,0.00014950368,0.002922009,0.000036853067,0.0014789854],"study_design_scores_gemma":[0.0023732642,0.0012028407,0.0016653055,0.00010065944,0.000029260076,0.000043327356,0.0004051139,0.9875909,0.0017809565,0.000028700104,0.0042074816,0.0005721557],"about_ca_topic_score_codex":0.00028640454,"about_ca_topic_score_gemma":0.000014594164,"teacher_disagreement_score":0.82886463,"about_ca_system_score_codex":0.0004244475,"about_ca_system_score_gemma":0.00028943285,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W2424764846","doi":"10.1109/syscon.2016.7490540","title":"A learning invader for the guarding a territory game","year":2016,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada; Carleton University","funders":"","keywords":"Guard (computer science); Nash equilibrium; Computer science; Robot; Game theory; Artificial intelligence; Mathematical economics; Mathematics","score_opus":0.021743686676913006,"score_gpt":0.24524124685625984,"score_spread":0.22349756017934683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2424764846","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":[0.0003226057,0.000022637507,0.9899185,0.004355107,0.00035711282,0.00018300589,7.355738e-8,0.00021599639,0.0046249623],"genre_scores_gemma":[0.9316471,0.000014185941,0.03027639,0.00078337494,0.0002022735,0.00005170374,2.042056e-7,0.000013552937,0.037011217],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916416,0.00003679892,0.0001446727,0.00020095511,0.00018828124,0.00026511398],"domain_scores_gemma":[0.99865025,0.0008343208,0.000064973625,0.000368137,0.000044354434,0.000037961185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003943981,0.00008613862,0.00007797247,0.000043038763,0.00017080273,0.00014960884,0.00075629057,0.00003409569,0.000041367653],"category_scores_gemma":[0.0002516718,0.000040892068,0.00006972056,0.00008275813,0.00004151141,0.00034365902,0.00022967492,0.00008849361,0.000101947306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019972273,0.000024270927,0.007165086,0.000041298015,0.00017753518,0.0000064652313,0.0037411698,0.35058618,0.012049421,0.25614172,0.027068272,0.34297863],"study_design_scores_gemma":[0.0005512509,0.00016171086,0.0008555336,0.000043552034,0.000008100075,0.000008009034,0.000114028866,0.68603,0.0013796878,0.0006435658,0.31001028,0.0001942735],"about_ca_topic_score_codex":0.000006758232,"about_ca_topic_score_gemma":0.0000011040047,"teacher_disagreement_score":0.9596421,"about_ca_system_score_codex":0.000037837686,"about_ca_system_score_gemma":0.00003410254,"threshold_uncertainty_score":0.16675302},"labels":[],"label_agreement":null},{"id":"W2431563754","doi":"","title":"On the influence of learning time on evolutionary online learning of cooperative behavior","year":2001,"lang":"en","type":"article","venue":"Genetic and Evolutionary Computation Conference","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Offline learning; Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Key (lock); Online learning; Action (physics); Evolutionary computation; Duration (music); Evolutionary algorithm","score_opus":0.020548650184544874,"score_gpt":0.2539995995415321,"score_spread":0.23345094935698724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2431563754","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":[0.5940582,0.000051225008,0.40511656,0.00019079172,0.000030811167,0.00016303116,0.0000020212738,0.000038325983,0.00034904407],"genre_scores_gemma":[0.99060357,0.000091224916,0.008551517,0.00007912101,0.000018558418,0.0000124615835,0.000023035755,0.000007847469,0.0006126564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983632,0.00027802208,0.0004023429,0.0003113288,0.00045125786,0.00019382543],"domain_scores_gemma":[0.998276,0.00066048827,0.0003092314,0.00020317691,0.00049373164,0.000057392495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001723874,0.00016814414,0.00019770139,0.00013972801,0.00028895456,0.000031804022,0.00035844048,0.00006443514,0.000053247328],"category_scores_gemma":[0.00024856004,0.00014028033,0.00004172813,0.0003737552,0.00024606485,0.00015991539,0.00016165907,0.00031508232,0.000038012782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022720506,0.000069968366,0.00855659,0.000008253858,0.000013633993,0.0000031519467,0.00037109831,0.9708221,0.0007287526,0.016248686,0.00007161963,0.003083411],"study_design_scores_gemma":[0.00019911569,0.00069411064,0.29412577,0.0000837631,0.000009194023,0.000018228657,0.00008347644,0.703836,0.000032809738,0.0007100456,0.00009512332,0.000112336966],"about_ca_topic_score_codex":0.000016259055,"about_ca_topic_score_gemma":3.593837e-7,"teacher_disagreement_score":0.39656505,"about_ca_system_score_codex":0.00004119434,"about_ca_system_score_gemma":0.00014518453,"threshold_uncertainty_score":0.5720466},"labels":[],"label_agreement":null},{"id":"W246639213","doi":"","title":"Prediction Driven Behavior: Learning Predictions that Drive Fixed Responses","year":2014,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Robot; Computer science; Artificial intelligence; Adaptive behavior; Behavior-based robotics; Adaptive control; Reinforcement learning; Latency (audio); Control (management); Control theory (sociology); Simulation; Mobile robot; Psychology","score_opus":0.15524353064616092,"score_gpt":0.3359340618331985,"score_spread":0.1806905311870376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W246639213","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":[0.004874456,0.000003220761,0.97738403,0.0010175953,0.0007589433,0.00028027038,0.000009327013,0.00045422337,0.015217922],"genre_scores_gemma":[0.9906122,0.000019572626,0.007575217,0.00021319737,0.00019723109,0.000088813395,0.00003544388,0.000015069789,0.0012432277],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696255,0.0003362664,0.00047969248,0.00058610627,0.0012819023,0.00035346148],"domain_scores_gemma":[0.9978317,0.0006422936,0.00025719526,0.00037325334,0.0007520555,0.00014347918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079309475,0.00023046538,0.00018658821,0.00036775434,0.0005716047,0.00042746938,0.00086143706,0.00015398276,0.00019879063],"category_scores_gemma":[0.0014155513,0.0002399035,0.00009180193,0.00045906403,0.0001664909,0.00062856165,0.0001673078,0.0005936932,0.0006388389],"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":[0.000023853489,0.00006603239,0.0015450156,0.0000031351046,0.000011553758,0.0000017693677,0.00037270575,0.427545,0.0009932461,0.55210364,0.00012642464,0.017207598],"study_design_scores_gemma":[0.00004252137,0.00041675367,0.0068238927,0.00004645137,0.000010769591,0.0000072035064,0.0001221755,0.97272104,0.0056296093,0.012157806,0.00179672,0.00022504167],"about_ca_topic_score_codex":0.000013492072,"about_ca_topic_score_gemma":0.000011673275,"teacher_disagreement_score":0.98573774,"about_ca_system_score_codex":0.00018350613,"about_ca_system_score_gemma":0.00024746603,"threshold_uncertainty_score":0.97829807},"labels":[],"label_agreement":null},{"id":"W2485417938","doi":"10.4018/978-1-59904-552-8.ch009","title":"Monocular Vision System that Learns with Approximation Spaces","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Reinforcement Learning in Robotics","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 Manitoba","funders":"","keywords":"Artificial intelligence; Reinforcement learning; Computer science; Computer vision; Machine vision; Robot; Crawling","score_opus":0.023229796509762136,"score_gpt":0.22607563529727262,"score_spread":0.20284583878751047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485417938","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008426857,0.00006852335,0.46629837,0.000015040617,0.00023408908,0.00031615133,0.0000022584475,0.0003382997,0.53271884],"genre_scores_gemma":[0.43882856,0.000014691458,0.10127133,0.00026587266,0.0003761231,0.000058087004,0.00001871744,0.00019294923,0.45897365],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763006,0.000037801863,0.000347241,0.0007121378,0.0008796837,0.00039308172],"domain_scores_gemma":[0.997878,0.000023375562,0.00057243253,0.0012171889,0.00014889208,0.00016009754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020464398,0.00051975786,0.00046501507,0.00011164484,0.00016573521,0.0004713935,0.001146686,0.0003884471,0.000009395088],"category_scores_gemma":[0.0000054817824,0.00043316386,0.00015240283,0.000032008167,0.00009722712,0.00027306945,0.00043015278,0.00036029215,0.0004257262],"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":[0.00001445519,0.0000032355322,0.000019994384,0.00012463778,0.000085523476,0.00006412195,0.00019189538,0.005158454,0.0000023186406,0.9892718,0.00022440041,0.0048391414],"study_design_scores_gemma":[0.0039007482,0.0046583987,0.00024011324,0.011267282,0.0009230324,0.0013333258,0.00033030394,0.50539505,0.00089851505,0.17926389,0.2841432,0.0076461104],"about_ca_topic_score_codex":0.000070961025,"about_ca_topic_score_gemma":0.000008434534,"teacher_disagreement_score":0.8100079,"about_ca_system_score_codex":0.00034247118,"about_ca_system_score_gemma":0.00014195371,"threshold_uncertainty_score":0.999812},"labels":[],"label_agreement":null},{"id":"W2490120274","doi":"10.4018/978-1-60960-165-2.ch003","title":"An Introduction to Fully and Partially Observable Markov Decision Processes","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Reinforcement Learning in Robotics","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":"Computer science; Management science; Partially observable Markov decision process; Markov decision process; Focus (optics); Markov process; Software deployment; Markov chain; Observable; Markov model; Risk analysis (engineering); Machine learning; Mathematics; Software engineering; Engineering; Business","score_opus":0.02260650668927809,"score_gpt":0.24811897239786734,"score_spread":0.22551246570858924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490120274","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":[0.00010439965,0.00008392948,0.5950894,0.00018541409,0.0008055984,0.0003934179,0.000005180416,0.00025819996,0.4030745],"genre_scores_gemma":[0.14538051,0.000086778775,0.52291465,0.003480846,0.0047657616,0.00010735488,0.000027817061,0.000256191,0.3229801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99770087,0.000021081229,0.0004295816,0.00092048437,0.00054156233,0.00038641776],"domain_scores_gemma":[0.99795806,0.000035642322,0.00023750983,0.0011150887,0.00035107142,0.00030264354],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002501401,0.00040254352,0.00035606054,0.00009658736,0.00015646432,0.00045270412,0.0010617247,0.00028314884,0.000031448402],"category_scores_gemma":[0.00010192987,0.00039534934,0.000054874683,0.00005439779,0.00006318021,0.0003573531,0.0005095677,0.00023183433,0.00015413169],"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":[0.000063505664,0.0000085097045,0.0000433179,0.000067598936,0.000032824057,0.000023962695,0.00016961915,0.00531804,0.000024343442,0.94713825,0.00413347,0.042976532],"study_design_scores_gemma":[0.0006935771,0.0024715343,0.0004298045,0.0005502161,0.00013368121,0.00020104907,0.00001194383,0.007619786,0.00040673203,0.44849864,0.53696436,0.002018681],"about_ca_topic_score_codex":0.000029374893,"about_ca_topic_score_gemma":0.00007411018,"teacher_disagreement_score":0.5328309,"about_ca_system_score_codex":0.00013398204,"about_ca_system_score_gemma":0.00029939684,"threshold_uncertainty_score":0.99984986},"labels":[],"label_agreement":null},{"id":"W2496219042","doi":"10.4018/978-1-60960-171-3.ch007","title":"Reward Shaping and Mixed Resolution Function Approximation","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Reinforcement Learning in Robotics","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":"Representation (politics); Function approximation; Function (biology); Reinforcement learning; Computer science; Space (punctuation); Core (optical fiber); Resolution (logic); Function space; Artificial intelligence; Quality (philosophy); Process (computing); Algorithm; Mathematics; Artificial neural network; Discrete mathematics","score_opus":0.043424739399203244,"score_gpt":0.23376106207356487,"score_spread":0.19033632267436162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496219042","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000008886765,0.00011092293,0.48795593,0.00001916221,0.0004972426,0.00018216565,0.000001663224,0.0001960267,0.511028],"genre_scores_gemma":[0.4574714,0.00009511531,0.12535301,0.0018069592,0.0014849494,0.00008730422,0.000061993385,0.00023013799,0.41340914],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983207,0.00002951831,0.0003874103,0.00055718474,0.00042150143,0.0002836947],"domain_scores_gemma":[0.99875855,0.000022362496,0.0003772655,0.0006082354,0.00012543437,0.00010812166],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024558726,0.00032100684,0.0002696944,0.00010418701,0.0001672713,0.00020455263,0.00042578197,0.00037665135,0.000009475409],"category_scores_gemma":[0.0000256717,0.0003416543,0.00009224607,0.000025018628,0.0000779241,0.00022998423,0.00037934812,0.0002869537,0.00014555467],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015015944,0.000001698323,0.000007076037,0.00004183278,0.000037130096,0.0000050562007,0.00008276875,0.0008771785,0.000009423378,0.98193437,0.00067071326,0.016317766],"study_design_scores_gemma":[0.00062347756,0.00047779205,0.000384695,0.00057213014,0.00013875136,0.00008237946,0.000007847912,0.067263775,0.000053733304,0.88021153,0.049153406,0.0010304643],"about_ca_topic_score_codex":0.000026587963,"about_ca_topic_score_gemma":0.0000072531093,"teacher_disagreement_score":0.45746252,"about_ca_system_score_codex":0.00022308687,"about_ca_system_score_gemma":0.00008362503,"threshold_uncertainty_score":0.99990356},"labels":[],"label_agreement":null},{"id":"W2510392992","doi":"10.1007/978-3-319-46073-4_6","title":"A Neural Field Approach to Obstacle Avoidance","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Artificial intelligence; Computer science; Robotics; Flexibility (engineering); Obstacle avoidance; Obstacle; Field (mathematics); Task (project management); Focus (optics); Cognitive robotics; Human–computer interaction; Robot; Mobile robot; Engineering; Systems engineering","score_opus":0.01967386230579018,"score_gpt":0.24170938995895433,"score_spread":0.22203552765316414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510392992","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":[0.000016515747,0.000111571266,0.9641494,0.0018043839,0.0019056835,0.0004743305,0.0000015394817,0.0002321147,0.031304438],"genre_scores_gemma":[0.14248346,0.000015846535,0.84094155,0.008966805,0.0008246832,0.00002451274,0.0000021241071,0.00006522509,0.0066758157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99555624,0.000035398956,0.0005370166,0.00172128,0.0012240104,0.00092608447],"domain_scores_gemma":[0.9965563,0.0006584288,0.00025458477,0.0020305703,0.00020926785,0.00029088033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063678325,0.00056197174,0.00050447136,0.0007055333,0.0002554678,0.00065342634,0.0053266184,0.0003012094,0.000018964527],"category_scores_gemma":[0.0002520038,0.0004588383,0.00013804056,0.0006126844,0.0003130552,0.0006648066,0.0022717987,0.0008567329,0.00018465988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005437265,0.000013283285,0.000038944312,0.000029923287,0.000007541171,0.000030199168,0.0006146444,0.5822251,0.00010617662,0.038576346,0.00010152939,0.3782509],"study_design_scores_gemma":[0.00025093587,0.0003373595,0.00007553123,0.00034324842,0.000004783081,0.000070412025,1.1056285e-7,0.9719393,0.0007409066,0.020411154,0.0049265446,0.000899677],"about_ca_topic_score_codex":0.0000073924657,"about_ca_topic_score_gemma":0.000004874717,"teacher_disagreement_score":0.38971427,"about_ca_system_score_codex":0.0002992532,"about_ca_system_score_gemma":0.00031697497,"threshold_uncertainty_score":0.9997863},"labels":[],"label_agreement":null},{"id":"W2519270595","doi":"","title":"Multi-step linear Dyna-style planning","year":2009,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Computer science; Iterated function; Projection (relational algebra); Linear model; Feature (linguistics); Algorithm; Mathematics; Machine learning","score_opus":0.035637737076629206,"score_gpt":0.3005928994693765,"score_spread":0.2649551623927473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2519270595","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":[0.0005421899,0.0000227357,0.9753914,0.00056125695,0.00018452984,0.000078704514,8.004178e-8,0.0004334099,0.02278569],"genre_scores_gemma":[0.27118436,0.0000020946293,0.7177078,0.0013656245,0.000067115005,0.0000011974394,0.0000017958929,0.0000054588368,0.00966452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901646,0.000022771892,0.00018851875,0.00024744225,0.00023833552,0.00028646408],"domain_scores_gemma":[0.9992909,0.000043705448,0.00006131876,0.0004757199,0.0000425862,0.00008580903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016054316,0.00011330419,0.000108247914,0.000076221775,0.00010347637,0.0001252934,0.00071695,0.00005265566,0.000039039936],"category_scores_gemma":[0.000054628792,0.000099642,0.000044176446,0.00022056873,0.000014433152,0.00035294937,0.00012047252,0.00015577795,0.000348473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020989992,0.000032597476,0.0007855841,0.0000037111631,0.000008183252,0.00002808617,0.0005818968,0.9733388,0.00062751776,0.008930794,0.0017271101,0.013933621],"study_design_scores_gemma":[0.00025991208,0.000107439766,0.0028274416,0.000012020002,0.0000016423305,0.0000067069855,0.000020880521,0.9872354,0.00039641216,0.000017926299,0.008973896,0.00014030052],"about_ca_topic_score_codex":0.000008529351,"about_ca_topic_score_gemma":5.007544e-7,"teacher_disagreement_score":0.27064216,"about_ca_system_score_codex":0.000026788606,"about_ca_system_score_gemma":0.000023761126,"threshold_uncertainty_score":0.44790316},"labels":[],"label_agreement":null},{"id":"W2520501711","doi":"","title":"Regularized policy iteration with nonparametric function spaces","year":2016,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Markov decision process; Mathematical optimization; Reproducing kernel Hilbert space; Reinforcement learning; Mathematics; Regularization (linguistics); Function space; Nonparametric statistics; Bellman equation; Minimax; Function (biology); Computer science; Applied mathematics; Hilbert space; Markov process; Artificial intelligence; Discrete mathematics","score_opus":0.008502984474690533,"score_gpt":0.21923521494304662,"score_spread":0.2107322304683561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520501711","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":[0.012168525,0.00009289952,0.9746076,0.0103728715,0.0001345012,0.0005308257,0.000002433996,0.0011627183,0.00092765637],"genre_scores_gemma":[0.73326725,0.000059855418,0.26062372,0.0013457729,0.00016534678,0.00016803059,0.0000056755584,0.00004001693,0.00432435],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752986,0.0001552216,0.00040243173,0.00057063333,0.0006350826,0.00070675573],"domain_scores_gemma":[0.99770063,0.00020369096,0.000337238,0.0013018886,0.00020555995,0.00025098512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005754485,0.00032821807,0.00028496908,0.0011210016,0.00026830914,0.0006264055,0.00087858416,0.00020922381,0.000020722913],"category_scores_gemma":[0.00037624245,0.00022744905,0.000100932506,0.0019811313,0.00009185708,0.0014822169,0.00026059538,0.00023377972,0.00007078295],"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":[0.00031232176,0.00018471779,0.034916785,0.000044691198,0.00015776644,0.000059996273,0.00039711836,0.10990318,0.04883586,0.6737007,0.0025195463,0.12896733],"study_design_scores_gemma":[0.0028540944,0.0016880202,0.059955962,0.0002347037,0.00005827831,0.00023329776,0.000031776766,0.8899009,0.024148406,0.0072769667,0.012405748,0.0012118239],"about_ca_topic_score_codex":0.0010995064,"about_ca_topic_score_gemma":0.00014781146,"teacher_disagreement_score":0.77999777,"about_ca_system_score_codex":0.0005845184,"about_ca_system_score_gemma":0.0003539122,"threshold_uncertainty_score":0.9275103},"labels":[],"label_agreement":null},{"id":"W2523728418","doi":"10.1609/aaai.v31i1.10916","title":"The Option-Critic Architecture","year":2017,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":209,"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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Flexibility (engineering); Computer science; Architecture; Abstraction; Key (lock); Artificial intelligence; Economics; Computer security; Management; Epistemology","score_opus":0.08507794004948784,"score_gpt":0.3192055271439572,"score_spread":0.2341275870944694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523728418","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":[0.0073035033,0.00017258969,0.9086833,0.033075627,0.005435375,0.0016989451,0.000009606189,0.0003039365,0.04331713],"genre_scores_gemma":[0.99204695,0.00024813705,0.005288757,0.00016774499,0.00023107816,0.00007133481,0.0000010539674,0.000025646283,0.0019193174],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9967235,0.000039706545,0.00080997933,0.0007982968,0.0010542844,0.00057425426],"domain_scores_gemma":[0.9955984,0.00029004214,0.0013161151,0.001578888,0.001104034,0.000112518304],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010185513,0.00045527614,0.00041405484,0.00012523892,0.0011558637,0.002453403,0.011235673,0.00028001046,0.000017859074],"category_scores_gemma":[0.0018895321,0.00028414765,0.00030858774,0.00021315833,0.000880312,0.00025833846,0.004104813,0.0017720071,0.00012406838],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022882536,0.00003127514,0.00002810786,0.00010487055,0.000037917154,6.2559826e-7,0.0009051112,0.030802201,0.0009967545,0.91139054,0.00023199664,0.055447694],"study_design_scores_gemma":[0.000017589595,0.000118296186,0.00009237354,0.0008913585,0.000028917695,0.0000058086157,0.0001584817,0.3900288,0.040965777,0.56627595,0.0010250609,0.0003915443],"about_ca_topic_score_codex":0.000046281297,"about_ca_topic_score_gemma":0.00000970352,"teacher_disagreement_score":0.9847434,"about_ca_system_score_codex":0.00008922501,"about_ca_system_score_gemma":0.00034294865,"threshold_uncertainty_score":0.9999611},"labels":[],"label_agreement":null},{"id":"W2538613533","doi":"10.1109/gem.2014.7048106","title":"Enabling motivated believable agents with reinforcement learning","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Action (physics); Narrative; Reinforcement; Human–computer interaction; Video game; Variety (cybernetics); Artificial intelligence; Multimedia; Psychology; Social psychology","score_opus":0.014877786932652947,"score_gpt":0.22514617005840445,"score_spread":0.2102683831257515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2538613533","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":[0.002271602,0.000004257466,0.905367,0.0002243653,0.000111003625,0.00014458851,1.0751376e-8,0.0004935811,0.091383584],"genre_scores_gemma":[0.93176925,0.000007642492,0.044938993,0.0006609105,0.00004340033,0.00000869375,0.000005429831,0.000019052255,0.02254663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821043,0.000077370925,0.0002790474,0.000380097,0.00056177774,0.00049127545],"domain_scores_gemma":[0.9989152,0.00010174469,0.00015457811,0.00057676324,0.00012143303,0.00013027595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048681564,0.00019265077,0.00017460021,0.00013670279,0.00028476852,0.0002946347,0.0007414029,0.000053771837,0.00020200411],"category_scores_gemma":[0.00013549114,0.0001501196,0.000037660204,0.00046809082,0.00003185816,0.00057995727,0.0003183171,0.00026256414,0.00030156886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004193102,0.0000075820617,0.0016172162,0.000011022665,0.000021703449,0.0000027360868,0.00022089985,0.97956955,0.00022894995,0.016182337,0.00045903347,0.0016747436],"study_design_scores_gemma":[0.0005224419,0.0003745893,0.00038214723,0.00003877815,0.0000056730996,0.0000055132114,0.00003339354,0.96008945,0.00253852,0.000049159113,0.03573068,0.00022968666],"about_ca_topic_score_codex":0.000039053488,"about_ca_topic_score_gemma":0.000001168898,"teacher_disagreement_score":0.92949766,"about_ca_system_score_codex":0.00006147869,"about_ca_system_score_gemma":0.000038940485,"threshold_uncertainty_score":0.6121699},"labels":[],"label_agreement":null},{"id":"W2545079506","doi":"10.1109/iat.2007.74","title":"Reinforcement Learning with Inertial Exploration","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Reinforcement learning; Abstraction; Computer science; Context (archaeology); Action selection; Inertial frame of reference; Set (abstract data type); Artificial intelligence; Selection (genetic algorithm); Scale (ratio); Control (management); Machine learning; Action (physics)","score_opus":0.018947262859378568,"score_gpt":0.24544685046786655,"score_spread":0.22649958760848798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2545079506","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":[0.0015541823,0.0000029254354,0.9427965,0.00026012555,0.00011762832,0.00010860135,3.2012641e-9,0.00032100786,0.054838996],"genre_scores_gemma":[0.9222404,0.0000031688207,0.06929609,0.00025968702,0.00006235098,0.0000038182275,0.000003260518,0.000007826901,0.00812344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99886876,0.0000176459,0.00022068006,0.00019820417,0.00040639,0.00028834186],"domain_scores_gemma":[0.99941415,0.0000505285,0.00009409093,0.00028119652,0.000083613595,0.000076397264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004518567,0.00010462243,0.00007918978,0.00010892946,0.00013303418,0.00013861925,0.0003336558,0.000034756787,0.000043989086],"category_scores_gemma":[0.000036315403,0.000080235484,0.000020515412,0.00032037063,0.000022290007,0.0009489374,0.00012110522,0.00015910648,0.00012956261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010967062,0.0000045306097,0.0006785109,0.000002872277,0.0000072741327,0.000008224132,0.0004794896,0.95033926,0.000409855,0.042936437,0.00011082164,0.005011771],"study_design_scores_gemma":[0.0005012949,0.0005689537,0.00065143657,0.000015281088,0.0000040341797,0.000010022224,0.00016990158,0.9730059,0.009069135,0.000053699347,0.01571429,0.0002360524],"about_ca_topic_score_codex":0.000017912305,"about_ca_topic_score_gemma":0.0000079456,"teacher_disagreement_score":0.9206862,"about_ca_system_score_codex":0.000049795588,"about_ca_system_score_gemma":0.0000325488,"threshold_uncertainty_score":0.32719082},"labels":[],"label_agreement":null},{"id":"W2546975091","doi":"","title":"Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?","year":2016,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Robustness (evolution); Reinforcement learning; Computer science; Artificial intelligence; Torque; Machine learning; Physics","score_opus":0.0546902574138028,"score_gpt":0.20722812833932142,"score_spread":0.15253787092551863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546975091","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":[0.39044908,0.0000014953315,0.6087761,0.00015064204,0.00014705487,0.000063553394,1.2742807e-7,0.000051373234,0.00036060647],"genre_scores_gemma":[0.99564815,0.000021574748,0.0013072544,0.000031936033,0.00003658871,1.1399254e-7,2.4787494e-7,0.00000859726,0.002945553],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990956,0.00015818838,0.00012638964,0.0003054352,0.00009632999,0.00021803901],"domain_scores_gemma":[0.9988663,0.00026414357,0.00025154895,0.0004738814,0.00009579642,0.0000482896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020588045,0.00011386474,0.00010981893,0.00011034931,0.00019942211,0.000043106982,0.00063339225,0.000058200745,0.000048047423],"category_scores_gemma":[0.00006886493,0.000071471244,0.00007039392,0.00044882335,0.000081752834,0.0007657071,0.0002513836,0.00013586356,0.00009794847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047396757,0.000017200415,0.07973522,0.000011534937,0.000021477896,0.000004917559,0.00016275773,0.90070283,0.005967107,0.012454545,0.00002312648,0.0008945575],"study_design_scores_gemma":[0.0005974778,0.00010032086,0.028659716,0.00011993586,0.000040646275,0.0000063046855,0.00016800537,0.9583537,0.009538287,0.0011655294,0.0009965253,0.0002535307],"about_ca_topic_score_codex":0.00007299505,"about_ca_topic_score_gemma":0.000008932317,"teacher_disagreement_score":0.60746884,"about_ca_system_score_codex":0.00012283087,"about_ca_system_score_gemma":0.000028839322,"threshold_uncertainty_score":0.29145128},"labels":[],"label_agreement":null},{"id":"W2552186722","doi":"10.1109/fuzz-ieee.2016.7737798","title":"Reinforcement learning in the guarding a territory game","year":2016,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Guard (computer science); Reinforcement learning; Computer science; Game theory; A priori and a posteriori; Set (abstract data type); Artificial intelligence; Repeated game; Non-cooperative game; Mathematical economics; Mathematics","score_opus":0.016922623687089227,"score_gpt":0.24108977273666846,"score_spread":0.22416714904957924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552186722","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":[0.0017192989,0.000010709213,0.9497309,0.0029059625,0.0001856028,0.00013141557,1.303019e-8,0.00015858456,0.045157537],"genre_scores_gemma":[0.98549616,0.000014240031,0.0034615528,0.0007330331,0.00006393428,0.000016976763,2.7381517e-7,0.0000061202263,0.0102077015],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986558,0.00012163883,0.0002549155,0.00022510151,0.00040692,0.00033564738],"domain_scores_gemma":[0.9990998,0.00027075654,0.00007810308,0.00049392437,0.00002271191,0.00003469555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007806756,0.00011016664,0.000097640026,0.00011196398,0.00008094787,0.0001447377,0.0010776259,0.00003788209,0.000064629836],"category_scores_gemma":[0.00012673961,0.00005543324,0.000049424412,0.00020556837,0.000035406043,0.00048624084,0.00025129315,0.00016879069,0.00021653833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005293087,0.000016574955,0.0099857,0.000011563584,0.000017123255,0.000035742345,0.0036694861,0.80512196,0.0019005681,0.13900277,0.0026742136,0.037558977],"study_design_scores_gemma":[0.0013898108,0.0003818735,0.009376571,0.0001912872,0.0000059993,0.00003708391,0.0004754155,0.78940606,0.0012179156,0.0008289701,0.1961614,0.00052761025],"about_ca_topic_score_codex":0.00002494303,"about_ca_topic_score_gemma":0.0000032759224,"teacher_disagreement_score":0.98377687,"about_ca_system_score_codex":0.000084173356,"about_ca_system_score_gemma":0.00003788032,"threshold_uncertainty_score":0.27832344},"labels":[],"label_agreement":null},{"id":"W2554885577","doi":"10.1109/ijcnn.2016.7727651","title":"Context-switching and adaptation: Brain-inspired mechanisms for handling environmental changes","year":2016,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Lethbridge","funders":"","keywords":"Reinforcement learning; Computer science; Abstraction; Adaptation (eye); Context (archaeology); Task (project management); Artificial intelligence; Process (computing); Transfer of learning; Grid; State (computer science); Machine learning; Neuroscience; Engineering; Algorithm","score_opus":0.02596948343333376,"score_gpt":0.22451772963762429,"score_spread":0.1985482462042905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554885577","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":[0.002055467,0.000038670783,0.99135524,0.0058187614,0.00018429977,0.00023852474,0.0000011223652,0.000121808866,0.00018608547],"genre_scores_gemma":[0.8330204,0.000016383578,0.16397719,0.001094946,0.00004071461,0.000021634009,0.0000011201306,0.000009374232,0.0018182542],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991789,0.000020267365,0.00014867092,0.0002715748,0.00016605644,0.00021454423],"domain_scores_gemma":[0.999308,0.00032370276,0.00008618862,0.00020406875,0.000011358724,0.00006667508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025168946,0.00010942433,0.00010677605,0.00005299519,0.00016777821,0.000108667424,0.0002461072,0.00004134105,0.000021459793],"category_scores_gemma":[0.00006348763,0.000076619115,0.000026599668,0.000034377153,0.000022217659,0.00034047075,0.00014532203,0.00003283745,0.000016188847],"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":[0.000015258759,0.000014900454,0.00019246538,0.00001881172,0.00003936272,0.0000029828043,0.00202479,0.002323095,0.10081281,0.31287223,0.00023036225,0.5814529],"study_design_scores_gemma":[0.0015697713,0.0004172414,0.00024512282,0.000060639646,0.000008477519,0.000012316005,0.00037665732,0.96556157,0.019097691,0.0054846345,0.0068572056,0.00030867194],"about_ca_topic_score_codex":0.000005671394,"about_ca_topic_score_gemma":0.000015353746,"teacher_disagreement_score":0.9632385,"about_ca_system_score_codex":0.00003497517,"about_ca_system_score_gemma":0.000012494433,"threshold_uncertainty_score":0.31244367},"labels":[],"label_agreement":null},{"id":"W2559277598","doi":"10.1523/jneurosci.0763-16.2016","title":"Memory Transformation Enhances Reinforcement Learning in Dynamic Environments","year":2016,"lang":"en","type":"article","venue":"Journal of Neuroscience","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; Hospital for Sick Children; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Schematic; Computer science; Episodic memory; Memory consolidation; Salience (neuroscience); Adaptive memory; Transformation (genetics); Artificial intelligence; Cognition; Psychology; Neuroscience","score_opus":0.014104161412884272,"score_gpt":0.2480868169701692,"score_spread":0.23398265555728492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559277598","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":[0.05804482,0.000015715266,0.93955666,0.0011337644,0.0005432853,0.000070009555,4.044338e-8,0.000013703536,0.00062198355],"genre_scores_gemma":[0.996963,0.00028327745,0.0013978073,0.0001943056,0.000014131212,0.0000012582941,4.3433563e-8,0.000004229831,0.0011419157],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821997,0.0000860129,0.00055398163,0.00016232273,0.000713636,0.000264082],"domain_scores_gemma":[0.99916023,0.000088490866,0.0004662255,0.00017880092,0.000025535697,0.00008068844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007215245,0.000101447804,0.00013921747,0.0002612181,0.000084549625,0.00008116562,0.00092130725,0.000028458691,0.000006754159],"category_scores_gemma":[0.00020204602,0.00006802877,0.000055835,0.00031131972,0.00008486355,0.0021834506,0.00008625115,0.00020436643,0.000016171442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008085848,0.000016665477,0.00027184183,0.0000051490765,0.0000011599403,0.000024001936,0.0005633649,0.64046454,0.3377278,0.00030589782,0.00000884497,0.020602684],"study_design_scores_gemma":[0.0019582927,0.0017315764,0.04150877,0.00034606966,0.00000782449,0.00025456015,0.000110711764,0.88199484,0.05971962,0.00032365465,0.011636653,0.00040739373],"about_ca_topic_score_codex":7.927661e-7,"about_ca_topic_score_gemma":4.493355e-7,"teacher_disagreement_score":0.93891823,"about_ca_system_score_codex":0.00013560653,"about_ca_system_score_gemma":0.00007027441,"threshold_uncertainty_score":0.27741328},"labels":[],"label_agreement":null},{"id":"W2561828331","doi":"10.1609/aaai.v30i1.10304","title":"Compressed Conditional Mean Embeddings for Model-Based Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Markov decision process; Class (philosophy); Context (archaeology); Kernel (algebra); Bottleneck; Mathematical optimization; Artificial intelligence; Machine learning; Markov process; Mathematics","score_opus":0.07598492911930667,"score_gpt":0.3017610321490101,"score_spread":0.22577610302970347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2561828331","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":[0.003757413,0.0000026726243,0.9878541,0.0032237184,0.00021403855,0.00058865704,0.0000037683974,0.00014534633,0.0042102556],"genre_scores_gemma":[0.98266035,0.000006642977,0.015428684,0.0003287807,0.000050821145,0.000085713305,0.0000022042395,0.000019692805,0.0014171265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755865,0.000016650014,0.0006833859,0.000527366,0.00073768693,0.00047626309],"domain_scores_gemma":[0.99753714,0.00032600955,0.00064633467,0.0003198538,0.0010589344,0.000111754685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006103294,0.00027617297,0.00029313882,0.00015950903,0.0003531101,0.00023034927,0.0020653019,0.00010074925,0.000072016504],"category_scores_gemma":[0.00065304874,0.00018234573,0.00019025887,0.0003160739,0.00031564396,0.000517995,0.0003098639,0.00023300864,0.00005734609],"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":[0.000054356664,0.000027682021,0.00004065334,0.000030355064,0.00001245331,6.996357e-8,0.0002689673,0.3903491,0.032653775,0.5725426,0.00015392138,0.003866043],"study_design_scores_gemma":[0.00008381339,0.0002312618,0.000008996112,0.00020236692,0.000009429312,5.947544e-7,0.000051376293,0.6683707,0.28102285,0.049671315,0.00016787573,0.00017942287],"about_ca_topic_score_codex":0.0000045705474,"about_ca_topic_score_gemma":8.138613e-7,"teacher_disagreement_score":0.97890294,"about_ca_system_score_codex":0.00010407024,"about_ca_system_score_gemma":0.00017329371,"threshold_uncertainty_score":0.7435843},"labels":[],"label_agreement":null},{"id":"W2567143531","doi":"10.6084/m9.figshare.3085861.v1","title":"Reinforcement Learning in a Nutshell","year":2016,"lang":"en","type":"article","venue":"Figshare","topic":"Reinforcement Learning in Robotics","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":"Reinforcement; Artificial intelligence; Reinforcement learning; Computer science; Psychology; Social psychology","score_opus":0.029458926697487377,"score_gpt":0.24673300033253034,"score_spread":0.21727407363504297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2567143531","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":[0.0002836689,0.00016196998,0.8554495,0.0023749203,0.00040260406,0.00093317445,0.0007074556,0.0016002005,0.13808651],"genre_scores_gemma":[0.9768835,0.000008789905,0.0027474605,0.00044495743,0.0000850567,0.00013428266,0.0013319862,0.000023268469,0.018340746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989068,0.00003822795,0.00021166004,0.00025153256,0.0002642726,0.0003274883],"domain_scores_gemma":[0.9992517,0.00016263865,0.00009456712,0.0003759603,0.000049260907,0.00006583539],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00008375951,0.00011210342,0.00010188525,0.00011749518,0.000050289982,0.000083823346,0.0007048458,0.000054301476,0.029817497],"category_scores_gemma":[0.00082170096,0.00008214253,0.000040451578,0.00026071852,0.000003853275,0.000473617,0.00040250266,0.00014078383,0.0073034856],"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":[0.0000064947258,0.000019528945,0.0013310942,0.0000876378,0.000014310231,0.00008466846,0.00062017486,0.81501573,0.0005103521,0.0034625086,0.1363515,0.04249603],"study_design_scores_gemma":[0.0010550705,0.00020004522,0.003511415,0.0026137398,0.0000013164597,0.000010300476,0.000013525553,0.36212936,0.0020713562,0.00013109643,0.6277889,0.00047386187],"about_ca_topic_score_codex":0.000002331759,"about_ca_topic_score_gemma":0.0000011983685,"teacher_disagreement_score":0.9765998,"about_ca_system_score_codex":0.000096550044,"about_ca_system_score_gemma":0.000060478695,"threshold_uncertainty_score":0.9934694},"labels":[],"label_agreement":null},{"id":"W2568999269","doi":"10.1609/aaai.v30i1.10311","title":"Incremental Stochastic Factorization for Online Reinforcement Learning","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Non-negative matrix factorization; Probabilistic logic; Multiplicative function; Factorization; Divergence (linguistics); Bellman equation; Markov chain; Artificial intelligence; Markov process; Algorithm; Mathematical optimization; Theoretical computer science; Machine learning; Matrix decomposition; Mathematics; Eigenvalues and eigenvectors","score_opus":0.0805954660865807,"score_gpt":0.3016254592844599,"score_spread":0.2210299931978792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568999269","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":[0.012607996,0.0000028436332,0.9835864,0.0017836102,0.00041868936,0.00057612034,0.0000026109285,0.00010477019,0.0009169755],"genre_scores_gemma":[0.99323547,0.000012420516,0.0056190887,0.00009665315,0.000083088904,0.00003433677,0.0000016794393,0.00001497579,0.00090231455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980616,0.000013598271,0.0005930647,0.00040148018,0.0005621952,0.0003680709],"domain_scores_gemma":[0.99828655,0.00019583918,0.0005468812,0.00023607185,0.00065781106,0.00007686178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003944895,0.00021545205,0.00021452978,0.00012814271,0.00023809688,0.00015928,0.001477672,0.000075640295,0.00005373303],"category_scores_gemma":[0.0010918921,0.00013637112,0.00010944462,0.00034544905,0.00015070481,0.0005138253,0.00037882983,0.00017566053,0.000041592586],"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":[0.000069922025,0.00006269114,0.00014443624,0.000035598503,0.000023655126,6.847533e-8,0.0005541049,0.0644859,0.103589475,0.77155375,0.00006285529,0.059417542],"study_design_scores_gemma":[0.00011310153,0.0007565454,0.00012688103,0.00041335687,0.00001742981,0.0000016181891,0.00024217642,0.651472,0.32003206,0.026295858,0.00022431424,0.00030468457],"about_ca_topic_score_codex":0.000008888307,"about_ca_topic_score_gemma":0.0000017259965,"teacher_disagreement_score":0.9806274,"about_ca_system_score_codex":0.00011732917,"about_ca_system_score_gemma":0.000082070845,"threshold_uncertainty_score":0.55610526},"labels":[],"label_agreement":null},{"id":"W2570416447","doi":"10.1007/978-3-642-33093-3_30","title":"Multi-timescale Nexting in a Reinforcement Learning Robot","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Robot; Artificial intelligence; Human–computer interaction","score_opus":0.02659981860661804,"score_gpt":0.2579270346567551,"score_spread":0.23132721605013706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2570416447","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":[0.000025631762,0.00052488036,0.9927851,0.00023777633,0.0013982734,0.00055608165,2.236553e-7,0.00024960804,0.0042224135],"genre_scores_gemma":[0.28567195,0.000106020685,0.7100174,0.000747437,0.00042586887,0.000018432978,0.000008526185,0.00007313938,0.0029312575],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943247,0.00008009119,0.0011497221,0.0015358804,0.0014240898,0.0014855482],"domain_scores_gemma":[0.9967717,0.0006496118,0.00066896796,0.0014441829,0.00018873166,0.0002768116],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021470778,0.0007535354,0.00073089206,0.0013840223,0.00034263334,0.00068469363,0.0036986324,0.00044659036,0.00006992231],"category_scores_gemma":[0.00037706757,0.00075481104,0.00014440829,0.00091619603,0.00046752638,0.0012449854,0.0027664262,0.0022355318,0.00019830132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025774534,0.000014591541,0.00039271617,0.000033161283,0.0000068574127,0.000039257597,0.0011719051,0.82781523,0.00019440457,0.0015507459,0.000002331887,0.16877623],"study_design_scores_gemma":[0.0004777134,0.00017517582,0.00030592046,0.00058950187,0.0000069455077,0.000036308425,5.081247e-7,0.99429274,0.00034959265,0.0010805319,0.0018584104,0.000826651],"about_ca_topic_score_codex":0.00005567269,"about_ca_topic_score_gemma":0.00003887051,"teacher_disagreement_score":0.28564632,"about_ca_system_score_codex":0.0008053603,"about_ca_system_score_gemma":0.0004520614,"threshold_uncertainty_score":0.99949026},"labels":[],"label_agreement":null},{"id":"W2574782009","doi":"","title":"Learning multi-step predictive state representations","year":2016,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Exploit; Observable; Dynamical systems theory; Variety (cybernetics); Representation (politics); Artificial intelligence; Class (philosophy); Machine learning; State (computer science); Theoretical computer science; Algorithm","score_opus":0.12193993464212904,"score_gpt":0.3447195660178371,"score_spread":0.22277963137570805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2574782009","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":[0.0014776732,0.0000026480466,0.97953874,0.0057551214,0.0013149991,0.0002265037,0.0000086412765,0.00032278194,0.011352892],"genre_scores_gemma":[0.9710233,0.000072644034,0.02271799,0.00021360413,0.000107029024,0.00004423832,0.0000064200926,0.00001659323,0.0057981396],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736017,0.00015100921,0.00066644273,0.00066920556,0.00077471643,0.00037845015],"domain_scores_gemma":[0.9980032,0.00033422958,0.0003281471,0.0005048373,0.00068110204,0.00014850334],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038857656,0.00023441631,0.00018490564,0.0003049737,0.00018834912,0.0003983823,0.001265121,0.000068495654,0.00060145924],"category_scores_gemma":[0.0010625619,0.00018394043,0.000109439905,0.00025472112,0.00018624982,0.000796593,0.00036594478,0.0003201067,0.002005688],"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":[0.00004867071,0.00012007224,0.0005680625,0.0000032769856,0.00007040185,0.00003267021,0.0011573411,0.1703261,0.00882121,0.5415319,0.00015504616,0.27716523],"study_design_scores_gemma":[0.00009579534,0.0003160192,0.0011195623,0.0001571621,0.0000044049993,0.000009683787,0.00027246133,0.9432174,0.034552436,0.018916197,0.0010360875,0.00030280827],"about_ca_topic_score_codex":0.00005760345,"about_ca_topic_score_gemma":0.000024945906,"teacher_disagreement_score":0.96954566,"about_ca_system_score_codex":0.00018392692,"about_ca_system_score_gemma":0.00013583172,"threshold_uncertainty_score":0.99877137},"labels":[],"label_agreement":null},{"id":"W2579061194","doi":"","title":"Pairwise Relative Offset Features for Atari 2600 Games.","year":2015,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Pairwise comparison; Computer science; Offset (computer science); Artificial intelligence; Feature (linguistics); Reinforcement learning; Computer vision; Set (abstract data type); Pattern recognition (psychology)","score_opus":0.04626850614696447,"score_gpt":0.281039109827256,"score_spread":0.2347706036802915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2579061194","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":[0.000121577206,0.000055731893,0.9607423,0.001977353,0.00042043178,0.0002554912,0.00000121842,0.0002463213,0.036179554],"genre_scores_gemma":[0.21794185,0.0000070208594,0.6574824,0.0017662618,0.00016660892,0.000046090758,0.000028559469,0.00002261665,0.12253861],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989896,0.00002815635,0.00016812677,0.00026977045,0.00028789538,0.0002564662],"domain_scores_gemma":[0.99894434,0.00016808348,0.00008259061,0.0004931847,0.00016972607,0.0001420477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035281765,0.00011936893,0.00012698058,0.00006493038,0.00007101731,0.00013697078,0.0006430607,0.00007027875,0.0000152509965],"category_scores_gemma":[0.00026427902,0.00009609933,0.00006263455,0.00018457498,0.000037780977,0.00061225105,0.00022255583,0.00013217682,0.00013679212],"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":[0.00001757701,0.000022808603,0.00065637194,0.000011183823,0.00003769766,0.000004734357,0.0019277077,0.15927514,0.000014634113,0.5405684,0.29167598,0.0057877535],"study_design_scores_gemma":[0.0010139812,0.00040464933,0.0010489011,0.000017169226,0.000011580273,0.000010119299,0.000116121075,0.7483549,0.00052546075,0.016344445,0.23184447,0.00030820054],"about_ca_topic_score_codex":0.000026367325,"about_ca_topic_score_gemma":0.000005608018,"teacher_disagreement_score":0.58907974,"about_ca_system_score_codex":0.00006749997,"about_ca_system_score_gemma":0.000091922746,"threshold_uncertainty_score":0.3918817},"labels":[],"label_agreement":null},{"id":"W2593237273","doi":"10.1609/aaai.v32i1.11631","title":"Multi-Step Reinforcement Learning: A Unifying Algorithm","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; DeepMind","keywords":"Reinforcement learning; Computer science; Backup; Algorithm; TRACE (psycholinguistics); Sampling (signal processing); Focus (optics); Monte Carlo method; Importance sampling; Artificial intelligence; Machine learning; Mathematics","score_opus":0.09247718432083181,"score_gpt":0.31363613619094266,"score_spread":0.22115895187011086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593237273","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":[0.0028911573,0.0000072342227,0.97949034,0.0010362939,0.0006558921,0.00041586993,4.0186242e-7,0.00020009733,0.015302712],"genre_scores_gemma":[0.9133315,0.000024136189,0.08332956,0.0002385959,0.00013481174,0.000019888645,5.478779e-7,0.000019633459,0.002901307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726117,0.000029451421,0.0007430391,0.00058646506,0.0008140761,0.0005658161],"domain_scores_gemma":[0.9975198,0.000087060966,0.00064876553,0.00045446932,0.0011587479,0.00013117744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007418666,0.000309026,0.0002912106,0.00019480371,0.000495519,0.00041521236,0.0028599845,0.00012095671,0.00012575167],"category_scores_gemma":[0.000633862,0.00024228597,0.00014116598,0.00089949113,0.0005071139,0.0005502939,0.0009153195,0.00055079133,0.0004037424],"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":[0.000052892916,0.00014796873,0.00039828022,0.0000670603,0.00006339402,0.0000014758173,0.004897086,0.028348925,0.029426862,0.7260391,0.00029887757,0.21025805],"study_design_scores_gemma":[0.00004546647,0.0004822668,0.00007046048,0.00017876511,0.000010132586,0.0000042981364,0.0004791254,0.8288441,0.16619682,0.0026358375,0.0008069917,0.0002457839],"about_ca_topic_score_codex":0.00005174801,"about_ca_topic_score_gemma":0.0000038250487,"teacher_disagreement_score":0.9104404,"about_ca_system_score_codex":0.000091223235,"about_ca_system_score_gemma":0.00012227043,"threshold_uncertainty_score":0.9880135},"labels":[],"label_agreement":null},{"id":"W2594903727","doi":"10.48550/arxiv.1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Observability; Artificial intelligence; Set (abstract data type); Artificial neural network; Simple (philosophy); Architecture; Memory map; Deep learning; Shared memory; Parallel computing; Programming language","score_opus":0.0666945800872272,"score_gpt":0.2102999486985228,"score_spread":0.1436053686112956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2594903727","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":[0.0051676044,0.000051178828,0.9881552,0.00014210212,0.0022463968,0.0008075247,0.0000018450331,0.00040552465,0.0030226419],"genre_scores_gemma":[0.97614974,0.00005160927,0.0057064258,0.00009852994,0.00020175031,0.0000042259685,0.00006987502,0.000040394065,0.017677438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973392,0.0001215288,0.0003509417,0.0012836673,0.00021122755,0.00069345586],"domain_scores_gemma":[0.99614877,0.00015948829,0.0009131315,0.0022644654,0.0002856208,0.0002285045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036805874,0.00051391765,0.0004963663,0.00028818133,0.0007730228,0.00055694726,0.004080839,0.00040844668,0.000045262837],"category_scores_gemma":[0.00018606913,0.0006003455,0.00039699092,0.00014495205,0.00015387032,0.0006326951,0.0036238998,0.0011052642,0.00006471768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034187455,0.000007983516,0.00041209,0.00015599413,0.000116424795,0.00007914371,0.00029506878,0.97421306,0.000016630445,0.02345428,0.00026517184,0.00094996305],"study_design_scores_gemma":[0.0008354995,0.00014599157,0.00024869796,0.00007610407,0.000088686254,0.0000036291758,0.000059387632,0.9912788,0.000105422805,0.004224052,0.0023065428,0.0006271667],"about_ca_topic_score_codex":0.00006482434,"about_ca_topic_score_gemma":0.000014465079,"teacher_disagreement_score":0.98244876,"about_ca_system_score_codex":0.00032614416,"about_ca_system_score_gemma":0.00020749914,"threshold_uncertainty_score":0.9996448},"labels":[],"label_agreement":null},{"id":"W2605760243","doi":"","title":"Teaching with RoboCup","year":2004,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Manitoba","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.009273550210222827,"score_gpt":0.22538821041693533,"score_spread":0.2161146602067125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2605760243","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":[0.0010269333,0.000002811945,0.9100688,0.0012688319,0.000053683292,0.000041999167,8.2065865e-9,0.00025226112,0.08728464],"genre_scores_gemma":[0.5591245,3.6070512e-7,0.43672386,0.00047989533,0.000017800277,0.0000013433994,2.1151092e-7,0.0000038720273,0.0036481104],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994343,0.000010493535,0.00007304145,0.00014408218,0.00018251398,0.00015560044],"domain_scores_gemma":[0.9995815,0.000015365287,0.000027321776,0.0003163053,0.000016193695,0.000043291435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000104802006,0.00006269795,0.000051880077,0.000037354414,0.0000913061,0.00011024785,0.00043722117,0.0000164645,0.000010523184],"category_scores_gemma":[0.000010464527,0.000043665677,0.000014092336,0.00009401478,0.0000146112,0.0003587537,0.00009922713,0.0001279056,0.00013919709],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.0865578e-7,0.000004805349,0.00014775143,0.0000013656188,0.0000032942519,0.0000056495187,0.00021415233,0.65700233,0.00004057701,0.3411336,0.000036345653,0.0014097103],"study_design_scores_gemma":[0.0034557001,0.0014428986,0.0042757792,0.00015226923,0.000016645534,0.00024993575,0.00021539634,0.9315151,0.0059190486,0.012768406,0.038744748,0.0012440692],"about_ca_topic_score_codex":0.00008186904,"about_ca_topic_score_gemma":0.000004522342,"teacher_disagreement_score":0.5580976,"about_ca_system_score_codex":0.00003236075,"about_ca_system_score_gemma":0.000037589012,"threshold_uncertainty_score":0.17891434},"labels":[],"label_agreement":null},{"id":"W2607014226","doi":"10.1109/tnnls.2017.2690910","title":"Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"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 Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Affordance; Robot; Human–computer interaction; Artificial intelligence; Robot learning; Semantics (computer science); Knowledge transfer; Transfer of learning; Task (project management); Knowledge management; Mobile robot","score_opus":0.025031320524130575,"score_gpt":0.2901557942169168,"score_spread":0.2651244736927862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607014226","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":[0.033328936,0.00013331708,0.96331894,0.0001761372,0.0010175089,0.0005401285,2.6881142e-7,0.00018078169,0.0013040033],"genre_scores_gemma":[0.9943551,0.00013749006,0.0010703325,0.00003550247,0.00007847206,0.000074721116,0.0000012381323,0.00003289046,0.0042142663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966539,0.00095405965,0.0007486114,0.00063081254,0.00042645578,0.00058615365],"domain_scores_gemma":[0.9981843,0.0006530946,0.0002998382,0.00051704975,0.00012089792,0.0002248234],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015723505,0.0003496916,0.0005770873,0.00036474038,0.0012817612,0.00054022454,0.00079522317,0.00019272896,0.000012627915],"category_scores_gemma":[0.00010918725,0.00033323967,0.00012087067,0.000355069,0.0001575377,0.0005542204,0.000021705724,0.0017745739,0.000014257487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006023516,0.000022949042,0.0010528641,0.00007588912,0.00004669173,0.000016373002,0.0024619647,0.9746279,0.0005033698,0.0003727494,0.000006847082,0.020752177],"study_design_scores_gemma":[0.00069061504,0.0016986574,0.0005265536,0.0005011404,0.000025475445,0.00005635716,0.0004762334,0.9941812,0.00040268115,0.0000027546591,0.0011100883,0.00032824944],"about_ca_topic_score_codex":0.00075692957,"about_ca_topic_score_gemma":0.000035883364,"teacher_disagreement_score":0.96224856,"about_ca_system_score_codex":0.00007317388,"about_ca_system_score_gemma":0.000064101645,"threshold_uncertainty_score":0.99991196},"labels":[],"label_agreement":null},{"id":"W2620853660","doi":"10.5555/3091125.3091207","title":"Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Function approximation; Nonlinear system; Function (biology); Class (philosophy); Artificial intelligence; Temporal difference learning; Mathematical optimization; Machine learning; Artificial neural network; Mathematics","score_opus":0.07223075096191683,"score_gpt":0.309418597286914,"score_spread":0.23718784632499718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620853660","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":[0.012294425,0.00008575003,0.9839391,0.000060002047,0.0011879375,0.0017537753,0.0000026723205,0.000078016245,0.0005983266],"genre_scores_gemma":[0.98591125,0.00007322879,0.011038232,0.00006920133,0.00011312218,0.00022707904,0.000032956756,0.000024876646,0.0025100673],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980228,0.00009896817,0.00051600416,0.0005155409,0.00039231364,0.00045437337],"domain_scores_gemma":[0.998518,0.000079762955,0.0004985808,0.00060206285,0.00017385899,0.00012777219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006936602,0.00025441914,0.00030798165,0.00016410781,0.0007158094,0.0007739886,0.0005820224,0.000118046555,0.0000041819376],"category_scores_gemma":[0.00023320618,0.00024108116,0.00006871614,0.000077733646,0.00005591044,0.0013659816,0.00032099447,0.00020003799,0.000028512359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013435516,0.00016962418,0.018791592,0.0005424324,0.0002547882,0.00001923575,0.0033818057,0.9513159,0.0005697796,0.010778279,0.0004754629,0.013566741],"study_design_scores_gemma":[0.0021147248,0.0003722293,0.011879541,0.00026723067,0.000022021486,0.0000028697157,0.00032784385,0.9791633,0.000051736213,0.000019775842,0.005518189,0.0002605273],"about_ca_topic_score_codex":0.00023033629,"about_ca_topic_score_gemma":0.000012891886,"teacher_disagreement_score":0.97361684,"about_ca_system_score_codex":0.0001364622,"about_ca_system_score_gemma":0.000039194805,"threshold_uncertainty_score":0.9831004},"labels":[],"label_agreement":null},{"id":"W2626637010","doi":"10.4230/lipics.cp.2023.25","title":"Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":523,"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":"Decomposition; Value (mathematics); Computer science; Artificial intelligence; Machine learning; Chemistry","score_opus":0.07875522306874225,"score_gpt":0.20925438421090964,"score_spread":0.1304991611421674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626637010","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":[0.034086764,0.000033766606,0.96025556,0.000049064754,0.0007744258,0.00041891506,8.086069e-7,0.00061779434,0.0037628715],"genre_scores_gemma":[0.97734976,0.00009790313,0.018830782,0.000045577293,0.00012774419,0.000002679999,0.000014603271,0.000033732773,0.003497223],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973414,0.00024380494,0.0003030628,0.001274081,0.00020722936,0.00063040864],"domain_scores_gemma":[0.9974022,0.00012408225,0.0007919993,0.0012251212,0.00024507596,0.00021151127],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046372414,0.00044103517,0.0004255934,0.00035044158,0.0007358423,0.00071271934,0.0020798338,0.00036869367,0.000020626881],"category_scores_gemma":[0.00030573664,0.0005387974,0.0002673581,0.00036901003,0.00024801292,0.0004863974,0.0024490042,0.0015276793,0.000120938676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009386253,0.000028737517,0.0030111223,0.00008415493,0.00010807076,0.00025347978,0.00028259913,0.9652758,0.000050540068,0.02693993,0.000044879907,0.0039112633],"study_design_scores_gemma":[0.0003688268,0.00014912922,0.0008215543,0.00016307407,0.00009291099,0.000024887602,0.00005360494,0.99269027,0.00005123162,0.0023246643,0.002688381,0.0005714926],"about_ca_topic_score_codex":0.00022026348,"about_ca_topic_score_gemma":0.000016827415,"teacher_disagreement_score":0.943263,"about_ca_system_score_codex":0.00043568166,"about_ca_system_score_gemma":0.00049927714,"threshold_uncertainty_score":0.9997063},"labels":[],"label_agreement":null},{"id":"W2724228633","doi":"10.1145/3071178.3071303","title":"Multi-task learning in Atari video games with emergent tangled program graphs","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Observability; Task (project management); Video game; Artificial intelligence; Variety (cybernetics); State (computer science); Matching (statistics); Human–computer interaction; Machine learning; Multimedia; Programming language","score_opus":0.021923593551869416,"score_gpt":0.25637648094619514,"score_spread":0.23445288739432574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2724228633","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":[0.56267226,0.00017056246,0.43456277,0.0010606449,0.00015799896,0.0006107312,6.313194e-7,0.00010811863,0.000656299],"genre_scores_gemma":[0.84426147,0.0000604423,0.1554326,0.000017801,0.000010145729,0.000029792172,0.0000010831058,0.0000062846566,0.00018036696],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882364,0.000016516919,0.0002798279,0.00033493072,0.00032410782,0.00022099959],"domain_scores_gemma":[0.9989178,0.000030094754,0.0004547024,0.0001684134,0.00037128388,0.00005769295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017027759,0.00014847238,0.0001639612,0.0000952959,0.0004408393,0.00023514513,0.00082052447,0.000048308815,0.0000030735575],"category_scores_gemma":[0.00012081426,0.00011365032,0.00003550985,0.00017969502,0.0002545675,0.00042326146,0.00045532652,0.00018793397,0.0000021480384],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003391296,0.00011545956,0.62907505,0.0001344063,0.00004392481,0.0000015449535,0.0018394626,0.32502228,0.0011275605,0.0076334733,0.00017093949,0.03480201],"study_design_scores_gemma":[0.00032953278,0.00012549659,0.45770073,0.00008622028,0.0000065668673,0.000008311287,0.0000689423,0.5403116,0.00004892419,0.0011178366,0.00010286932,0.00009300018],"about_ca_topic_score_codex":0.00005210789,"about_ca_topic_score_gemma":0.0000065734616,"teacher_disagreement_score":0.28158924,"about_ca_system_score_codex":0.0000279621,"about_ca_system_score_gemma":0.00009073815,"threshold_uncertainty_score":0.46345255},"labels":[],"label_agreement":null},{"id":"W2733958039","doi":"10.1609/aiide.v11i1.12801","title":"Maximizing Flow as a Metacontrol in Angband","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"University of Alberta","keywords":"Computer science; State (computer science); Flow (mathematics); Artificial intelligence; Operations research; Psychology; Engineering; Mathematics","score_opus":0.05941970819663916,"score_gpt":0.28596994665065184,"score_spread":0.22655023845401268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733958039","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":[0.54714173,0.0000777274,0.32584727,0.007585557,0.0011195136,0.001613669,0.000009652367,0.00012879752,0.1164761],"genre_scores_gemma":[0.99857813,0.000015615009,0.00064364664,0.00030164278,0.000022629209,0.000027278302,7.9909114e-7,0.0000091623215,0.00040109895],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982963,0.000015922009,0.0004989282,0.0004052957,0.00047577452,0.0003077736],"domain_scores_gemma":[0.99897397,0.00009092573,0.00029259815,0.0001861796,0.00033008665,0.00012623098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030559197,0.00022558664,0.00027360025,0.00017108608,0.000058390055,0.0006779983,0.00087802525,0.000051043855,0.000014292352],"category_scores_gemma":[0.00056240155,0.00016564853,0.000090013826,0.00027626526,0.00013597243,0.0014901838,0.00048076062,0.00027417214,0.000050205996],"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":[0.0009524794,0.00075153465,0.0033663295,0.0000677992,0.00017364592,0.000013175711,0.021447578,0.01773785,0.006634952,0.6499826,0.00023040877,0.2986417],"study_design_scores_gemma":[0.0002886868,0.001374618,0.00022712181,0.0005944413,0.000017246497,0.000025296726,0.0074963747,0.80232024,0.12523682,0.0615311,0.00045316634,0.00043489764],"about_ca_topic_score_codex":0.00002963199,"about_ca_topic_score_gemma":0.0000029484827,"teacher_disagreement_score":0.7845824,"about_ca_system_score_codex":0.00012804924,"about_ca_system_score_gemma":0.000055763805,"threshold_uncertainty_score":0.6754951},"labels":[],"label_agreement":null},{"id":"W2735649811","doi":"10.1007/s10994-017-5657-1","title":"Generalized exploration in policy search","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Seventh Framework Programme; Technische Universität Darmstadt","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Entropy (arrow of time); Policy learning; Machine learning; Mathematical optimization; Mathematics","score_opus":0.05004398310810728,"score_gpt":0.33199694268441793,"score_spread":0.28195295957631067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735649811","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":[0.033805106,0.00003210797,0.9499956,0.0053218263,0.00015694907,0.00012128982,1.273012e-7,0.00016531452,0.010401704],"genre_scores_gemma":[0.97775114,0.000038540587,0.017607665,0.0001528087,0.00013360548,0.000008388068,0.000006124803,0.000014098485,0.004287634],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987234,0.00017347687,0.00020218542,0.0002707607,0.00030098407,0.00032923443],"domain_scores_gemma":[0.9990062,0.00004563515,0.00014152988,0.00070436357,0.000039257462,0.000063004445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064282265,0.000116331226,0.00014000414,0.0002491295,0.00055592484,0.0006979775,0.0011297861,0.00005046502,0.000022222079],"category_scores_gemma":[0.0005954194,0.00011517728,0.00003848538,0.00017802078,0.000037829366,0.0011267762,0.00058455067,0.00039733818,0.00011525934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038084327,0.0000073215037,0.04780951,0.0000067268065,0.0000039390825,0.000014678674,0.001040809,0.906871,0.00039191305,0.026926177,0.000021313414,0.016902769],"study_design_scores_gemma":[0.00050457456,0.00005081924,0.017376885,0.000016567856,8.7023307e-7,0.0000031611191,0.000013643594,0.9765167,0.00027144438,0.00034418964,0.004770864,0.00013023968],"about_ca_topic_score_codex":0.0013324973,"about_ca_topic_score_gemma":0.00005964848,"teacher_disagreement_score":0.943946,"about_ca_system_score_codex":0.00007797277,"about_ca_system_score_gemma":0.00006998652,"threshold_uncertainty_score":0.6730613},"labels":[],"label_agreement":null},{"id":"W2737821837","doi":"10.1109/icra.2017.7989686","title":"Adapting learned robotics behaviours through policy adjustment","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Robot; Computer science; Inverted pendulum; Task (project management); Artificial intelligence; Robotics; Action (physics); State space; Physical system; Mobile robot; Control theory (sociology); Control (management); Engineering; Mathematics","score_opus":0.07174920135323527,"score_gpt":0.3402462901202425,"score_spread":0.26849708876700723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737821837","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":[0.00047984577,0.000026633237,0.917501,0.007152887,0.0005847751,0.00015118974,2.8570275e-7,0.00028836413,0.07381506],"genre_scores_gemma":[0.55954653,0.000055298926,0.42115805,0.0009822764,0.00035916225,0.0000075922703,0.000002761867,0.000025732705,0.017862573],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831843,0.000039861505,0.00027707012,0.00039057093,0.0004561705,0.00051789015],"domain_scores_gemma":[0.997529,0.00005212981,0.0003080918,0.0019093426,0.00008832567,0.00011313097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024275942,0.00019277557,0.00018502212,0.000070029826,0.00077145157,0.00078311743,0.0023656916,0.00008445605,0.000032814714],"category_scores_gemma":[0.00027072686,0.00017572781,0.000089695466,0.00010636321,0.00010100764,0.0011918877,0.0011359705,0.0002314161,0.00020185966],"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":[0.0000015579911,0.000025004361,0.0023839276,0.000004743812,0.000017648825,0.00001575309,0.00040443713,0.44388926,0.000043574644,0.54096675,0.0007982485,0.0114490595],"study_design_scores_gemma":[0.0011723029,0.00036212412,0.042588554,0.00007282089,0.00003487618,0.000047972142,0.00013610355,0.94200504,0.0010532098,0.005502697,0.0061916653,0.0008326378],"about_ca_topic_score_codex":0.00077220233,"about_ca_topic_score_gemma":0.000016642409,"teacher_disagreement_score":0.5590667,"about_ca_system_score_codex":0.000116849915,"about_ca_system_score_gemma":0.00014417192,"threshold_uncertainty_score":0.75516194},"labels":[],"label_agreement":null},{"id":"W2738109916","doi":"10.1109/adconip.2017.7983780","title":"Deep reinforcement learning approaches for process control","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":137,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Process (computing); Controller (irrigation); Artificial neural network; Process control; Control (management); Artificial intelligence; Control system; Control engineering; Function (biology); Deep learning; Control theory (sociology); MIMO; Engineering; Channel (broadcasting)","score_opus":0.049513320306949236,"score_gpt":0.28178940841336486,"score_spread":0.23227608810641562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738109916","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":[0.0001529556,0.000011359804,0.9618305,0.00081475184,0.00020845774,0.0005197524,3.761568e-8,0.00020573166,0.03625648],"genre_scores_gemma":[0.96577877,0.0000026067241,0.027294802,0.00019714808,0.000083311636,0.00011355429,0.000002704023,0.000013072821,0.0065140543],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986842,0.000020567877,0.00025186408,0.0003405335,0.00030201173,0.00040080462],"domain_scores_gemma":[0.99850434,0.00009934389,0.00031923104,0.0008708144,0.000114860784,0.000091394584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044484448,0.0001574064,0.00018248257,0.000054176213,0.0009779142,0.000840867,0.0017540964,0.0000629116,0.00002786817],"category_scores_gemma":[0.00041247628,0.00013480235,0.00008312708,0.000040586376,0.0000634754,0.0008750503,0.00020978952,0.0001532778,0.00004735761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008090954,0.0000066792245,0.0011936019,0.000031288546,0.000025275598,7.9094343e-7,0.0002880701,0.92523396,0.0000064470614,0.064791724,0.00006363242,0.008350421],"study_design_scores_gemma":[0.0009857106,0.00017266431,0.0004783247,0.000011304959,0.00000944029,0.0000021685996,0.00006169959,0.99505854,0.00025783406,0.0005769857,0.0021927317,0.00019261563],"about_ca_topic_score_codex":0.0000072071707,"about_ca_topic_score_gemma":0.0000017948944,"teacher_disagreement_score":0.96562576,"about_ca_system_score_codex":0.00003298042,"about_ca_system_score_gemma":0.000050473198,"threshold_uncertainty_score":0.81084996},"labels":[],"label_agreement":null},{"id":"W2739573821","doi":"10.3390/make1010002","title":"Learning to Teach Reinforcement Learning Agents","year":2017,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":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":"Washington State University; U.S. Department of Agriculture; National Aeronautics and Space Administration; National Science Foundation","keywords":"Reinforcement learning; Advice (programming); Heuristics; Statistic; Action (physics); Variance (accounting); Quality (philosophy); Discounting","score_opus":0.02352967150582671,"score_gpt":0.323069848083718,"score_spread":0.29954017657789134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739573821","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":[0.03505318,0.00023764993,0.8910411,0.0010241542,0.0012575646,0.00036896786,1.4197289e-7,0.0008464083,0.07017086],"genre_scores_gemma":[0.91461504,0.00015906061,0.0041728416,0.0000586977,0.00026724476,0.000025750309,0.000015023882,0.000043109365,0.08064327],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99735963,0.00035411556,0.000456608,0.00075952185,0.00043709046,0.0006330081],"domain_scores_gemma":[0.9981717,0.00019131438,0.00054444995,0.00061358797,0.00016230605,0.000316649],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014046244,0.00037357668,0.00033641563,0.00032448347,0.0036350524,0.0013996185,0.0008401965,0.00016105433,0.00009134802],"category_scores_gemma":[0.0017603529,0.0003808316,0.00010504374,0.00019598128,0.00006832341,0.0010743252,0.000966385,0.0018394416,0.0006477701],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003218047,0.000047223773,0.057554558,0.00006122237,0.00005602143,0.000020331541,0.0042685713,0.75943893,0.001677009,0.0011707431,0.00042618517,0.17524704],"study_design_scores_gemma":[0.0004936064,0.0005111747,0.015120032,0.000085862506,0.000017736664,0.000030829764,0.00016109046,0.6942566,0.00023626171,0.000019954561,0.2887004,0.00036643143],"about_ca_topic_score_codex":0.000171842,"about_ca_topic_score_gemma":0.000018173652,"teacher_disagreement_score":0.88686824,"about_ca_system_score_codex":0.00014907225,"about_ca_system_score_gemma":0.00005948714,"threshold_uncertainty_score":0.99986434},"labels":[],"label_agreement":null},{"id":"W2739747865","doi":"10.24963/ijcai.2017/290","title":"Constrained Bayesian Reinforcement Learning via Approximate Linear Programming","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Defense Acquisition Program Administration; Korea Advanced Institute of Science and Technology; Agency for Defense Development; Ministry of Science, ICT and Future Planning","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Bayesian probability; Mathematical optimization; Machine learning; Linear programming; Bayesian optimization; State (computer science); Algorithm; Mathematics","score_opus":0.020878168153838497,"score_gpt":0.2726533437933096,"score_spread":0.2517751756394711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739747865","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":[0.00011046516,0.000005850897,0.93585724,0.0004340626,0.0002972036,0.0003376806,4.336112e-8,0.0005640608,0.062393382],"genre_scores_gemma":[0.7201626,0.0000052018736,0.27294314,0.000121291014,0.00007731198,0.000020003285,0.000004420723,0.000016553931,0.006649508],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798703,0.000046241683,0.0004095842,0.00045155076,0.00048550934,0.00062008086],"domain_scores_gemma":[0.9978651,0.000052952,0.0004307569,0.0013543149,0.00011444988,0.00018246156],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005992876,0.0002408588,0.00023243131,0.0000981561,0.0012133959,0.0010699361,0.0018691305,0.00009156088,0.00009709175],"category_scores_gemma":[0.00025127962,0.00021836691,0.00010045766,0.00009931535,0.00017456176,0.0009855592,0.0008294573,0.00036127842,0.00016030842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000765384,0.000025199439,0.0032502036,0.000055197324,0.00006326764,0.00004405678,0.00061458815,0.8323537,0.00040885873,0.07938593,0.00009264463,0.08369869],"study_design_scores_gemma":[0.00047154535,0.0001758174,0.00023390127,0.000032067168,0.0000073333676,0.000018071798,0.00004463903,0.9887114,0.0009744252,0.00012570432,0.008914045,0.00029103475],"about_ca_topic_score_codex":0.000058358866,"about_ca_topic_score_gemma":0.0000020774353,"teacher_disagreement_score":0.7200521,"about_ca_system_score_codex":0.00005242438,"about_ca_system_score_gemma":0.00006992065,"threshold_uncertainty_score":0.99996704},"labels":[],"label_agreement":null},{"id":"W2740174381","doi":"10.24963/ijcai.2017/717","title":"Approximate Value Iteration with Temporally Extended Actions (Extended Abstract)","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Landmark; Convergence (economics); Computer science; Mathematical optimization; Bellman equation; Value (mathematics); Function (biology); State space; Term (time); Algorithm; Mathematics; Artificial intelligence; Machine learning; Statistics; Economics","score_opus":0.03463366844770536,"score_gpt":0.2920029215859134,"score_spread":0.257369253138208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740174381","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":[0.002253381,0.0000029269763,0.90516436,0.001529331,0.00025849094,0.00022280417,4.19849e-7,0.00031776822,0.09025049],"genre_scores_gemma":[0.8248396,0.0000044359176,0.16717061,0.00022028899,0.00005715565,0.00001767132,0.0000060097636,0.000013075405,0.007671162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986684,0.000021329188,0.00024044779,0.00037539873,0.0004027327,0.00029170208],"domain_scores_gemma":[0.9979372,0.00003442526,0.00032089747,0.001476356,0.00012960976,0.00010151757],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00025651493,0.00017075268,0.00014160997,0.000083063525,0.00083492603,0.0016093897,0.0011609319,0.000063829284,0.000056976172],"category_scores_gemma":[0.00006235905,0.00013196896,0.00004628814,0.00007906776,0.000079265184,0.002152519,0.00021426367,0.00019299761,0.00013204175],"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":[0.00004242444,0.00020088749,0.0018101991,0.00005761098,0.00013310711,0.000078833604,0.00096448755,0.31651413,0.0035914506,0.6500452,0.0025167349,0.02404491],"study_design_scores_gemma":[0.00076609943,0.0002382823,0.062201798,0.00004546334,0.0000147105875,0.00004349501,0.000039946703,0.926466,0.003218993,0.0018475304,0.0047059185,0.00041177912],"about_ca_topic_score_codex":0.000057539397,"about_ca_topic_score_gemma":0.000011900553,"teacher_disagreement_score":0.8225862,"about_ca_system_score_codex":0.000045759374,"about_ca_system_score_gemma":0.00009961055,"threshold_uncertainty_score":0.999427},"labels":[],"label_agreement":null},{"id":"W2744625767","doi":"10.48550/arxiv.1708.01298","title":"Effective sketching methods for value function approximation","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Sketch; Computer science; Reinforcement learning; Variety (cybernetics); Function (biology); Matrix (chemical analysis); Coding (social sciences); Artificial intelligence; Machine learning; Algorithm; Theoretical computer science; Mathematics","score_opus":0.08423265039614783,"score_gpt":0.26367145793553604,"score_spread":0.1794388075393882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2744625767","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":[0.0020745888,0.000027295138,0.9912142,0.000050799576,0.0019815464,0.0012064915,0.0000020047114,0.00031633867,0.003126727],"genre_scores_gemma":[0.7467034,0.00002643403,0.25106674,0.000052200045,0.00015923833,0.000011811952,0.000030536226,0.000026960091,0.0019226917],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979824,0.00039081453,0.0001986404,0.0010116732,0.00008694924,0.00032956383],"domain_scores_gemma":[0.99691445,0.0005212622,0.00066459976,0.0015734691,0.00022757942,0.00009862528],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012404643,0.0003082139,0.00034412937,0.0002581415,0.0005249811,0.0003956124,0.0018026743,0.0003324532,0.0000039224537],"category_scores_gemma":[0.0003718021,0.00036039826,0.00027877858,0.00016811288,0.00006926464,0.00076277996,0.0016079589,0.0005838328,0.000028445042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025567382,0.0000138283895,0.0001157714,0.00012752497,0.000097299475,0.000003841227,0.00016829281,0.80407524,0.000049579816,0.18196593,0.000042409036,0.01331473],"study_design_scores_gemma":[0.00042786746,0.000111967856,0.0005628124,0.00009702629,0.00012006834,0.0000011104253,0.000015880934,0.9132786,0.0002458008,0.083779246,0.0010243529,0.00033530762],"about_ca_topic_score_codex":0.000048185477,"about_ca_topic_score_gemma":0.0000014062091,"teacher_disagreement_score":0.7446288,"about_ca_system_score_codex":0.00033714194,"about_ca_system_score_gemma":0.00012536795,"threshold_uncertainty_score":0.9998848},"labels":[],"label_agreement":null},{"id":"W2750726423","doi":"","title":"Natural Value Approximators: Learning when to Trust Past Estimates","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Observability; Reinforcement learning; Bellman equation; Classification of discontinuities; Interpolation (computer graphics); Computer science; Value (mathematics); Artificial neural network; Discontinuity (linguistics); Function approximation; Inductive bias; Artificial intelligence; Function (biology); Mathematical optimization; Algorithm; Machine learning; Mathematics; Applied mathematics; Image (mathematics); Multi-task learning","score_opus":0.01702164821844596,"score_gpt":0.264931605515689,"score_spread":0.24790995729724305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2750726423","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":[0.011809858,0.00006900305,0.97775424,0.0010422932,0.0019001579,0.0005103405,7.210636e-7,0.00075752905,0.00615587],"genre_scores_gemma":[0.9807247,9.516551e-7,0.017910175,0.00030123722,0.00017976528,0.00004729583,0.000013722244,0.00001460195,0.0008075781],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979434,0.000047799684,0.0006552893,0.00024514188,0.0006580655,0.00045030398],"domain_scores_gemma":[0.9978771,0.0000490816,0.00090450473,0.00069684396,0.0003180133,0.00015443745],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004964991,0.000253868,0.0002660428,0.00022018673,0.0015272036,0.007459884,0.0017079615,0.00009125905,0.0000021369601],"category_scores_gemma":[0.000508384,0.00022242423,0.000056256184,0.00016537512,0.00005705388,0.010412533,0.0004536705,0.0003775054,0.0002421855],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008276865,0.000006888933,0.0065605063,0.0004822203,0.000014085018,0.000003133743,0.0058476576,0.9530508,0.00016333318,0.005568286,0.0014036875,0.026891159],"study_design_scores_gemma":[0.0002475296,0.000064245105,0.0017767806,0.00023320431,0.0000055362907,0.00004514326,0.00023962313,0.9867523,0.00025286814,0.00003574179,0.010068619,0.00027842453],"about_ca_topic_score_codex":0.00005532262,"about_ca_topic_score_gemma":3.0044433e-7,"teacher_disagreement_score":0.9689148,"about_ca_system_score_codex":0.00009867145,"about_ca_system_score_gemma":0.00006966023,"threshold_uncertainty_score":0.99977267},"labels":[],"label_agreement":null},{"id":"W2753431380","doi":"","title":"Second-order Optimization for Deep Reinforcement Learning using Kronecker-factored Approximation","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Kronecker delta; Reinforcement learning; Computer science; Scalability; Curvature; Trust region; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.0371741992360738,"score_gpt":0.28445717157899536,"score_spread":0.24728297234292157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753431380","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":[0.0018694324,0.00003146362,0.9936087,0.0001024438,0.0009695865,0.000911873,7.2452895e-7,0.0002444733,0.0022612938],"genre_scores_gemma":[0.91380376,0.0000032187963,0.08535161,0.00009412473,0.00012348837,0.00008327051,0.00010472823,0.000019128724,0.00041667637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978343,0.000051657,0.00090353994,0.00024896328,0.0005469827,0.00041451768],"domain_scores_gemma":[0.9965259,0.000045630295,0.0019507811,0.00058840506,0.00079483184,0.000094497605],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005815895,0.00025513637,0.00026169306,0.00023060561,0.0018988175,0.0045086914,0.00088072073,0.00014675314,0.000014096291],"category_scores_gemma":[0.00042037995,0.00024885716,0.00006641103,0.00019010715,0.00005134557,0.013304263,0.00019085166,0.00021594464,0.000019763676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008880264,0.0000040311984,0.00012667512,0.00040793017,0.000011165293,1.9596641e-7,0.0013583603,0.98823947,0.00008445798,0.0009411682,0.000036445268,0.0087812245],"study_design_scores_gemma":[0.00071528147,0.000086120934,0.00006322516,0.00012792471,0.0000127516805,0.000014894957,0.00022111855,0.99582076,0.00030582782,0.000010291237,0.0023313516,0.00029042634],"about_ca_topic_score_codex":0.000019195468,"about_ca_topic_score_gemma":7.3546977e-7,"teacher_disagreement_score":0.9119343,"about_ca_system_score_codex":0.00019528739,"about_ca_system_score_gemma":0.00013154591,"threshold_uncertainty_score":0.99999636},"labels":[],"label_agreement":null},{"id":"W2754203286","doi":"10.1609/aaai.v32i1.11831","title":"When Waiting Is Not an Option: Learning Options With a Deliberation Cost","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Deliberation; Interpretability; Bounded rationality; Computer science; Rationality; Management science; Risk analysis (engineering); Artificial intelligence; Epistemology; Economics; Business; Political science","score_opus":0.12388612333898766,"score_gpt":0.3176455879313191,"score_spread":0.19375946459233143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754203286","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":[0.05731665,0.000008991417,0.9303127,0.004541708,0.0006322532,0.0010817879,0.000005283614,0.00030709518,0.005793556],"genre_scores_gemma":[0.95041555,0.000046020992,0.047986742,0.00035821187,0.0002666632,0.000097014716,0.0000070203464,0.00003618588,0.00078659214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965002,0.00005936492,0.00086694275,0.0010379114,0.0010438627,0.0004917292],"domain_scores_gemma":[0.9955813,0.00009027215,0.0012935002,0.0006882527,0.0021982754,0.00014834493],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008671142,0.00046927633,0.00042186605,0.00023477753,0.0006097288,0.0015406145,0.0032089157,0.00028800638,0.00012115606],"category_scores_gemma":[0.00037800558,0.00037326428,0.00014343894,0.00042899925,0.00041288187,0.00088696345,0.0015116056,0.0013639517,0.00012466597],"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":[0.00010894105,0.00011757605,0.00023558144,0.00015579461,0.00006817714,9.0614867e-7,0.008787661,0.25789633,0.004465611,0.68249977,0.00016149317,0.045502126],"study_design_scores_gemma":[0.00003025495,0.00047730748,0.000056163495,0.00084728625,0.000035941783,0.0000069071066,0.00043722457,0.8798712,0.0885994,0.029027946,0.00019375504,0.00041660696],"about_ca_topic_score_codex":0.00006138556,"about_ca_topic_score_gemma":0.000010981727,"teacher_disagreement_score":0.8930989,"about_ca_system_score_codex":0.00014099227,"about_ca_system_score_gemma":0.0003264886,"threshold_uncertainty_score":0.9998719},"labels":[],"label_agreement":null},{"id":"W2754517384","doi":"10.1609/aaai.v32i1.11694","title":"Deep Reinforcement Learning That Matters","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1504,"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":"Open Philanthropy Project; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Standardization; Benchmark (surveying); Artificial intelligence; Field (mathematics); Variance (accounting); Deep learning; Machine learning; Data science; Risk analysis (engineering); Mathematics","score_opus":0.07088540185984533,"score_gpt":0.28886615983652203,"score_spread":0.2179807579766767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2754517384","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":[0.0067699202,0.0000063123193,0.95107377,0.0052902084,0.00077959034,0.00037902506,1.1122048e-7,0.00018674672,0.03551434],"genre_scores_gemma":[0.99274653,0.000020350386,0.004614619,0.0009793142,0.00010769012,0.000015974907,3.7427887e-7,0.000016671764,0.0014984788],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997621,0.000022334594,0.0005475839,0.0004922792,0.000811318,0.0005054875],"domain_scores_gemma":[0.99818,0.000085795255,0.00056999887,0.0004080477,0.0006502195,0.00010594401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005631779,0.0002654556,0.00024587108,0.0001622093,0.00040626965,0.0004135727,0.0027048115,0.00009179958,0.00022886187],"category_scores_gemma":[0.00032171656,0.00020448735,0.0001248941,0.00061548135,0.00047306227,0.00057485513,0.0007581514,0.00042762328,0.000534609],"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":[0.000051348154,0.00004301838,0.0006511355,0.000044953467,0.00003394356,5.7290583e-7,0.003763529,0.06442562,0.012574565,0.8939208,0.0004977569,0.023992777],"study_design_scores_gemma":[0.000025838795,0.00038955838,0.00010516312,0.00015642493,0.0000094888255,0.0000038560347,0.0005007188,0.7046347,0.28184244,0.011422211,0.0006802078,0.00022934817],"about_ca_topic_score_codex":0.000024732883,"about_ca_topic_score_gemma":0.0000028973368,"teacher_disagreement_score":0.9859766,"about_ca_system_score_codex":0.00007581721,"about_ca_system_score_gemma":0.000063968604,"threshold_uncertainty_score":0.83387524},"labels":[],"label_agreement":null},{"id":"W2757609746","doi":"10.1609/aaai.v32i1.11775","title":"OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Open Philanthropy Project; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Adversarial system; Generative grammar; Artificial intelligence; Function (biology); Set (abstract data type); Machine learning","score_opus":0.13871062076476812,"score_gpt":0.32905867573710673,"score_spread":0.19034805497233862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2757609746","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":[0.028875975,0.000019015908,0.95364326,0.0021354312,0.0024083264,0.0013101685,0.0000031353331,0.00037407817,0.011230612],"genre_scores_gemma":[0.95145917,0.00021004352,0.044846985,0.00020101767,0.0010630108,0.00006539036,0.000009995584,0.000061250175,0.0020831102],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946806,0.0001629085,0.0015959427,0.0012856486,0.0014260653,0.0008488584],"domain_scores_gemma":[0.99421424,0.00012403956,0.0024411078,0.00077461766,0.0022157247,0.00023028087],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0015566082,0.0007570882,0.0007915881,0.00069817284,0.0010895123,0.001105429,0.0033956107,0.0005023198,0.00014281283],"category_scores_gemma":[0.0027660204,0.0006747153,0.00045246162,0.0010836174,0.0007594664,0.00071306044,0.0048322575,0.0026956056,0.00018947787],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004092481,0.00004081823,0.000059270304,0.00009855376,0.00007909249,8.5668006e-7,0.003590338,0.75167763,0.009525106,0.23333484,0.00009474572,0.0014578057],"study_design_scores_gemma":[0.000064389926,0.0004121511,0.000018788776,0.0009610763,0.000063346204,0.000006433413,0.0007516318,0.8895832,0.08529224,0.022009436,0.0002297254,0.00060758664],"about_ca_topic_score_codex":0.00028476262,"about_ca_topic_score_gemma":0.000006758771,"teacher_disagreement_score":0.9225832,"about_ca_system_score_codex":0.00069591624,"about_ca_system_score_gemma":0.0011371516,"threshold_uncertainty_score":0.9999315},"labels":[],"label_agreement":null},{"id":"W2759254424","doi":"10.1609/aiide.v13i1.12926","title":"Improvised Theatre Alongside Artificial Intelligences","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Improvisation; Conversation; Computer science; Performing arts; Natural (archaeology); Narrative; Artificial intelligence; Visual arts; Linguistics; Psychology; Communication; Art","score_opus":0.05173471714296771,"score_gpt":0.2952074338759871,"score_spread":0.24347271673301937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759254424","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":[0.4748287,0.00004113434,0.35212266,0.013841735,0.0026824323,0.0020845851,0.000031134085,0.00023852734,0.1541291],"genre_scores_gemma":[0.9987412,0.000035604855,0.00037795107,0.00018713943,0.00007793596,0.000030573417,0.000001287221,0.00001579504,0.0005324761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975521,0.000015131596,0.00070728734,0.000661153,0.0006144893,0.00044985756],"domain_scores_gemma":[0.9977978,0.00013048307,0.00090323715,0.00060493883,0.00042263448,0.00014089566],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00029443947,0.00036454637,0.00035297326,0.00013565202,0.0006185722,0.00291808,0.0027720628,0.00008884144,0.000042742435],"category_scores_gemma":[0.00051840895,0.00025975567,0.0001969553,0.00012919401,0.0006118931,0.0024496652,0.001263363,0.00039517402,0.00008021715],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025141408,0.00029568106,0.0014603722,0.00005257308,0.00010916668,0.000004208066,0.003113802,0.0004423248,0.007980988,0.49906546,0.000079074576,0.48714492],"study_design_scores_gemma":[0.00009934875,0.0014572648,0.0010610208,0.00084066024,0.00003613856,0.000024352854,0.005157752,0.21636058,0.66940945,0.104234174,0.000594534,0.0007247318],"about_ca_topic_score_codex":0.000052621454,"about_ca_topic_score_gemma":0.000006895828,"teacher_disagreement_score":0.66142845,"about_ca_system_score_codex":0.000084016334,"about_ca_system_score_gemma":0.00006533966,"threshold_uncertainty_score":0.99998546},"labels":[],"label_agreement":null},{"id":"W2760276144","doi":"10.1609/icaps.v27i1.13803","title":"Analytic Decision Analysis via Symbolic Dynamic Programming for Parameterized Hybrid MDPs","year":2017,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","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":"Parameterized complexity; Mathematical optimization; Computer science; Leverage (statistics); Discretization; Nonlinear programming; Convex optimization; Dynamic programming; Scalability; Piecewise; Optimization problem; Nonlinear system; Mathematics; Regular polygon; Algorithm; Artificial intelligence","score_opus":0.03706048564634457,"score_gpt":0.3302437727257557,"score_spread":0.29318328707941116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2760276144","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":[0.58571804,0.000012641448,0.41257322,0.0005825278,0.0002556452,0.0001931016,0.0000030076385,0.0001885879,0.00047322427],"genre_scores_gemma":[0.9038379,0.000007230429,0.09597579,0.00004386581,0.000016884635,0.000018316683,0.0000049696755,0.000009034948,0.00008599583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984875,0.0000065619397,0.00038861006,0.00039821948,0.00047772427,0.00024142789],"domain_scores_gemma":[0.998258,0.00015595107,0.00077454804,0.00028386043,0.0004627568,0.00006487887],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005826006,0.00018148539,0.00029919096,0.00030701162,0.00050658087,0.0012875793,0.0019785804,0.00006101223,0.00000327082],"category_scores_gemma":[0.00084466586,0.00014139498,0.00015574075,0.00017871108,0.000090161775,0.0004635203,0.00041131896,0.00019116458,0.0000017121544],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005149153,0.00017813343,0.12100202,0.000303105,0.0037018342,0.000010569457,0.0024797274,0.69142044,0.043570213,0.078183465,0.00010960701,0.058525972],"study_design_scores_gemma":[0.0003804905,0.00007175876,0.01134292,0.0003548182,0.000107466236,0.000008801695,0.000058445607,0.98397154,0.0019267453,0.001598872,0.000022985352,0.00015516575],"about_ca_topic_score_codex":0.000013663217,"about_ca_topic_score_gemma":5.8010363e-7,"teacher_disagreement_score":0.31811988,"about_ca_system_score_codex":0.000047325844,"about_ca_system_score_gemma":0.000038824364,"threshold_uncertainty_score":0.9997492},"labels":[],"label_agreement":null},{"id":"W2767354950","doi":"10.1609/aaai.v32i1.11740","title":"Learning With Options That Terminate Off-Policy","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Dilemma; Flexibility (engineering); Computer science; Odds; Decoupling (probability); Set (abstract data type); Quality (philosophy); Task (project management); Reinforcement learning; Mathematical optimization; Artificial intelligence; Economics; Mathematics; Machine learning","score_opus":0.08436074975531656,"score_gpt":0.3127829237718858,"score_spread":0.22842217401656928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767354950","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":[0.1082753,0.000068850095,0.78447723,0.011785535,0.0021351806,0.0023730972,0.000011680162,0.0009096369,0.08996349],"genre_scores_gemma":[0.9850879,0.00019719741,0.011664413,0.0001608974,0.0002458176,0.00006515523,0.000002286085,0.000040088977,0.002536261],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99657613,0.000048335478,0.0007042829,0.0009864842,0.0010588504,0.0006258874],"domain_scores_gemma":[0.99625325,0.00011965679,0.001370828,0.0008168916,0.0012930613,0.00014628434],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073680846,0.0005456244,0.00052180514,0.00041443398,0.00043966572,0.0009923832,0.0050824364,0.0003023357,0.00006177164],"category_scores_gemma":[0.00065817457,0.00039698093,0.00020673072,0.0007827334,0.0007774841,0.00044949754,0.003203654,0.0016097924,0.0001785267],"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":[0.000086273016,0.00013074471,0.0009257648,0.00029123278,0.00010810654,0.0000024939848,0.004523757,0.11448748,0.0019456807,0.8203344,0.00023332701,0.05693074],"study_design_scores_gemma":[0.000048819158,0.00092284055,0.00040179002,0.0022279301,0.00006123115,0.000018127026,0.0006152476,0.759514,0.14358646,0.09104863,0.00068861584,0.00086634356],"about_ca_topic_score_codex":0.00007003221,"about_ca_topic_score_gemma":0.000005577178,"teacher_disagreement_score":0.8768126,"about_ca_system_score_codex":0.00016081869,"about_ca_system_score_gemma":0.00056348904,"threshold_uncertainty_score":0.9998482},"labels":[],"label_agreement":null},{"id":"W2771302359","doi":"10.3389/fnbot.2019.00052","title":"A Novel Model for Arbitration Between Planning and Habitual Control Systems","year":2019,"lang":"en","type":"preprint","venue":"Frontiers in Neurorobotics","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Action selection; Internal model; Reinforcement learning; Task (project management); Control (management); Action (physics); Artificial intelligence; Kinematics; A priori and a posteriori; Machine learning; Engineering","score_opus":0.042683427339276145,"score_gpt":0.26828128658745193,"score_spread":0.22559785924817577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771302359","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":[0.0005373993,0.0003830157,0.9918098,0.00029928546,0.0047959774,0.0018626169,0.00004014834,0.00015100709,0.00012078457],"genre_scores_gemma":[0.50822926,0.000023050135,0.490634,0.0002692247,0.00021027727,0.000078977675,0.00005560265,0.000060094546,0.00043949654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972556,0.00009195405,0.0007589732,0.0009036575,0.00044108508,0.0005486812],"domain_scores_gemma":[0.998016,0.0003139642,0.000531855,0.0008912898,0.0001288704,0.000118044525],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057330687,0.000439637,0.00082131993,0.00037725453,0.00009874116,0.0005628259,0.0011302435,0.00046414128,6.9726426e-8],"category_scores_gemma":[0.00020445442,0.0004928925,0.00011285643,0.00013749884,0.00006978198,0.000308048,0.00065534195,0.00099249,0.0000013552828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014388072,0.00001578972,0.017620979,0.00040139566,0.00005903111,0.000003223899,0.0005984779,0.978142,0.000021488244,0.0016274713,0.0013826384,0.00011310802],"study_design_scores_gemma":[0.0012722133,0.00010793443,0.0014356229,0.00027612282,0.0000661653,0.0000041138937,0.000029473813,0.99559605,0.000004768131,0.00065976137,0.000098236684,0.00044954856],"about_ca_topic_score_codex":0.000009758319,"about_ca_topic_score_gemma":5.506764e-7,"teacher_disagreement_score":0.50769186,"about_ca_system_score_codex":0.00015689989,"about_ca_system_score_gemma":0.00026345378,"threshold_uncertainty_score":0.9997523},"labels":[],"label_agreement":null},{"id":"W2783392051","doi":"10.1609/aaai.v32i1.12095","title":"Planning With Pixels in (Almost) Real Time","year":2018,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"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":"University of Alberta","keywords":"Computer science; Pixel; Artificial intelligence; State (computer science); Computer vision; Machine learning; Algorithm","score_opus":0.07757191859625165,"score_gpt":0.3079997685792846,"score_spread":0.23042784998303298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783392051","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":[0.4573435,0.000034707038,0.35890314,0.0038826196,0.001877028,0.0027400847,0.000011621107,0.0006272962,0.17458001],"genre_scores_gemma":[0.9849361,0.00003463114,0.013827325,0.00009675688,0.00013597046,0.000045964494,0.0000020928974,0.000033441687,0.0008876964],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99654645,0.000035464367,0.0009042252,0.0009723003,0.0009535032,0.0005880751],"domain_scores_gemma":[0.9971122,0.00013842672,0.0010588022,0.00074740173,0.0008363621,0.00010680342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008758117,0.00048851507,0.00057314034,0.0003273028,0.00015693175,0.0005769467,0.0047214846,0.00030140986,0.00007432872],"category_scores_gemma":[0.0003439134,0.00036245873,0.00012500412,0.00072079105,0.00048782167,0.0003766768,0.0024130053,0.0011536097,0.00020622728],"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":[0.0004978377,0.0003570329,0.005956042,0.00058447936,0.00015008924,0.000015855256,0.014921249,0.29104063,0.017318456,0.6516342,0.0008849665,0.016639164],"study_design_scores_gemma":[0.000057198133,0.00065760873,0.00084692106,0.0035509355,0.000027123177,0.000008986933,0.0002936314,0.8190357,0.109047025,0.0656613,0.00006820319,0.00074536394],"about_ca_topic_score_codex":0.000097759854,"about_ca_topic_score_gemma":0.000005166384,"teacher_disagreement_score":0.5859729,"about_ca_system_score_codex":0.00015258523,"about_ca_system_score_gemma":0.0003738673,"threshold_uncertainty_score":0.99988276},"labels":[],"label_agreement":null},{"id":"W2783447922","doi":"10.1109/allerton.2017.8262843","title":"Transition-based versus state-based reward functions for MDPs with Value-at-Risk","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"","keywords":"Markov decision process; Reinforcement learning; Markov process; Function (biology); Bellman equation; Action (physics); Transformation (genetics); Computer science; Markov chain; Mathematical optimization; State (computer science); Markov model; Mathematics; Artificial intelligence; Machine learning; Statistics; Algorithm","score_opus":0.02514385116644622,"score_gpt":0.2594024720053066,"score_spread":0.23425862083886037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783447922","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":[0.0047146454,0.0000034994966,0.9882697,0.0019984597,0.0005518816,0.00040847037,0.000014314098,0.00028073494,0.0037583117],"genre_scores_gemma":[0.7803119,0.0000015908184,0.21549352,0.0004745182,0.00005370679,0.00008227329,0.00003448948,0.000025588795,0.003522436],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986494,0.000043567812,0.00019833361,0.00039442864,0.00036396054,0.00035026346],"domain_scores_gemma":[0.9978032,0.00037746382,0.00022667639,0.0012972173,0.00017138028,0.00012406352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029729,0.00017585936,0.00015502889,0.00008678412,0.0012713354,0.0004120767,0.00081265543,0.000053676136,0.000056915127],"category_scores_gemma":[0.00011822421,0.00014439704,0.00010518248,0.00009436767,0.0001158366,0.00038486344,0.00004904264,0.00012940097,0.000092487324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032751955,0.000026468819,0.00073936116,0.000017430704,0.00003588131,0.000003050876,0.00009780949,0.99512476,0.000027425907,0.0012169937,0.0014203294,0.0009629745],"study_design_scores_gemma":[0.004433372,0.0010220194,0.0015592908,0.000021612108,0.000043561133,5.714902e-7,0.000015073168,0.98475593,0.0014256006,0.00006583086,0.006408793,0.000248352],"about_ca_topic_score_codex":0.00014331788,"about_ca_topic_score_gemma":0.00010704206,"teacher_disagreement_score":0.7755972,"about_ca_system_score_codex":0.0001132506,"about_ca_system_score_gemma":0.00023826079,"threshold_uncertainty_score":0.9778213},"labels":[],"label_agreement":null},{"id":"W2784831250","doi":"10.1109/icra.2018.8462977","title":"Cross-Domain Transfer in Reinforcement Learning Using Target Apprentice","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"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":"Air Force Office of Scientific Research; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Transfer of learning; Task (project management); Domain (mathematical analysis); Sample (material); Artificial intelligence; Apprenticeship; Negative transfer; Sample complexity; Reuse; Multi-task learning; Machine learning; Policy learning; Engineering; Mathematics","score_opus":0.033226289462589445,"score_gpt":0.2995726163778216,"score_spread":0.2663463269152322,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784831250","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":[0.033904422,0.00004812312,0.94402236,0.00007964824,0.0014520492,0.00063853204,5.2526644e-7,0.00038281098,0.019471545],"genre_scores_gemma":[0.70756775,0.000026686364,0.28602722,0.00021909726,0.00023954856,0.000038487626,0.000040367413,0.00006034655,0.0057804706],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955481,0.00026003382,0.0011158485,0.0011875371,0.00096449204,0.00092395063],"domain_scores_gemma":[0.99786246,0.00011189919,0.00024204036,0.0013994507,0.00021503544,0.0001691033],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014667035,0.00058147317,0.00058528053,0.00049300486,0.00024105598,0.0010977188,0.0024837926,0.00048548076,0.00057903817],"category_scores_gemma":[0.00011379834,0.00059901824,0.00019716102,0.00048397473,0.00017416767,0.00062648865,0.0028427537,0.0016779774,0.00016353834],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011618309,0.000022061418,0.003940451,0.00015822158,0.00004490356,0.000020350013,0.0016236937,0.9885763,0.00017561675,0.005262335,0.000045884666,0.000118569296],"study_design_scores_gemma":[0.00060066645,0.00011597533,0.00047243133,0.00026614845,0.000012070791,0.0000074990694,0.00004611232,0.9929179,0.00092327606,0.0009025936,0.0030477294,0.00068759994],"about_ca_topic_score_codex":0.00021630964,"about_ca_topic_score_gemma":0.0000068964114,"teacher_disagreement_score":0.6736634,"about_ca_system_score_codex":0.00042029584,"about_ca_system_score_gemma":0.00034139748,"threshold_uncertainty_score":0.99993926},"labels":[],"label_agreement":null},{"id":"W2785529341","doi":"10.1609/aaai.v32i1.12115","title":"Learning Robust Options","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Robustness (evolution); Reinforcement learning; Computer science; Artificial intelligence; Robust control; Mathematical optimization; Machine learning; Convergence (economics); Artificial neural network; Mathematics; Nonlinear system","score_opus":0.09360344398562903,"score_gpt":0.2975536324951889,"score_spread":0.20395018850955987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785529341","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":[0.033042174,0.000009361038,0.8841439,0.0036911722,0.0009435476,0.00037958624,6.8508535e-7,0.00029143158,0.07749815],"genre_scores_gemma":[0.9830374,0.000021750846,0.014765478,0.0001603324,0.00014188081,0.000011519464,2.4886117e-7,0.000012404492,0.0018489453],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99816865,0.00002197638,0.00047133994,0.00042218855,0.0005373764,0.00037848522],"domain_scores_gemma":[0.9981746,0.00008199643,0.0003903506,0.0003300728,0.00093786506,0.00008510109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005351925,0.00019435275,0.00019004261,0.00013934128,0.0004487199,0.00035655362,0.0023496705,0.00008458081,0.00014748459],"category_scores_gemma":[0.00069240987,0.00015094013,0.00010200113,0.0008133183,0.00046669465,0.00048161563,0.0005800494,0.00043004265,0.0004858063],"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":[0.000013918204,0.000039119885,0.0002612524,0.000013209303,0.000011797434,1.8431498e-7,0.0012944478,0.02105871,0.010646724,0.9502605,0.0001778029,0.016222313],"study_design_scores_gemma":[0.000021382968,0.0005521205,0.00022085007,0.0001644001,0.000010145202,0.000005008787,0.0004898432,0.74445695,0.2190859,0.034125376,0.0006282575,0.0002397504],"about_ca_topic_score_codex":0.000015999636,"about_ca_topic_score_gemma":0.0000027949372,"teacher_disagreement_score":0.9499953,"about_ca_system_score_codex":0.000046063004,"about_ca_system_score_gemma":0.00008280168,"threshold_uncertainty_score":0.6244219},"labels":[],"label_agreement":null},{"id":"W2785940258","doi":"","title":"An inference-based policy gradient method for learning options","year":2018,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Inference; Abstraction; Scalability; Artificial intelligence; Machine learning; A priori and a posteriori; Formalism (music); Differentiable function","score_opus":0.025741822831532517,"score_gpt":0.29847202001778317,"score_spread":0.27273019718625063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785940258","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":[0.007715416,0.0000044745725,0.9885425,0.0010665623,0.00015745814,0.00022377713,0.000005874993,0.00019164447,0.0020922807],"genre_scores_gemma":[0.5074362,0.0000025521463,0.4912693,0.00012996927,0.00007372131,5.556398e-7,0.000017783806,0.000008923055,0.0010609736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871373,0.0001609712,0.00014452424,0.0003759705,0.00026265465,0.00034215857],"domain_scores_gemma":[0.9984515,0.00019928771,0.0002224922,0.00058834895,0.00037977504,0.00015862842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003776441,0.00014734009,0.00021210781,0.00039851718,0.0005637829,0.000083336425,0.0011611674,0.000088418485,0.000065985056],"category_scores_gemma":[0.0001120574,0.00018176797,0.00012642705,0.0005450328,0.00017771444,0.00064059265,0.00024239259,0.00015748777,0.000041680083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000114169714,0.00020527877,0.0042772,0.00013950714,0.00012483192,0.0000134630245,0.015372748,0.71709067,0.0040728403,0.17050041,0.0009972716,0.087091625],"study_design_scores_gemma":[0.00080457726,0.0012442927,0.0039549633,0.0000466656,0.000023798419,0.0000022020683,0.00077938393,0.97597915,0.00040182483,0.00061209616,0.01591606,0.00023499555],"about_ca_topic_score_codex":0.0003557699,"about_ca_topic_score_gemma":0.000054448567,"teacher_disagreement_score":0.4997208,"about_ca_system_score_codex":0.00011531178,"about_ca_system_score_gemma":0.00024926828,"threshold_uncertainty_score":0.7412283},"labels":[],"label_agreement":null},{"id":"W2785948534","doi":"","title":"NerveNet: Learning Structured Policy with Graph Neural Networks","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":155,"is_retracted":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; Concatenation (mathematics); Computer science; Transfer of learning; Artificial intelligence; Graph; Benchmarking; Machine learning; Artificial neural network; Control (management); Theoretical computer science; Mathematics","score_opus":0.031554453052495206,"score_gpt":0.32419013458969764,"score_spread":0.29263568153720243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2785948534","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":[0.017860444,0.0000063233006,0.9243043,0.0035263484,0.0006315684,0.0001796455,0.0000010101314,0.00044095988,0.0530494],"genre_scores_gemma":[0.9871295,0.000015819818,0.005333061,0.0003050997,0.0005668472,0.00002630485,0.000051912102,0.000026355778,0.0065451143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997707,0.00022551756,0.00034000125,0.00059091055,0.0007317698,0.00040480145],"domain_scores_gemma":[0.998197,0.00020114517,0.0003335754,0.00045617597,0.00067256315,0.00013951343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019919102,0.00024478778,0.00017438391,0.00047633259,0.000558124,0.000728846,0.0011904512,0.00008664132,0.0003598428],"category_scores_gemma":[0.00044200965,0.00022299857,0.00008436919,0.00073660066,0.00023033726,0.0006319091,0.00026240692,0.00078069494,0.00009284297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030559444,0.000014665001,0.015172842,0.0000017317911,0.00006474299,0.000011689906,0.0009398565,0.86299914,0.00015767121,0.11343006,0.00010227691,0.00707478],"study_design_scores_gemma":[0.00046802318,0.0005168562,0.018056551,0.000040605522,0.000007939104,0.000034679146,0.0002290695,0.97767574,0.00012799885,0.0009978125,0.0015911194,0.00025362772],"about_ca_topic_score_codex":0.00017660244,"about_ca_topic_score_gemma":0.000030029425,"teacher_disagreement_score":0.96926904,"about_ca_system_score_codex":0.00009306435,"about_ca_system_score_gemma":0.00013928994,"threshold_uncertainty_score":0.9093618},"labels":[],"label_agreement":null},{"id":"W2786478526","doi":"","title":"Adversarial Policy Gradient for Alternating Markov Games","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Artificial neural network; Computer science; Markov decision process; Markov chain; Gradient descent; Mathematical optimization; Temporal difference learning; Artificial intelligence; Markov process; Machine learning; Mathematics; Statistics","score_opus":0.05030579220343445,"score_gpt":0.3677090667664834,"score_spread":0.31740327456304895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786478526","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":[0.0063223206,0.0000022429256,0.8893006,0.007155095,0.0017437128,0.00028503055,0.0000054930897,0.00025105663,0.09493446],"genre_scores_gemma":[0.9567552,0.000013554368,0.029750917,0.00036565002,0.0011780227,0.00008053984,0.000047764443,0.000018303821,0.011790022],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981179,0.00009509576,0.00036258425,0.00051870506,0.00057465065,0.00033103404],"domain_scores_gemma":[0.998107,0.0003809718,0.00029164992,0.00039683378,0.00072130834,0.000102228165],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030480872,0.00017331747,0.00013928818,0.00040933563,0.00040466443,0.0005135774,0.0011723143,0.000058806923,0.00020703652],"category_scores_gemma":[0.0017395058,0.00018083466,0.00011207079,0.00028396712,0.00012945442,0.0005105786,0.00026384267,0.00026242985,0.00019739395],"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":[0.000055874763,0.00005264203,0.003097879,0.000006553353,0.000117819975,0.000005023688,0.0030551874,0.09530484,0.0011727737,0.8742134,0.0016225069,0.021295518],"study_design_scores_gemma":[0.00077692594,0.00037732528,0.0026122169,0.000055243538,0.000007716234,0.000010152297,0.00026141544,0.9709676,0.0008990321,0.0061063445,0.017695343,0.00023068441],"about_ca_topic_score_codex":0.00013709645,"about_ca_topic_score_gemma":0.0000092692735,"teacher_disagreement_score":0.9504329,"about_ca_system_score_codex":0.00015519776,"about_ca_system_score_gemma":0.00019883689,"threshold_uncertainty_score":0.7374223},"labels":[],"label_agreement":null},{"id":"W2787477569","doi":"10.1609/aaai.v32i1.11594","title":"PAC Reinforcement Learning With an Imperfect Model","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"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":"McGill University","keywords":"Reinforcement learning; Fidelity; Computer science; Reduction (mathematics); Action (physics); Simple (philosophy); Artificial intelligence; Sample (material); Transfer of learning; Imperfect; Sample complexity; State space; Polynomial; Machine learning; Mathematics","score_opus":0.0664821800134268,"score_gpt":0.2958776474047536,"score_spread":0.22939546739132677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2787477569","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":[0.07177303,0.0000027333674,0.8979242,0.00075180485,0.00018853693,0.0003874348,3.1287902e-7,0.00019169992,0.028780257],"genre_scores_gemma":[0.9857633,0.000011830829,0.012814465,0.00021879829,0.00008696041,0.000019117806,5.425423e-7,0.000020128065,0.0010648469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762726,0.000022349252,0.00051016465,0.00055790367,0.00078634947,0.0004959923],"domain_scores_gemma":[0.99784404,0.00005032175,0.00048475323,0.0004785731,0.0010055223,0.00013676153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006178284,0.00028589682,0.00025426605,0.00014233761,0.00043425127,0.0004012135,0.002322532,0.000088751076,0.00006357094],"category_scores_gemma":[0.0002529796,0.00019589302,0.00007799167,0.0006369992,0.00046897755,0.0008655668,0.0004624169,0.0004461812,0.000113566486],"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":[0.00010915814,0.000046621455,0.0002238433,0.000021494923,0.000019203962,3.2551537e-7,0.0025828872,0.33014968,0.013248186,0.6426756,0.000040552586,0.010882449],"study_design_scores_gemma":[0.00003037527,0.001582703,0.000026090662,0.00012568457,0.000010270008,0.0000037391187,0.000281171,0.7899683,0.19710149,0.0106105115,0.0000431454,0.00021650002],"about_ca_topic_score_codex":0.000026475056,"about_ca_topic_score_gemma":0.0000061474884,"teacher_disagreement_score":0.91399026,"about_ca_system_score_codex":0.00006588811,"about_ca_system_score_gemma":0.00016103178,"threshold_uncertainty_score":0.79882854},"labels":[],"label_agreement":null},{"id":"W2788842776","doi":"10.3389/frobt.2018.00079","title":"Reactive Reinforcement Learning in Asynchronous Environments","year":2018,"lang":"en","type":"article","venue":"Frontiers in Robotics and AI","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Canada Research Chairs; DeepMind; Canada Foundation for Innovation; Alberta Machine Intelligence Institute","keywords":"Reinforcement learning; Computer science; Asynchronous communication; Markov decision process; Artificial intelligence; Distributed computing; Machine learning; Markov process; Computer network","score_opus":0.00789269640831681,"score_gpt":0.22459539567674328,"score_spread":0.21670269926842647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788842776","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":[0.0024645766,0.00009572272,0.99353224,0.0004525622,0.0006673289,0.0001837558,8.817147e-8,0.000035395246,0.002568307],"genre_scores_gemma":[0.8924298,0.00012226665,0.1059134,0.0003775616,0.000063716456,0.000008556805,0.0000036960007,0.000015031217,0.0010659153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850875,0.0000668348,0.0003338771,0.0003893247,0.00026671958,0.00043451964],"domain_scores_gemma":[0.99943256,0.000030970237,0.00011766524,0.00031739654,0.00001710082,0.000084293286],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003236688,0.00017752832,0.00022950929,0.0002652456,0.000112495196,0.00011336503,0.00039759363,0.00009584072,0.000007251619],"category_scores_gemma":[0.00005668733,0.00018642617,0.00002723341,0.00028942354,0.00014289477,0.00041042248,0.0003228846,0.0003931811,0.000022367058],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008892736,0.00002242671,0.060958885,0.000007483456,0.000012912635,0.000017208698,0.0011318926,0.9295753,0.00004820316,0.0029150823,0.0003804861,0.004921208],"study_design_scores_gemma":[0.0006369367,0.00029020204,0.012246973,0.000057014877,0.000004208782,0.0000036336255,0.00014805103,0.9815795,0.00019314396,0.00071432145,0.003889509,0.00023649866],"about_ca_topic_score_codex":0.00002487938,"about_ca_topic_score_gemma":0.0000043543428,"teacher_disagreement_score":0.8899653,"about_ca_system_score_codex":0.00021265938,"about_ca_system_score_gemma":0.000042591804,"threshold_uncertainty_score":0.76022387},"labels":[],"label_agreement":null},{"id":"W2791039059","doi":"10.1007/978-3-319-77553-1_9","title":"Scaling Tangled Program Graphs to Visual Reinforcement Learning in ViZDoom","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Frame (networking); Process (computing); Code (set theory); Pixel; Graph; Machine learning; Theoretical computer science; Programming language","score_opus":0.01606880271556596,"score_gpt":0.27940287635503464,"score_spread":0.2633340736394687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791039059","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":[0.00052701234,0.00006857871,0.99166864,0.00033286004,0.0016511311,0.0013032793,2.8250972e-7,0.0005149077,0.003933328],"genre_scores_gemma":[0.37545514,0.000032289496,0.6200158,0.0019241554,0.00056381215,0.00007292929,0.000013523907,0.000100645986,0.001821696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9934533,0.0000759116,0.0010953454,0.0020577183,0.0018943448,0.0014233433],"domain_scores_gemma":[0.9969941,0.00046677163,0.0004743441,0.0013312083,0.0003742391,0.0003593373],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018079143,0.00080245914,0.0007600332,0.0022533839,0.00037574724,0.0011652082,0.004029999,0.00042813708,0.00006819616],"category_scores_gemma":[0.00039726138,0.0007939676,0.0001802622,0.0019443167,0.0005908401,0.0007252152,0.0028243603,0.0015645768,0.00022840315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008814852,0.000021200898,0.00014535457,0.000028695324,0.000009050403,0.000058428184,0.0013750596,0.760992,0.000052384985,0.0029051816,0.000013336374,0.23439051],"study_design_scores_gemma":[0.00039899984,0.0011879912,0.00012356103,0.0008740992,0.0000069062644,0.00002294433,8.7734475e-7,0.98320544,0.00045951147,0.009454544,0.003327713,0.0009374351],"about_ca_topic_score_codex":0.000033937944,"about_ca_topic_score_gemma":0.00005289411,"teacher_disagreement_score":0.37492815,"about_ca_system_score_codex":0.000708014,"about_ca_system_score_gemma":0.00057207426,"threshold_uncertainty_score":0.9998717},"labels":[],"label_agreement":null},{"id":"W2791696004","doi":"10.1109/cig.2018.8490448","title":"Automated Curriculum Learning by Rewarding Temporally Rare Events","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Reinforcement learning; Computer science; Event (particle physics); Function (biology); Simple (philosophy); Artificial intelligence; Human–computer interaction; Machine learning; Cognitive psychology; Psychology","score_opus":0.014086455632860425,"score_gpt":0.2715538308190012,"score_spread":0.25746737518614077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791696004","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":[0.0053275214,0.00008980316,0.96884197,0.00039524463,0.002216796,0.00046650894,0.000001930111,0.006043588,0.016616618],"genre_scores_gemma":[0.760808,0.000083077866,0.20905387,0.0003973698,0.00038855898,0.00006648479,0.00031425303,0.00011642598,0.02877197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961724,0.0002941829,0.00072707795,0.0011592857,0.0009509927,0.00069600873],"domain_scores_gemma":[0.997296,0.00007420982,0.00071036624,0.0013705057,0.0003403273,0.00020862841],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008131469,0.0005406288,0.00052499876,0.0002387326,0.0003274167,0.0006589564,0.00302319,0.00048678025,0.00014541844],"category_scores_gemma":[0.00030815814,0.0005122465,0.00022292619,0.0004004455,0.00005729552,0.00046982907,0.005486461,0.0013503565,0.0007173102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002467612,0.00005218138,0.023080412,0.00020449115,0.00017269992,0.00002730727,0.0005324146,0.79265195,0.00010382318,0.0006938825,0.1815672,0.0009111362],"study_design_scores_gemma":[0.00022342459,0.00010582276,0.0003706137,0.00035777947,0.000016671675,0.00000947428,0.00003323818,0.98240733,0.0001950173,0.00021672518,0.01541492,0.0006489964],"about_ca_topic_score_codex":0.00014521352,"about_ca_topic_score_gemma":0.000001020307,"teacher_disagreement_score":0.7597881,"about_ca_system_score_codex":0.0002339195,"about_ca_system_score_gemma":0.00024085255,"threshold_uncertainty_score":0.9997329},"labels":[],"label_agreement":null},{"id":"W2794940174","doi":"10.1609/aimag.v39i1.2780","title":"Constructing Temporal Abstractions Autonomously in Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"AI Magazine","topic":"Reinforcement Learning in Robotics","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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Abstraction; Artificial intelligence; Thread (computing); Architecture; Programming language","score_opus":0.015208194459727754,"score_gpt":0.2693107594008761,"score_spread":0.25410256494114836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794940174","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":[0.007318405,0.000007668798,0.90833235,0.0013692575,0.00058947713,0.00016070079,1.3912779e-7,0.0003065499,0.08191546],"genre_scores_gemma":[0.962129,0.0000027489955,0.031060074,0.00043123803,0.0001531367,0.000008865896,0.000008388457,0.000013159254,0.0061933696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998492,0.000047079426,0.0004477561,0.0003272219,0.0002700034,0.00041592846],"domain_scores_gemma":[0.9991171,0.00007608535,0.00019212469,0.00041115296,0.000120603334,0.00008294012],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003928268,0.00015804972,0.00016884049,0.00022398701,0.00018781771,0.00023388623,0.0004886997,0.00006733733,0.00024722336],"category_scores_gemma":[0.00012524016,0.00016702156,0.000037690166,0.00041509885,0.00012089899,0.0007095125,0.00026556794,0.00044722864,0.0014265652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000116191395,0.000036138863,0.059361268,0.000025468335,0.000033942833,0.000056803732,0.0012220143,0.829207,0.0010608287,0.083674066,0.002598504,0.022712357],"study_design_scores_gemma":[0.000554037,0.0003467412,0.005861467,0.000042764987,0.000004785039,0.00005264407,0.000098647004,0.9375591,0.00051799684,0.00025330327,0.05442018,0.00028829856],"about_ca_topic_score_codex":0.00007467556,"about_ca_topic_score_gemma":0.000056683188,"teacher_disagreement_score":0.9548106,"about_ca_system_score_codex":0.00017287658,"about_ca_system_score_gemma":0.00011398427,"threshold_uncertainty_score":0.99935097},"labels":[],"label_agreement":null},{"id":"W2794958591","doi":"10.1109/iros.2018.8594242","title":"Accelerating Learning in Constructive Predictive Frameworks with the Successor Representation","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Constructive; Successor cardinal; Reinforcement learning; Interdependence; Representation (politics); Machine learning; Process (computing); Task (project management); Robot; Grid; Field (mathematics); Robotics; Engineering","score_opus":0.024046678949333006,"score_gpt":0.2852600510444348,"score_spread":0.2612133720951018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794958591","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":[0.025714172,0.00001734674,0.9496009,0.0012740981,0.00042103152,0.0007262895,5.0575613e-7,0.00030395904,0.021941697],"genre_scores_gemma":[0.894711,0.0000127674,0.1039576,0.00024292675,0.00019505677,0.000111681744,0.000013637157,0.000023300587,0.00073202304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736416,0.000383889,0.0004036519,0.00083717844,0.0006294978,0.00038162188],"domain_scores_gemma":[0.9974059,0.000670151,0.0005956734,0.0009136249,0.0003603487,0.000054340886],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0006161292,0.0003100227,0.00031367468,0.00018022828,0.00028318795,0.0009361591,0.0015787357,0.0004667176,0.00004646548],"category_scores_gemma":[0.000377029,0.00020684616,0.000060930466,0.0005211548,0.00029062,0.0005481516,0.0021259093,0.00365495,0.000018689781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018689114,0.000007316689,0.0287441,0.00001742241,0.00006054303,0.000008101554,0.0042858063,0.9603757,0.000004729995,0.004795572,0.00015319069,0.0015288149],"study_design_scores_gemma":[0.00025980338,0.00016341836,0.012905671,0.00025997244,0.000015879421,0.000008996429,0.0010555787,0.9834116,0.00023384202,0.0013438637,0.000060652317,0.0002807081],"about_ca_topic_score_codex":0.00017852079,"about_ca_topic_score_gemma":0.00003988631,"teacher_disagreement_score":0.86899686,"about_ca_system_score_codex":0.00015709118,"about_ca_system_score_gemma":0.00027087887,"threshold_uncertainty_score":0.99864364},"labels":[],"label_agreement":null},{"id":"W2796085096","doi":"10.1007/978-3-319-89656-4_6","title":"Advice-Based Exploration in Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Social Innovation; Vector Institute; University of Toronto","funders":"","keywords":"Reinforcement learning; Satisficing; Computer science; Advice (programming); Robustness (evolution); Convergence (economics); Grid; Artificial intelligence; Operations research; Mathematical optimization; Engineering","score_opus":0.026662711587482006,"score_gpt":0.2551386000725917,"score_spread":0.2284758884851097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796085096","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":[0.000026803642,0.00004952014,0.9934032,0.00059279305,0.00091305573,0.0005876628,4.459913e-7,0.00035259075,0.0040739155],"genre_scores_gemma":[0.3560344,0.0000152556795,0.63974243,0.0024644807,0.00030891437,0.000036428908,0.000031550175,0.00007093279,0.0012955691],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947171,0.000074107236,0.00094570883,0.0016374956,0.0016936542,0.0009319216],"domain_scores_gemma":[0.9968217,0.0004176736,0.0006002897,0.0015807811,0.0003931437,0.00018642927],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015603651,0.0006864014,0.0005745076,0.0017618391,0.00031278873,0.0006964096,0.003207467,0.00041524787,0.000056932924],"category_scores_gemma":[0.00021225029,0.0006965353,0.00014453923,0.0009764398,0.0005841382,0.001174495,0.00083006633,0.0013288714,0.00012692196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011609889,0.000013451795,0.000052141197,0.000045057004,0.0000036103947,0.00002587275,0.0006424331,0.9718223,0.00003252987,0.0021325212,0.00001672147,0.025201725],"study_design_scores_gemma":[0.0006146638,0.0004171708,0.0000103323255,0.0006543874,0.0000058524574,0.000002583605,2.8622614e-7,0.98597425,0.0008281986,0.010119856,0.0006485623,0.0007238467],"about_ca_topic_score_codex":0.000019463638,"about_ca_topic_score_gemma":0.000053024578,"teacher_disagreement_score":0.3560076,"about_ca_system_score_codex":0.0008733012,"about_ca_system_score_gemma":0.0014467106,"threshold_uncertainty_score":0.99954855},"labels":[],"label_agreement":null},{"id":"W2796389682","doi":"10.1109/cdc.2018.8619180","title":"Renewal Monte Carlo: Renewal Theory Based Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Markov decision process; Monte Carlo method; Estimator; Computer science; Reinforcement learning; Mathematical optimization; Importance sampling; Variance (accounting); Key (lock); Markov process; Mathematics; Artificial intelligence; Statistics; Economics","score_opus":0.0209271306621518,"score_gpt":0.2568127963650557,"score_spread":0.23588566570290392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796389682","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":[0.0006479621,0.00006895103,0.88241905,0.00048495264,0.0022964822,0.0005729146,9.323588e-7,0.0011950763,0.11231367],"genre_scores_gemma":[0.780091,0.000054258075,0.12414268,0.0011543152,0.0007145887,0.00011117734,0.00006371665,0.000104696286,0.093563564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99448186,0.0005650746,0.0010499663,0.0014956256,0.0014004133,0.0010070795],"domain_scores_gemma":[0.9951114,0.0003746675,0.0008181372,0.0029287168,0.0004465787,0.0003204693],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020724256,0.00080347894,0.0006877814,0.00044953593,0.0004151678,0.00089077756,0.003810432,0.00061707577,0.0005407925],"category_scores_gemma":[0.00047789997,0.00075647887,0.00042586823,0.0003582847,0.00020760004,0.00030294628,0.0052020974,0.0015847377,0.00038619677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029681434,0.000016865517,0.00027869947,0.00009283238,0.00010325987,0.0000222967,0.0004737737,0.97715026,0.00003123613,0.018777564,0.0019165603,0.0011069431],"study_design_scores_gemma":[0.00054371683,0.0003753787,0.000055931647,0.00028123305,0.000047871872,0.000005084078,0.00003139045,0.98494196,0.0010453042,0.0031772093,0.008586192,0.0009087511],"about_ca_topic_score_codex":0.00034863423,"about_ca_topic_score_gemma":0.000017700588,"teacher_disagreement_score":0.779443,"about_ca_system_score_codex":0.0004118427,"about_ca_system_score_gemma":0.0007656166,"threshold_uncertainty_score":0.9994886},"labels":[],"label_agreement":null},{"id":"W2800222226","doi":"10.7939/r3cw3c","title":"A general framework for reducing variance in agent evaluation","year":2010,"lang":"en","type":"article","venue":"University of Alberta Library","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Variance (accounting); Computer science; Risk analysis (engineering); Business","score_opus":0.01671819584397845,"score_gpt":0.2321567703057499,"score_spread":0.21543857446177145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2800222226","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":[0.14123172,0.0000074104664,0.8504765,0.0014666934,0.0004338412,0.00024141314,3.0548338e-7,0.00002839194,0.0061137406],"genre_scores_gemma":[0.36519235,0.0000056201147,0.63108456,0.00009973229,0.00004343355,4.2778495e-7,0.000009661448,0.000005704277,0.0035584702],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993781,0.000037747905,0.00009683194,0.00019866295,0.00015123341,0.0001374191],"domain_scores_gemma":[0.9992855,0.00021098397,0.00009795797,0.00033617544,0.000026970192,0.000042408283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014892383,0.000062072846,0.000090601054,0.000102724225,0.000063311876,0.00003278918,0.000614404,0.00007962764,0.00014560971],"category_scores_gemma":[0.000113189824,0.000076800774,0.000043635697,0.00021768612,0.000032473115,0.00096270634,0.00018650775,0.00015992681,0.000009063375],"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":[0.000040774165,0.00006487267,0.007965283,0.000040599676,0.000027360375,0.0000051605098,0.010371456,0.3132281,0.00080975343,0.6571007,0.0028544045,0.007491557],"study_design_scores_gemma":[0.0004147875,0.000051105402,0.0069337185,0.000043111355,0.00000783114,0.0000010773136,0.00005564419,0.97751397,0.0004739488,0.0065212627,0.00787233,0.00011122035],"about_ca_topic_score_codex":0.00019810343,"about_ca_topic_score_gemma":0.000025874293,"teacher_disagreement_score":0.66428584,"about_ca_system_score_codex":0.000015263882,"about_ca_system_score_gemma":0.00013426118,"threshold_uncertainty_score":0.31318447},"labels":[],"label_agreement":null},{"id":"W2804948070","doi":"","title":"Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":129,"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; Task (project management); Decomposition; Artificial intelligence; Human–computer interaction; Engineering","score_opus":0.09333430035172953,"score_gpt":0.3548435333796292,"score_spread":0.2615092330278997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804948070","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":[0.03878467,0.000012548217,0.95384485,0.0012168662,0.00049599103,0.00027133746,0.0000021579765,0.00011871526,0.0052528414],"genre_scores_gemma":[0.9404784,0.000034592715,0.05795851,0.00016528023,0.00020597452,0.00002163337,0.00009358234,0.000020318752,0.0010216933],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981607,0.00013553664,0.00045957786,0.0005091034,0.00043704073,0.0002979974],"domain_scores_gemma":[0.99887276,0.00017221333,0.00034129847,0.00021517728,0.00032831493,0.00007024964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005974613,0.000226202,0.00020009812,0.00041874283,0.00030538815,0.0003731153,0.0005681012,0.00008287372,0.00008011689],"category_scores_gemma":[0.00033045703,0.0002333267,0.000038121503,0.000201728,0.00007441393,0.00053680385,0.00023015607,0.0004673228,0.000032550615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012529475,0.00002815578,0.010549135,0.000019108704,0.000036666814,0.000004320693,0.0008235468,0.67962855,0.013811333,0.2791476,0.00002038995,0.015805937],"study_design_scores_gemma":[0.0008115113,0.00048975146,0.0057551907,0.00013011144,0.0000060882107,0.000011919759,0.000037893577,0.98768985,0.0006453297,0.003197852,0.0009762649,0.0002482276],"about_ca_topic_score_codex":0.00021625607,"about_ca_topic_score_gemma":0.00003057971,"teacher_disagreement_score":0.90169376,"about_ca_system_score_codex":0.00018860296,"about_ca_system_score_gemma":0.000054382894,"threshold_uncertainty_score":0.95147866},"labels":[],"label_agreement":null},{"id":"W2807787719","doi":"10.65109/mhju3374","title":"Leveraging Observational Learning for Exploration in Bandits","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Reinforcement learning; Imitation; Observational learning; Observational study; Function (biology); Artificial intelligence; Multi-agent system; Intelligent agent; Machine learning; Cloning (programming); Psychology; Mathematics","score_opus":0.13077818732367666,"score_gpt":0.3125012498775136,"score_spread":0.18172306255383694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807787719","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":[0.0055969846,0.0000023638727,0.98950136,0.000898402,0.00024181274,0.00012336212,2.2717893e-8,0.00010329894,0.0035323843],"genre_scores_gemma":[0.84057367,0.0000013228247,0.15609711,0.00033580163,0.0001266887,0.000020233567,0.0000072013268,0.000005092038,0.002832891],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933356,0.000024056424,0.00015881215,0.00017116177,0.00015240679,0.00016000797],"domain_scores_gemma":[0.9995775,0.000116582465,0.000052693864,0.00012502575,0.0001067048,0.000021500518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119211,0.00005723472,0.00005823082,0.00008506559,0.0001173253,0.000112263035,0.00023814639,0.000025950296,0.000026196802],"category_scores_gemma":[0.00016757079,0.000056673307,0.000017836495,0.00022054493,0.000015141131,0.00089824054,0.00006914352,0.000068456226,0.000052397165],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003791095,0.000006795259,0.010255445,0.0000060404227,0.0000032760806,4.3405626e-7,0.0015519107,0.91966885,0.00025614124,0.06271223,0.00078681385,0.004748294],"study_design_scores_gemma":[0.00023712846,0.00008242823,0.0070937183,0.0000106096195,5.4877773e-7,5.03092e-7,0.00004543056,0.9815735,0.0007434201,0.0016593869,0.008475518,0.00007781368],"about_ca_topic_score_codex":0.000006945236,"about_ca_topic_score_gemma":0.0000037246816,"teacher_disagreement_score":0.8349767,"about_ca_system_score_codex":0.00003869198,"about_ca_system_score_gemma":0.00003793326,"threshold_uncertainty_score":0.23110703},"labels":[],"label_agreement":null},{"id":"W2808117931","doi":"10.65109/ohiq4340","title":"Faster Policy Adaptation in Environments with Exogeneity: A State Augmentation Approach","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Kernel (algebra); State (computer science); Embedding; Subspace topology; Variable (mathematics); State space; Function (biology); Q-learning; Variance (accounting); Artificial intelligence; Algorithm; Mathematics","score_opus":0.022305160159295453,"score_gpt":0.24347652072051407,"score_spread":0.2211713605612186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808117931","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":[0.027399117,0.0000015294702,0.9615623,0.00013764,0.000032623793,0.000190743,1.7293381e-7,0.000041993524,0.010633901],"genre_scores_gemma":[0.8206172,0.0000031883596,0.17568417,0.00035679663,0.00003169376,0.00001496044,0.0000053794006,0.000007481749,0.0032791528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901736,0.000048570877,0.00016589295,0.00025461512,0.0002984756,0.00021506163],"domain_scores_gemma":[0.9995673,0.000013408461,0.00007785548,0.0002816197,0.0000149451525,0.000044905482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014331829,0.0000978328,0.00007360995,0.00017199144,0.000051100895,0.00009976905,0.00026871255,0.000023456661,0.000014039572],"category_scores_gemma":[0.0000073908036,0.0000805563,0.000011185862,0.00033510185,0.00005170211,0.0005716097,0.0000999246,0.00005844949,0.00011387475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027258751,0.00006525649,0.0065343454,0.000008715976,0.000019212384,0.0000030084043,0.008119457,0.9522208,0.0007366533,0.006983546,0.000045066623,0.02523669],"study_design_scores_gemma":[0.00061345095,0.00025465904,0.015620179,0.0000071415743,0.0000018924377,0.0000038044086,0.00016140954,0.98111606,0.0014502452,0.00014359868,0.0004953763,0.00013220533],"about_ca_topic_score_codex":0.00013119038,"about_ca_topic_score_gemma":0.00003222259,"teacher_disagreement_score":0.7932181,"about_ca_system_score_codex":0.00012329812,"about_ca_system_score_gemma":0.000048570702,"threshold_uncertainty_score":0.32849908},"labels":[],"label_agreement":null},{"id":"W2808315817","doi":"10.65109/ntef7045","title":"Eligibility Traces for Options","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Backup; Reinforcement learning; Abstraction; Sampling (signal processing); Tree (set theory); Machine learning; Database","score_opus":0.0352984014728696,"score_gpt":0.33755489885714995,"score_spread":0.30225649738428034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808315817","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":[0.0017211159,0.000007347782,0.980527,0.0007677796,0.00027253578,0.00013671817,2.5316243e-7,0.00018760473,0.016379688],"genre_scores_gemma":[0.49338192,0.000002761111,0.5016931,0.00030591022,0.000104325314,0.000012660994,7.964735e-7,0.0000029889254,0.004495546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999474,0.000011028466,0.0001079872,0.00016944211,0.00009395602,0.00014358944],"domain_scores_gemma":[0.99938,0.00008123259,0.000028180782,0.00037098568,0.000103526385,0.000036091664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021864957,0.000046578854,0.000050040413,0.000027144213,0.00012507093,0.00009503324,0.00042437768,0.000023031957,0.000051776085],"category_scores_gemma":[0.00007947283,0.000038726248,0.00003354401,0.00011264272,0.000049810937,0.00024165811,0.000074885895,0.000028538705,0.00015454281],"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":[0.0000047955905,0.00003811213,0.0011522674,0.000014293407,0.00001662347,2.7137526e-7,0.0005780033,0.031655524,0.00069405534,0.9343499,0.016616963,0.014879192],"study_design_scores_gemma":[0.00014860764,0.00020917934,0.0015510531,0.0000034896225,0.0000023522925,0.0000013170055,0.000012769281,0.94835734,0.0031901489,0.0051115826,0.0413173,0.00009484858],"about_ca_topic_score_codex":0.000005216685,"about_ca_topic_score_gemma":0.000004563726,"teacher_disagreement_score":0.9292383,"about_ca_system_score_codex":0.000013750872,"about_ca_system_score_gemma":0.000024690362,"threshold_uncertainty_score":0.19863866},"labels":[],"label_agreement":null},{"id":"W2808386811","doi":"10.65109/fknq6967","title":"Teaching Multiple Tasks to an RL Agent using LTL","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Linear temporal logic; Convergence (economics); Exploit; Temporal logic; State (computer science); Artificial intelligence; Model checking; Theoretical computer science; Programming language","score_opus":0.05619774051327824,"score_gpt":0.32256481769397255,"score_spread":0.2663670771806943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808386811","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":[0.08525823,0.0000013923069,0.9059398,0.00021270322,0.0004735152,0.000121526646,1.2711209e-7,0.00024792174,0.0077447947],"genre_scores_gemma":[0.6047791,9.085344e-8,0.39264393,0.0009536582,0.0001529106,0.0000012385835,5.6810933e-7,0.000007572517,0.0014609424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882776,0.00006897327,0.00018331897,0.000323776,0.00027338997,0.000322773],"domain_scores_gemma":[0.99899113,0.00004264539,0.00005199385,0.00067754433,0.0000634881,0.00017316887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037986448,0.00011324843,0.000095166826,0.00010176009,0.00029454206,0.00025395962,0.0008342366,0.000037803573,0.0000539886],"category_scores_gemma":[0.000107783286,0.000101953265,0.000029881387,0.0001676666,0.000026990387,0.0005361431,0.00046333368,0.00013243615,0.0003659634],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000075394732,0.00007517299,0.0066253515,0.00001162249,0.000026325552,0.000013973274,0.008774843,0.88567805,0.023367867,0.02546249,0.0020094537,0.047947332],"study_design_scores_gemma":[0.000114039794,0.00019514015,0.0008547778,0.000011238695,0.0000022816014,0.0000054748657,0.000056536956,0.98237336,0.0020070674,0.000045661287,0.014173962,0.00016048427],"about_ca_topic_score_codex":0.0003859095,"about_ca_topic_score_gemma":0.00003154564,"teacher_disagreement_score":0.5195209,"about_ca_system_score_codex":0.00006934304,"about_ca_system_score_gemma":0.00003288544,"threshold_uncertainty_score":0.47038412},"labels":[],"label_agreement":null},{"id":"W2809151193","doi":"10.48550/arxiv.1808.09127","title":"High-confidence error estimates for learned value functions","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Bellman equation; Benchmark (surveying); Computer science; Value (mathematics); Convergence (economics); Stability (learning theory); Function (biology); Mathematical optimization; Upper and lower bounds; Artificial intelligence; Machine learning; Mathematics","score_opus":0.08861862077521193,"score_gpt":0.21932372073798673,"score_spread":0.1307050999627748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809151193","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":[0.022144236,0.0000062497365,0.97482157,0.0002288142,0.00065897376,0.00020101386,0.0000018080971,0.00032227533,0.0016150407],"genre_scores_gemma":[0.9649066,0.00000423477,0.027147388,0.00016032558,0.0000984476,0.0000010986571,0.000004566767,0.000012186598,0.0076651517],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883944,0.0000376366,0.00013711018,0.0005470573,0.000078437784,0.00036034881],"domain_scores_gemma":[0.99861157,0.00023653719,0.00012114325,0.0006877731,0.00022543961,0.000117541764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019761494,0.00015586945,0.00014920454,0.00014148712,0.00042322275,0.00011064019,0.0009696576,0.000078324716,0.00006715247],"category_scores_gemma":[0.00016348368,0.00017320053,0.000088949826,0.00059288257,0.0001933691,0.0006848249,0.000253284,0.000119875265,0.00054243614],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015207488,0.0000135396485,0.0006148407,0.0000062376125,0.000024509158,0.000007755261,0.00007628676,0.5893306,0.00015818836,0.408956,0.0006206082,0.00017623819],"study_design_scores_gemma":[0.00048114033,0.00033000542,0.0007232252,0.000019663656,0.000037270784,0.0000033719969,0.00005571287,0.98380744,0.0009903177,0.011294926,0.0020349985,0.00022193739],"about_ca_topic_score_codex":0.00006994038,"about_ca_topic_score_gemma":0.00001071107,"teacher_disagreement_score":0.9476742,"about_ca_system_score_codex":0.00008118354,"about_ca_system_score_gemma":0.000084076346,"threshold_uncertainty_score":0.70629126},"labels":[],"label_agreement":null},{"id":"W2809487708","doi":"","title":"Comparing Direct and Indirect Temporal-Difference Methods for Estimating the Variance of the Return","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Variance (accounting); Temporal difference learning; Computer science; Reinforcement learning; Mean squared error; Lookup table; Function (biology); Algorithm; Artificial intelligence; Statistics; Mathematics","score_opus":0.10081530290189013,"score_gpt":0.3667202816540406,"score_spread":0.26590497875215047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809487708","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":[0.016845755,0.000056518416,0.98041606,0.0005722437,0.0008506401,0.00051907444,9.868444e-7,0.000049242997,0.0006894831],"genre_scores_gemma":[0.71684253,0.0000035164721,0.28287148,0.00010627588,0.0000766349,0.000026391655,4.915146e-7,0.0000070200463,0.00006563711],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99799544,0.00037470978,0.00063358666,0.0004044402,0.00023532312,0.0003565166],"domain_scores_gemma":[0.99687046,0.0017802938,0.00037629687,0.00073124847,0.00019807542,0.000043618616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023272978,0.00018037287,0.00029550478,0.00007973375,0.00037552303,0.00017378469,0.0015124287,0.00007041315,0.000005240654],"category_scores_gemma":[0.002208543,0.00011339364,0.00006906054,0.0007697128,0.0005769173,0.00015060267,0.00047185627,0.00025808075,0.0000029517446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004864595,0.00004294043,0.007104582,0.00006798737,0.00003092308,6.8925004e-7,0.010404069,0.65884894,0.005068832,0.06448582,0.00003421429,0.25386235],"study_design_scores_gemma":[0.000028215805,0.00008760605,0.0011365286,0.00013793792,0.000007399344,0.0000026428925,0.00013730988,0.949399,0.026623124,0.022148438,0.00015669568,0.00013508541],"about_ca_topic_score_codex":0.00032705552,"about_ca_topic_score_gemma":0.00023664869,"teacher_disagreement_score":0.69999677,"about_ca_system_score_codex":0.000060663046,"about_ca_system_score_gemma":0.0000908607,"threshold_uncertainty_score":0.46240586},"labels":[],"label_agreement":null},{"id":"W2817967199","doi":"10.1613/jair.1.12463","title":"The Bottleneck Simulator: A Model-Based Deep Reinforcement Learning Approach","year":2020,"lang":"en","type":"preprint","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","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":"McGill University; Université de Montréal; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Compute Canada; Amazon Web Services; Nuance Foundation; Canadian Institute for Advanced Research; Nvidia","keywords":"Bottleneck; Reinforcement learning; Computer science; Variance (accounting); Task (project management); Obstacle; Artificial intelligence; State space; Engineering; Statistics; Mathematics","score_opus":0.20092186190179046,"score_gpt":0.4031124373316161,"score_spread":0.20219057542982566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2817967199","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":[0.0002832109,0.0005037952,0.9930928,0.003199608,0.0007393008,0.0005903254,3.4606236e-7,0.00006689233,0.0015237649],"genre_scores_gemma":[0.94157094,0.0005029519,0.056825433,0.00010666084,0.00063136395,0.00002669632,0.0000047623003,0.000050873266,0.0002803302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990688,0.0010843669,0.0021119455,0.0006830533,0.004277774,0.0011548391],"domain_scores_gemma":[0.99260604,0.0017150459,0.0013387686,0.0012869543,0.002542421,0.00051076506],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009576301,0.00042622758,0.00064780744,0.00064825284,0.0011144198,0.002265962,0.0063873534,0.0003762155,0.000018316354],"category_scores_gemma":[0.003551013,0.0003169867,0.0005456689,0.0010744453,0.00048928644,0.00038523393,0.0031347235,0.0073863952,0.00011111245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012239406,0.000056888824,0.000011370955,0.00011185782,0.00009779144,0.00003567083,0.0013947341,0.9499118,0.00022087057,0.024967832,0.00024108854,0.022827715],"study_design_scores_gemma":[0.000049030084,0.00058452855,0.0000013726246,0.00017309275,0.000019743964,0.000008514786,0.00048641616,0.9741672,0.0027465639,0.020302016,0.0011707651,0.00029070777],"about_ca_topic_score_codex":0.000018550885,"about_ca_topic_score_gemma":0.0000027128701,"teacher_disagreement_score":0.9412877,"about_ca_system_score_codex":0.00062920107,"about_ca_system_score_gemma":0.0024227023,"threshold_uncertainty_score":0.99992824},"labels":[],"label_agreement":null},{"id":"W2884439071","doi":"10.1017/s0269888921000035","title":"Safe option-critic: learning safety in the option-critic architecture","year":2021,"lang":"en","type":"article","venue":"The Knowledge Engineering Review","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Consistency (knowledge bases); State space; Variance (accounting); Function (biology); Artificial intelligence; Grid; Architecture; Machine learning; Mathematical optimization; Mathematics","score_opus":0.011610790669513473,"score_gpt":0.25518738082408904,"score_spread":0.24357659015457556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884439071","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":[0.00010527793,0.10213107,0.8887724,0.0044994596,0.00047567414,0.00037002077,4.1668534e-7,0.00015997392,0.0034856715],"genre_scores_gemma":[0.69069326,0.1747999,0.115485206,0.005543835,0.0018012553,0.0005579196,0.00009113982,0.00024632044,0.010781145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979494,0.00045077276,0.00049746386,0.00033975937,0.00032436696,0.00043819996],"domain_scores_gemma":[0.9978253,0.0009706583,0.00006709701,0.0009417705,0.00013188503,0.0000632521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016437891,0.00025255396,0.00034845647,0.000077566525,0.00021743923,0.0001816222,0.0013597932,0.000056768225,0.000045801276],"category_scores_gemma":[0.0013891067,0.00016773902,0.00015747952,0.0011471601,0.000041025978,0.00017920272,0.00032060742,0.00097156153,0.00029833106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.844007e-7,0.000032859727,0.000019556976,0.0021825423,0.000027146205,0.00003877484,0.0018426131,0.8661623,0.00011451437,0.08294491,0.00025653918,0.046377257],"study_design_scores_gemma":[0.00022496829,0.00004013082,0.0007308767,0.0055419113,0.00005358993,0.00024919797,0.00005991611,0.61340547,0.000042816002,0.00025527153,0.37901953,0.000376346],"about_ca_topic_score_codex":0.000002195289,"about_ca_topic_score_gemma":0.0000027276733,"teacher_disagreement_score":0.77328724,"about_ca_system_score_codex":0.000094845054,"about_ca_system_score_gemma":0.0001016009,"threshold_uncertainty_score":0.6840199},"labels":[],"label_agreement":null},{"id":"W2885541157","doi":"10.1109/tac.2020.2978037","title":"On Passivity, Reinforcement Learning, and Higher Order Learning in Multiagent Finite Games","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Automatic Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"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; Convergence (economics); Monotonic function; Nash equilibrium; Stochastic game; Property (philosophy); Class (philosophy); Exploit","score_opus":0.015711761885379833,"score_gpt":0.24572690650981754,"score_spread":0.2300151446244377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885541157","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":[0.0032430398,0.000018505418,0.9905873,0.0038887965,0.00029447972,0.00051126676,5.6839576e-7,0.00056652585,0.00088951056],"genre_scores_gemma":[0.9937051,0.000028734126,0.0026509797,0.0017335634,0.000023394678,0.00008882175,9.2306516e-7,0.000026755624,0.0017417455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779373,0.00026409072,0.0005098646,0.00048681174,0.0005264327,0.0004190685],"domain_scores_gemma":[0.9984085,0.0008587104,0.00019854432,0.0002816614,0.000057374666,0.00019519567],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028146178,0.00029930088,0.0003722203,0.00022838566,0.00023361765,0.00021460072,0.0003414505,0.000104743325,0.0003752672],"category_scores_gemma":[0.00012942882,0.00028512595,0.00009279706,0.00048231264,0.00005730538,0.00027374865,0.000009315008,0.000686726,0.00022569628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025611937,0.000053391283,0.00009326361,0.00004253025,0.000053645934,0.00001851929,0.001024589,0.9501436,0.00015681786,0.00036257316,0.000047680973,0.047977783],"study_design_scores_gemma":[0.0027792049,0.0008405565,0.0008893826,0.00010012244,0.000027224876,0.0000020694838,0.00004066938,0.9927779,0.00023826712,0.000022363869,0.0019967975,0.00028547776],"about_ca_topic_score_codex":0.000021646538,"about_ca_topic_score_gemma":0.000005162521,"teacher_disagreement_score":0.99046206,"about_ca_system_score_codex":0.000098180695,"about_ca_system_score_gemma":0.000064325446,"threshold_uncertainty_score":0.99996006},"labels":[],"label_agreement":null},{"id":"W2886012730","doi":"10.1609/aaai.v34i04.5955","title":"Count-Based Exploration with the Successor Representation","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada","keywords":"Successor cardinal; Representation (politics); Computer science; Norm (philosophy); Generalization; Sample complexity; Reinforcement learning; Similarity (geometry); Artificial intelligence; State (computer science); Algorithm; Theoretical computer science; Mathematics","score_opus":0.15508351119977026,"score_gpt":0.3234339624244677,"score_spread":0.16835045122469744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2886012730","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":[0.006363585,0.000009933099,0.938601,0.04882531,0.00054034294,0.0011330531,0.0000041485923,0.0001760032,0.0043466114],"genre_scores_gemma":[0.9930834,0.000023799888,0.005789479,0.00065925263,0.00011878196,0.0001288228,0.000005418257,0.000023637584,0.00016738851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698186,0.00005143351,0.0006421657,0.0007949288,0.0012166532,0.00031295995],"domain_scores_gemma":[0.996449,0.00019206475,0.0012938791,0.0007315352,0.0012549061,0.00007859176],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005463233,0.0003702988,0.00035458224,0.00011383109,0.00029764738,0.0010688864,0.0041848803,0.00016334778,0.000026636793],"category_scores_gemma":[0.00048557605,0.0002238458,0.00014506278,0.0007660489,0.0003729519,0.00054973527,0.0010939064,0.00097639405,0.00006619743],"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":[0.00016578713,0.000066209876,0.0001943477,0.00019039765,0.000052236417,0.0000010628042,0.003490627,0.42010674,0.0043995474,0.5628826,0.00070147135,0.0077489377],"study_design_scores_gemma":[0.000031294476,0.0002203018,0.000078850564,0.00038916696,0.000036236946,8.5455974e-7,0.00055672554,0.78131336,0.18029362,0.03669108,0.00011665215,0.00027187532],"about_ca_topic_score_codex":0.00006937898,"about_ca_topic_score_gemma":0.0000131550505,"teacher_disagreement_score":0.98671985,"about_ca_system_score_codex":0.00008591529,"about_ca_system_score_gemma":0.0003782121,"threshold_uncertainty_score":0.9999681},"labels":[],"label_agreement":null},{"id":"W2889310374","doi":"10.1109/ccece.2018.8447854","title":"Socially Aware Robot Navigation Using Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Prince Edward Island","funders":"","keywords":"Reinforcement learning; Mobile robot; Computer science; Social robot; Robot; Artificial intelligence; Mobile robot navigation; Robot learning; Human–computer interaction; Human–robot interaction; Robot control","score_opus":0.028587905249804244,"score_gpt":0.2871830959177124,"score_spread":0.25859519066790815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889310374","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":[0.002043559,0.000006448896,0.98231393,0.00019976342,0.0004869478,0.00015395813,1.6592283e-8,0.00038918806,0.014406163],"genre_scores_gemma":[0.86683947,0.0000027552449,0.12942606,0.00031292962,0.0002629403,0.0000034478808,0.000006880344,0.000015579126,0.0031299496],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983357,0.000072336996,0.00034003763,0.00032970135,0.0005089305,0.00041329645],"domain_scores_gemma":[0.99899447,0.0000491909,0.00020430185,0.00039253666,0.00026643957,0.00009306256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036540502,0.00016595524,0.00014356498,0.0000963281,0.0005591532,0.00030803267,0.0006530994,0.00008706235,0.00017301063],"category_scores_gemma":[0.00006345218,0.00016358659,0.0000654507,0.00040129124,0.0000848131,0.00074183196,0.0003856524,0.00021791694,0.00034441866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000021136352,0.0000044951767,0.00055290497,0.000007960243,0.000015352975,0.0000028512718,0.00084513996,0.97621447,0.00095715694,0.018194044,0.0000665962,0.0031369096],"study_design_scores_gemma":[0.00020486512,0.00017734787,0.00022489468,0.000031462245,0.000007172367,0.000008067511,0.000095774536,0.9955039,0.0021042828,0.00024375554,0.0011834366,0.00021504733],"about_ca_topic_score_codex":0.000062893676,"about_ca_topic_score_gemma":0.000005747153,"teacher_disagreement_score":0.8647959,"about_ca_system_score_codex":0.0001741296,"about_ca_system_score_gemma":0.00014637876,"threshold_uncertainty_score":0.6670868},"labels":[],"label_agreement":null},{"id":"W2889665471","doi":"10.1109/agents.2018.8460004","title":"Autonomous Agents in Snake Game via Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"People's Government of Jilin Province; National Research Foundation","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Constraint (computer-aided design); Dual (grammatical number); Machine learning; Engineering","score_opus":0.024876329767722426,"score_gpt":0.2714467120606008,"score_spread":0.24657038229287837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889665471","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":[0.0035147516,0.000008160951,0.9235235,0.0002091147,0.00042642627,0.00018803177,1.0432337e-8,0.0002987275,0.071831316],"genre_scores_gemma":[0.9631847,0.000006890511,0.022074876,0.00074307795,0.00009061846,0.000012008299,0.000003118681,0.0000150282,0.013869672],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980689,0.000072492105,0.00044782567,0.00041683484,0.00042544078,0.00056849275],"domain_scores_gemma":[0.9989911,0.000056616926,0.00014666353,0.0005966951,0.00008819369,0.00012077654],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00042595287,0.00019287599,0.00018428295,0.0002284075,0.00012543848,0.0001916523,0.0009790758,0.00008232559,0.000657179],"category_scores_gemma":[0.00008502013,0.00018425728,0.00005561917,0.00049385,0.00007513904,0.00050471147,0.0005550223,0.00028344273,0.0017680366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039951055,0.000014880071,0.0037543345,0.0000068048444,0.000012052248,0.00001549186,0.0013900691,0.97640395,0.000104537605,0.0077559943,0.0002387216,0.010299163],"study_design_scores_gemma":[0.00040843978,0.00030692588,0.004063553,0.000015832764,0.0000024645256,0.000007919975,0.000026212436,0.9767043,0.00063529145,0.00014994075,0.017447636,0.00023147049],"about_ca_topic_score_codex":0.00009182224,"about_ca_topic_score_gemma":0.0000287382,"teacher_disagreement_score":0.95966995,"about_ca_system_score_codex":0.00018229567,"about_ca_system_score_gemma":0.00005640209,"threshold_uncertainty_score":0.9990092},"labels":[],"label_agreement":null},{"id":"W2889732123","doi":"10.1609/aaai.v33i01.33013582","title":"Combined Reinforcement Learning via Abstract Representations","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Modularity (biology); Bridging (networking); Generalization; Artificial intelligence; Representation (politics); Encoding (memory); Machine learning; Theoretical computer science; Mathematics","score_opus":0.08144392931513404,"score_gpt":0.31546580598770657,"score_spread":0.23402187667257252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889732123","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":[0.013309464,0.000018061432,0.90318394,0.0035880157,0.0026206367,0.001847124,0.0000025249208,0.0003556055,0.07507465],"genre_scores_gemma":[0.9926826,0.000079191006,0.0034848906,0.00015376382,0.00009335329,0.00006719714,0.000007644338,0.000034144417,0.003397232],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9957383,0.000034623416,0.0013392993,0.0010168257,0.0012931849,0.00057774043],"domain_scores_gemma":[0.9954885,0.00022496025,0.0018846971,0.0010480142,0.0012239559,0.00012985097],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000852802,0.00052958546,0.00059132656,0.00029915242,0.0003212537,0.0007946454,0.004906607,0.0003288576,0.00019018787],"category_scores_gemma":[0.00078860443,0.00044743135,0.00034644053,0.00056744245,0.00027419618,0.00046254677,0.0034070187,0.001962822,0.0004462048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003972487,0.00006284066,0.00035442662,0.0001889727,0.00005980782,6.188363e-7,0.00122924,0.695423,0.0038342243,0.2926874,0.00020609068,0.0059136744],"study_design_scores_gemma":[0.000046193283,0.00028451133,0.00043152564,0.0007196451,0.00003418831,0.000001834422,0.0002739636,0.8684066,0.081821375,0.04739388,0.00010723467,0.00047904698],"about_ca_topic_score_codex":0.00011279629,"about_ca_topic_score_gemma":0.0000019637125,"teacher_disagreement_score":0.9793731,"about_ca_system_score_codex":0.00016538371,"about_ca_system_score_gemma":0.00031302567,"threshold_uncertainty_score":0.99979776},"labels":[],"label_agreement":null},{"id":"W2890043461","doi":"10.1609/aiide.v14i1.13030","title":"Improbotics: Exploring the Imitation Game Using Machine Intelligence in Improvised Theatre","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Imitation; Turing test; Computer science; Improvisation; Test (biology); Human–computer interaction; Narrative; Perception; Context (archaeology); Control (management); Entertainment; Artificial intelligence; Multimedia; Psychology; Visual arts; Art; Social psychology","score_opus":0.07447162716838729,"score_gpt":0.29601916611341855,"score_spread":0.22154753894503126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890043461","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":[0.40862525,0.000018121198,0.5822665,0.0017008713,0.0007707184,0.00092830346,0.0000049611817,0.0000560404,0.0056292266],"genre_scores_gemma":[0.9986899,0.000038159986,0.0008918971,0.00018929102,0.0000617572,0.000036047964,8.878073e-7,0.000015089414,0.00007700533],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793386,0.000025913901,0.0006797585,0.00050446216,0.0004638978,0.00039211533],"domain_scores_gemma":[0.99860543,0.00018417067,0.00042568045,0.00029992286,0.00041176676,0.00007302544],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034830507,0.00029159553,0.0002484269,0.0001862991,0.00018187704,0.0007605656,0.0012756017,0.000048392714,0.000016901533],"category_scores_gemma":[0.00027925463,0.00018720294,0.00010503078,0.00045891412,0.00042700514,0.0017805016,0.00067911315,0.00038028165,0.000026621605],"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":[0.0005374213,0.00045774798,0.0027726502,0.00010071365,0.0001169052,0.0000025241159,0.027280513,0.01395124,0.037284825,0.3208351,0.0000109577995,0.5966494],"study_design_scores_gemma":[0.000045687302,0.0006439279,0.00027846935,0.0004045745,0.000010666752,0.000007118901,0.0043939785,0.7656485,0.2146116,0.013692786,0.000039722592,0.00022296749],"about_ca_topic_score_codex":0.00006711107,"about_ca_topic_score_gemma":0.000012119398,"teacher_disagreement_score":0.75169724,"about_ca_system_score_codex":0.00015946133,"about_ca_system_score_gemma":0.000051791183,"threshold_uncertainty_score":0.76339144},"labels":[],"label_agreement":null},{"id":"W2890047470","doi":"10.48550/arxiv.1811.09013","title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Unicode; Counterexample; Reinforcement learning; Computer science; Key (lock); Mathematical economics; Mathematics; Mathematical optimization; Artificial intelligence; Discrete mathematics; Computer security","score_opus":0.06837137357235425,"score_gpt":0.23102146841004043,"score_spread":0.16265009483768617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890047470","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":[0.24731342,0.000016888062,0.7469126,0.00011308173,0.0005151219,0.00028971556,0.0000037072382,0.0003822064,0.0044532483],"genre_scores_gemma":[0.98688686,0.00009647676,0.010522607,0.00033188297,0.00071376417,5.9469374e-7,0.000015276179,0.000048951697,0.0013835746],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678326,0.0003255153,0.0003818591,0.0014408,0.00024324027,0.0008253332],"domain_scores_gemma":[0.99590844,0.000103360646,0.0006459751,0.0026394366,0.0003017199,0.0004010713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005013978,0.0005464406,0.0004707989,0.0011216592,0.00042931744,0.00043594826,0.0040228455,0.0003693894,0.000032934797],"category_scores_gemma":[0.00015615813,0.0006149259,0.00026410073,0.0015168225,0.0003760344,0.0008040623,0.0030872512,0.0006216188,0.00015989665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008286493,0.00004234383,0.0008377396,0.000044934397,0.000060412145,0.00007143701,0.00070482574,0.6821077,0.000036590656,0.31568888,0.000046092824,0.0003507597],"study_design_scores_gemma":[0.0003329636,0.00014868486,0.00046504595,0.000144059,0.000059743474,0.000013491291,0.000056013694,0.95724577,0.00016251246,0.040179044,0.0005746679,0.0006180115],"about_ca_topic_score_codex":0.0008401272,"about_ca_topic_score_gemma":0.000011993762,"teacher_disagreement_score":0.7395734,"about_ca_system_score_codex":0.0010353468,"about_ca_system_score_gemma":0.0011179771,"threshold_uncertainty_score":0.9996302},"labels":[],"label_agreement":null},{"id":"W2890185089","doi":"","title":"Monte-Carlo Tree Search for Constrained POMDPs","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Monte Carlo tree search; Computer science; Partially observable Markov decision process; Mathematical optimization; Monte Carlo method; Markov decision process; Tree (set theory); Action selection; Scale (ratio); Markov process; Machine learning; Markov model; Mathematics; Markov chain","score_opus":0.035799904152969325,"score_gpt":0.284999641127341,"score_spread":0.24919973697437167,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890185089","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":[0.006091552,0.000034622288,0.98289126,0.0004080106,0.0010214614,0.0006697832,0.0000028652282,0.0006285235,0.008251899],"genre_scores_gemma":[0.987573,0.0000010758059,0.011348344,0.00027604564,0.0002314483,0.00005572253,0.0000071104405,0.000009099813,0.0004981319],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832845,0.00004247398,0.0005998756,0.00017144367,0.00047371234,0.00038401774],"domain_scores_gemma":[0.9984265,0.000074897005,0.00031319543,0.00032797354,0.00076057704,0.00009687597],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004897292,0.00016191344,0.00018106942,0.00019754653,0.00041080054,0.0013767533,0.0006856057,0.0000895092,0.0000023364153],"category_scores_gemma":[0.00007424262,0.00014286411,0.000053220065,0.00038835165,0.00008486136,0.0043762675,0.00009978944,0.00012999441,0.000103308805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070144015,0.0000611916,0.0008270518,0.0024195057,0.0000811324,0.0000030018564,0.02870303,0.72768444,0.0008026172,0.040226564,0.012117705,0.18700361],"study_design_scores_gemma":[0.00048546953,0.00026394543,0.000077029086,0.00007260291,0.000004670851,0.000031005264,0.00031217525,0.9863509,0.00051685155,0.00000808995,0.011710722,0.00016654006],"about_ca_topic_score_codex":0.000016932605,"about_ca_topic_score_gemma":6.462033e-7,"teacher_disagreement_score":0.9814815,"about_ca_system_score_codex":0.00007809958,"about_ca_system_score_gemma":0.00016237293,"threshold_uncertainty_score":0.9996599},"labels":[],"label_agreement":null},{"id":"W2890960027","doi":"","title":"Iterative Value-Aware Model Learning","year":2018,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute","funders":"","keywords":"Reinforcement learning; Computer science; Contrast (vision); Class (philosophy); Mathematical optimization; Artificial intelligence; Value (mathematics); Iterative learning control; Iterative method; Optimization problem; Decision problem; Machine learning; Algorithm; Mathematics; Control (management)","score_opus":0.014372635973734319,"score_gpt":0.24675203116280983,"score_spread":0.23237939518907552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890960027","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":[0.005478566,0.0001013954,0.98546696,0.001940242,0.00019906375,0.0004298387,0.000002726306,0.0017776306,0.00460356],"genre_scores_gemma":[0.6614044,0.000029981138,0.33141488,0.0021295,0.0001668867,0.000104358296,0.000008323273,0.00004813899,0.0046935827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695855,0.00021397356,0.00051325926,0.0007055965,0.00063467363,0.00097395835],"domain_scores_gemma":[0.9976655,0.00013360077,0.0003047631,0.001248695,0.0003194079,0.00032802377],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007544464,0.00040715258,0.00034681853,0.00043305944,0.00067143963,0.00064849353,0.0016641957,0.00026078805,0.000031719053],"category_scores_gemma":[0.00028528867,0.00041240407,0.00016415348,0.00082488067,0.00017639369,0.0011294463,0.0008372888,0.00075309316,0.00016808699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015894411,0.000041708012,0.0033641255,0.000012187335,0.00003311913,0.000022636574,0.0013650685,0.85717535,0.002012925,0.12916055,0.0016439024,0.0051525184],"study_design_scores_gemma":[0.00029638567,0.00033623315,0.0011369125,0.00004951145,0.000012061693,0.000045795256,0.000046941128,0.9860516,0.006765958,0.0026847967,0.0021176622,0.00045613255],"about_ca_topic_score_codex":0.00057775597,"about_ca_topic_score_gemma":0.000084405176,"teacher_disagreement_score":0.6559258,"about_ca_system_score_codex":0.000420956,"about_ca_system_score_gemma":0.00031176716,"threshold_uncertainty_score":0.9998328},"labels":[],"label_agreement":null},{"id":"W2891166116","doi":"10.48550/arxiv.1811.00429","title":"Temporal Regularization in Markov Decision Process","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Université Laval; McGill University","funders":"","keywords":"Regularization (linguistics); Markov decision process; Reinforcement learning; Computer science; Exploit; Artificial intelligence; Machine learning; Markov process; Mathematical optimization; Partially observable Markov decision process; Markov chain; Regularization perspectives on support vector machines; Inverse problem; Mathematics; Markov model; Statistics","score_opus":0.03660652369230544,"score_gpt":0.1961727198969281,"score_spread":0.15956619620462267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891166116","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":[0.15300167,0.0000019974448,0.8415634,0.00003348176,0.00015608461,0.00009194637,1.2365126e-7,0.00009072828,0.00506057],"genre_scores_gemma":[0.9907403,0.0000047229796,0.0062305704,0.00006042452,0.000032414424,1.5705771e-7,0.000002180047,0.000006372859,0.0029228444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991238,0.0000472197,0.0001296925,0.0003929659,0.00009229992,0.00021402874],"domain_scores_gemma":[0.9992209,0.00004774902,0.000090657704,0.00045276058,0.00012510702,0.00006282693],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021253436,0.000097983146,0.00009396816,0.00021510078,0.00010374318,0.00006205772,0.0007607485,0.00007095346,0.000030034522],"category_scores_gemma":[0.000067951674,0.00010930731,0.000028794377,0.0012204866,0.00007557053,0.0007659731,0.00020070336,0.000103642415,0.00012290383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040226147,0.000036266298,0.056939393,0.000010682514,0.0000069642206,0.00007961525,0.00035674786,0.8439007,0.00003786844,0.09641014,0.00016370787,0.0020177015],"study_design_scores_gemma":[0.00041578047,0.00009175183,0.0053429427,0.000032589305,0.0000031582513,0.0000022319425,0.00003442476,0.98236626,0.00024008422,0.010964627,0.0003653443,0.00014080298],"about_ca_topic_score_codex":0.000012931131,"about_ca_topic_score_gemma":0.00001836304,"teacher_disagreement_score":0.83773863,"about_ca_system_score_codex":0.00008636899,"about_ca_system_score_gemma":0.00006254163,"threshold_uncertainty_score":0.44574228},"labels":[],"label_agreement":null},{"id":"W2891236810","doi":"","title":"Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Artificial intelligence; Machine learning; Bayesian probability; Bellman equation; Domain (mathematical analysis); Function (biology); Mathematical optimization; Mathematics","score_opus":0.019661178052500883,"score_gpt":0.23828292618312835,"score_spread":0.21862174813062746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891236810","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":[0.0015145389,0.00002027108,0.9837318,0.00009694678,0.00021918054,0.00050207635,2.0778366e-7,0.0005929423,0.013322033],"genre_scores_gemma":[0.9780061,0.000001667494,0.020687148,0.0002746753,0.00007158335,0.0000978226,0.00004310816,0.000015084138,0.0008028018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782544,0.00006306753,0.0006654976,0.00024388675,0.000803831,0.00039825978],"domain_scores_gemma":[0.99822944,0.00003100316,0.00064464106,0.00037523647,0.0006105974,0.00010909849],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00038855744,0.00024404578,0.00021112165,0.00026661888,0.0006520991,0.0014094696,0.0006064018,0.000097156175,0.0000018063236],"category_scores_gemma":[0.00008123305,0.00019858786,0.000034746317,0.0005553014,0.000086663575,0.0070580523,0.00013307843,0.00021838576,0.000034977485],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013916476,0.0000111133,0.0003376985,0.00016519231,0.00000790629,3.172682e-7,0.007530181,0.985354,0.000044202603,0.002602434,0.00026014115,0.0036728897],"study_design_scores_gemma":[0.0007354796,0.0003035837,0.000029609824,0.00011402093,0.000005391278,0.000035860794,0.0006888896,0.9958278,0.000189875,0.000009552587,0.0017901707,0.00026979702],"about_ca_topic_score_codex":0.00002604243,"about_ca_topic_score_gemma":5.5567267e-7,"teacher_disagreement_score":0.9764916,"about_ca_system_score_codex":0.00014389092,"about_ca_system_score_gemma":0.000121752695,"threshold_uncertainty_score":0.9996272},"labels":[],"label_agreement":null},{"id":"W2895478303","doi":"10.48550/arxiv.1810.01032","title":"Reinforcement Learning with Perturbed Rewards","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Noise (video); Confusion matrix; Artificial intelligence; Convergence (economics); Confusion; Set (abstract data type); Gaussian; Machine learning; Matrix (chemical analysis); Mathematical optimization; Algorithm; Mathematics","score_opus":0.053332976380586775,"score_gpt":0.18502390545204497,"score_spread":0.13169092907145818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2895478303","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":[0.018506411,0.000017094486,0.9587017,0.00009589128,0.0005409274,0.00035987183,5.822206e-7,0.00061560737,0.021161912],"genre_scores_gemma":[0.9703809,0.00009656811,0.0064355377,0.00014763889,0.00014424458,0.0000016039968,0.000026392807,0.000038275248,0.022728866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972911,0.00017307165,0.00029659367,0.0013205088,0.00029482588,0.0006239256],"domain_scores_gemma":[0.9969497,0.000101745594,0.00052581995,0.0018066198,0.00037729592,0.00023881698],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039756962,0.0004979665,0.0004212342,0.00033043048,0.0003545504,0.00031106596,0.002578481,0.00033178515,0.000112605674],"category_scores_gemma":[0.0000833095,0.00049911306,0.00018659857,0.00063266716,0.00022331493,0.00049205276,0.003182948,0.0011911308,0.0003194128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039731403,0.000015505437,0.0018767039,0.000064217005,0.00013518384,0.00018572797,0.00042833464,0.9748817,0.0000061806713,0.021804027,0.00045189488,0.00011078487],"study_design_scores_gemma":[0.00058270775,0.0004385648,0.00033560654,0.00021097888,0.00007465584,0.000009283199,0.00006782396,0.9914374,0.0000897249,0.0008166537,0.005272031,0.00066458154],"about_ca_topic_score_codex":0.00008670337,"about_ca_topic_score_gemma":0.0000070674673,"teacher_disagreement_score":0.95226616,"about_ca_system_score_codex":0.00041671234,"about_ca_system_score_gemma":0.0003838235,"threshold_uncertainty_score":0.999746},"labels":[],"label_agreement":null},{"id":"W2898050260","doi":"10.1109/ijcnn.2018.8489122","title":"Mixing Habits and Planning for Multi-Step Target Reaching Using Arbitrated Predictive Actor-Critic","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Computer science; Task (project management); Control (management); Model predictive control; Internal model; Controller (irrigation); Artificial intelligence; Work (physics); Engineering","score_opus":0.07409115597081546,"score_gpt":0.32788170110033965,"score_spread":0.2537905451295242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898050260","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":[0.046596874,0.000040812964,0.9512708,0.00004321584,0.00046869123,0.00031604615,0.000001435296,0.0002723058,0.000989793],"genre_scores_gemma":[0.49199036,4.807045e-7,0.50759333,0.00016344845,0.000119308526,0.0000048155807,0.0000024604592,0.000011075946,0.000114730035],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859226,0.000059799633,0.00027394327,0.00042987877,0.00020355123,0.00044056028],"domain_scores_gemma":[0.99905443,0.00022359277,0.000113477785,0.000283921,0.00020997833,0.00011460457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004068277,0.00018428132,0.00018784076,0.00013334803,0.0004425364,0.00029259914,0.0003753304,0.00008571735,0.0000048644883],"category_scores_gemma":[0.00036999193,0.00017408511,0.00003886284,0.00019711613,0.00009472334,0.0008224455,0.00022566413,0.00018809519,0.0000041117974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016021033,0.00017226455,0.07332642,0.00045861522,0.00046125852,0.00005676179,0.036883105,0.7810611,0.068600014,0.031534474,0.0012549998,0.0060307807],"study_design_scores_gemma":[0.0005286758,0.00019882785,0.0012347404,0.00012533492,0.000012640761,0.000013447045,0.00023829017,0.9935275,0.0035378104,0.00009822184,0.00027062482,0.0002139158],"about_ca_topic_score_codex":0.000043450837,"about_ca_topic_score_gemma":0.000002421986,"teacher_disagreement_score":0.4453935,"about_ca_system_score_codex":0.00007281542,"about_ca_system_score_gemma":0.00006390902,"threshold_uncertainty_score":0.7098985},"labels":[],"label_agreement":null},{"id":"W2900798285","doi":"10.65109/loxq3741","title":"Urban Driving with Multi-Objective Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Domain (mathematical analysis); Dual (grammatical number); Markov decision process; Function (biology); Lexicographical order; Collision; Markov process; Machine learning; Computer security; Engineering; Mathematics","score_opus":0.016748048215011115,"score_gpt":0.24694989287972507,"score_spread":0.23020184466471397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900798285","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":[0.00043513175,0.00005387791,0.9587708,0.00011045729,0.0009182039,0.0009673595,9.0018695e-8,0.00082608644,0.037917957],"genre_scores_gemma":[0.7881457,0.000033012366,0.17624974,0.00020173618,0.000113272115,0.00006733445,0.000027691458,0.000065011394,0.035096478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961822,0.0001658935,0.0006001622,0.0012674914,0.0009950122,0.0007892077],"domain_scores_gemma":[0.9967346,0.0002087998,0.00070478563,0.0018354107,0.00033003264,0.00018634407],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051845756,0.00065503776,0.0006039941,0.00034687563,0.00025225632,0.0008187518,0.0022830453,0.0003467366,0.00009571503],"category_scores_gemma":[0.0001464729,0.0005524237,0.00018569565,0.00032316404,0.000076717035,0.0005140052,0.0044948757,0.0020721185,0.0004514179],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061356454,0.00001760706,0.012232908,0.00009050852,0.00015984467,0.000015053398,0.0022659942,0.98088115,0.0000147556075,0.0034218626,0.0002549639,0.00063921313],"study_design_scores_gemma":[0.0006202883,0.00031977857,0.0022676196,0.00031750108,0.00003278976,0.00000914514,0.00017631272,0.9935004,0.00023369263,0.00002035695,0.0017073806,0.00079472415],"about_ca_topic_score_codex":0.00011215342,"about_ca_topic_score_gemma":0.0000192814,"teacher_disagreement_score":0.7877106,"about_ca_system_score_codex":0.00042879104,"about_ca_system_score_gemma":0.00037575013,"threshold_uncertainty_score":0.99969274},"labels":[],"label_agreement":null},{"id":"W2900994167","doi":"","title":"A Fitted-Q Algorithm for Budgeted MDPs","year":2018,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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":"Computer science; Algorithm; Mathematical optimization; Mathematics","score_opus":0.016624235311717504,"score_gpt":0.24256595073113119,"score_spread":0.22594171541941369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900994167","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":[0.00066233566,0.00025705327,0.97371763,0.0055843242,0.0008454506,0.00087231037,0.000037664977,0.0007026271,0.01732058],"genre_scores_gemma":[0.027941627,0.00017283556,0.951548,0.00031168837,0.00010438912,0.00022564906,0.00049771817,0.00007528849,0.019122845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9943461,0.0024519523,0.00071171205,0.001220323,0.0006466612,0.0006232712],"domain_scores_gemma":[0.9894705,0.0017441182,0.0007880071,0.0040402263,0.0037177082,0.00023945681],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0052759643,0.00046401107,0.00046954482,0.00028906853,0.00050817727,0.001139643,0.0043700286,0.0004305861,0.00006885665],"category_scores_gemma":[0.0017618337,0.0005090042,0.00032880832,0.00050649553,0.00026176788,0.00028470028,0.0038650236,0.00070740556,0.00012862313],"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":[0.000018358392,0.00093425537,0.00063614425,0.0007286614,0.00062985055,0.000018547194,0.022726612,0.01787254,0.001044333,0.2423069,0.04209709,0.6709867],"study_design_scores_gemma":[0.0005226999,0.0000012225532,0.00031728228,0.0008230967,0.00003272129,0.0000075295375,0.000017086977,0.944098,0.00978004,0.005127728,0.03872993,0.00054266065],"about_ca_topic_score_codex":0.0002225988,"about_ca_topic_score_gemma":0.000068181114,"teacher_disagreement_score":0.9262255,"about_ca_system_score_codex":0.00017966272,"about_ca_system_score_gemma":0.00046491274,"threshold_uncertainty_score":0.99989724},"labels":[],"label_agreement":null},{"id":"W2901559512","doi":"10.22215/etd/2013-09907","title":"Study of Multiple Multiagent Reinforcement Learning Algorithms in Grid Games","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Nash equilibrium; Minimax; Computer science; Algorithm; Best response; Grid; Game theory; Mathematical optimization; Artificial intelligence; Mathematics; Mathematical economics","score_opus":0.024807483136685807,"score_gpt":0.28220742561284134,"score_spread":0.25739994247615555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901559512","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":[0.38286248,0.00016898682,0.5867743,0.000027265669,0.0052689165,0.004689835,5.906398e-7,0.0004868327,0.019720819],"genre_scores_gemma":[0.9329322,0.00008042626,0.013461957,0.000024970232,0.00010289791,0.0002276126,0.00019291232,0.00004828452,0.052928727],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965774,0.00015594815,0.001148135,0.00066310423,0.0009888493,0.0004665956],"domain_scores_gemma":[0.9978614,0.00020354205,0.0007630153,0.00081678294,0.00025925535,0.000096028656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041666944,0.0004274772,0.0005994458,0.0005936629,0.0000931606,0.0001593593,0.0013037319,0.00021653087,0.0001471628],"category_scores_gemma":[0.000237579,0.00039829325,0.000115280796,0.00050658325,0.000016867398,0.000435836,0.00028938928,0.00071508315,0.00012213406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010732681,0.00021202631,0.0041968566,0.00010022174,0.0000731703,0.000015156469,0.013343953,0.97473013,0.00010832393,0.00018199635,0.00030685094,0.006720598],"study_design_scores_gemma":[0.00163399,0.0009374625,0.017331881,0.00018116634,0.000022142061,0.0000011103755,0.011266099,0.965827,0.0015995798,0.0000041576,0.0006856467,0.0005098048],"about_ca_topic_score_codex":0.0015761557,"about_ca_topic_score_gemma":0.0003034911,"teacher_disagreement_score":0.5733123,"about_ca_system_score_codex":0.0001372478,"about_ca_system_score_gemma":0.00010910617,"threshold_uncertainty_score":0.9998469},"labels":[],"label_agreement":null},{"id":"W2902062907","doi":"","title":"Nonlinear Optimization and Symbolic Dynamic Programming for Parameterized Hybrid Markov Decision Processes.","year":2017,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Parameterized complexity; Markov decision process; Computer science; Mathematical optimization; Dynamic programming; Nonlinear system; Markov process; Markov chain; Nonlinear programming; Mathematics; Algorithm; Machine learning","score_opus":0.08557820677108352,"score_gpt":0.3627951243467675,"score_spread":0.27721691757568395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902062907","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":[0.0031482065,0.000013163705,0.9944566,0.0008966205,0.00030283563,0.0005759243,0.000009169749,0.000091341404,0.00050616864],"genre_scores_gemma":[0.6324118,0.00005590521,0.367228,0.000091006,0.00004212803,0.000065347325,0.000019982894,0.000010063724,0.00007580429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813217,0.000030502995,0.00042284408,0.00052650744,0.0006049556,0.00028299756],"domain_scores_gemma":[0.9975454,0.0004579496,0.00036494984,0.0004239057,0.0011124568,0.00009532688],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000570996,0.00019074194,0.00019287421,0.00015879456,0.0007244019,0.0015197977,0.0010113544,0.00007473079,0.00002002722],"category_scores_gemma":[0.0033110627,0.00018707481,0.00004509869,0.00013673362,0.00016576645,0.00072416104,0.00019788604,0.00015974439,0.000027715807],"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":[0.00010248103,0.00009447585,0.00004507399,0.000056377863,0.000018250665,0.0000029948455,0.00014184667,0.36272317,0.00021475107,0.107229546,0.000016831784,0.5293542],"study_design_scores_gemma":[0.000075730786,0.00017689826,0.00008543318,0.00009293173,0.0000053695653,0.0000049183595,0.000017990056,0.97579163,0.002661178,0.020664982,0.00021504615,0.0002078811],"about_ca_topic_score_codex":0.0000066613893,"about_ca_topic_score_gemma":0.000009924099,"teacher_disagreement_score":0.6292635,"about_ca_system_score_codex":0.000070120426,"about_ca_system_score_gemma":0.0003116529,"threshold_uncertainty_score":0.9995167},"labels":[],"label_agreement":null},{"id":"W2902729397","doi":"10.1613/jair.1.11263","title":"Grounding Language for Transfer in Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Transfer of learning; Representation (politics); Artificial intelligence; Task (project management); Differentiable function; Domain (mathematical analysis); Component (thermodynamics); Meaning (existential); Machine learning","score_opus":0.15032975293862594,"score_gpt":0.4297375410971567,"score_spread":0.27940778815853073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902729397","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":[0.028658245,0.00007677845,0.96916276,0.00046251036,0.00044229568,0.00025943483,5.0301512e-8,0.000017163791,0.00092076766],"genre_scores_gemma":[0.9842557,0.000057663743,0.014801483,0.000035863344,0.00053203077,0.000008064632,4.8750303e-7,0.000013971968,0.00029479116],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968134,0.0002717424,0.00091277604,0.0002266861,0.0010820848,0.00069331436],"domain_scores_gemma":[0.9976851,0.0007932528,0.00013697406,0.00026787378,0.0009700863,0.00014673245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0067849164,0.0001218318,0.00023680703,0.0009064999,0.0003003027,0.0003595669,0.0012197223,0.00008679832,0.000083514584],"category_scores_gemma":[0.0014432075,0.00010873279,0.000121697485,0.0010851932,0.00020037443,0.000704085,0.0001497349,0.00087130733,0.00007713437],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026246632,0.000088997076,0.00029001271,0.000058760117,0.000041356903,0.00007738389,0.0215409,0.64706117,0.01701873,0.11281687,0.00007751374,0.20066582],"study_design_scores_gemma":[0.00010186643,0.0020641594,0.000049279464,0.00013733759,0.0000039044,0.000025206738,0.004052348,0.92315626,0.06543958,0.0036480378,0.0011741504,0.00014784792],"about_ca_topic_score_codex":0.000036532798,"about_ca_topic_score_gemma":0.000044336197,"teacher_disagreement_score":0.9555974,"about_ca_system_score_codex":0.000260527,"about_ca_system_score_gemma":0.00020379259,"threshold_uncertainty_score":0.44339946},"labels":[],"label_agreement":null},{"id":"W2903017298","doi":"10.1609/aaai.v33i01.33014512","title":"State-Augmentation Transformations for Risk-Sensitive Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"China Scholarship Council","keywords":"Reinforcement learning; Markov decision process; Markov chain; Successor cardinal; Markov process; Function (biology); Computer science; Bellman equation; Q-learning; State (computer science); Mathematical optimization; Mathematics; Artificial intelligence; Machine learning; Algorithm; Statistics","score_opus":0.043402280773973005,"score_gpt":0.2852395603095862,"score_spread":0.24183727953561318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903017298","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":[0.061810516,0.0000026235334,0.9267079,0.0007961463,0.0003764446,0.0011402614,0.000002701255,0.000093234135,0.009070151],"genre_scores_gemma":[0.99310946,0.000042335676,0.005459989,0.00010909012,0.000021450538,0.000045084733,0.0000029050036,0.000012194609,0.0011975142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981782,0.000022534325,0.0006107399,0.00034268477,0.0005123499,0.00033351217],"domain_scores_gemma":[0.99813354,0.00018852488,0.00065649464,0.00021636541,0.0007445381,0.000060560677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006410653,0.00019628352,0.00021881767,0.00014075091,0.00029370553,0.00025748948,0.0009659635,0.000059526476,0.000041893698],"category_scores_gemma":[0.00031823863,0.0001587961,0.0001353337,0.00042540094,0.00009269619,0.00072195265,0.0001405887,0.00032601823,0.00015310949],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007758974,0.00002987522,0.0003372649,0.0000628662,0.000029532894,4.643773e-8,0.0047455337,0.5037624,0.012391637,0.45759544,0.000044901943,0.02092291],"study_design_scores_gemma":[0.00006371517,0.00041050417,0.00012894906,0.00010411192,0.000012728799,7.7157216e-7,0.00081430445,0.71645415,0.26820076,0.013516904,0.00013527443,0.00015786513],"about_ca_topic_score_codex":0.00002552277,"about_ca_topic_score_gemma":0.0000025163488,"teacher_disagreement_score":0.9312989,"about_ca_system_score_codex":0.00008194862,"about_ca_system_score_gemma":0.00008090899,"threshold_uncertainty_score":0.6475517},"labels":[],"label_agreement":null},{"id":"W2903094830","doi":"","title":"First, Scale Up to the Robotic Turing Test, Then Worry about Feeling.","year":2007,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université du Québec à Montréal","funders":"","keywords":"Feeling; Turing test; Consciousness; Worry; Test (biology); Turing; Psychology; Scale (ratio); Cognitive psychology; Cognition; Power (physics); Computer science; Cognitive science; Social psychology; Artificial intelligence","score_opus":0.01600279103353435,"score_gpt":0.24775324926058973,"score_spread":0.23175045822705537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2903094830","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":[0.002724138,0.0000733665,0.973267,0.0027492754,0.0008867745,0.00026748655,9.623469e-8,0.00033680367,0.019695023],"genre_scores_gemma":[0.85428387,0.000013741389,0.11321822,0.002876479,0.00033111707,0.000009599692,6.684811e-7,0.000024490098,0.029241797],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981716,0.000023026627,0.00034188904,0.00037509343,0.00048000223,0.0006083628],"domain_scores_gemma":[0.9980365,0.00060812075,0.000082584294,0.0010216018,0.00008095872,0.00017024374],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00094666,0.00018241249,0.00014929412,0.000117431024,0.0003756745,0.000371371,0.0018183081,0.000060854145,0.00005948131],"category_scores_gemma":[0.00022737055,0.0001222729,0.000076445474,0.0005707941,0.000039181275,0.00027911796,0.00067298795,0.00026076267,0.000838475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022372897,0.000009948451,0.0035188491,0.000007575109,0.000007781559,0.0000056389763,0.0019615297,0.9849606,0.000036761154,0.0029712573,0.0025978603,0.0039199647],"study_design_scores_gemma":[0.00023326781,0.00011546351,0.027837906,0.00007804154,0.000009934367,0.000022404736,0.00021582321,0.93409693,0.0011641525,0.00018657699,0.035674166,0.00036531154],"about_ca_topic_score_codex":0.00006012995,"about_ca_topic_score_gemma":0.000078372774,"teacher_disagreement_score":0.86004883,"about_ca_system_score_codex":0.000078345736,"about_ca_system_score_gemma":0.00003481562,"threshold_uncertainty_score":0.9999395},"labels":[],"label_agreement":null},{"id":"W2904453761","doi":"10.48550/arxiv.1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":280,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Extrapolation; Artificial intelligence; Reinforcement; Class (philosophy); Uncorrelated; Space (punctuation); Action (physics); Control (management); Machine learning; Mathematics; Engineering","score_opus":0.0781399192839883,"score_gpt":0.21755028897240594,"score_spread":0.13941036968841763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2904453761","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":[0.009142648,0.000022394335,0.9742266,0.00015489984,0.0007084008,0.00042020384,3.3670113e-7,0.000602242,0.014722289],"genre_scores_gemma":[0.9831737,0.0003554383,0.003483821,0.00016045096,0.00036057696,0.0000027862297,0.0000442914,0.00003730545,0.01238158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973186,0.0002327417,0.00039299295,0.0011851672,0.00027044886,0.0006000365],"domain_scores_gemma":[0.99708086,0.00007720346,0.00066888815,0.0016151394,0.00032827264,0.00022962908],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043760327,0.00046878195,0.0003984674,0.0005934703,0.0003966733,0.00036782876,0.0022760401,0.0003665528,0.00006599739],"category_scores_gemma":[0.00019543347,0.0005605649,0.0002121429,0.0008241462,0.0001709339,0.0011317632,0.0034149094,0.00097391603,0.0006518754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017023181,0.00001533724,0.0012722563,0.000046951056,0.00007843606,0.00003759088,0.0007431455,0.9362316,0.0000114860095,0.060673945,0.00013892137,0.00073331775],"study_design_scores_gemma":[0.00043700603,0.00018849262,0.00017525387,0.00011056658,0.000046528887,0.000002832795,0.00009162052,0.9903445,0.00012781304,0.0043308353,0.0035798138,0.0005647122],"about_ca_topic_score_codex":0.0001160187,"about_ca_topic_score_gemma":0.00001215629,"teacher_disagreement_score":0.9740311,"about_ca_system_score_codex":0.00061148236,"about_ca_system_score_gemma":0.00042547935,"threshold_uncertainty_score":0.9996846},"labels":[],"label_agreement":null},{"id":"W2905224739","doi":"10.1609/aaai.v33i01.33014504","title":"A Comparative Analysis of Expected and Distributional Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Convergence (economics); Computer science; Mathematical optimization; Linear approximation; Mathematics; Econometrics; Artificial intelligence; Nonlinear system; Economics","score_opus":0.058978497480422894,"score_gpt":0.3011855220912152,"score_spread":0.2422070246107923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905224739","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":[0.5583579,0.000014546519,0.42861202,0.00045642562,0.00015600449,0.00042825894,0.000002577864,0.00005624675,0.011916034],"genre_scores_gemma":[0.9984943,0.000013227751,0.0010736854,0.000027234431,0.00000814152,0.000007750928,0.0000027792655,0.0000031571894,0.0003697247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983263,0.000020290658,0.0005444512,0.00033409498,0.00055564387,0.00021924448],"domain_scores_gemma":[0.9983392,0.00014280873,0.0006018691,0.00021486511,0.0006465844,0.000054673827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033591336,0.00016131134,0.0004066781,0.00023226651,0.000106768064,0.00011288147,0.0009235543,0.00005440448,0.000117020645],"category_scores_gemma":[0.00019314254,0.0001248806,0.0001229727,0.0013216117,0.00020878772,0.00027833277,0.00039871436,0.0002454377,0.000023454157],"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":[0.00003833142,0.00003322822,0.0051836385,0.00002521669,0.00018196943,6.440613e-8,0.0024830317,0.1878407,0.01686059,0.78656137,0.000009007363,0.00078282953],"study_design_scores_gemma":[0.000030606545,0.0002628663,0.0035148042,0.0000872216,0.000073052775,5.882295e-7,0.00088406075,0.8796436,0.11286916,0.0024662497,0.000027476903,0.00014032319],"about_ca_topic_score_codex":0.000025371923,"about_ca_topic_score_gemma":0.0000015246237,"teacher_disagreement_score":0.78409517,"about_ca_system_score_codex":0.000041018295,"about_ca_system_score_gemma":0.000056392266,"threshold_uncertainty_score":0.50924826},"labels":[],"label_agreement":null},{"id":"W2906796853","doi":"10.1109/ijcnn52387.2021.9533459","title":"Dynamic Planning Networks","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"Ontario Centres of Excellence","keywords":"Traverse; Computer science; Generalization; Reinforcement learning; Action (physics); Artificial intelligence; Construct (python library); State (computer science); Architecture; Machine learning; Algorithm; Mathematics","score_opus":0.019736730170050912,"score_gpt":0.27609669820521315,"score_spread":0.25635996803516226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906796853","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":[0.00043254497,0.00043371934,0.9779558,0.00024089994,0.0022870868,0.00012288411,1.0238214e-7,0.00049128645,0.018035654],"genre_scores_gemma":[0.57604104,0.00007034675,0.41690287,0.000615219,0.00007938788,0.000015746638,0.000056760986,0.00002476479,0.006193839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983841,0.00006116359,0.0002960018,0.0005964329,0.0003192173,0.00034304068],"domain_scores_gemma":[0.99829125,0.00008277066,0.00017122897,0.0012906175,0.00008280708,0.00008133069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021407136,0.00023295166,0.00025723776,0.00008973411,0.00007873028,0.0009237582,0.0016860507,0.00027102974,0.000062120664],"category_scores_gemma":[0.000036931717,0.0002336453,0.00012325608,0.0001732818,0.000021198435,0.00016981526,0.004601176,0.00097408076,0.00002726869],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.930754e-7,0.0000042132447,0.00022809039,0.000022688115,0.000030455214,0.000052457628,0.00019767311,0.9956477,0.0000023235689,0.0018409205,0.00043602134,0.0015371211],"study_design_scores_gemma":[0.000055443576,0.000011571005,0.00072965084,0.00015294808,0.0000064624805,0.0000084190815,0.000025561385,0.99811774,0.0000064945225,0.00012989693,0.0004905688,0.0002652136],"about_ca_topic_score_codex":0.000014879803,"about_ca_topic_score_gemma":0.0000016752573,"teacher_disagreement_score":0.5756085,"about_ca_system_score_codex":0.000090592126,"about_ca_system_score_gemma":0.00014881844,"threshold_uncertainty_score":0.9527779},"labels":[],"label_agreement":null},{"id":"W2908832955","doi":"10.1109/smc.2018.00226","title":"Solving Home Robotics Challenges with Game Theory and Machine Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada","funders":"","keywords":"Learning automata; PID controller; Automaton; Robot; Computer science; Action (physics); Motion planning; Artificial intelligence; Path (computing); Finite-state machine; Automata theory; Controller (irrigation); Robotics; Game theory; Mobile robot; Control engineering; Control (management); Engineering; Temperature control; Mathematics; Algorithm","score_opus":0.022491271114616428,"score_gpt":0.22942792053014177,"score_spread":0.20693664941552534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2908832955","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":[0.0014759962,0.0005026219,0.9780199,0.0007018413,0.00011541469,0.000077724544,4.814366e-8,0.00032757307,0.018778905],"genre_scores_gemma":[0.8932333,0.0003113018,0.10232766,0.00020079914,0.00009062026,0.0000021376882,6.5174646e-7,0.00001868963,0.0038148728],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881774,0.00012543205,0.00014711004,0.00033482414,0.00025429268,0.0003205814],"domain_scores_gemma":[0.9990915,0.00025747615,0.00008642825,0.00038293033,0.00008817232,0.0000934809],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006358463,0.00015911658,0.0001529482,0.00009300273,0.0001801619,0.00019598693,0.00044333053,0.00005047923,0.000031764495],"category_scores_gemma":[0.00008711347,0.00011739688,0.000018568664,0.00014585868,0.00016914056,0.00039174044,0.00037899392,0.00022933149,0.00006222097],"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":[0.000024320067,0.00001679515,0.003387445,0.00003771731,0.000054319913,0.000015859003,0.0038009905,0.19476898,0.00009590149,0.768639,0.0000261678,0.029132472],"study_design_scores_gemma":[0.00045363023,0.0009653637,0.0033880179,0.000055958775,0.000012902385,0.00006604517,0.00022306124,0.9889479,0.00027876341,0.0027264946,0.0025233366,0.00035850776],"about_ca_topic_score_codex":0.0000059140366,"about_ca_topic_score_gemma":0.000010134361,"teacher_disagreement_score":0.89175725,"about_ca_system_score_codex":0.000017737086,"about_ca_system_score_gemma":0.000024481324,"threshold_uncertainty_score":0.4787306},"labels":[],"label_agreement":null},{"id":"W2909958171","doi":"10.1007/978-3-030-10546-4_2","title":"Reinforcement Learning and Deep Reinforcement Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Springer briefs in electrical and computer engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Artificial intelligence; Deep learning; Q-learning; Computer science; Psychology; Social psychology","score_opus":0.006681597574720062,"score_gpt":0.19333488369683516,"score_spread":0.1866532861221151,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2909958171","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":[0.00009352972,0.00153566,0.9755058,0.00006572286,0.0004161577,0.00043138518,5.009786e-8,0.00036830676,0.021583337],"genre_scores_gemma":[0.5613054,0.010133171,0.06890713,0.0009701056,0.0016159735,0.000084878746,0.000066791894,0.0005840155,0.35633254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996617,0.00002951989,0.00082150305,0.0010057841,0.0006438792,0.0008823204],"domain_scores_gemma":[0.9986823,0.0002659847,0.00028801642,0.0004439042,0.000074800635,0.00024498356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039732413,0.0007325314,0.00077125494,0.0006527505,0.0001482366,0.00040930507,0.0006030983,0.00039540423,0.000029101117],"category_scores_gemma":[0.00004840068,0.0007978489,0.00013207042,0.00020078347,0.000047447542,0.00034165778,0.0012851502,0.0021717194,0.00004923774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070894084,0.000004116095,0.00023008004,0.00013986813,0.000074688876,0.00004529079,0.00017372458,0.86777186,0.000019969533,0.10784333,0.000017285267,0.023672704],"study_design_scores_gemma":[0.00054736115,0.00045829688,0.00025548245,0.00036888174,0.000022264227,0.000048328624,0.0000010969603,0.92320406,0.000023693818,0.00013667351,0.07411368,0.00082017086],"about_ca_topic_score_codex":0.000013918809,"about_ca_topic_score_gemma":8.93066e-7,"teacher_disagreement_score":0.90659875,"about_ca_system_score_codex":0.00026718935,"about_ca_system_score_gemma":0.00007456013,"threshold_uncertainty_score":0.9994472},"labels":[],"label_agreement":null},{"id":"W291243768","doi":"","title":"Efficient Reinforcement Learning with Multiple Reward Functions for Randomized Controlled Trial Analysis","year":2010,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Generalization; Set (abstract data type); Extension (predicate logic); Reinforcement; State (computer science); Artificial intelligence; Mathematical optimization; Mathematics; Algorithm; Psychology","score_opus":0.00903513300406085,"score_gpt":0.24007088710621052,"score_spread":0.23103575410214966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W291243768","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":[0.0117503675,0.0000040205973,0.97471344,0.00028605564,0.0008566234,0.0056449594,2.4894206e-7,0.0003522958,0.0063920077],"genre_scores_gemma":[0.90220517,0.0000010408638,0.07467612,0.00009433038,0.00012081732,0.0014230695,0.000017549006,0.00001524927,0.021446666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745744,0.00018469307,0.00081615977,0.00048326637,0.0006103572,0.00044806793],"domain_scores_gemma":[0.9957588,0.0025273524,0.0005049499,0.00070963753,0.00035260737,0.00014667319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025331685,0.0002614544,0.0012581316,0.00045983482,0.00044008365,0.00032039385,0.00054725003,0.00009767538,0.00015684795],"category_scores_gemma":[0.0019372032,0.00016546993,0.0008462377,0.00084086024,0.00010642872,0.00012201394,0.00012668582,0.00037610886,0.00003716881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.2767102,0.000031579042,0.0000774992,0.0000032261312,0.00092525716,5.2141326e-7,0.00013645302,0.7168636,0.000054251515,0.0050681042,0.00005829147,0.00007107172],"study_design_scores_gemma":[0.4680588,0.00025356878,0.000005306466,0.0000021641415,0.00048008066,4.7815513e-7,0.00001967831,0.53037715,0.000024514951,0.0000053801155,0.0006427831,0.00013009233],"about_ca_topic_score_codex":0.000039799783,"about_ca_topic_score_gemma":0.000032786076,"teacher_disagreement_score":0.9000373,"about_ca_system_score_codex":0.000036733094,"about_ca_system_score_gemma":0.00011774496,"threshold_uncertainty_score":0.67476684},"labels":[],"label_agreement":null},{"id":"W2912943342","doi":"","title":"Improving generalization in reinforcement learning on Atari 2600 games","year":2019,"lang":"en","type":"article","venue":"International journal of advance research, ideas and innovations in technology","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Hyperparameter; Machine learning; Regularization (linguistics); Overfitting; Deep learning; Transfer of learning; Artificial neural network","score_opus":0.01771163940650869,"score_gpt":0.3392445821240863,"score_spread":0.3215329427175776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912943342","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":[0.3185229,0.00017621843,0.6739059,0.0053682015,0.00048199604,0.00020041208,2.4463003e-7,0.0000316072,0.0013124811],"genre_scores_gemma":[0.97984105,0.00044911765,0.019169977,0.00014219237,0.000042050116,0.000007832794,0.0000029105988,0.000008053077,0.0003368309],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809504,0.00006855091,0.0006561436,0.00021124842,0.0007030121,0.00026601224],"domain_scores_gemma":[0.99798846,0.000154897,0.00035547564,0.00021400559,0.0012621062,0.00002503587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012698501,0.000093737486,0.00016455955,0.0033837478,0.000055028453,0.00010929822,0.0008991689,0.00009446643,0.000014777653],"category_scores_gemma":[0.0014841096,0.00009072343,0.000018257444,0.0016724054,0.00009318613,0.0008268675,0.0003700095,0.0009717518,0.000009471064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022007434,0.000025242078,0.025470745,0.0000071323416,0.000011657547,0.000025242254,0.000098442666,0.57896566,0.0026901485,0.35038793,0.000028263476,0.042267546],"study_design_scores_gemma":[0.0026651747,0.0015901206,0.012962431,0.0006625226,0.0000018146656,0.00013356998,0.0006036264,0.90572214,0.0044956687,0.049867436,0.020980202,0.0003152834],"about_ca_topic_score_codex":0.000029660223,"about_ca_topic_score_gemma":0.000009543767,"teacher_disagreement_score":0.6613181,"about_ca_system_score_codex":0.0003602396,"about_ca_system_score_gemma":0.00013016589,"threshold_uncertainty_score":0.42218322},"labels":[],"label_agreement":null},{"id":"W2913966743","doi":"10.1109/cdc.2018.8619157","title":"On Passivity and Reinforcement Learning in Finite Games","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Passivity; Reinforcement learning; Convergence (economics); Monotonic function; Stochastic game; Computer science; Property (philosophy); Class (philosophy); Exploit; Reinforcement; Mathematical optimization; Scheme (mathematics); Artificial intelligence; Mathematics; Mathematical economics; Engineering; Economics","score_opus":0.014901823723644646,"score_gpt":0.2495275137318254,"score_spread":0.23462569000818076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913966743","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":[0.013747062,0.0000047328604,0.9364775,0.00048733136,0.00012878582,0.00008838617,1.5469412e-8,0.00013298988,0.04893322],"genre_scores_gemma":[0.9849105,0.000011653432,0.0075427433,0.0006880549,0.000031701748,0.000004652587,5.735085e-7,0.000005075123,0.00680506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904037,0.000050190956,0.00017813152,0.00025616834,0.000226378,0.00024877995],"domain_scores_gemma":[0.9993322,0.00022426847,0.00006412797,0.00028645995,0.000035287205,0.00005768853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031007914,0.00010387408,0.00010336111,0.00013352271,0.000097545446,0.0001323597,0.00027823023,0.000040699415,0.00007791791],"category_scores_gemma":[0.00023876908,0.000089471454,0.000016934075,0.00022276067,0.00006497522,0.00026557778,0.00026451293,0.00018536791,0.00015711845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008307043,0.000011442377,0.006134047,0.0000079298425,0.000006074544,0.0000068732793,0.0007938813,0.86840296,0.00006303509,0.10879585,0.00051291933,0.015256672],"study_design_scores_gemma":[0.00030379553,0.0004904846,0.007065823,0.000030230747,9.1517705e-7,0.0000014471984,0.000019902112,0.9854684,0.0005214897,0.00049584697,0.0054702684,0.00013141443],"about_ca_topic_score_codex":0.00002787686,"about_ca_topic_score_gemma":0.00000956545,"teacher_disagreement_score":0.97116345,"about_ca_system_score_codex":0.00003567902,"about_ca_system_score_gemma":0.00002387921,"threshold_uncertainty_score":0.36485398},"labels":[],"label_agreement":null},{"id":"W2914461813","doi":"10.1007/978-3-030-04735-1_3","title":"Emergent Policy Discovery for Visual Reinforcement Learning Through Tangled Program Graphs: A Tutorial","year":2019,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Constructive; Task (project management); Computer science; A priori and a posteriori; Artificial intelligence; Human–computer interaction; Theoretical computer science; Machine learning; Programming language; Engineering","score_opus":0.016988921752373022,"score_gpt":0.27830949845595915,"score_spread":0.2613205767035861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914461813","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":[0.00013594312,0.0006609578,0.97882473,0.0002005368,0.0016958065,0.001818796,0.00000445728,0.00025168885,0.016407074],"genre_scores_gemma":[0.13300297,0.0019485058,0.36099845,0.00048510436,0.003978679,0.00040573865,0.002080097,0.0002498925,0.49685058],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750775,0.00004239508,0.00065866805,0.00071951543,0.000631308,0.00044038641],"domain_scores_gemma":[0.9987252,0.00013236402,0.0005196659,0.00028287308,0.0002457326,0.0000941806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014313693,0.00044433554,0.00039282924,0.00027704483,0.00036694808,0.00025466198,0.00033631013,0.00027796332,0.000013938475],"category_scores_gemma":[0.000041772626,0.0004685286,0.00022120374,0.00012376362,0.00010238269,0.00047546157,0.0003562237,0.00029390078,0.00004621684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037673646,0.000019658608,0.00003126316,0.00010997516,0.00012910608,0.000002154387,0.0002655052,0.78167444,0.000007365796,0.20203145,0.0015222299,0.014169166],"study_design_scores_gemma":[0.0010034982,0.0017267232,0.00046179007,0.00013136979,0.00008183141,0.000018936575,0.000018110424,0.8821999,0.0000022911486,0.048729997,0.06502155,0.0006039963],"about_ca_topic_score_codex":0.000024922725,"about_ca_topic_score_gemma":9.306257e-7,"teacher_disagreement_score":0.6178263,"about_ca_system_score_codex":0.00025971956,"about_ca_system_score_gemma":0.00050759374,"threshold_uncertainty_score":0.99977666},"labels":[],"label_agreement":null},{"id":"W2918549499","doi":"10.1145/3319619.3321956","title":"Novelty search for deep reinforcement learning policy network weights by action sequence edit metric distance","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Neuroevolution; Computer science; Novelty; Metric (unit); Benchmark (surveying); Deep learning; Machine learning; Action (physics); Artificial neural network","score_opus":0.04233092629446205,"score_gpt":0.2901398948073653,"score_spread":0.24780896851290324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2918549499","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":[0.016025875,0.0005798574,0.9794462,0.00087135227,0.0011360149,0.0013607696,0.0000065519544,0.00011734711,0.00045604113],"genre_scores_gemma":[0.947812,0.0004780988,0.05051413,0.00006724621,0.000373351,0.00006929907,0.00008666609,0.000025056283,0.00057414593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969352,0.000061048006,0.0007569444,0.0008164805,0.0008967895,0.00053355255],"domain_scores_gemma":[0.9969152,0.0002458722,0.001081103,0.00027891347,0.0013559514,0.0001229586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004961826,0.00041217552,0.0004775243,0.0002851379,0.00055771874,0.0003518965,0.0013254215,0.00025798992,0.0000047995773],"category_scores_gemma":[0.0001286769,0.00037322228,0.0001601746,0.00075433054,0.00019013153,0.00040706858,0.0016633797,0.000691253,0.000005611929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025887357,0.000021077432,0.0051025264,0.0005293107,0.0000541063,4.7171195e-8,0.0003712396,0.9686683,0.00025456178,0.019645829,0.0014676243,0.0038595048],"study_design_scores_gemma":[0.00041345798,0.00019452558,0.012561808,0.0003812916,0.00003962315,0.000009014224,0.000079141246,0.97487086,0.00023251786,0.009839672,0.0010062449,0.00037183883],"about_ca_topic_score_codex":0.00007599423,"about_ca_topic_score_gemma":7.1107286e-7,"teacher_disagreement_score":0.9317861,"about_ca_system_score_codex":0.0004200783,"about_ca_system_score_gemma":0.0004870877,"threshold_uncertainty_score":0.99987197},"labels":[],"label_agreement":null},{"id":"W2919205453","doi":"10.48550/arxiv.1903.00194","title":"Should All Temporal Difference Learning Use Emphasis?","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Counterexample; Convergence (economics); Temporal difference learning; Computer science; Simple (philosophy); Class (philosophy); Artificial intelligence; Mathematics; Economics; Reinforcement learning; Epistemology; Discrete mathematics","score_opus":0.18257296351319344,"score_gpt":0.22286829858392074,"score_spread":0.0402953350707273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919205453","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":[0.16205756,0.000021886715,0.8342632,0.00008744911,0.000920164,0.0003328431,0.0000026397597,0.00053438277,0.0017798548],"genre_scores_gemma":[0.96756905,0.00015034231,0.0037764693,0.00021781327,0.00006279454,8.279506e-7,0.00004521078,0.000038640777,0.028138869],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692786,0.0002945088,0.00033144007,0.0015251176,0.00026351213,0.00065758923],"domain_scores_gemma":[0.99674505,0.0003029727,0.0005371541,0.0019784637,0.00019763943,0.00023873652],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031215165,0.0005355574,0.0005212705,0.00036202342,0.00018581311,0.0006143313,0.0032437835,0.00050795823,0.000046674588],"category_scores_gemma":[0.00015062078,0.0006147572,0.000304976,0.00048106542,0.00011550036,0.00077248545,0.004624381,0.0018229049,0.00045057354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012990248,0.000030856878,0.08017468,0.000059926693,0.000098455625,0.00017067626,0.00023650784,0.8996584,0.000019568146,0.019132465,0.00015697854,0.00024850122],"study_design_scores_gemma":[0.00042342537,0.00011057222,0.008725437,0.00012785407,0.00006479557,0.000004681741,0.000035391095,0.9842499,0.000032232252,0.0009804505,0.0045388425,0.00070643617],"about_ca_topic_score_codex":0.0002686908,"about_ca_topic_score_gemma":0.000013092132,"teacher_disagreement_score":0.8304868,"about_ca_system_score_codex":0.00031365757,"about_ca_system_score_gemma":0.00026585726,"threshold_uncertainty_score":0.9996304},"labels":[],"label_agreement":null},{"id":"W2922221969","doi":"10.65109/knvj7743","title":"On the Pitfalls of Measuring Emergent Communication","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Set (abstract data type); Task (project management); Action (physics); Human–computer interaction; Reinforcement learning; Channel (broadcasting); Simple (philosophy); Measure (data warehouse); Data science; Artificial intelligence; Telecommunications; Data mining; Engineering","score_opus":0.05880800494805078,"score_gpt":0.26068876717904227,"score_spread":0.2018807622309915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922221969","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":[0.0029737859,0.0000661864,0.9374107,0.0017799005,0.0005267725,0.00037617842,3.3635473e-7,0.000081341896,0.056784783],"genre_scores_gemma":[0.98002446,0.00013321338,0.017144443,0.0002698761,0.000012747923,0.00001470695,0.0000042952265,0.000010096696,0.002386139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998593,0.00017703202,0.00033973035,0.00024061126,0.0005103669,0.00013927564],"domain_scores_gemma":[0.99602,0.00032540015,0.0003635467,0.0031316036,0.00013562117,0.000023821842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077828893,0.00014440018,0.00017872706,0.00007114805,0.00006274077,0.0000925956,0.00334142,0.00009725813,0.00008450047],"category_scores_gemma":[0.00013409537,0.000097181925,0.00010687139,0.00009493145,0.00003268855,0.00006211126,0.0031352711,0.0005260045,0.00015540181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.538071e-7,0.000010461603,0.00009302131,0.000030138131,0.000026409289,6.382322e-8,0.00028175532,0.7824155,0.00002922221,0.2155924,0.0012634615,0.00025673743],"study_design_scores_gemma":[0.00008223448,0.000045571524,0.0009201918,0.000264585,0.000009015173,3.2714848e-7,0.000025466166,0.98997855,0.001902709,0.005577838,0.0010031085,0.00019037857],"about_ca_topic_score_codex":0.00006166663,"about_ca_topic_score_gemma":0.000002130948,"teacher_disagreement_score":0.9770507,"about_ca_system_score_codex":0.00005458347,"about_ca_system_score_gemma":0.00007729986,"threshold_uncertainty_score":0.62092453},"labels":[],"label_agreement":null},{"id":"W2923023063","doi":"","title":"Modeling the Long Term Future in Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Term (time); Computer science; Artificial intelligence","score_opus":0.05336023462993137,"score_gpt":0.3395181485785783,"score_spread":0.2861579139486469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923023063","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":[0.022364546,0.0000068754734,0.9443343,0.0053693927,0.0005962415,0.00023402543,3.3172103e-7,0.00019278828,0.02690149],"genre_scores_gemma":[0.99102056,0.000027519127,0.0040627695,0.0004029264,0.00029843624,0.00006261072,0.000038432274,0.000019145022,0.004067599],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99760765,0.00019271462,0.000478996,0.0005234884,0.000834597,0.00036254327],"domain_scores_gemma":[0.9985235,0.00016308326,0.00020881023,0.00052868883,0.000499045,0.00007691718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00050632824,0.00021718588,0.00015119107,0.00035923487,0.00051763334,0.00056117866,0.0014540895,0.00008671531,0.00020383946],"category_scores_gemma":[0.0003475939,0.00018553913,0.00009041037,0.00041409268,0.000118270735,0.0005557809,0.00028184656,0.00091501843,0.00017475509],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018679137,0.000020690892,0.0075202994,0.0000033409253,0.00002029792,0.0000061644523,0.0019422547,0.9346972,0.00016215653,0.053045616,0.000029290437,0.002533969],"study_design_scores_gemma":[0.0004504243,0.00012735702,0.0024030972,0.00008758438,0.000005412826,0.000003825444,0.0003157911,0.99559313,0.00014094084,0.0004990416,0.00017274564,0.00020063134],"about_ca_topic_score_codex":0.00006324796,"about_ca_topic_score_gemma":0.000039805593,"teacher_disagreement_score":0.968656,"about_ca_system_score_codex":0.00017103976,"about_ca_system_score_gemma":0.0002157337,"threshold_uncertainty_score":0.75660664},"labels":[],"label_agreement":null},{"id":"W2924816077","doi":"10.1613/jair.1.11418","title":"Modeling and Planning with Macro-Actions in Decentralized POMDPs","year":2019,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Office of Naval Research; National Institute of Mental Health; Multidisciplinary University Research Initiative; Air Force Office of Scientific Research; Defense Advanced Research Projects Agency; National Institutes of Health; National Science Foundation","keywords":"Computer science; Partially observable Markov decision process; Macro; Markov decision process; Exploit; Action (physics); Class (philosophy); Mathematical optimization; Artificial intelligence; Markov chain; Markov process; Markov model; Machine learning","score_opus":0.20964206851014752,"score_gpt":0.4311779567163518,"score_spread":0.22153588820620426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2924816077","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":[0.36278734,0.00010050133,0.6362987,0.00030767152,0.00013210576,0.000106173626,5.580359e-8,0.000009727021,0.0002577418],"genre_scores_gemma":[0.9662137,0.00016058079,0.033509724,0.000016236843,0.00005124862,0.0000013794031,1.1066834e-7,0.000007967464,0.00003903439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978803,0.00017102473,0.0005053427,0.00018438071,0.000822575,0.00043638007],"domain_scores_gemma":[0.9987199,0.00030542834,0.00011269359,0.00022550022,0.0005032152,0.00013330425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018558255,0.000088824876,0.00018916817,0.0005993817,0.000113842994,0.00032907902,0.00058448134,0.00005387374,0.000025271758],"category_scores_gemma":[0.00022947647,0.00007097164,0.000033416298,0.00079452427,0.000057580277,0.00069117954,0.00014941422,0.0008143232,0.000034851117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080288046,0.000036098427,0.0027333284,0.000014194178,0.000014638573,0.000063933585,0.0021579328,0.97746897,0.0014558723,0.009273256,0.00000569837,0.006695802],"study_design_scores_gemma":[0.00006661425,0.00036394031,0.00018003826,0.00017279711,0.0000020491366,0.00007099236,0.0016895753,0.99303955,0.0019521796,0.002272105,0.000105936684,0.00008421562],"about_ca_topic_score_codex":0.000044577468,"about_ca_topic_score_gemma":0.000012790404,"teacher_disagreement_score":0.6034264,"about_ca_system_score_codex":0.00012291558,"about_ca_system_score_gemma":0.00023613962,"threshold_uncertainty_score":0.35378742},"labels":[],"label_agreement":null},{"id":"W2925216817","doi":"10.48550/arxiv.1903.09295","title":"DQN with model-based exploration: efficient learning on environments with sparse rewards","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.06704040110681203,"score_gpt":0.17622591528041712,"score_spread":0.10918551417360509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925216817","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":[0.065414175,0.000004770893,0.93017155,0.000081635924,0.00016880025,0.0005008143,0.0000016714655,0.00021705632,0.003439537],"genre_scores_gemma":[0.9850028,0.000018356443,0.008681974,0.000121128236,0.000026219868,0.0000028868265,0.000032178246,0.00004294223,0.0060714963],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745077,0.00015821536,0.00020123001,0.0013398033,0.00040321818,0.00044673853],"domain_scores_gemma":[0.9975382,0.00008587239,0.00045155195,0.0016762522,0.00008014704,0.00016794764],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024533054,0.0004728897,0.000358497,0.00030087365,0.00023026964,0.00018309691,0.0013946069,0.0002191868,0.000014915538],"category_scores_gemma":[0.000015636197,0.00044215404,0.00010455237,0.0004102327,0.00013691915,0.0003125949,0.00078666094,0.0010271852,0.00025664782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013739434,0.000080976584,0.0016255856,0.000044164608,0.000062786276,0.00013343428,0.00029000873,0.98794913,0.000006477475,0.009593773,0.000021875974,0.00005438118],"study_design_scores_gemma":[0.0010292219,0.0006178865,0.00018096552,0.000271427,0.00006330882,0.0000015421961,0.00005621008,0.99663305,0.00015525495,0.000102644175,0.0003203279,0.0005681366],"about_ca_topic_score_codex":0.000012669284,"about_ca_topic_score_gemma":0.0000019851584,"teacher_disagreement_score":0.92148954,"about_ca_system_score_codex":0.0004938805,"about_ca_system_score_gemma":0.0003593204,"threshold_uncertainty_score":0.999803},"labels":[],"label_agreement":null},{"id":"W2925234320","doi":"10.48550/arxiv.1903.09762","title":"TTR-Based Reward for Reinforcement Learning with Implicit Model Priors","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Key (lock); Function (biology); Inefficiency; Artificial intelligence; Process (computing); Exploit; Temporal difference learning; State (computer science); Machine learning; Algorithm","score_opus":0.06577840482045562,"score_gpt":0.19876942502459402,"score_spread":0.1329910202041384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2925234320","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":[0.01540967,0.000008610238,0.9791676,0.00010789839,0.00029475533,0.0012779501,0.000003204333,0.00046218463,0.0032681199],"genre_scores_gemma":[0.95753354,0.000024984074,0.029201636,0.00021130942,0.000041320356,0.000007768915,0.000060241313,0.000057217017,0.012861993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971322,0.000083366365,0.00035672018,0.0014358958,0.00026184611,0.0007299878],"domain_scores_gemma":[0.99669677,0.00020200321,0.00067094027,0.0018551005,0.0003679423,0.00020723314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040971127,0.00054882566,0.00053841906,0.00039036717,0.00028540782,0.0002526101,0.002386465,0.00036151268,0.000012733373],"category_scores_gemma":[0.00006046814,0.00057988596,0.00030409332,0.0004469784,0.00009351291,0.0004146022,0.0015268596,0.0009664318,0.000071114286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010246073,0.000020290245,0.0014203205,0.0002275378,0.000108747125,0.000022107804,0.00019356515,0.9587315,0.000020686288,0.038927764,0.00015638098,0.00006868828],"study_design_scores_gemma":[0.0013259348,0.00043699876,0.00007243012,0.00021799938,0.000108084736,0.0000014815058,0.000043733085,0.9952367,0.00012618728,0.000890116,0.0008096861,0.00073067384],"about_ca_topic_score_codex":0.000045427852,"about_ca_topic_score_gemma":0.0000047456383,"teacher_disagreement_score":0.94996595,"about_ca_system_score_codex":0.0005134555,"about_ca_system_score_gemma":0.00081655395,"threshold_uncertainty_score":0.99966526},"labels":[],"label_agreement":null},{"id":"W2928034659","doi":"10.1109/icpr48806.2021.9412212","title":"Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; College of Natural Resources and Sciences, Humboldt State University; Agence Nationale de la Recherche","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Robotics; High fidelity; Deep learning; Suite; Human–computer interaction; Fidelity; Distributed computing; Machine learning; Robot","score_opus":0.008855926514395013,"score_gpt":0.23073166799091988,"score_spread":0.22187574147652486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2928034659","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":[0.0019668208,0.00009516179,0.98006564,0.00074021873,0.00024759362,0.00016037178,3.1658836e-8,0.00028078095,0.01644335],"genre_scores_gemma":[0.81998837,0.000037722355,0.17167714,0.0025013029,0.00008029413,0.00001272828,0.000003833203,0.000019436917,0.005679153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809206,0.00014091545,0.0003170009,0.0005436449,0.00045648508,0.00044990034],"domain_scores_gemma":[0.99891704,0.0001587073,0.00009124178,0.00053110824,0.00014162822,0.00016027447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000339609,0.000229881,0.00027572952,0.00010911444,0.00026114116,0.0004875441,0.00037240802,0.00007827125,0.00006232362],"category_scores_gemma":[0.00017615235,0.00020842988,0.0000625339,0.000263949,0.00004116635,0.00041290288,0.00035537046,0.0003657741,0.00008409088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009821094,0.0000132146615,0.005948067,0.00001319095,0.00004976062,0.000051479517,0.00064459955,0.9578801,0.00019196124,0.027974077,0.00015996132,0.0070637763],"study_design_scores_gemma":[0.0010983484,0.0002527752,0.0011649505,0.00005886958,0.0000120588165,0.00006347201,0.00006560103,0.99105287,0.00028107848,0.000040220875,0.005646084,0.0002636761],"about_ca_topic_score_codex":0.000014212343,"about_ca_topic_score_gemma":0.0000029097432,"teacher_disagreement_score":0.8180216,"about_ca_system_score_codex":0.00006288122,"about_ca_system_score_gemma":0.00007157344,"threshold_uncertainty_score":0.8499524},"labels":[],"label_agreement":null},{"id":"W2930281309","doi":"10.48550/arxiv.1904.01191","title":"Planning with Expectation Models","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Parametrization (atmospheric modeling); Convergence (economics); Mathematical optimization; Bellman equation; Function (biology); State (computer science); Artificial intelligence; Mathematics; Algorithm","score_opus":0.10319231109665329,"score_gpt":0.19053988156606383,"score_spread":0.08734757046941054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930281309","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":[0.04830114,0.000018415625,0.9385781,0.000026081107,0.00032992338,0.0002484556,9.227472e-7,0.0002848172,0.0122121],"genre_scores_gemma":[0.9871695,0.000017069755,0.009301573,0.000051218078,0.00003269067,6.294429e-7,0.000015127944,0.00001891358,0.0033932794],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985452,0.00006781927,0.00014047902,0.00081553485,0.00013960988,0.0002913355],"domain_scores_gemma":[0.99830246,0.00007625933,0.00028356066,0.001120216,0.00013067164,0.00008680413],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011293359,0.00025477482,0.00023602824,0.00023299051,0.000100047044,0.00016349058,0.0014296371,0.00018534463,0.000008843119],"category_scores_gemma":[0.000008945869,0.00027088655,0.00008257115,0.0003383713,0.00004549578,0.0006905291,0.0011199359,0.00052016176,0.000092310176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014513297,0.00000930208,0.0020669578,0.00003799006,0.000047256566,0.000098255216,0.0006936194,0.9372456,0.0000030359274,0.059679322,0.0000735802,0.00003059001],"study_design_scores_gemma":[0.0003235267,0.00007481882,0.00039308314,0.0001446457,0.000027815891,0.0000030464498,0.00012252101,0.99463314,0.000026223699,0.0038463275,0.00006100817,0.00034383315],"about_ca_topic_score_codex":0.00003142,"about_ca_topic_score_gemma":0.0000013647316,"teacher_disagreement_score":0.93886834,"about_ca_system_score_codex":0.00017409469,"about_ca_system_score_gemma":0.00018706878,"threshold_uncertainty_score":0.9999743},"labels":[],"label_agreement":null},{"id":"W2936568671","doi":"10.48550/arxiv.1904.09024","title":"When is a Prediction Knowledge?","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Variety (cybernetics); Computer science; Reinforcement learning; Value (mathematics); Artificial intelligence; Predictive value; Body of knowledge; Work (physics); Knowledge management; Data science; Epistemology; Machine learning; Engineering","score_opus":0.07118221310828741,"score_gpt":0.19075482663090618,"score_spread":0.11957261352261876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936568671","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":[0.009176275,0.00004888804,0.9555806,0.00011425375,0.0015470531,0.00036951245,0.000008103856,0.00043351366,0.03272179],"genre_scores_gemma":[0.9630311,0.00009927189,0.002459701,0.0001305672,0.00009589589,8.0200016e-7,0.000018332772,0.000021816784,0.034142483],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981047,0.00011213011,0.00021751311,0.0010839741,0.00012273701,0.00035894223],"domain_scores_gemma":[0.99749017,0.00008284473,0.0002731713,0.0018237783,0.00019487037,0.000135168],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00022025216,0.00030901318,0.000292907,0.00029747136,0.000119300006,0.00018922701,0.002277746,0.0003692662,0.000104854655],"category_scores_gemma":[0.000027505734,0.00037168124,0.0002149338,0.00035734347,0.0000659933,0.00046334026,0.0031358877,0.00074390386,0.0014173388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063976795,0.000030633357,0.003406824,0.00009342525,0.000082240986,0.000027053098,0.00094701094,0.95661515,0.0000051890293,0.033117253,0.005419091,0.00024974823],"study_design_scores_gemma":[0.00033913742,0.00006678515,0.0006776692,0.00011032138,0.000050831706,0.0000024385618,0.00002576253,0.9758659,0.000044201894,0.010060737,0.012423246,0.0003329431],"about_ca_topic_score_codex":0.000040389164,"about_ca_topic_score_gemma":0.0000030307622,"teacher_disagreement_score":0.95385486,"about_ca_system_score_codex":0.0003166965,"about_ca_system_score_gemma":0.0002914165,"threshold_uncertainty_score":0.9998735},"labels":[],"label_agreement":null},{"id":"W2941011530","doi":"","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Variance reduction; Reduction (mathematics); Computer science; Variance (accounting); Estimation; Artificial intelligence; Reinforcement; Machine learning; Statistics; Econometrics; Psychology; Mathematics; Engineering; Economics; Social psychology","score_opus":0.050061910459263996,"score_gpt":0.3514664291660533,"score_spread":0.3014045187067893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941011530","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":[0.002523527,0.0000038316425,0.9629498,0.0023364895,0.0010383397,0.000390612,3.5136165e-7,0.00022060916,0.030536426],"genre_scores_gemma":[0.9528331,0.000029124656,0.038642287,0.000085683474,0.00022732583,0.00016183939,0.00008436644,0.00001744572,0.0079187825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979142,0.0001416655,0.0005085344,0.00056343275,0.00055551325,0.00031664225],"domain_scores_gemma":[0.9983661,0.00023520784,0.0003558306,0.00035132543,0.00062068336,0.00007085899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005266555,0.00018093985,0.00015729728,0.00044262077,0.0003647114,0.000399239,0.00072638545,0.00008665099,0.00019464169],"category_scores_gemma":[0.0013387975,0.00020433681,0.00007214658,0.00041789367,0.00009674174,0.0008841581,0.00014845174,0.00043453352,0.00020710085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035922138,0.000022514421,0.0009021045,0.000006721565,0.000022406311,0.0000016806978,0.0021735965,0.82472324,0.0006026715,0.16426854,0.0001000622,0.007140503],"study_design_scores_gemma":[0.00062066974,0.0003707816,0.0014450029,0.00009933899,0.0000057364746,0.000010101881,0.00035098428,0.9904602,0.00076098286,0.0032892718,0.0023843127,0.000202627],"about_ca_topic_score_codex":0.00006449973,"about_ca_topic_score_gemma":0.0000072247167,"teacher_disagreement_score":0.95030963,"about_ca_system_score_codex":0.00023378403,"about_ca_system_score_gemma":0.00011390149,"threshold_uncertainty_score":0.8332614},"labels":[],"label_agreement":null},{"id":"W2943366292","doi":"10.1038/s42256-019-0053-0","title":"Moving beyond reward prediction errors","year":2019,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Reinforcement Learning in Robotics","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 Scarborough Hospital; Canadian Institute for Advanced Research; University of Toronto; Vector Institute","funders":"","keywords":"Business; Computer science","score_opus":0.006224225736806918,"score_gpt":0.25221000272268734,"score_spread":0.24598577698588042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943366292","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":[0.0043258485,0.0004596941,0.9710661,0.00071471324,0.0026022939,0.0002685733,0.0000025733677,0.00040428917,0.020155875],"genre_scores_gemma":[0.96459013,0.000041616728,0.03104098,0.00089337275,0.000111122696,0.0000053939716,0.0000117228665,0.00001849287,0.003287183],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980791,0.000060470305,0.00034203214,0.0005345851,0.0006197447,0.00036402853],"domain_scores_gemma":[0.9985601,0.00015141886,0.00015816769,0.00090363366,0.00012781612,0.00009888591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043158745,0.00021578422,0.00018536393,0.00018719929,0.00010520796,0.000157589,0.0014690965,0.00027887002,0.00015458053],"category_scores_gemma":[0.00022419677,0.0001936553,0.000091740156,0.00060652284,0.000036123438,0.00059954793,0.00042115632,0.0012833481,0.00068513735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015217331,0.000032887765,0.025241053,0.000059876635,0.000040021587,0.000018110819,0.0008365958,0.83449656,0.0009155343,0.09966774,0.0012550046,0.037421398],"study_design_scores_gemma":[0.0000841907,0.00017563933,0.0027424665,0.000054196953,0.0000070620954,0.000033343636,0.000029128441,0.9756142,0.005417157,0.002659484,0.01291193,0.00027118376],"about_ca_topic_score_codex":0.000023359044,"about_ca_topic_score_gemma":0.0000035021417,"teacher_disagreement_score":0.96026427,"about_ca_system_score_codex":0.000093247145,"about_ca_system_score_gemma":0.00005501392,"threshold_uncertainty_score":0.8806283},"labels":[],"label_agreement":null},{"id":"W2945054955","doi":"10.48550/arxiv.1905.10016","title":"A Micro-Objective Perspective of Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Perspective (graphical); Reinforcement learning; Reinforcement; Computer science; Psychology; Artificial intelligence; Social psychology","score_opus":0.04403034584286141,"score_gpt":0.1983845935839299,"score_spread":0.15435424774106848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945054955","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":[0.022328047,0.000057160403,0.9467029,0.000050498034,0.000602484,0.0005418347,0.0000018640548,0.0002069965,0.029508218],"genre_scores_gemma":[0.9864228,0.00013948164,0.0026024522,0.000042710697,0.000043874796,9.666978e-7,0.000011091323,0.000026911503,0.010709721],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757683,0.00020947882,0.000351376,0.0011824605,0.00021812099,0.00046173646],"domain_scores_gemma":[0.99678534,0.00019041957,0.0008334872,0.0014385196,0.00063102617,0.000121196645],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034188948,0.0004165032,0.00055319525,0.00047188273,0.00013609802,0.00009878967,0.0021467337,0.00032774126,0.000049827893],"category_scores_gemma":[0.00013710393,0.0004980929,0.00035932916,0.00064462936,0.00015528568,0.00039649397,0.0035144202,0.0012370963,0.00017962839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030125446,0.000024911578,0.0019348598,0.00008698015,0.00020431263,0.00003945844,0.0016687203,0.8548553,0.00011472881,0.14095427,0.000056575198,0.000029750396],"study_design_scores_gemma":[0.00064595946,0.0002772103,0.00060899154,0.0002015673,0.000083273466,0.0000033545114,0.0010078889,0.99134386,0.0009053676,0.0041558314,0.0002385035,0.000528202],"about_ca_topic_score_codex":0.0003334157,"about_ca_topic_score_gemma":0.000004017805,"teacher_disagreement_score":0.96409476,"about_ca_system_score_codex":0.0008315761,"about_ca_system_score_gemma":0.00047032087,"threshold_uncertainty_score":0.9997471},"labels":[],"label_agreement":null},{"id":"W2945090640","doi":"10.1007/978-3-030-18305-9_18","title":"Options in Multi-task Reinforcement Learning - Transfer via Reflection","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Ottawa","funders":"","keywords":"Reinforcement learning; Regret; Computer science; Transfer of learning; Artificial intelligence; Context (archaeology); State space; Task (project management); Landmark; Formalism (music); Reflection (computer programming); Machine learning","score_opus":0.029580750455954798,"score_gpt":0.27283070230665457,"score_spread":0.24324995185069978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945090640","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":[0.00003908031,0.00013222011,0.99263144,0.00026737835,0.0019437606,0.00074703543,4.618864e-7,0.00022756124,0.0040110443],"genre_scores_gemma":[0.6094308,0.00022340534,0.38038793,0.0011257544,0.0002962424,0.000029704743,0.000027760536,0.00010101186,0.008377407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519575,0.00008782197,0.0009030528,0.0016362872,0.0012488796,0.00092819537],"domain_scores_gemma":[0.9977198,0.00032505044,0.00024349683,0.0013424259,0.00021344141,0.00015577352],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013407787,0.00063956867,0.0006064167,0.0016511474,0.00030268455,0.00053388526,0.002588277,0.0004623015,0.000046341393],"category_scores_gemma":[0.000093180286,0.0006480951,0.00017314342,0.00101638,0.00034986573,0.0009976637,0.0008313095,0.0020530755,0.00021971254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053904587,0.000015716614,0.000107788,0.00003678577,0.000009365505,0.000025681751,0.0008364464,0.93899286,0.00042841333,0.0058670617,0.000002432966,0.053672068],"study_design_scores_gemma":[0.0005853624,0.00034014336,0.00021332825,0.00042014944,0.000007925979,0.000034432724,3.2628276e-7,0.9930965,0.00036468368,0.0022546921,0.0019793932,0.00070310675],"about_ca_topic_score_codex":0.000060649836,"about_ca_topic_score_gemma":0.00010698928,"teacher_disagreement_score":0.61224353,"about_ca_system_score_codex":0.00091232435,"about_ca_system_score_gemma":0.00058217073,"threshold_uncertainty_score":0.999597},"labels":[],"label_agreement":null},{"id":"W2945334994","doi":"10.65109/iadj1863","title":"Exploration in the Face of Parametric and Intrinsic Uncertainties","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Reinforcement learning; Parametric statistics; Schedule; Computer science; Face (sociological concept); Quantile; Mathematical optimization; Probability distribution; Artificial intelligence; Mathematics; Statistics","score_opus":0.024700165815132093,"score_gpt":0.24619408057435277,"score_spread":0.22149391475922067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945334994","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":[0.24321988,0.000030982574,0.75292677,0.0005187141,0.00006601998,0.0001415213,2.1611665e-8,0.000015615231,0.0030804547],"genre_scores_gemma":[0.99535304,0.000023257526,0.0040708464,0.00010583751,0.000003020069,0.0000021870792,2.879175e-7,0.0000011349222,0.00044040062],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995461,0.000040030016,0.00010950104,0.000086263535,0.00014900407,0.00006909066],"domain_scores_gemma":[0.9995382,0.0001659091,0.00004484228,0.00022390866,0.000020083462,0.0000070469473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024642935,0.000037286572,0.000058684396,0.00010522857,0.000011717402,0.000054309447,0.0002790383,0.000016315333,0.0000051979455],"category_scores_gemma":[0.00005143758,0.000023674944,0.000008682954,0.00048127215,0.000017398132,0.00034348955,0.000076795935,0.000054977307,0.000019467581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023674063,0.000012054954,0.03109245,0.000022155293,0.0000040221817,5.617417e-7,0.0051847105,0.8057129,0.00005894038,0.14743902,0.00014722855,0.010323621],"study_design_scores_gemma":[0.00022614378,0.00016195374,0.02054617,0.000011107802,0.0000013322067,0.0000015314138,0.0018696062,0.9746916,0.00044620055,0.0013043123,0.00066491135,0.0000751048],"about_ca_topic_score_codex":0.00003436134,"about_ca_topic_score_gemma":0.0000022025931,"teacher_disagreement_score":0.75213313,"about_ca_system_score_codex":0.00000739872,"about_ca_system_score_gemma":0.00001091357,"threshold_uncertainty_score":0.09654362},"labels":[],"label_agreement":null},{"id":"W2945374007","doi":"10.1007/978-3-030-18305-9_68","title":"Safe Policy Learning with Constrained Return Variance","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Variance (accounting); Artificial intelligence; Machine learning; Accounting","score_opus":0.011840084781795424,"score_gpt":0.23573608348315536,"score_spread":0.22389599870135993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945374007","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":[0.000011165955,0.000095694966,0.9542358,0.0014353427,0.0009599048,0.0004935893,0.0000013963295,0.0002730445,0.04249405],"genre_scores_gemma":[0.16921754,0.000064107844,0.8123914,0.0028619752,0.0009014324,0.000007678427,0.00001213153,0.00010688807,0.01443684],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994888,0.00006453341,0.00061217975,0.0018409938,0.0015375223,0.0010567628],"domain_scores_gemma":[0.9962356,0.0006899589,0.0006151683,0.0018762109,0.00035609998,0.00022695337],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009777768,0.00073719345,0.00072412076,0.0011203472,0.00034866823,0.0009246892,0.004065661,0.00039958957,0.000045057524],"category_scores_gemma":[0.00028057717,0.0006345338,0.00012181963,0.0011007278,0.001072986,0.0008128109,0.0014100734,0.001980544,0.00017949195],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008055686,0.0000064367814,0.00015859546,0.000041800788,0.000017911509,0.00008291264,0.00047927277,0.84006155,0.0000574368,0.063093424,0.000007902089,0.095984735],"study_design_scores_gemma":[0.0005305195,0.0005839366,0.00010394125,0.00072671677,0.000010092204,0.00020273251,2.783664e-7,0.9778859,0.00021397593,0.011828969,0.00695263,0.00096028333],"about_ca_topic_score_codex":0.000030758332,"about_ca_topic_score_gemma":0.000015717518,"teacher_disagreement_score":0.16920638,"about_ca_system_score_codex":0.000528103,"about_ca_system_score_gemma":0.0027581628,"threshold_uncertainty_score":0.9996106},"labels":[],"label_agreement":null},{"id":"W2945943081","doi":"10.24963/ijcai.2019/581","title":"Metatrace Actor-Critic: Online Step-Size Tuning by Meta-gradient Descent for Reinforcement Learning Control","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Hyperparameter; Reinforcement learning; Computer science; Robustness (evolution); Gradient descent; Artificial intelligence; Nonlinear system; Function approximation; Machine learning; Mathematical optimization; Artificial neural network; Mathematics","score_opus":0.04272323222080878,"score_gpt":0.286499092031481,"score_spread":0.2437758598106722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945943081","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":[0.0002418253,0.0012780474,0.988843,0.0016280148,0.0023261376,0.003341442,0.000035790235,0.0007303784,0.0015753304],"genre_scores_gemma":[0.6450583,0.00031996903,0.3172833,0.0019552356,0.00026459916,0.0005544031,0.0003833122,0.00015770651,0.034023214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99313575,0.00039958025,0.0016943173,0.0018120578,0.001465357,0.0014929175],"domain_scores_gemma":[0.9934676,0.0019723482,0.0012326166,0.0022240041,0.0006865549,0.00041683763],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018284451,0.0011822638,0.0019872633,0.0002731766,0.00036864687,0.0010556603,0.0031736656,0.00051174493,0.00022659267],"category_scores_gemma":[0.0010316217,0.0010310606,0.0013095152,0.00026268463,0.00009783634,0.00057897647,0.0022282547,0.0020152573,0.000083866085],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004008587,0.000094659394,0.00011410199,0.00045366582,0.003029108,0.0000056101558,0.0002824261,0.9815964,0.00044502996,0.006622696,0.006021292,0.0012949],"study_design_scores_gemma":[0.0018935482,0.00052464113,0.000038485618,0.00014929727,0.0017080306,0.000005961144,0.00013098873,0.9231559,0.0005440687,0.00009417424,0.070668995,0.0010859298],"about_ca_topic_score_codex":0.00011817402,"about_ca_topic_score_gemma":0.0000058972246,"teacher_disagreement_score":0.67155975,"about_ca_system_score_codex":0.000576345,"about_ca_system_score_gemma":0.00042700508,"threshold_uncertainty_score":0.99998134},"labels":[],"label_agreement":null},{"id":"W2946045694","doi":"10.24963/ijcai.2019/85","title":"A Regularized Opponent Model with Maximum Entropy Objective","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Principle of maximum entropy; Computer science; Inference; Binary number; Mathematical optimization; Probabilistic logic; Iterated function; Random variable; Artificial intelligence; Algorithm; Mathematics","score_opus":0.018995473682165354,"score_gpt":0.23647779733778454,"score_spread":0.21748232365561918,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946045694","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":[0.00059654913,0.000020436737,0.9731176,0.00085310335,0.00059175305,0.0010094665,0.000002611729,0.0005083341,0.02330014],"genre_scores_gemma":[0.17662312,0.000033949094,0.78931576,0.00055184856,0.000066097135,0.000090316455,0.000039024537,0.000055313078,0.033224538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99693227,0.0000985715,0.00039734598,0.0011155662,0.00091720035,0.00053905457],"domain_scores_gemma":[0.99665654,0.000071372604,0.00039204396,0.0024727474,0.0002592389,0.00014804475],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030643796,0.00048557285,0.00054798386,0.00021263446,0.00008412526,0.00053133385,0.0022807622,0.0003073368,0.00003497357],"category_scores_gemma":[0.000031747983,0.00037779665,0.00017320311,0.00017875564,0.00006565231,0.00028291566,0.0035770007,0.0009466971,0.00022420193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003298082,0.000026984144,0.0000782222,0.000060856975,0.00012611225,0.000012688315,0.0004870593,0.9513723,0.00012813434,0.04700194,0.0004390023,0.00023370393],"study_design_scores_gemma":[0.0007270946,0.00014017553,0.00007854938,0.00010784006,0.000031843636,0.000010314624,0.00002008912,0.98922354,0.00046715877,0.008448056,0.0002152179,0.0005301042],"about_ca_topic_score_codex":0.00005559376,"about_ca_topic_score_gemma":0.0000017174068,"teacher_disagreement_score":0.18380181,"about_ca_system_score_codex":0.0002957916,"about_ca_system_score_gemma":0.0007367008,"threshold_uncertainty_score":0.9998674},"labels":[],"label_agreement":null},{"id":"W2946669606","doi":"10.65109/ugvb1408","title":"Building Knowledge for AI Agents with Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Generalization; Artificial intelligence; Function (biology); Reinforcement; Machine learning; Engineering","score_opus":0.01839217257182383,"score_gpt":0.2856183917926542,"score_spread":0.26722621922083034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946669606","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":[0.0024594243,0.000010949729,0.95300835,0.00020957128,0.00031246623,0.0005334624,4.0782563e-8,0.0002719782,0.04319374],"genre_scores_gemma":[0.8069296,0.0000026717419,0.14645202,0.00042379322,0.000042818872,0.000030083047,0.0000030258511,0.000019810073,0.046096187],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986644,0.00002653072,0.00023354706,0.00036937997,0.00027976686,0.00042641902],"domain_scores_gemma":[0.99906206,0.00012311935,0.00011350074,0.00046856422,0.00014478709,0.0000879718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031735236,0.0001696875,0.00017031333,0.000118265525,0.00015024435,0.0002256976,0.0007002175,0.000049634673,0.0001427727],"category_scores_gemma":[0.000037804406,0.00013504364,0.00006096069,0.00026406677,0.000017530125,0.0005495141,0.00028179737,0.00018556433,0.0003647088],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008817993,0.000008587284,0.0015990651,0.00004038466,0.000027766306,7.747044e-7,0.00029319685,0.8964993,0.00021041765,0.097861424,0.0011672223,0.002283057],"study_design_scores_gemma":[0.0007443922,0.00052060996,0.00020563898,0.000047200057,0.0000061045494,0.0000034884447,0.000025608171,0.9178354,0.0011674854,0.00008442525,0.07914468,0.00021492301],"about_ca_topic_score_codex":0.0000062908202,"about_ca_topic_score_gemma":8.38015e-7,"teacher_disagreement_score":0.80655634,"about_ca_system_score_codex":0.00008207352,"about_ca_system_score_gemma":0.00007764645,"threshold_uncertainty_score":0.550692},"labels":[],"label_agreement":null},{"id":"W2947183726","doi":"10.1287/moor.2021.1177","title":"On Linear Programming for Constrained and Unconstrained Average-Cost Markov Decision Processes with Countable Action Spaces and Strictly Unbounded Costs","year":2021,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"Alberta Innovates; Alberta Innovates - Technology Futures; DeepMind; Alberta Machine Intelligence Institute","keywords":"Mathematics; Countable set; Markov decision process; Duality (order theory); Mathematical optimization; State space; Action (physics); Markov kernel; Markov chain; Discrete mathematics; Applied mathematics; Markov process; Markov model; Variable-order Markov model; Statistics","score_opus":0.07719914338480655,"score_gpt":0.38038640943968005,"score_spread":0.3031872660548735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947183726","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":[0.086334586,0.000045534533,0.91155744,0.00036390114,0.000025407691,0.0010619429,0.000009453721,0.000032731,0.0005689937],"genre_scores_gemma":[0.4551454,0.00007824663,0.54411703,0.000014597984,0.000013114019,0.00010673911,0.00001716528,0.000012361962,0.00049535476],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984006,0.0000649227,0.0002980748,0.00031535805,0.00063949305,0.00028150552],"domain_scores_gemma":[0.99593896,0.0021012533,0.000062631014,0.00033084702,0.0014753798,0.000090957896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096084323,0.00012934228,0.0002081609,0.00021304979,0.00049325306,0.00085685204,0.00021923336,0.00006330857,0.000011894721],"category_scores_gemma":[0.0027122414,0.00010531474,0.000016477064,0.00072122953,0.0002403018,0.00042667016,0.00013743195,0.00018989967,0.0000020397345],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029316617,0.0012036026,0.0005941934,0.005102712,0.00031154658,0.000051495477,0.007827589,0.49705645,0.008713468,0.39986435,0.0004401256,0.078541294],"study_design_scores_gemma":[0.0014513347,0.0008433194,0.000036901773,0.0006510528,0.000015126684,0.0000704877,0.0018228668,0.98256373,0.010663197,0.0012518658,0.00043132438,0.00019879515],"about_ca_topic_score_codex":0.000015248917,"about_ca_topic_score_gemma":0.00018657616,"teacher_disagreement_score":0.48550728,"about_ca_system_score_codex":0.000068536494,"about_ca_system_score_gemma":0.00078377855,"threshold_uncertainty_score":0.8262644},"labels":[],"label_agreement":null},{"id":"W2947766523","doi":"10.24963/ijcai.2019/439","title":"Advantage Amplification in Slowly Evolving Latent-State Environments","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Stylized fact; Abstraction; Computer science; Reinforcement learning; Key (lock); Artificial intelligence; Action (physics); Machine learning; State (computer science); Task (project management); Algorithm; Computer security; Engineering","score_opus":0.018052120014348937,"score_gpt":0.2516236503439548,"score_spread":0.23357153032960584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947766523","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":[0.0069015133,0.0000684354,0.98535943,0.00014165563,0.00091466395,0.0005777526,0.0000015701847,0.00014148522,0.0058935033],"genre_scores_gemma":[0.8237867,0.00028453764,0.15934078,0.000244358,0.00003435751,0.000044189077,0.00006921106,0.000038723385,0.016157147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976674,0.00007328279,0.0005335902,0.00081036385,0.00050861854,0.00040678566],"domain_scores_gemma":[0.99789965,0.0000824367,0.0003459801,0.0015786123,0.000021875927,0.00007141882],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00040766897,0.00029177355,0.0002871453,0.0002621625,0.00003913123,0.00032725063,0.0017009522,0.0001816281,0.00007377383],"category_scores_gemma":[0.00003980503,0.0002985779,0.00008888202,0.00014318475,0.000026728589,0.00045203217,0.0024106957,0.00069031975,0.0011242126],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001696326,0.000022393702,0.015119679,0.000050158775,0.000013607152,0.000006538353,0.00030920276,0.979381,0.00030326535,0.0015546089,0.000107011634,0.003130805],"study_design_scores_gemma":[0.0002408802,0.000023946748,0.030495366,0.00010459333,0.0000042026045,0.0000012234009,0.000009398121,0.9665113,0.00022935396,0.0011012747,0.00093143526,0.00034703795],"about_ca_topic_score_codex":0.00005319411,"about_ca_topic_score_gemma":0.000003170719,"teacher_disagreement_score":0.82601863,"about_ca_system_score_codex":0.00031729764,"about_ca_system_score_gemma":0.0000784058,"threshold_uncertainty_score":0.99994665},"labels":[],"label_agreement":null},{"id":"W2948937890","doi":"10.48550/arxiv.1903.03176","title":"MinAtar: An Atari-Inspired Testbed for Thorough and Reproducible Reinforcement Learning Experiments","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Testbed; Computer science; Representation (politics); Breakout; Artificial intelligence; Set (abstract data type); Human–computer interaction; Toolbox; Machine learning","score_opus":0.11093294896298513,"score_gpt":0.2332999492194836,"score_spread":0.12236700025649848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948937890","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":[0.082272016,0.00008714031,0.91284025,0.000061439525,0.0007601437,0.0011829126,0.000003112281,0.00037794054,0.002415065],"genre_scores_gemma":[0.96810406,0.00011728846,0.016214497,0.00010098133,0.00009610628,0.000008395828,0.00013444225,0.000046025485,0.01517818],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963516,0.00016208825,0.00040416338,0.002277078,0.00020626398,0.00059879484],"domain_scores_gemma":[0.996111,0.00016091761,0.00056719984,0.0026753854,0.0002544219,0.0002311055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007138331,0.00050579617,0.00051118986,0.000292453,0.00035890014,0.0003602437,0.0019560459,0.00033945314,0.000018884537],"category_scores_gemma":[0.00019093255,0.0006028981,0.00017043231,0.0003387648,0.00011100095,0.0010287854,0.0030868251,0.00067489257,0.00004747968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005672743,0.000040601135,0.0034784672,0.00016416598,0.00008791967,0.000029963689,0.0007686754,0.9747337,0.00015194245,0.019935967,0.00016447887,0.00038738427],"study_design_scores_gemma":[0.001059176,0.00053731224,0.00042826228,0.00015142625,0.00007408286,0.0000038749545,0.00022005191,0.99132997,0.00093453965,0.0010477931,0.0035139988,0.00069952203],"about_ca_topic_score_codex":0.00016466537,"about_ca_topic_score_gemma":0.0000041855083,"teacher_disagreement_score":0.89662576,"about_ca_system_score_codex":0.00028583218,"about_ca_system_score_gemma":0.00020913017,"threshold_uncertainty_score":0.99964225},"labels":[],"label_agreement":null},{"id":"W2948949475","doi":"10.1109/cybermatics_2018.2018.00148","title":"Optimizing Rescheduling Intervals Through Using Multi-Armed Bandit Algorithms","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Athabasca University","funders":"New York State Department of Environmental Conservation","keywords":"Schedule; Computer science; Scheduling (production processes); Job shop scheduling; Reinforcement learning; Mathematical optimization; Operations research; Artificial intelligence; Engineering; Mathematics","score_opus":0.09642049829386522,"score_gpt":0.34390516150211603,"score_spread":0.2474846632082508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948949475","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":[0.0030996748,0.000039424838,0.99128646,0.00019357043,0.0010795018,0.00015710859,2.045226e-7,0.00038949752,0.003754579],"genre_scores_gemma":[0.16082077,0.0000068827994,0.83744437,0.0005579746,0.00024241244,0.0000026701455,0.000001040668,0.000018329896,0.0009055461],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982068,0.00007584265,0.00039819512,0.00046744145,0.00035087235,0.0005008668],"domain_scores_gemma":[0.99878305,0.00009486955,0.0001602122,0.000687021,0.00018419267,0.00009065076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004245353,0.00020001066,0.00021078344,0.000098035074,0.00030109135,0.00038747417,0.0010465345,0.00008951562,0.000120166034],"category_scores_gemma":[0.00014234275,0.00018048898,0.00008617049,0.00039878028,0.00013167641,0.0011233804,0.00068563205,0.00020633562,0.00019988508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009832601,0.000065438246,0.00053438754,0.000033748467,0.00010858607,0.00003281976,0.010204238,0.9639813,0.009671545,0.00964773,0.00042202792,0.0052883695],"study_design_scores_gemma":[0.00042472561,0.00009982859,0.000046868852,0.0000717051,0.000007939232,0.000015021446,0.00013078627,0.98097736,0.016472742,0.000089389214,0.0014189667,0.0002446686],"about_ca_topic_score_codex":0.000088433335,"about_ca_topic_score_gemma":0.0000034989569,"teacher_disagreement_score":0.15772109,"about_ca_system_score_codex":0.00009778195,"about_ca_system_score_gemma":0.00006198949,"threshold_uncertainty_score":0.7360127},"labels":[],"label_agreement":null},{"id":"W2949600864","doi":"","title":"Model-Based Bayesian Reinforcement Learning in Large Structured Domains","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Scalability; Artificial intelligence; Bayesian probability; Machine learning; Bayesian inference","score_opus":0.046170896446990024,"score_gpt":0.20111054857377583,"score_spread":0.15493965212678582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949600864","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":[0.017937558,0.000025931937,0.9765015,0.00006302251,0.00049503177,0.0004655608,0.0000025751401,0.00038554173,0.0041232756],"genre_scores_gemma":[0.98694694,0.000031571286,0.010297414,0.0001750825,0.00006019528,0.0000022722331,0.000061181236,0.000038222068,0.002387093],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699867,0.00023625277,0.00043186804,0.0010836929,0.00026429477,0.0009852297],"domain_scores_gemma":[0.99744165,0.000096359014,0.00050217094,0.0015558756,0.000119468095,0.0002844531],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006096997,0.0005216278,0.00048624258,0.00061096234,0.0002399715,0.0001779872,0.0022913513,0.0004858457,0.00007163067],"category_scores_gemma":[0.00006445932,0.00062870595,0.0002480048,0.00071341515,0.00008010686,0.0005480705,0.002338841,0.0016685128,0.00006118551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020681255,0.00003355676,0.0099009825,0.00007998595,0.00003746552,0.00008286995,0.0004127862,0.91369283,0.000016125594,0.07561042,0.000032097152,0.00008016917],"study_design_scores_gemma":[0.0011082722,0.00004498566,0.0009999392,0.00011513952,0.00004076765,0.0000011212489,0.00004162065,0.9941511,0.000053927866,0.0025061325,0.00029773347,0.00063923333],"about_ca_topic_score_codex":0.00005669545,"about_ca_topic_score_gemma":0.00004835963,"teacher_disagreement_score":0.9690094,"about_ca_system_score_codex":0.0007139545,"about_ca_system_score_gemma":0.00044248026,"threshold_uncertainty_score":0.99961644},"labels":[],"label_agreement":null},{"id":"W2950048158","doi":"10.48550/arxiv.1404.3328","title":"Myopic Bounds for Optimal Policy of POMDPs: An extension of Lovejoy's structural results","year":2014,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Canada Research Chairs","keywords":"Extension (predicate logic); Bounded function; Markov decision process; Mathematical optimization; Relaxation (psychology); Mathematical economics; Upper and lower bounds; Mathematics; Computer science; Markov process; Economics; Statistics","score_opus":0.07299322227582464,"score_gpt":0.23164626624484466,"score_spread":0.15865304396902002,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950048158","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":[0.33595437,0.0000075726693,0.6627658,0.000043519627,0.00032370095,0.00027469482,0.000017561351,0.00008521347,0.0005275435],"genre_scores_gemma":[0.96677154,0.00002452373,0.032286596,0.000034405293,0.000117377975,3.5406816e-7,0.000044586945,0.000019126184,0.0007015005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979711,0.00012894977,0.00047106616,0.000894443,0.00016914053,0.00036527414],"domain_scores_gemma":[0.99642426,0.00017634554,0.0009261806,0.0018475584,0.00048216272,0.00014350258],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038489723,0.0003015669,0.0005037995,0.00045384353,0.0000980647,0.000065122025,0.0020980216,0.0003029961,0.0000037376935],"category_scores_gemma":[0.00019882302,0.00033245812,0.00024751725,0.00040977303,0.0001691199,0.0003824671,0.0015214607,0.00032885498,0.0000040962664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010056881,0.000024290403,0.00028593978,0.00016563294,0.000057584995,0.000006358854,0.0003877022,0.90557194,0.00014803902,0.092989676,0.00005171393,0.00021054088],"study_design_scores_gemma":[0.0010339724,0.00052383135,0.002739372,0.000113088274,0.00005699545,0.0000023558514,0.000037573795,0.9890705,0.0006031425,0.005314229,0.00019829231,0.00030667416],"about_ca_topic_score_codex":0.0002344338,"about_ca_topic_score_gemma":0.0000057478874,"teacher_disagreement_score":0.6308172,"about_ca_system_score_codex":0.00016225556,"about_ca_system_score_gemma":0.00037700948,"threshold_uncertainty_score":0.99991274},"labels":[],"label_agreement":null},{"id":"W2950527138","doi":"10.48550/arxiv.math/0506489","title":"Acceleration Operators in the Value Iteration Algorithms for Markov Decision Processes","year":2005,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Markov decision process; Monotone polygon; Convergence (economics); Mathematical optimization; Algorithm; Markov chain; Operator (biology); Mathematics; Acceleration; Contraction (grammar); Dynamic programming; Computer science; Markov process; Applied mathematics","score_opus":0.06572374678319638,"score_gpt":0.325058715766949,"score_spread":0.25933496898375263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950527138","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":[0.13639374,0.00015445138,0.8598895,0.0012157701,0.00083304953,0.0011758136,0.0000025958352,0.00009712602,0.00023792636],"genre_scores_gemma":[0.8548509,0.0001960672,0.14208128,0.0013455191,0.0006382907,0.0004334816,0.000117293086,0.000030880023,0.0003063097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769837,0.00013874593,0.00061023305,0.0006964569,0.0005251632,0.00033102234],"domain_scores_gemma":[0.9979524,0.00047543703,0.0002867346,0.00093388115,0.00031302517,0.00003852497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010597748,0.0003064,0.0002550936,0.00020335604,0.00023812821,0.00093943934,0.0018687102,0.00026189047,0.0000094848065],"category_scores_gemma":[0.00061796245,0.00023555613,0.00008834063,0.00044463578,0.000028510218,0.00082947325,0.0006186062,0.00053521583,0.000038792306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012092488,0.000056049685,0.01599078,0.00014011175,0.000016119166,0.0000037228024,0.002448608,0.9579417,0.000057106416,0.0006869614,0.00082475314,0.021821978],"study_design_scores_gemma":[0.000468502,0.00011548658,0.026663706,0.00028605983,0.000017343798,0.0000051945353,0.00005594163,0.96546644,0.0010108817,0.00047076578,0.00504161,0.00039805757],"about_ca_topic_score_codex":0.00002064923,"about_ca_topic_score_gemma":0.000023727263,"teacher_disagreement_score":0.71845716,"about_ca_system_score_codex":0.00015523855,"about_ca_system_score_gemma":0.0003418953,"threshold_uncertainty_score":0.96057004},"labels":[],"label_agreement":null},{"id":"W2950564923","doi":"10.48550/arxiv.1906.08649","title":"Exploring Model-based Planning with Policy Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":76,"is_retracted":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; Benchmarking; Computer science; Code (set theory); Artificial neural network; Sample (material); Control (management); Action (physics); Artificial intelligence; Mathematical optimization; Optimization problem; State space; Machine learning; Algorithm; Mathematics","score_opus":0.19532087655417027,"score_gpt":0.20715320251527736,"score_spread":0.011832325961107087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950564923","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":[0.020989127,0.0000166304,0.9735274,0.00007113989,0.00037619993,0.0002873595,0.0000011900117,0.0004313581,0.0042996123],"genre_scores_gemma":[0.98727983,0.000038161714,0.010913519,0.00018549147,0.00011853658,0.0000019470203,0.000014255912,0.000038463062,0.001409811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997942,0.000079621925,0.00019480301,0.0010513011,0.00015407312,0.00057822966],"domain_scores_gemma":[0.99753594,0.00011526061,0.00032688535,0.0017083097,0.0001340256,0.00017958858],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019272415,0.00040340933,0.00035892022,0.00048699087,0.00016767016,0.00022921468,0.0021831924,0.00021414428,0.0000037205593],"category_scores_gemma":[0.000021692824,0.00043775875,0.00014351963,0.0007479093,0.00007868203,0.0006884305,0.001643101,0.00097497285,0.000044662753],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026778262,0.000013590314,0.0029735705,0.000054906526,0.00005303891,0.00011999256,0.0001752361,0.9597287,9.86561e-7,0.036729354,0.000033465105,0.00009037317],"study_design_scores_gemma":[0.0004682041,0.00007904929,0.00024805887,0.00029927408,0.0000348566,0.0000016290224,0.00002585047,0.9977442,0.00001721438,0.0004897301,0.00007682095,0.00051512127],"about_ca_topic_score_codex":0.000069408605,"about_ca_topic_score_gemma":0.0000018439496,"teacher_disagreement_score":0.9662907,"about_ca_system_score_codex":0.00036693958,"about_ca_system_score_gemma":0.00062879047,"threshold_uncertainty_score":0.9998074},"labels":[],"label_agreement":null},{"id":"W2950638477","doi":"10.48550/arxiv.1112.1133","title":"Multi-timescale Nexting in a Reinforcement Learning Robot","year":2011,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Alberta Innovates","keywords":"Laptop; Reinforcement learning; Computer science; Feature (linguistics); Range (aeronautics); Artificial intelligence; Robot; Function (biology); Temporal difference learning; Bellman equation; Representation (politics); State (computer science); Dimension (graph theory); Machine learning; Algorithm; Mathematics; Mathematical optimization; Engineering","score_opus":0.1086868290083088,"score_gpt":0.20306236592929322,"score_spread":0.09437553692098442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950638477","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":[0.011646522,0.000036726655,0.97766864,0.000025998725,0.00052320346,0.00042925336,2.901158e-7,0.0004040504,0.009265334],"genre_scores_gemma":[0.962208,0.00012986122,0.026972972,0.00006589174,0.00004308345,0.0000024337867,0.000014218071,0.000034287037,0.01052929],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99699926,0.00024361815,0.00053602643,0.001309749,0.00017337565,0.00073798315],"domain_scores_gemma":[0.9975402,0.00014059659,0.0006230388,0.0013594645,0.00013573281,0.00020100543],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063606835,0.00047732462,0.000488015,0.0005630418,0.0002033562,0.0001935836,0.002562241,0.00039814602,0.00009099402],"category_scores_gemma":[0.00015533781,0.0005936707,0.00020026865,0.00073643116,0.00009900327,0.00059888297,0.0044356426,0.0017456157,0.00028107042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012987688,0.000042854346,0.005618142,0.00006825582,0.000047176658,0.00023678748,0.0009601305,0.9818726,0.00006304692,0.010734489,0.000020299422,0.0003232219],"study_design_scores_gemma":[0.0007476204,0.000096053765,0.0014767846,0.00023757028,0.000028574113,0.0000032689038,0.00010356547,0.9956574,0.00009888723,0.0006240113,0.00031574877,0.00061055145],"about_ca_topic_score_codex":0.0005084017,"about_ca_topic_score_gemma":0.000037346595,"teacher_disagreement_score":0.95069563,"about_ca_system_score_codex":0.00046485558,"about_ca_system_score_gemma":0.00022568998,"threshold_uncertainty_score":0.9996515},"labels":[],"label_agreement":null},{"id":"W2950653703","doi":"10.48550/arxiv.1312.0286","title":"Efficient Learning and Planning with Compressed Predictive States","year":2013,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Computer science; Reinforcement learning; Artificial intelligence; Observable; A priori and a posteriori; Dimensionality reduction; Machine learning; Curse of dimensionality","score_opus":0.03664535695537425,"score_gpt":0.18255154166165422,"score_spread":0.14590618470627997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950653703","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":[0.28280973,0.000048505048,0.71505326,0.000018823583,0.0001434486,0.000268423,0.0000014872983,0.0002784561,0.0013778777],"genre_scores_gemma":[0.99451154,0.00004820397,0.004030781,0.000027243896,0.000032075724,0.0000016358108,0.000015610496,0.000021999906,0.001310912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818337,0.00014809723,0.00017008343,0.00094393536,0.00015626487,0.00039824698],"domain_scores_gemma":[0.9984962,0.0002224529,0.00033556775,0.0005539539,0.00021359156,0.00017825219],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016522124,0.00033763872,0.00031883613,0.00023088866,0.00025840837,0.0002939402,0.0008851367,0.00017277291,0.0000140936145],"category_scores_gemma":[0.000034235687,0.00033403345,0.00005523673,0.00030008765,0.00018198203,0.00017715189,0.0020319116,0.0009557654,0.000029923303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025790652,0.000018123588,0.011282251,0.00006585245,0.000100231744,0.00012151499,0.0011955743,0.9808943,0.0000059061645,0.006189002,0.00004843623,0.000053013384],"study_design_scores_gemma":[0.00047559943,0.00018713358,0.0023011018,0.0002557228,0.000048699025,0.0000045676734,0.00040122546,0.9952729,0.00002291646,0.00046999127,0.00017915106,0.00038104458],"about_ca_topic_score_codex":0.000073760275,"about_ca_topic_score_gemma":6.7346053e-7,"teacher_disagreement_score":0.7117018,"about_ca_system_score_codex":0.0001205742,"about_ca_system_score_gemma":0.00009755264,"threshold_uncertainty_score":0.9999112},"labels":[],"label_agreement":null},{"id":"W2950989964","doi":"","title":"Apprenticeship Learning using Inverse Reinforcement Learning and Gradient Methods","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Markov decision process; Computer science; Function (biology); Artificial intelligence; Mathematical optimization; Inverse; Apprenticeship; Gradient method; Machine learning; Algorithm; Markov process; Mathematics; Statistics","score_opus":0.13644769773097773,"score_gpt":0.2590478520903364,"score_spread":0.12260015435935864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950989964","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":[0.053004544,0.00014878728,0.941695,0.000018255876,0.0009089616,0.0003571108,2.6760318e-7,0.00039022038,0.0034768695],"genre_scores_gemma":[0.92348146,0.00032077052,0.07206266,0.0000436228,0.00010664572,0.0000012765885,0.000016387765,0.00004211989,0.003925072],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99637306,0.00089187024,0.00043441207,0.0012242977,0.0002261579,0.0008502132],"domain_scores_gemma":[0.99737823,0.00029832826,0.00083789544,0.00090293784,0.00016873103,0.00041389492],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014746081,0.0005630098,0.00054029975,0.00049583433,0.0005750607,0.00037480608,0.0013440874,0.00039983797,0.000055053806],"category_scores_gemma":[0.00022230227,0.00067599246,0.00022941425,0.000619826,0.00019748382,0.0008389332,0.0053234156,0.0020334255,0.000049508988],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001304878,0.000018952565,0.00899232,0.00017571513,0.00013898937,0.000041539664,0.0011925936,0.967137,0.000107705455,0.021187723,0.000011853206,0.0009825625],"study_design_scores_gemma":[0.0004462345,0.000077189405,0.00024278792,0.00016959738,0.00020633748,0.000011722476,0.00031629915,0.9944353,0.00011256735,0.0007576522,0.0025284512,0.00069583644],"about_ca_topic_score_codex":0.00013437653,"about_ca_topic_score_gemma":0.0000033462252,"teacher_disagreement_score":0.8704769,"about_ca_system_score_codex":0.00044198576,"about_ca_system_score_gemma":0.00014515007,"threshold_uncertainty_score":0.9995691},"labels":[],"label_agreement":null},{"id":"W2951110424","doi":"10.48550/arxiv.1612.02088","title":"Transition-based versus State-based Reward Functions for MDPs with Value-at-Risk","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Markov decision process; Reinforcement learning; Function (biology); Action (physics); Transformation (genetics); Bellman equation; Markov process; Markov chain; State (computer science); Current (fluid); Order (exchange); Computer science; Mathematical optimization; Econometrics; Mathematics; Economics; Artificial intelligence; Statistics; Machine learning; Engineering; Algorithm; Finance","score_opus":0.05494755650732404,"score_gpt":0.1875184610339302,"score_spread":0.13257090452660614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951110424","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":[0.020407204,0.000009617196,0.97577703,0.0003471228,0.00095865375,0.00079031254,0.00014115733,0.00049474183,0.0010741606],"genre_scores_gemma":[0.98332304,0.000015928266,0.013395419,0.0001560043,0.00007309777,0.00001124944,0.00012327396,0.000050258415,0.0028517307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974579,0.00019450586,0.00027112657,0.0012819596,0.00022702085,0.00056747725],"domain_scores_gemma":[0.9964986,0.0007769953,0.00047989472,0.0016323423,0.0003697919,0.00024238335],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032787613,0.00046025976,0.00037727202,0.00038220012,0.00050905865,0.00013943537,0.0013721503,0.00026338678,0.000047289603],"category_scores_gemma":[0.00006369517,0.0004384424,0.00034057244,0.0004865971,0.00020372246,0.00029084005,0.00032408937,0.0004878378,0.00011977545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093914644,0.000050755534,0.00075532263,0.000093036695,0.00017056949,0.00004631685,0.00009518043,0.992417,0.000009896819,0.0048355577,0.00045320747,0.0001340093],"study_design_scores_gemma":[0.0049835946,0.0006739076,0.0002474394,0.00017542866,0.00026204687,6.404839e-7,0.000022144879,0.9893674,0.00024321009,0.0013538292,0.0020214408,0.00064891286],"about_ca_topic_score_codex":0.00008044081,"about_ca_topic_score_gemma":0.00005204712,"teacher_disagreement_score":0.96291584,"about_ca_system_score_codex":0.0007299475,"about_ca_system_score_gemma":0.00079120626,"threshold_uncertainty_score":0.99980676},"labels":[],"label_agreement":null},{"id":"W2951553872","doi":"","title":"SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Robotics; Range (aeronautics); Simple (philosophy); Linear-quadratic regulator; Offline learning; Quadratic equation; Image (mathematics); Machine learning; Control (management); Robot; Online learning; Mathematics; Engineering","score_opus":0.0705683000237207,"score_gpt":0.2240496447580726,"score_spread":0.15348134473435188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951553872","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":[0.0030210945,0.000011135081,0.9924273,0.000088604196,0.00068415323,0.000871775,0.0000042885063,0.00047011304,0.002421573],"genre_scores_gemma":[0.9314914,0.000020603267,0.06296216,0.00014908725,0.00011362013,0.000008191168,0.00013962826,0.00003995038,0.00507541],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973418,0.00012853899,0.00039798403,0.0013212016,0.00021723937,0.0005932099],"domain_scores_gemma":[0.9967065,0.00020383735,0.00061369746,0.0017490976,0.0005176009,0.00020927461],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036229112,0.0004359431,0.00038449073,0.00038986822,0.000556014,0.00030995806,0.002285217,0.00037212134,0.000044036577],"category_scores_gemma":[0.00020132013,0.0005289992,0.00035805936,0.00044974257,0.00015963757,0.00043462642,0.0016581501,0.00074556266,0.00004799826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036200323,0.00001447711,0.00049044046,0.00009265749,0.00009481391,0.000013607894,0.0002770986,0.96275795,0.000021900434,0.03575049,0.00030713028,0.0001432291],"study_design_scores_gemma":[0.00083777565,0.00014695044,0.00006832611,0.00006384507,0.00010369212,9.1961005e-7,0.000042692285,0.98688734,0.00030484408,0.01048078,0.0005245291,0.00053833367],"about_ca_topic_score_codex":0.000032083513,"about_ca_topic_score_gemma":0.000012747594,"teacher_disagreement_score":0.9294651,"about_ca_system_score_codex":0.0003683252,"about_ca_system_score_gemma":0.00044631815,"threshold_uncertainty_score":0.99971616},"labels":[],"label_agreement":null},{"id":"W2952014622","doi":"10.48550/arxiv.1503.04269","title":"An Emphatic Approach to the Problem of Off-policy Temporal-Difference Learning","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Temporal difference learning; Discounting; Lambda; Bootstrapping (finance); Computer science; Computation; Parametric statistics; Function (biology); Algorithm; State (computer science); Applied mathematics; Artificial intelligence; Mathematics; Reinforcement learning; Statistics; Econometrics","score_opus":0.09377041807705082,"score_gpt":0.21911309879659377,"score_spread":0.12534268071954296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952014622","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":[0.054259673,0.000024052684,0.935317,0.00013876082,0.00011291216,0.00062488747,0.0000024484677,0.00022314776,0.009297126],"genre_scores_gemma":[0.975976,0.00003174384,0.01932789,0.00008326304,0.00008446246,0.0000029438863,0.000022146356,0.0000240144,0.004447551],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751127,0.0004462444,0.00034167588,0.0009856123,0.00027445023,0.00044073895],"domain_scores_gemma":[0.996845,0.000093515475,0.0005517593,0.0018402522,0.00038482607,0.00028461355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00079780206,0.00036004724,0.00042736946,0.00040216677,0.00019080719,0.0002037276,0.0044473344,0.00022531943,0.0000038951553],"category_scores_gemma":[0.00010007994,0.0003178243,0.00013635018,0.0011841089,0.00013982898,0.00031836412,0.0027232922,0.0008189343,0.00005234472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010502079,0.00006611102,0.0036683716,0.00009189475,0.000044700304,0.000008214167,0.0020935645,0.9437818,0.000012670812,0.048565656,0.000108727196,0.0015478021],"study_design_scores_gemma":[0.00023342784,0.00019930654,0.0010311633,0.00008890172,0.000035129313,0.0000029496937,0.00025889213,0.9934338,0.000021432927,0.003299136,0.0010368823,0.00035901103],"about_ca_topic_score_codex":0.00039859244,"about_ca_topic_score_gemma":0.000010920261,"teacher_disagreement_score":0.92171633,"about_ca_system_score_codex":0.00025908917,"about_ca_system_score_gemma":0.00070729683,"threshold_uncertainty_score":0.9999274},"labels":[],"label_agreement":null},{"id":"W2952348496","doi":"10.3389/fnbot.2018.00032","title":"Experience Replay Using Transition Sequences","year":2018,"lang":"en","type":"article","venue":"Frontiers in Neurorobotics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"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":"Singapore University of Technology and Design; Ministry of Education - Singapore; Ministry of Education, India; University of Alberta","keywords":"Reinforcement learning; Computer science; Construct (python library); Artificial intelligence; State space; Space (punctuation); Transition (genetics); State (computer science); Function (biology); Machine learning; Algorithm","score_opus":0.027803115942547044,"score_gpt":0.27424405348465974,"score_spread":0.24644093754211271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952348496","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":[0.029411467,0.00003599146,0.9657541,0.0003009701,0.0036005795,0.00014590687,3.4800496e-7,0.00014273076,0.0006079364],"genre_scores_gemma":[0.53546494,0.000018867797,0.46371993,0.00054786896,0.000115687515,0.0000029267694,9.327583e-7,0.000013216569,0.00011561773],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982489,0.000109039865,0.00036564918,0.00047294295,0.00037360477,0.0004299072],"domain_scores_gemma":[0.999028,0.000034908422,0.00012419173,0.00064457057,0.00008365687,0.00008462924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021201064,0.00017481469,0.00019709888,0.00022075846,0.00016986206,0.00015968372,0.0009252133,0.00008333411,0.000008376611],"category_scores_gemma":[0.00009711172,0.00018480321,0.000047589263,0.00072741765,0.00027343657,0.0007845346,0.00012684993,0.00021634685,0.00001434926],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009460528,0.000022551456,0.0072997026,0.000013245323,0.0000068995723,0.00006471065,0.0049790046,0.98273146,0.0012358078,0.0012512795,0.0010637054,0.0013221807],"study_design_scores_gemma":[0.00019212773,0.00013887997,0.00068725814,0.000035826954,0.000004614875,0.000031858308,0.00017577947,0.9952765,0.0019446847,0.0005684123,0.00072922924,0.00021480666],"about_ca_topic_score_codex":0.0000178578,"about_ca_topic_score_gemma":0.000002278665,"teacher_disagreement_score":0.5060535,"about_ca_system_score_codex":0.0001058912,"about_ca_system_score_gemma":0.00007085866,"threshold_uncertainty_score":0.7536056},"labels":[],"label_agreement":null},{"id":"W2952662670","doi":"10.48550/arxiv.1906.04328","title":"Importance Resampling for Off-policy Prediction","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Resampling; Consistency (knowledge bases); Variance (accounting); Computer science; Reinforcement learning; Sampling (signal processing); Jackknife resampling; Function (biology); Statistics; Artificial intelligence; Machine learning; Econometrics; Mathematics","score_opus":0.08829860924234678,"score_gpt":0.21524033782485585,"score_spread":0.12694172858250907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952662670","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":[0.015897503,0.000042105945,0.9782839,0.000121290745,0.0011250168,0.0006943757,0.000021228909,0.00037482558,0.0034397985],"genre_scores_gemma":[0.9801338,0.0002616565,0.010596789,0.00015106858,0.00030564176,0.0000029770606,0.00006433404,0.00003114818,0.008452608],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980398,0.000053025877,0.00028205483,0.0010679599,0.00012250998,0.0004346454],"domain_scores_gemma":[0.9974092,0.00017316274,0.00045007706,0.0016299151,0.00021830217,0.00011929702],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003324009,0.00028947083,0.00030384012,0.00034535074,0.00016720657,0.0001658551,0.0018713628,0.00028157837,0.000008035873],"category_scores_gemma":[0.00015645001,0.00035680336,0.0002303697,0.0004730548,0.00005590347,0.00043258688,0.0015252932,0.0005182231,0.000068516936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015459585,0.000012221112,0.004798691,0.0001044921,0.000051305047,0.000010465173,0.000088222405,0.9087995,0.000010924499,0.08523894,0.00057870796,0.00029102157],"study_design_scores_gemma":[0.0004177455,0.00008041999,0.0017125956,0.000097866054,0.00003595964,0.0000018147024,0.000015402878,0.9844982,0.00003181753,0.008042074,0.004754392,0.00031168625],"about_ca_topic_score_codex":0.00003991971,"about_ca_topic_score_gemma":0.000004526296,"teacher_disagreement_score":0.9676871,"about_ca_system_score_codex":0.00043126263,"about_ca_system_score_gemma":0.00046390525,"threshold_uncertainty_score":0.9998884},"labels":[],"label_agreement":null},{"id":"W2952735266","doi":"10.48550/arxiv.1205.2606","title":"Exploring compact reinforcement-learning representations with linear regression","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Regression; Linear regression; Artificial intelligence; Computer science; Machine learning; Mathematics; Statistics; Psychology; Social psychology","score_opus":0.21910190354494213,"score_gpt":0.2371817989078626,"score_spread":0.018079895362920456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952735266","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":[0.046403013,0.000025010342,0.9414567,0.000084908694,0.00058625784,0.0003611496,8.089398e-7,0.0005780737,0.010504128],"genre_scores_gemma":[0.9881687,0.00025613813,0.0049227797,0.00003495881,0.00015561793,0.0000024775961,0.000053880427,0.000040468185,0.0063649337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751276,0.00022473268,0.00033174863,0.0009895231,0.00029235252,0.00064886466],"domain_scores_gemma":[0.9969368,0.00020791807,0.00063928624,0.0016724359,0.00023171038,0.00031185668],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035140675,0.00046219592,0.00040775337,0.00040104406,0.0004660098,0.00020539733,0.0016946688,0.00018754741,0.000060568564],"category_scores_gemma":[0.00008853874,0.0004485306,0.0001806985,0.0007525017,0.00011842261,0.0017594756,0.001844292,0.0013896164,0.00018583353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031900254,0.000025087873,0.010554292,0.000065496984,0.00010767062,0.00009724756,0.00083653984,0.9691879,0.000020745692,0.018850029,0.00009231612,0.00013074494],"study_design_scores_gemma":[0.0005410785,0.00010666163,0.0021210015,0.0003852923,0.0000923328,0.000008315945,0.00026884922,0.99419504,0.00024587775,0.00015404931,0.0012975932,0.0005838998],"about_ca_topic_score_codex":0.0001668132,"about_ca_topic_score_gemma":0.000004150615,"teacher_disagreement_score":0.9417657,"about_ca_system_score_codex":0.00033603775,"about_ca_system_score_gemma":0.00018837026,"threshold_uncertainty_score":0.9997966},"labels":[],"label_agreement":null},{"id":"W2953243993","doi":"10.48550/arxiv.1906.08226","title":"Unsupervised State Representation Learning in Atari","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Université de Sherbrooke; Université de Montréal","funders":"","keywords":"Representation (politics); Computer science; Benchmark (surveying); Feature learning; Artificial intelligence; Generative grammar; Variety (cybernetics); Generative model; Encoder; Code (set theory); Machine learning; State (computer science); Encoding (memory)","score_opus":0.0804774768729731,"score_gpt":0.20423136063171912,"score_spread":0.12375388375874602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953243993","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":[0.20536277,0.00001571682,0.7898845,0.00006444737,0.00048883737,0.0003239986,0.0000011096508,0.00024676934,0.0036118361],"genre_scores_gemma":[0.9878013,0.00017260594,0.0018500776,0.000057575624,0.000024459729,7.6505836e-7,0.000039986866,0.000021763564,0.010031444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769527,0.00030004428,0.00029688567,0.0011283105,0.00016298499,0.0004165146],"domain_scores_gemma":[0.9979779,0.00017782715,0.00032658956,0.0012967647,0.00012235911,0.00009856124],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036555072,0.00028810833,0.00034073475,0.00045964788,0.00008993852,0.00020382948,0.0017607101,0.00021972686,0.000032690896],"category_scores_gemma":[0.0000955173,0.0003668293,0.00013939948,0.0007944341,0.000052864794,0.0006247039,0.0024230778,0.0011972372,0.00032785878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015431287,0.000017674229,0.060985476,0.000053636468,0.000029907835,0.0001481538,0.00060159154,0.9312325,0.000018223365,0.006507329,0.00004845509,0.00034159503],"study_design_scores_gemma":[0.0005895116,0.000049451824,0.011489898,0.00010217748,0.000014346835,0.000001274727,0.0000850027,0.98435795,0.000055126526,0.002529733,0.0003527762,0.00037274577],"about_ca_topic_score_codex":0.0004382021,"about_ca_topic_score_gemma":0.00003301225,"teacher_disagreement_score":0.78803444,"about_ca_system_score_codex":0.0003306898,"about_ca_system_score_gemma":0.00024162585,"threshold_uncertainty_score":0.99987835},"labels":[],"label_agreement":null},{"id":"W2953351167","doi":"10.48550/arxiv.1704.02544","title":"A Linearly Relaxed Approximate Linear Program for Markov Decision Processes","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Linear programming; Constraint (computer-aided design); Markov decision process; Mathematical optimization; Markov chain; Markov process; Computer science; Mathematics; Linear approximation; Applied mathematics; Nonlinear system; Statistics; Physics; Machine learning","score_opus":0.08128687683702827,"score_gpt":0.24218287870035018,"score_spread":0.16089600186332192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2953351167","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":[0.008903763,0.000061653125,0.9858714,0.00009337676,0.00083816174,0.0018084252,0.000012312725,0.0007819255,0.0016289813],"genre_scores_gemma":[0.65909374,0.00035161083,0.33234167,0.000053706026,0.00023389555,0.000029719966,0.000071120754,0.00006682101,0.0077577243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972245,0.00006582381,0.00036562097,0.0015089302,0.00021638277,0.0006187294],"domain_scores_gemma":[0.99531204,0.00035656738,0.0008100546,0.0025426089,0.00075897056,0.0002197833],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052839797,0.0004832771,0.00050728134,0.00029302484,0.0005316405,0.00072674017,0.0044486145,0.0005015477,0.000008055029],"category_scores_gemma":[0.00084967853,0.0005190704,0.00029176183,0.00040995327,0.00016811433,0.00075118546,0.0031955675,0.00073347957,0.00006431244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117185715,0.00013750051,0.00077598786,0.0007020407,0.000108764136,0.0001021499,0.00018135492,0.9794956,0.0000040679147,0.008480804,0.0005250179,0.009369525],"study_design_scores_gemma":[0.00083789387,0.00029521494,0.0001527748,0.00040775765,0.000082065715,0.000004113554,0.000014164604,0.9833447,0.000076179174,0.0075730095,0.006629424,0.0005827176],"about_ca_topic_score_codex":0.000029074225,"about_ca_topic_score_gemma":0.000011210821,"teacher_disagreement_score":0.65352976,"about_ca_system_score_codex":0.00017236976,"about_ca_system_score_gemma":0.0006164256,"threshold_uncertainty_score":0.9997261},"labels":[],"label_agreement":null},{"id":"W2954388198","doi":"10.1109/icit.2019.8755084","title":"Evaluating Architecture Impacts on Deep Imitation Learning Performance for Autonomous Driving","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Architecture; Imitation; Deep learning; Artificial intelligence; Human–computer interaction; Computer architecture; Psychology; Geography","score_opus":0.02746936062123937,"score_gpt":0.3030474467729648,"score_spread":0.2755780861517254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954388198","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":[0.3041993,0.0000047623807,0.6891981,0.000159128,0.00024410553,0.00034437038,3.2300136e-8,0.00020981036,0.005640397],"genre_scores_gemma":[0.8201092,0.0000018231424,0.17722806,0.00020673347,0.000049139508,0.000015980499,0.0000042897223,0.000015542038,0.0023692667],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858624,0.000062051964,0.00024169606,0.0003499808,0.00036544693,0.00039458773],"domain_scores_gemma":[0.9987763,0.0005065882,0.00017971071,0.00037003463,0.00009964455,0.00006767563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007078383,0.00015704386,0.00014249948,0.00014023928,0.0002148824,0.0002251993,0.00047068245,0.0000590551,0.000035698034],"category_scores_gemma":[0.00038025415,0.00013706059,0.000065748674,0.00019041922,0.000011175533,0.00042418326,0.00012211714,0.00028202092,0.00021024431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061139267,0.000005006174,0.0037446802,0.000034358316,0.00000838432,1.6893199e-7,0.00086736225,0.9262773,0.0014666,0.0026184875,0.000010015955,0.06496155],"study_design_scores_gemma":[0.00040572297,0.0010896558,0.007283509,0.000060833794,0.000004227526,0.0000037148097,0.000041018455,0.9890401,0.0013565723,0.00010086028,0.00042803097,0.0001857631],"about_ca_topic_score_codex":0.0000024059816,"about_ca_topic_score_gemma":0.000001203205,"teacher_disagreement_score":0.51590985,"about_ca_system_score_codex":0.00010451042,"about_ca_system_score_gemma":0.000070541464,"threshold_uncertainty_score":0.55891687},"labels":[],"label_agreement":null},{"id":"W2955319481","doi":"10.1002/aic.16689","title":"Toward self‐driving processes: A deep reinforcement learning approach to control","year":2019,"lang":"en","type":"article","venue":"AIChE Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":144,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Self driving; Reinforcement; Self-control; Control (management); Computer science; Artificial intelligence; Engineering; Psychology; Social psychology; Transport engineering","score_opus":0.014074329873777026,"score_gpt":0.23225183349437672,"score_spread":0.2181775036205997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2955319481","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":[0.004727904,0.00007124669,0.9750943,0.0005210634,0.0004517825,0.0004052233,2.5438098e-8,0.00021855593,0.018509887],"genre_scores_gemma":[0.92143166,0.00003249938,0.07533312,0.0009769913,0.00020485399,0.000014523726,9.862044e-7,0.000025245474,0.0019801261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997352,0.0001332799,0.00055267115,0.0003794606,0.00089584466,0.00068672013],"domain_scores_gemma":[0.9983295,0.00014877795,0.0003808956,0.00043853885,0.00036038604,0.00034190377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001138623,0.00025331834,0.00031811537,0.00024500393,0.00028798686,0.0007887878,0.0014698077,0.00009303768,0.00006086119],"category_scores_gemma":[0.0003866476,0.00022137554,0.00010670422,0.0006346806,0.000014086675,0.0009767221,0.00033938445,0.0008947324,0.000553608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008640446,0.00002862933,0.0038165764,0.00006669356,0.00007920179,0.000008602614,0.0047298195,0.9886008,0.00018006425,0.0013733509,0.00028581367,0.00082180806],"study_design_scores_gemma":[0.001118433,0.00048926054,0.0005941306,0.00009198642,0.00002414759,0.0002772099,0.00033334497,0.98571235,0.00014461105,0.000057859626,0.010809191,0.00034747252],"about_ca_topic_score_codex":0.0000032477753,"about_ca_topic_score_gemma":2.7273876e-7,"teacher_disagreement_score":0.91670376,"about_ca_system_score_codex":0.00021618983,"about_ca_system_score_gemma":0.00029389455,"threshold_uncertainty_score":0.9027432},"labels":[],"label_agreement":null},{"id":"W2956872166","doi":"10.48550/arxiv.1907.04651","title":"Incrementally Learning Functions of the Return","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Taylor series; Value (mathematics); Computer science; Temporal difference learning; Mathematics; Mathematical optimization; Applied mathematics; Artificial intelligence; Machine learning; Mathematical analysis","score_opus":0.05402498703515711,"score_gpt":0.17527060647856768,"score_spread":0.12124561944341057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956872166","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":[0.086039655,0.0000151140175,0.898011,0.0000811845,0.0011517444,0.00027477893,0.000001927288,0.00012521635,0.014299372],"genre_scores_gemma":[0.97800434,0.000032108714,0.0006285842,0.000052684496,0.000031270487,3.1151362e-7,0.000006830002,0.000013327372,0.021230573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985834,0.00020530712,0.0002180717,0.0005819135,0.0001667691,0.00024454866],"domain_scores_gemma":[0.9977218,0.000107032625,0.0005104981,0.0014507658,0.00015344132,0.000056479257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028094047,0.000210285,0.00023362233,0.00014640576,0.00018635605,0.00007541815,0.0024060498,0.00019662414,0.0000477025],"category_scores_gemma":[0.000077202174,0.0001957238,0.0002454421,0.00052958785,0.00010903885,0.00022775115,0.004175777,0.0010105091,0.00010488261],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000051652723,0.000013611891,0.029634826,0.000046948324,0.00006387148,0.000005487539,0.00014945005,0.95381945,0.0000806788,0.015907645,0.00022418429,0.000048672133],"study_design_scores_gemma":[0.00024958156,0.000058258942,0.0047028507,0.00012429593,0.000057000336,0.0000018296199,0.00010457301,0.9918023,0.00016082166,0.0007638798,0.001741275,0.0002333565],"about_ca_topic_score_codex":0.0000839241,"about_ca_topic_score_gemma":0.0000076155343,"teacher_disagreement_score":0.89738244,"about_ca_system_score_codex":0.00018841572,"about_ca_system_score_gemma":0.0002366138,"threshold_uncertainty_score":0.7981385},"labels":[],"label_agreement":null},{"id":"W2962845991","doi":"10.1609/aaai.v32i1.11775","title":"OptionGAN: Learning Joint Reward-Policy Options Using Generative Adversarial Inverse Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":57,"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":"Open Philanthropy Project; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Adversarial system; Artificial intelligence; Generative grammar; Machine learning; Function (biology); Set (abstract data type)","score_opus":0.0495135636832109,"score_gpt":0.29439513433302306,"score_spread":0.24488157064981214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962845991","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":[0.005584269,0.000008727493,0.968722,0.00060792814,0.00083746423,0.00030389207,1.5456618e-7,0.00060150836,0.023334041],"genre_scores_gemma":[0.61873066,0.000045759673,0.3572925,0.0007252691,0.001826092,0.000017302595,0.000017837598,0.000044709577,0.021299856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695027,0.00032702906,0.0006446605,0.00063974556,0.00070039567,0.00073792995],"domain_scores_gemma":[0.9982073,0.00008673546,0.00039331496,0.0006221466,0.0004438845,0.000246662],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00081411895,0.00034300896,0.000307431,0.0005275657,0.0013781463,0.00049482874,0.0006989074,0.00015597,0.00035722568],"category_scores_gemma":[0.0007218023,0.0003412949,0.0001582899,0.0010180732,0.0002441881,0.0012848539,0.0008994888,0.00067543436,0.0006592838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008478677,0.00001153882,0.00018542832,0.000007018304,0.00005080866,0.0000057456027,0.0023878273,0.9361864,0.0044650887,0.05573429,0.00040110247,0.00055630854],"study_design_scores_gemma":[0.00067086815,0.00050142274,0.00008517036,0.00004082955,0.000019662622,0.00002290283,0.00038042662,0.98176044,0.0037365789,0.00016514157,0.012205759,0.00041076602],"about_ca_topic_score_codex":0.0003270934,"about_ca_topic_score_gemma":0.000012239174,"teacher_disagreement_score":0.6131464,"about_ca_system_score_codex":0.0005493599,"about_ca_system_score_gemma":0.00046046337,"threshold_uncertainty_score":0.9999219},"labels":[],"label_agreement":null},{"id":"W2962985403","doi":"","title":"Universal Successor Representations for Transfer Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Initialization; Successor cardinal; Artificial intelligence; Set (abstract data type); Transfer of learning; Focus (optics); Function (biology); Machine learning; Reinforcement; Value (mathematics); Mathematics; Programming language","score_opus":0.057285571163360936,"score_gpt":0.34720038236061634,"score_spread":0.28991481119725543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962985403","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":[0.0036328144,0.0000029047396,0.8863748,0.004339714,0.00095436507,0.00045273502,0.0000033174929,0.0003920005,0.10384736],"genre_scores_gemma":[0.9568276,0.000031920667,0.008169136,0.00023008611,0.00034065277,0.00013241897,0.00015923055,0.000028944893,0.034080014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973381,0.00017380917,0.0005313139,0.0007311915,0.0007895802,0.00043599244],"domain_scores_gemma":[0.9974065,0.0005294795,0.00021168438,0.00051777874,0.001185457,0.00014909756],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038601106,0.00025544403,0.00020553869,0.0004556193,0.0008462836,0.0006392947,0.0013106087,0.00010182606,0.0008189778],"category_scores_gemma":[0.0008723523,0.00027665013,0.00016976547,0.0004440285,0.00020531089,0.0010206131,0.00020976788,0.00051051215,0.0003443466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006226524,0.000039983137,0.002302328,0.0000068646973,0.00011753479,0.0000052177566,0.003105864,0.5506719,0.0014649142,0.43927875,0.000797132,0.0021472506],"study_design_scores_gemma":[0.001153241,0.000639581,0.0017249709,0.000061501596,0.00002424736,0.000009384714,0.0010123497,0.96703345,0.002136154,0.0016233239,0.024234792,0.00034702301],"about_ca_topic_score_codex":0.00010048675,"about_ca_topic_score_gemma":0.000016340671,"teacher_disagreement_score":0.9531948,"about_ca_system_score_codex":0.0001619587,"about_ca_system_score_gemma":0.0001924054,"threshold_uncertainty_score":0.9999686},"labels":[],"label_agreement":null},{"id":"W2963097726","doi":"10.1609/aaai.v33i01.33014384","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Sparse approximation; Computer science; Neural coding; Bootstrapping (finance); Artificial intelligence; Representation (politics); Machine learning; Artificial neural network; Locality; Mathematics","score_opus":0.06591031971543576,"score_gpt":0.3089931647799222,"score_spread":0.24308284506448646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963097726","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":[0.06049748,0.000019102883,0.9095155,0.0033638102,0.0006481271,0.0022204758,0.0000016571538,0.000059554943,0.023674292],"genre_scores_gemma":[0.9978248,0.00002319853,0.0011099054,0.00006512476,0.000016103855,0.00004986652,3.9907246e-7,0.000007289918,0.0009033142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807966,0.000030543728,0.0007682811,0.00032934351,0.00047086034,0.00032128964],"domain_scores_gemma":[0.9977136,0.0005579638,0.00065431214,0.00039155033,0.0006429854,0.000039544466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012102897,0.00014831629,0.0002478248,0.00009228829,0.00018148782,0.0001422239,0.001715291,0.000059047903,0.000039132643],"category_scores_gemma":[0.0011602845,0.000100669364,0.000107167056,0.0004649673,0.00020995806,0.00028815467,0.00025534444,0.00029133016,0.000025859043],"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":[0.00014201146,0.00004345335,0.0049972795,0.000058407073,0.000019965464,6.240522e-8,0.001250829,0.17861748,0.009504087,0.7957736,0.00007729853,0.009515489],"study_design_scores_gemma":[0.000083124825,0.00026416863,0.0008704393,0.00011744119,0.0000069685866,4.5689671e-7,0.0006582504,0.9182219,0.060416024,0.019062702,0.00019671941,0.00010182951],"about_ca_topic_score_codex":0.000046709636,"about_ca_topic_score_gemma":0.000008056903,"teacher_disagreement_score":0.9373273,"about_ca_system_score_codex":0.00003296167,"about_ca_system_score_gemma":0.00010116275,"threshold_uncertainty_score":0.41051775},"labels":[],"label_agreement":null},{"id":"W2963142324","doi":"10.1609/aaai.v32i1.11831","title":"When Waiting Is Not an Option: Learning Options With a Deliberation Cost","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":80,"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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données","keywords":"Deliberation; Interpretability; Bounded rationality; Computer science; Rationality; Work (physics); Management science; Risk analysis (engineering); Artificial intelligence; Epistemology; Economics; Business; Political science; Engineering; Philosophy","score_opus":0.03604037314581124,"score_gpt":0.27441794202672404,"score_spread":0.2383775688809128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963142324","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":[0.012335676,0.000002284221,0.9748003,0.0014178936,0.00010330216,0.00015719488,1.4169287e-7,0.00038918894,0.010794016],"genre_scores_gemma":[0.65027225,0.000002479375,0.34288162,0.0009974121,0.00017345937,0.000011781137,0.000006358484,0.000010879402,0.005643788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988305,0.00006734195,0.0001945141,0.00032607606,0.00032623156,0.00025535285],"domain_scores_gemma":[0.9990908,0.00004125467,0.00010396603,0.00039364127,0.00027509232,0.00009524218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000260551,0.00011863786,0.0000896298,0.00008494749,0.0005097354,0.00055619463,0.00040431577,0.000047969326,0.00022791969],"category_scores_gemma":[0.000032298474,0.00010148607,0.00002204168,0.0002256832,0.000064005064,0.0013725684,0.00012282823,0.0001761136,0.00030770674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015374424,0.00003137839,0.0014532945,0.00000810894,0.00002860656,0.000004968424,0.006161982,0.76820433,0.0011846562,0.18212177,0.0009072204,0.03987833],"study_design_scores_gemma":[0.00022465659,0.00045050343,0.00047517256,0.000018978977,0.0000055128594,0.000018527855,0.00011440375,0.9877355,0.0016870954,0.00009883279,0.009005747,0.0001650717],"about_ca_topic_score_codex":0.00003144758,"about_ca_topic_score_gemma":0.0000192815,"teacher_disagreement_score":0.63793653,"about_ca_system_score_codex":0.00004667035,"about_ca_system_score_gemma":0.00005675307,"threshold_uncertainty_score":0.53633976},"labels":[],"label_agreement":null},{"id":"W2963250930","doi":"","title":"Convergent Tree Backup and Retrace with Function Approximation","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Backup; Reinforcement learning; Saddle point; Computer science; Tree (set theory); Function approximation; Mathematical optimization; Convergence (economics); Function (biology); Approximation algorithm; Bootstrapping (finance); Saddle; Quadratic equation; Applied mathematics; Mathematics; Algorithm; Artificial intelligence; Combinatorics","score_opus":0.0275852956681716,"score_gpt":0.265515831660857,"score_spread":0.2379305359926854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963250930","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":[0.015463401,0.000008837257,0.93049985,0.0017096206,0.00044352672,0.00010668286,5.7273144e-7,0.00016739822,0.0516001],"genre_scores_gemma":[0.9806107,0.00002055241,0.015351065,0.00027747563,0.00013298591,0.000007852477,0.000021877466,0.000011260283,0.0035661801],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872017,0.00007861716,0.00018987345,0.00035793538,0.00048329204,0.00017013565],"domain_scores_gemma":[0.99919766,0.000058989925,0.00018287252,0.000201704,0.00029192618,0.000066874905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026617156,0.00015175353,0.00010763825,0.00015105116,0.00017750186,0.00030515168,0.00039384572,0.000051057912,0.000317947],"category_scores_gemma":[0.00010300532,0.00012872824,0.000021522132,0.00014528184,0.00008724393,0.00047433266,0.00013106293,0.00034726856,0.00016959537],"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":[0.0003084109,0.000058266847,0.031989805,0.000022673516,0.00014169574,0.000012522785,0.0013834041,0.05123719,0.0030516468,0.83282924,0.00023383308,0.07873134],"study_design_scores_gemma":[0.00048673703,0.0008404995,0.008655562,0.000054670832,0.000006196357,0.00001628999,0.00004624257,0.9833678,0.000293576,0.0007184054,0.0053486023,0.0001653896],"about_ca_topic_score_codex":0.000025700476,"about_ca_topic_score_gemma":0.000016477237,"teacher_disagreement_score":0.9651474,"about_ca_system_score_codex":0.00005269845,"about_ca_system_score_gemma":0.000038668764,"threshold_uncertainty_score":0.5249385},"labels":[],"label_agreement":null},{"id":"W2963274839","doi":"","title":"Reinforcement Learning based Embodied Agents Modelling Human Users Through Interaction and Multi-Sensory Perception","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Computer science; Task (project management); Reinforcement learning; Embodied cognition; Perception; Artificial intelligence; Control (management); Human–computer interaction; Complement (music); Feedback control; Machine learning; Control engineering; Engineering","score_opus":0.20392061309279874,"score_gpt":0.2604560799500727,"score_spread":0.05653546685727395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963274839","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":[0.19609341,0.0000014734256,0.8003227,0.00003668237,0.00016769806,0.00013444708,1.5264472e-7,0.00013070604,0.0031127052],"genre_scores_gemma":[0.9877468,0.00004080411,0.00822708,0.00007912085,0.000026965223,4.951473e-7,0.0000071655495,0.000013822244,0.0038578005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878067,0.00008735219,0.00018065171,0.00053968426,0.00011588379,0.00029577536],"domain_scores_gemma":[0.9986936,0.000042197695,0.00034398396,0.0007320257,0.00009272504,0.00009547152],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00020262582,0.00019214934,0.00015957507,0.00012396186,0.0013477728,0.00034975348,0.0006951614,0.000092118884,0.000032828335],"category_scores_gemma":[0.00003594446,0.00022798998,0.00007890808,0.00008863089,0.00011516631,0.0018315886,0.0003582477,0.00031689872,0.00005588527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015214449,0.000016721946,0.005866436,0.000016912392,0.000022329243,0.000027276094,0.0006227537,0.9861292,0.00022728948,0.0069156745,0.000014745235,0.000125445],"study_design_scores_gemma":[0.0009735622,0.00009833418,0.0022903434,0.000052600284,0.000025096499,0.0000015481794,0.00031767314,0.9954831,0.00008317886,0.00012525663,0.0003045203,0.00024480157],"about_ca_topic_score_codex":0.00026515638,"about_ca_topic_score_gemma":0.0000114901,"teacher_disagreement_score":0.79209566,"about_ca_system_score_codex":0.00018704317,"about_ca_system_score_gemma":0.00002327849,"threshold_uncertainty_score":0.9999523},"labels":[],"label_agreement":null},{"id":"W2963313316","doi":"","title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":92,"is_retracted":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":"Kronecker delta; Reinforcement learning; Scalability; Computer science; Trust region; Curvature; Mathematical optimization; Artificial intelligence; Theoretical computer science; Mathematics","score_opus":0.05248858218001681,"score_gpt":0.31582601486795703,"score_spread":0.2633374326879402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963313316","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":[0.0015760745,0.00003949447,0.99408025,0.00017793968,0.0009905299,0.0009904318,3.7729953e-7,0.0002776186,0.0018672592],"genre_scores_gemma":[0.8919091,0.000003522369,0.10700553,0.00010019058,0.00014896772,0.00009959544,0.000045350487,0.000020804886,0.0006668938],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99744946,0.000092684415,0.000996241,0.0002987434,0.00064335094,0.00051954866],"domain_scores_gemma":[0.9963442,0.00007674344,0.00214865,0.00072438654,0.0005847944,0.00012121818],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009493851,0.00029308072,0.00034141322,0.00026117061,0.002178416,0.004574608,0.0010977865,0.00017001297,0.0000022953282],"category_scores_gemma":[0.00047495717,0.00027539016,0.00010234224,0.00019370764,0.000053206317,0.012488752,0.00023755887,0.00027005107,0.0000258228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013985549,0.000004738736,0.00034934623,0.00046477868,0.000013039592,4.8107e-7,0.0014992561,0.96002185,0.00020231475,0.0019971607,0.000063487285,0.035369586],"study_design_scores_gemma":[0.00077301986,0.00010984698,0.00012187508,0.00018955731,0.000020142443,0.000042028383,0.00030556112,0.99272275,0.00080611464,0.000039362843,0.0045507695,0.00031894597],"about_ca_topic_score_codex":0.00008821909,"about_ca_topic_score_gemma":5.932486e-7,"teacher_disagreement_score":0.89033306,"about_ca_system_score_codex":0.00025362594,"about_ca_system_score_gemma":0.00012751056,"threshold_uncertainty_score":0.99996984},"labels":[],"label_agreement":null},{"id":"W2963388106","doi":"10.1609/aaai.v33i01.33015797","title":"QUOTA: The Quantile Option Architecture for Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Quantile; Reinforcement learning; Architecture; Computer science; Optimism; Value (mathematics); Artificial intelligence; Econometrics; Machine learning; Economics; Psychology","score_opus":0.05244733210608453,"score_gpt":0.2880631182674069,"score_spread":0.23561578616132234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963388106","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":[0.03267565,0.000012624405,0.9510278,0.0046155257,0.00076948537,0.0013479983,6.678984e-7,0.00011805446,0.009432181],"genre_scores_gemma":[0.99332064,0.000019806439,0.003917509,0.00025307294,0.00007235236,0.000055326927,9.875596e-7,0.000015391839,0.0023448975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979764,0.00002322944,0.00054139073,0.0004356984,0.00061173714,0.00041153302],"domain_scores_gemma":[0.9982339,0.0002019663,0.0005587248,0.00041570695,0.0005355528,0.000054156808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007923636,0.00023100215,0.00024002662,0.00010022958,0.00034133167,0.00036336004,0.00238043,0.00008854191,0.000053228378],"category_scores_gemma":[0.00048940064,0.00014297225,0.00017424916,0.0004605703,0.00016005024,0.00032165032,0.00044651335,0.00049446826,0.00015220208],"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":[0.000035547746,0.00001652103,0.0001252654,0.00004546625,0.000014285829,3.752374e-8,0.0011677832,0.3084116,0.012518495,0.6661253,0.000076014476,0.01146369],"study_design_scores_gemma":[0.00004721397,0.00051692943,0.00009017536,0.00018142993,0.000012907912,0.0000026545717,0.00058644015,0.8548919,0.11236616,0.029375156,0.0017203332,0.00020872305],"about_ca_topic_score_codex":0.000017383121,"about_ca_topic_score_gemma":0.0000020699338,"teacher_disagreement_score":0.960645,"about_ca_system_score_codex":0.00005225942,"about_ca_system_score_gemma":0.00008114483,"threshold_uncertainty_score":0.5830239},"labels":[],"label_agreement":null},{"id":"W2963430540","doi":"10.1609/aaai.v33i01.33015789","title":"ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Ensemble learning; Search tree; Computer science; Perspective (graphical); Tree (set theory); Control (management); Artificial intelligence; Value (mathematics); Machine learning; Search algorithm; Ensemble forecasting; Mathematical optimization; Algorithm; Mathematics","score_opus":0.048752940312597276,"score_gpt":0.28943699690266234,"score_spread":0.24068405659006506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963430540","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":[0.064276695,0.000005809146,0.9277467,0.0012201745,0.0003583681,0.0014246105,0.000005737993,0.00012343917,0.004838426],"genre_scores_gemma":[0.9608443,0.0000059073272,0.037344243,0.00021505896,0.00007306519,0.000048627295,0.0000010729088,0.00002445065,0.0014433122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976074,0.000025236875,0.00047635526,0.00061718345,0.00071783015,0.00055598107],"domain_scores_gemma":[0.9975915,0.000210815,0.00037565656,0.0005044559,0.0011830928,0.00013446786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006857785,0.00027926525,0.0003939899,0.00012826623,0.00018278799,0.00044396814,0.0024860615,0.00011225832,0.0000463225],"category_scores_gemma":[0.00014752871,0.0001945699,0.00011284882,0.0004453006,0.00020823473,0.000698142,0.00021186301,0.00034347558,0.00010359009],"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":[0.00031232825,0.00021618044,0.00093894365,0.00008843421,0.00007446129,8.213211e-7,0.0022431181,0.010883067,0.06846494,0.5930616,0.00010975635,0.3236063],"study_design_scores_gemma":[0.0001593472,0.0015899207,0.00011454044,0.00012477815,0.0000156546,0.0000046527894,0.0005415235,0.74914074,0.24340855,0.0044930424,0.00015643585,0.0002508112],"about_ca_topic_score_codex":0.000022187118,"about_ca_topic_score_gemma":0.0000051948996,"teacher_disagreement_score":0.8965676,"about_ca_system_score_codex":0.00005500747,"about_ca_system_score_gemma":0.00016807442,"threshold_uncertainty_score":0.793433},"labels":[],"label_agreement":null},{"id":"W2963437270","doi":"","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates.","year":2018,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta; University of British Columbia","funders":"","keywords":"Control variates; Temporal difference learning; Reinforcement learning; Variance (accounting); Computer science; Control (management); Variance reduction; Monte Carlo method; Artificial intelligence; Machine learning; Statistics; Mathematics; Hybrid Monte Carlo; Bayesian probability; Markov chain Monte Carlo","score_opus":0.04175902341515242,"score_gpt":0.29736944076871763,"score_spread":0.2556104173535652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963437270","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":[0.024280187,0.0000232633,0.973681,0.00029625397,0.00054851745,0.0004097868,0.000001129842,0.0002514954,0.00050839724],"genre_scores_gemma":[0.91474295,0.0000094348125,0.08444803,0.00023781971,0.0001397444,0.00002624314,0.000003935175,0.000022428932,0.00036943913],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668896,0.00023484034,0.00078894803,0.0008340014,0.000687497,0.0007657619],"domain_scores_gemma":[0.99770385,0.00065604196,0.00028941644,0.00077351654,0.0004007421,0.00017643554],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092065445,0.00036139082,0.0003918751,0.0003060785,0.00031762547,0.000430544,0.001517513,0.00015544784,0.00015444499],"category_scores_gemma":[0.0006751445,0.00029851322,0.000076389006,0.0009073229,0.0004176887,0.00039926902,0.00027601467,0.0006631381,0.00063286873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016779288,0.000114814626,0.009597239,0.0000087900435,0.000017471828,0.000032048378,0.002219321,0.83322,0.00066613225,0.022699425,0.000010766723,0.13124622],"study_design_scores_gemma":[0.00021600001,0.0007720465,0.0019823331,0.00012931618,0.0000073778715,0.000010932565,0.00036889198,0.992449,0.0011450279,0.0019423176,0.00056600274,0.00041076576],"about_ca_topic_score_codex":0.0011615485,"about_ca_topic_score_gemma":0.0012752519,"teacher_disagreement_score":0.89046276,"about_ca_system_score_codex":0.00018773622,"about_ca_system_score_gemma":0.00017620399,"threshold_uncertainty_score":0.9999467},"labels":[],"label_agreement":null},{"id":"W2963462732","doi":"","title":"Planning by Prioritized Sweeping with Small Backups","year":2013,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Backup; Successor cardinal; Computer science; Reinforcement learning; Flexibility (engineering); Computation; Implementation; Process (computing); Distributed computing; State (computer science); Artificial intelligence; Algorithm; Mathematics","score_opus":0.03698794599683398,"score_gpt":0.27144154936796033,"score_spread":0.23445360337112636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963462732","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":[0.017891286,0.000029485465,0.9226633,0.003062324,0.00028300798,0.00020659076,0.0000011389749,0.00035299687,0.055509914],"genre_scores_gemma":[0.95176524,0.000016113283,0.04068546,0.00065348734,0.00007654795,0.000034413995,0.000049383634,0.000025808618,0.0066935294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814576,0.00011609148,0.00030792717,0.00047379988,0.00058969535,0.0003667483],"domain_scores_gemma":[0.99885905,0.0001817858,0.00025295065,0.0002945954,0.00028882653,0.0001227762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024163345,0.00024893298,0.00020025721,0.00018246727,0.00020434648,0.0008433923,0.001226661,0.000068389854,0.0005560522],"category_scores_gemma":[0.00017231396,0.00021764499,0.000049579507,0.00017404403,0.000049666203,0.00060438656,0.00025529286,0.0007772346,0.0004653224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007303282,0.00008313533,0.049858656,0.00002941942,0.00021838376,0.00006403576,0.0016399835,0.7411642,0.00819745,0.15386318,0.0010800646,0.043728467],"study_design_scores_gemma":[0.00074757147,0.00025507296,0.002122056,0.00018452069,0.0000042360493,0.000021075733,0.00008039359,0.9871492,0.00029086624,0.0004467488,0.008365401,0.00033288877],"about_ca_topic_score_codex":0.00017493949,"about_ca_topic_score_gemma":0.0000028140078,"teacher_disagreement_score":0.93387395,"about_ca_system_score_codex":0.00008426362,"about_ca_system_score_gemma":0.00006377364,"threshold_uncertainty_score":0.8875305},"labels":[],"label_agreement":null},{"id":"W2963558674","doi":"","title":"Context-dependent upper-confidence bounds for directed exploration","year":2018,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Context (archaeology); Computation; Machine learning; Artificial intelligence; Variance (accounting); Mathematical optimization; Algorithm; Mathematics","score_opus":0.03561658697522566,"score_gpt":0.2804357901936462,"score_spread":0.24481920321842052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963558674","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":[0.0011931859,0.00009977607,0.9934945,0.0003785633,0.001715937,0.0006450327,0.000002286368,0.00074646424,0.001724272],"genre_scores_gemma":[0.9945136,0.0000033071867,0.003879485,0.00048756474,0.00023795001,0.00015023637,0.0000283888,0.000009894326,0.0006896007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981853,0.00004949502,0.00070029247,0.0002072824,0.00053623656,0.0003213946],"domain_scores_gemma":[0.9979626,0.00006831512,0.0005282941,0.00037628703,0.0009848616,0.00007965672],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00050075416,0.00017600853,0.00019538397,0.00018890835,0.0005320724,0.0021005736,0.00061418157,0.00009244297,0.0000033497447],"category_scores_gemma":[0.00021837372,0.00016009863,0.00005500822,0.0003722262,0.00006745748,0.010790187,0.00008401065,0.000113445116,0.0001356408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001273028,0.00005814899,0.00063347333,0.0020395836,0.00010180507,0.0000021764624,0.041839346,0.41304547,0.0015434709,0.11524869,0.015771285,0.40958926],"study_design_scores_gemma":[0.00038160832,0.00019795077,0.000049357197,0.000109153014,0.0000066462567,0.000017915065,0.0004763891,0.96972334,0.0014889378,0.00012537358,0.027226336,0.00019700087],"about_ca_topic_score_codex":0.00003808277,"about_ca_topic_score_gemma":0.0000025961192,"teacher_disagreement_score":0.9933204,"about_ca_system_score_codex":0.000099747456,"about_ca_system_score_gemma":0.00012610522,"threshold_uncertainty_score":0.99893534},"labels":[],"label_agreement":null},{"id":"W2963800416","doi":"","title":"Policy Error Bounds for Model-Based Reinforcement Learning with Factored Linear Models","year":2016,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Mathematical proof; Markov decision process; Contraction (grammar); Property (philosophy); Computer science; Mathematics; Applied mathematics; Mathematical optimization; Measure (data warehouse); Class (philosophy); Markov process; Linear model; Artificial intelligence; Machine learning; Statistics","score_opus":0.0519210604033747,"score_gpt":0.29348081808446674,"score_spread":0.24155975768109206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963800416","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":[0.0016897339,0.0000071539666,0.9836047,0.0013604157,0.00010978968,0.00051982334,0.0000015381991,0.00071618106,0.011990612],"genre_scores_gemma":[0.94151676,0.00001674277,0.031600088,0.00044495251,0.00009973693,0.00012360954,0.000015704021,0.00007344195,0.026108969],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968311,0.00027278758,0.00047101834,0.00082397216,0.0006782445,0.0009228412],"domain_scores_gemma":[0.99710447,0.0008285419,0.00045325083,0.0009167666,0.00043448887,0.0002624787],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011423086,0.000488501,0.00042109878,0.00042121086,0.00060628064,0.00028518325,0.0013223019,0.00018584967,0.00005324014],"category_scores_gemma":[0.00084171497,0.00033597634,0.00015956546,0.00034338105,0.00025879996,0.00073659467,0.00022578202,0.00058698683,0.00009424819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018821444,0.0000152219845,0.000053024523,0.00001908062,0.000026958858,0.0000018179347,0.0004753046,0.59856814,0.0004307534,0.39399788,0.000015751752,0.00620784],"study_design_scores_gemma":[0.0017329222,0.0015715811,0.000016343882,0.0003082883,0.000018177772,0.0000023174125,0.00008121869,0.97203183,0.00097192335,0.021512104,0.0012055776,0.0005477313],"about_ca_topic_score_codex":0.0000069815433,"about_ca_topic_score_gemma":9.0650025e-7,"teacher_disagreement_score":0.9520047,"about_ca_system_score_codex":0.000254692,"about_ca_system_score_gemma":0.000971865,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W2963828709","doi":"10.48550/arxiv.1703.01327","title":"Multi-step Reinforcement Learning: A Unifying Algorithm","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Backup; Algorithm; TRACE (psycholinguistics); Sampling (signal processing); Focus (optics); Monte Carlo method; Importance sampling; Artificial intelligence; Machine learning; Mathematics","score_opus":0.09250465055229885,"score_gpt":0.2190304302502291,"score_spread":0.12652577969793027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963828709","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":[0.0036045425,0.000007937349,0.98711914,0.00008929949,0.0003706131,0.00016933226,2.4569363e-7,0.00029305616,0.0083458265],"genre_scores_gemma":[0.92979765,0.000051568684,0.041697286,0.00007199572,0.00004452097,5.04876e-7,0.00000306983,0.000015828711,0.028317558],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984516,0.0000778037,0.00019505787,0.00062941044,0.00014961467,0.0004964932],"domain_scores_gemma":[0.99763435,0.00006359884,0.00039232144,0.001575753,0.00013580461,0.00019819793],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032486152,0.00022913665,0.00020427925,0.00015818649,0.0012604888,0.0004570763,0.0025591967,0.00010770864,0.000043554137],"category_scores_gemma":[0.00014656635,0.0002611924,0.00012658663,0.00022770923,0.00015319874,0.0013607382,0.0012344638,0.00039199964,0.00036721726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049286255,0.000019335017,0.004457998,0.000009683474,0.0000395155,0.00019310428,0.00016831952,0.9633358,0.00004955169,0.028081903,0.000075772936,0.0035640683],"study_design_scores_gemma":[0.00097655295,0.00010801928,0.0025360791,0.000030133322,0.000018733228,0.000005852884,0.000091645794,0.9900383,0.00010365975,0.00009973636,0.0056765224,0.00031480019],"about_ca_topic_score_codex":0.00016073299,"about_ca_topic_score_gemma":0.000008760825,"teacher_disagreement_score":0.9454219,"about_ca_system_score_codex":0.00015875134,"about_ca_system_score_gemma":0.00007868621,"threshold_uncertainty_score":0.999984},"labels":[],"label_agreement":null},{"id":"W2963923407","doi":"","title":"Addressing Function Approximation Error in Actor-Critic Methods","year":2018,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":414,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Bellman equation; Suite; Function (biology); Function approximation; Value (mathematics); Limit (mathematics); Artificial intelligence; Approximation algorithm; Temporal difference learning; Mathematical optimization; Machine learning; Algorithm; Artificial neural network; Mathematics","score_opus":0.07700182874909071,"score_gpt":0.32152854316397317,"score_spread":0.24452671441488244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963923407","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":[0.034672778,0.000015698655,0.9586182,0.00030591153,0.00039637391,0.00013783907,7.9690477e-7,0.000103758386,0.0057486165],"genre_scores_gemma":[0.7351088,0.000002276131,0.26410782,0.00007124237,0.00003908871,1.837117e-7,0.0000057800225,0.000006758804,0.0006580958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882597,0.00020860751,0.00015793472,0.0003034289,0.00026402465,0.00024006421],"domain_scores_gemma":[0.99906206,0.00009876372,0.00017667988,0.00043617663,0.00016418255,0.00006210866],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046953472,0.00011673912,0.00018830308,0.0003085093,0.00019659665,0.000061242004,0.00063767383,0.00009508116,0.000114093884],"category_scores_gemma":[0.00006597937,0.00014726164,0.00006337802,0.00054045825,0.00015735449,0.0011708307,0.00033022522,0.00016252145,0.0000588998],"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":[0.00046570876,0.00044088357,0.015899327,0.0010216153,0.0002674565,0.00010719704,0.06703836,0.06675688,0.04366093,0.05056656,0.0042539556,0.74952114],"study_design_scores_gemma":[0.0010746331,0.00043230076,0.04460939,0.0002488052,0.000032623328,0.0000074395325,0.002492132,0.94362915,0.0011983272,0.0009356977,0.004993854,0.00034567952],"about_ca_topic_score_codex":0.00009073262,"about_ca_topic_score_gemma":0.00003730231,"teacher_disagreement_score":0.87687224,"about_ca_system_score_codex":0.000114327166,"about_ca_system_score_gemma":0.00005961961,"threshold_uncertainty_score":0.60051554},"labels":[],"label_agreement":null},{"id":"W2963969179","doi":"10.3389/fnbot.2019.00052","title":"A Novel Model for Arbitration Between Planning and Habitual Control Systems","year":2019,"lang":"en","type":"article","venue":"PubMed Central","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Action selection; Reinforcement learning; Internal model; Task (project management); Control (management); Artificial intelligence; Action (physics); A priori and a posteriori; Kinematics; Machine learning; Human–computer interaction","score_opus":0.030970041851913634,"score_gpt":0.2354315636919563,"score_spread":0.20446152184004268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963969179","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":[0.03744147,0.000048303722,0.9604368,0.0001511294,0.0005433676,0.00096559373,0.000007709093,0.00009229849,0.00031332322],"genre_scores_gemma":[0.985963,6.9447043e-7,0.0131912595,0.00013862869,0.00019107238,0.00009130238,0.000010104547,0.000010125681,0.00040380383],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984745,0.00001811129,0.00021969949,0.00026667945,0.0002144959,0.0008065348],"domain_scores_gemma":[0.99931556,0.00014187305,0.00011026384,0.00021269609,0.000034080185,0.00018552542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044610264,0.00011560645,0.00017844413,0.00005312669,0.000070350965,0.0002680497,0.00028011328,0.00006665253,3.402606e-7],"category_scores_gemma":[0.000062008694,0.000111486755,0.000037375296,0.000064545864,0.000017561812,0.00044030612,0.000048360474,0.00011043559,0.000003351255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007952844,0.0000057830653,0.04071702,0.000034855224,0.00002556244,2.385627e-7,0.0005315342,0.9423239,0.00012670296,0.015812475,0.000060225073,0.00035372097],"study_design_scores_gemma":[0.0011775024,0.000037662696,0.04470473,0.000015564376,0.000012919775,0.0000029620885,0.000016030772,0.95361584,0.000028945438,0.000054812983,0.00020279133,0.0001302521],"about_ca_topic_score_codex":0.0000063679527,"about_ca_topic_score_gemma":3.7536816e-7,"teacher_disagreement_score":0.94852155,"about_ca_system_score_codex":0.00008176962,"about_ca_system_score_gemma":0.0000694781,"threshold_uncertainty_score":0.4546298},"labels":[],"label_agreement":null},{"id":"W2964112145","doi":"","title":"Weak convergence properties of constrained emphatic temporal-difference learning with constant and slowly diminishing stepsize","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"","keywords":"Iterated function; Convergence (economics); Markov decision process; Markov chain; Mathematics; Weak convergence; Constant (computer programming); Ergodic theory; Applied mathematics; Divergence (linguistics); Rate of convergence; Limit (mathematics); Stochastic approximation; Markov process; Mathematical optimization; Computer science; Key (lock); Mathematical analysis; Statistics","score_opus":0.05478746984954716,"score_gpt":0.3014922333272734,"score_spread":0.2467047634777262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964112145","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":[0.69054276,0.000757149,0.30555472,0.002142891,0.000109910296,0.00023133893,6.4584566e-7,0.000051407376,0.00060919643],"genre_scores_gemma":[0.9850425,0.00043837895,0.012296807,0.0000148091,0.000042517713,0.0000034412085,3.225768e-7,0.000024214987,0.002136998],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99523056,0.0011840545,0.0008706066,0.0003528706,0.0017658345,0.00059607066],"domain_scores_gemma":[0.9955349,0.0017377362,0.0009328045,0.00033032702,0.0012044797,0.00025975928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050131464,0.00023945441,0.00054553576,0.00050901575,0.00038245955,0.00027813637,0.0010531949,0.00008988054,0.000042245767],"category_scores_gemma":[0.0044634882,0.00013643964,0.000079184094,0.0005774282,0.0009105948,0.0007533361,0.00047755562,0.0014907024,0.000007703147],"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":[0.000763562,0.00013542733,0.71450895,0.00060884183,0.00033055226,0.00027410136,0.0057651857,0.035680708,0.19205506,0.007446728,0.000059059596,0.042371817],"study_design_scores_gemma":[0.01358927,0.021732457,0.046880536,0.018067723,0.00013328822,0.003037219,0.0051865545,0.8441844,0.039583556,0.00095232506,0.004825151,0.0018275253],"about_ca_topic_score_codex":0.000069538764,"about_ca_topic_score_gemma":0.0000053935437,"teacher_disagreement_score":0.8085037,"about_ca_system_score_codex":0.00009295855,"about_ca_system_score_gemma":0.0005817413,"threshold_uncertainty_score":0.6476443},"labels":[],"label_agreement":null},{"id":"W2964190622","doi":"","title":"Eigenoption Discovery through the Deep Successor Representation","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Successor cardinal; Representation (politics); Feature learning; Exploit; Deep learning; Leverage (statistics); ENCODE; Machine learning; Intuition; Cognitive science; Mathematics","score_opus":0.09020491085728016,"score_gpt":0.22714582750763676,"score_spread":0.1369409166503566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964190622","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":[0.06979012,0.000007200205,0.91760796,0.000422138,0.00035957532,0.00013133748,3.4922098e-7,0.0000807578,0.011600548],"genre_scores_gemma":[0.9923828,0.00006894466,0.0012268069,0.000098923025,0.00005858966,4.1124576e-7,0.0000024819342,0.000006323544,0.006154669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911547,0.000074105075,0.000105645566,0.0003865557,0.00010148569,0.00021676588],"domain_scores_gemma":[0.99799776,0.000086348424,0.0002579065,0.0015531991,0.00006831507,0.000036445323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014620495,0.00010652183,0.00009080571,0.000035729205,0.0010147595,0.00066338066,0.0019786255,0.000049733477,0.000012861085],"category_scores_gemma":[0.00009331385,0.000090394875,0.00007469303,0.0001856523,0.00015388861,0.003736949,0.0005512228,0.0001403309,0.000119567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007085392,0.000008833543,0.008886182,0.0000030316894,0.000016839049,0.000026454429,0.00029896124,0.7025069,0.000047795453,0.28785852,0.000068986126,0.00027042747],"study_design_scores_gemma":[0.00035743255,0.000042236745,0.028430717,0.000010953769,0.00002318593,0.000003334382,0.00016116585,0.95922667,0.0003782186,0.010140975,0.0010526449,0.00017249104],"about_ca_topic_score_codex":0.00022273415,"about_ca_topic_score_gemma":0.00004390253,"teacher_disagreement_score":0.92259276,"about_ca_system_score_codex":0.00006823154,"about_ca_system_score_gemma":0.000029741186,"threshold_uncertainty_score":0.7804812},"labels":[],"label_agreement":null},{"id":"W2964191931","doi":"","title":"Unsupervised Video Object Segmentation for Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":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; Artificial intelligence; Segmentation; Representation (politics); Object (grammar); Motion (physics); Code (set theory); Unsupervised learning; Object detection; Focus (optics); Computer vision; Action (physics); Suite; Feature learning; Deep learning; Machine learning; Set (abstract data type)","score_opus":0.0505535799427427,"score_gpt":0.20287374622500598,"score_spread":0.15232016628226328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964191931","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":[0.020803398,0.000005850268,0.9739411,0.000052042567,0.0003079886,0.00036210037,1.7924317e-7,0.00026109378,0.0042662523],"genre_scores_gemma":[0.98451173,0.000018656347,0.010150418,0.00020220503,0.00009709257,0.0000021257904,0.00001244443,0.000015094102,0.0049902564],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869275,0.000074755364,0.00019659309,0.0005184315,0.00011817815,0.00039930805],"domain_scores_gemma":[0.9988548,0.00014461568,0.00016522352,0.00048559252,0.00023396214,0.000115813324],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029045375,0.00017722994,0.00014911836,0.00017966655,0.00044862524,0.00012234725,0.00076414744,0.00007584065,0.00007805285],"category_scores_gemma":[0.0000905545,0.00020301034,0.00010477534,0.0006056595,0.00009177024,0.00080631283,0.0002500259,0.00013771979,0.00021877547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003312266,0.000010901174,0.0013924297,0.00001561546,0.000036213463,0.000007618895,0.0005806465,0.95028895,0.0005049824,0.04613548,0.00012894005,0.0008650952],"study_design_scores_gemma":[0.001030969,0.00052442914,0.00029905455,0.000016767186,0.00002654522,0.0000018731994,0.00020676495,0.9926014,0.0021857708,0.00065567676,0.0022058806,0.00024488854],"about_ca_topic_score_codex":0.000022873406,"about_ca_topic_score_gemma":0.000008726201,"teacher_disagreement_score":0.96379066,"about_ca_system_score_codex":0.00018471248,"about_ca_system_score_gemma":0.000063944375,"threshold_uncertainty_score":0.82785213},"labels":[],"label_agreement":null},{"id":"W2964227312","doi":"10.1609/aaai.v31i1.10916","title":"The Option-Critic Architecture","year":2017,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":695,"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":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Flexibility (engineering); Computer science; Abstraction; Architecture; Key (lock); Artificial intelligence; Machine learning; Computer security; Economics; Management; Epistemology","score_opus":0.014118730041843058,"score_gpt":0.26830135844916925,"score_spread":0.2541826284073262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964227312","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":[0.00025326523,0.000014303602,0.93272,0.008261321,0.00039823167,0.000050387313,2.852388e-8,0.00008044368,0.058222003],"genre_scores_gemma":[0.930691,0.000014305571,0.047951914,0.00036557188,0.00008126167,0.000004686381,1.7527252e-7,0.0000041309654,0.020886948],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945915,0.000016506137,0.00007638545,0.000114349474,0.00016726619,0.00016636624],"domain_scores_gemma":[0.9985939,0.000097288554,0.000050366987,0.0011915446,0.000031608368,0.000035242378],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00016775199,0.000051504594,0.000038135673,0.000012221529,0.0011864849,0.0011661336,0.0019252119,0.000018416256,0.000009146883],"category_scores_gemma":[0.00019236446,0.00002995117,0.000028593215,0.000020886422,0.000082667255,0.00021163923,0.00034957158,0.00010622746,0.00017670667],"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":[6.5278005e-7,0.000002478694,0.000277192,0.0000022931154,0.0000067932797,0.0000033494864,0.00010849939,0.06727173,0.000050348215,0.89376193,0.0011793202,0.037335392],"study_design_scores_gemma":[0.00017589661,0.00004970566,0.010186613,0.0000111481595,0.0000027361193,0.00001534647,0.000016550981,0.8550664,0.0003721338,0.01743314,0.116514385,0.00015592949],"about_ca_topic_score_codex":0.000010973381,"about_ca_topic_score_gemma":0.0000052126775,"teacher_disagreement_score":0.93043774,"about_ca_system_score_codex":0.00000868247,"about_ca_system_score_gemma":0.00001906291,"threshold_uncertainty_score":0.9998708},"labels":[],"label_agreement":null},{"id":"W2964295739","doi":"","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":163,"is_retracted":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; Robustness (evolution); Computer science; Artificial intelligence; Construct (python library); Policy learning; Machine learning; Contrast (vision); Deep learning; Context (archaeology); Architecture","score_opus":0.0722518834787979,"score_gpt":0.22074985081393533,"score_spread":0.14849796733513743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964295739","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":[0.0061124936,0.000005699126,0.98317707,0.00019101826,0.00035167407,0.00028960613,2.392711e-7,0.00016242184,0.009709782],"genre_scores_gemma":[0.97742015,0.000028408245,0.003015302,0.00010242237,0.00003797056,0.0000016964414,0.000009398245,0.000012399974,0.01937227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885064,0.000037644382,0.00015938048,0.00046985282,0.00011554959,0.00036691077],"domain_scores_gemma":[0.99830186,0.00007673725,0.0003472595,0.00096284656,0.00019302663,0.00011828894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025698091,0.0001626348,0.00014288371,0.0001286689,0.0010866127,0.00036078438,0.0017120765,0.0000586294,0.000043116568],"category_scores_gemma":[0.00021081841,0.00019056199,0.000108086904,0.00014248064,0.000089966576,0.0013054945,0.00054077775,0.00015778044,0.00012104097],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010838434,0.000011761792,0.004639879,0.000011966915,0.00003420143,0.000019494591,0.00011821002,0.8581836,0.000030577925,0.13602057,0.00019875584,0.00072014873],"study_design_scores_gemma":[0.0010314548,0.00011068285,0.0025426466,0.00001765658,0.000021709968,0.0000013098015,0.000045017816,0.9879441,0.00018312607,0.0010907553,0.006795222,0.00021630427],"about_ca_topic_score_codex":0.000029143246,"about_ca_topic_score_gemma":0.000004092922,"teacher_disagreement_score":0.9801618,"about_ca_system_score_codex":0.00015359044,"about_ca_system_score_gemma":0.000044778808,"threshold_uncertainty_score":0.83574563},"labels":[],"label_agreement":null},{"id":"W2964363500","doi":"10.11159/cist19.118","title":"LongiControl: A New Reinforcement Learning Environment","year":2019,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Reinforcement Learning in Robotics","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; Computer science; Human–computer interaction; Artificial intelligence","score_opus":0.005112510692350032,"score_gpt":0.18142821253822908,"score_spread":0.17631570184587905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964363500","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":[0.27045485,0.0011018208,0.7174401,0.0010608365,0.004497122,0.0016338497,2.041724e-7,0.00041178125,0.0033994054],"genre_scores_gemma":[0.99355024,0.0000330932,0.0017698362,0.00005158036,0.00007286551,0.0000062076188,4.167421e-8,0.00000757722,0.0045085656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983731,0.0000054574175,0.0002707069,0.00041284182,0.00057116715,0.000366728],"domain_scores_gemma":[0.99935335,0.00008205017,0.0001729305,0.00017915477,0.000056729637,0.0001558049],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042565042,0.00017229623,0.00024030889,0.0001926448,0.0001467284,0.000412618,0.0008184094,0.000030270641,0.0000011405403],"category_scores_gemma":[0.000031186406,0.00012258702,0.000039643324,0.00060483656,0.00007123755,0.000328799,0.00045336667,0.00026782873,0.0000037925304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050583935,0.0000066703806,0.002627134,0.00005009853,0.000013310594,3.1807713e-7,0.000093970186,0.87729216,0.0018524425,0.115394615,0.000113143025,0.002551098],"study_design_scores_gemma":[0.0002976804,0.00025412423,0.00211731,0.00015894379,0.0000046370333,0.000014626376,0.0000027083115,0.9932398,0.0006703192,0.000015816491,0.0030718572,0.0001521425],"about_ca_topic_score_codex":0.00000884795,"about_ca_topic_score_gemma":5.198977e-8,"teacher_disagreement_score":0.72309536,"about_ca_system_score_codex":0.000055508317,"about_ca_system_score_gemma":0.000033183864,"threshold_uncertainty_score":0.49989536},"labels":[],"label_agreement":null},{"id":"W2964469479","doi":"","title":"Understanding the Relation Between Maximum-Entropy Inverse Reinforcement Learning and Behaviour Cloning.","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"University of Toronto","funders":"","keywords":"Reinforcement learning; Principle of maximum entropy; Cloning (programming); Artificial intelligence; Computer science; Relation (database); Inverse; Entropy (arrow of time); Mathematics; Machine learning; Data mining; Physics; Thermodynamics","score_opus":0.0945946462711303,"score_gpt":0.3266313768676395,"score_spread":0.2320367305965092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964469479","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":[0.048949543,0.000005737455,0.8974964,0.0041039265,0.00059405214,0.00039213875,7.9944937e-7,0.00023072911,0.0482267],"genre_scores_gemma":[0.9870116,0.000052448235,0.0019364149,0.00011107472,0.00008419365,0.00002151569,0.00006707069,0.000018028335,0.010697624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99774057,0.00023444448,0.00041385,0.0004937571,0.0008252705,0.0002921347],"domain_scores_gemma":[0.99841577,0.00055862626,0.00039105717,0.0003441362,0.00019761837,0.0000927928],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052074785,0.00020121303,0.00016474964,0.00026847332,0.0005541941,0.00070662843,0.00067786773,0.000089624606,0.00036245646],"category_scores_gemma":[0.0003753715,0.0001778774,0.00007485493,0.00027639698,0.0000992838,0.00073336274,0.00036403848,0.00091857126,0.00028793621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009659366,0.000006086881,0.23044664,0.000004130556,0.000058253707,0.0000033067786,0.0021151006,0.54755455,0.00028359654,0.21904193,0.00007723915,0.00039948858],"study_design_scores_gemma":[0.0006801739,0.0002447456,0.058515605,0.00009689059,0.000025224586,0.000010491998,0.0023871688,0.93109566,0.000087137225,0.005112426,0.0014758524,0.00026865205],"about_ca_topic_score_codex":0.00005631406,"about_ca_topic_score_gemma":0.0000031934057,"teacher_disagreement_score":0.9380621,"about_ca_system_score_codex":0.00025620655,"about_ca_system_score_gemma":0.00008076348,"threshold_uncertainty_score":0.72536296},"labels":[],"label_agreement":null},{"id":"W2964599462","doi":"10.1609/aaai.v33i01.33019955","title":"Learning Options with Interest Functions","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Task (project management); Function (biology); State space; Plan (archaeology); Space (punctuation); Architecture; State (computer science); Artificial intelligence; Theoretical computer science; Mathematics; Algorithm; Economics","score_opus":0.06783980109864947,"score_gpt":0.2736481056250446,"score_spread":0.20580830452639515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964599462","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":[0.337202,0.000010886082,0.5782211,0.005296431,0.0009853629,0.00085883396,0.0000014378462,0.00036154792,0.07706239],"genre_scores_gemma":[0.9913886,0.000010982248,0.0036365362,0.00009060701,0.000032972563,0.000016238164,5.559536e-7,0.0000133669955,0.004810124],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984579,0.000017764738,0.00037740683,0.00041441704,0.00041972625,0.00031276868],"domain_scores_gemma":[0.99857885,0.00009389195,0.00035653228,0.0003414048,0.0005571645,0.00007218471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031376389,0.00019457588,0.00019828371,0.00014490272,0.00022433167,0.00032489793,0.0016187768,0.00006620943,0.00017606634],"category_scores_gemma":[0.00019707208,0.0001354933,0.00008458374,0.0007240108,0.00017972334,0.0005339525,0.00038261237,0.000531202,0.00070914475],"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":[0.000032567634,0.00005120982,0.0017173226,0.00002653954,0.000021732865,2.250435e-7,0.00071966165,0.05698576,0.010909812,0.92159534,0.00006322992,0.00787659],"study_design_scores_gemma":[0.00008864138,0.0019217582,0.001057388,0.0006805283,0.000031433203,0.000019427198,0.0027163362,0.8456983,0.129827,0.01577777,0.0016058594,0.0005755506],"about_ca_topic_score_codex":0.000013112953,"about_ca_topic_score_gemma":0.0000043285286,"teacher_disagreement_score":0.90581757,"about_ca_system_score_codex":0.000047524612,"about_ca_system_score_gemma":0.00008564916,"threshold_uncertainty_score":0.9114858},"labels":[],"label_agreement":null},{"id":"W2964760189","doi":"","title":"Epsilon-BMC: A Bayesian Ensemble Approach to Epsilon-Greedy Exploration in Model-Free Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Bayesian probability; Computer science; Perspective (graphical); Mathematical optimization; Monotone polygon; Convergence (economics); Greedy algorithm; Simulated annealing; Bellman equation; Q-learning; Function (biology); Artificial intelligence; Algorithm; Mathematics","score_opus":0.11597923760732981,"score_gpt":0.19311238480803547,"score_spread":0.07713314720070566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964760189","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":[0.008175722,0.0000054166776,0.9745935,0.00043548632,0.00007120399,0.00045077698,3.5771424e-7,0.0002924862,0.01597505],"genre_scores_gemma":[0.93129754,0.000014137252,0.06633697,0.00050271966,0.000022345806,0.0000034931886,0.0000096706435,0.000023107537,0.0017900357],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978074,0.00014018796,0.00034441767,0.0009138107,0.0002454466,0.0005487538],"domain_scores_gemma":[0.9984164,0.000072325034,0.00018138466,0.0008692304,0.00010007728,0.00036056002],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003238508,0.0002881435,0.00029332656,0.00032194145,0.00020386204,0.00015489687,0.0017687329,0.000118955,0.00001238015],"category_scores_gemma":[0.00020069357,0.0003489728,0.00010671578,0.0017492368,0.000041503674,0.0015028133,0.0009990104,0.0004400138,0.00017176812],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004877622,0.000030048555,0.0018775363,0.000031652846,0.000013345607,0.000028279515,0.002268971,0.893671,0.000100707526,0.10161625,0.0002394097,0.00007404562],"study_design_scores_gemma":[0.000915941,0.000264916,0.000109903805,0.000027400283,0.00001342478,0.0000014907743,0.00037037488,0.996316,0.00011183711,0.001279187,0.0002059383,0.0003835948],"about_ca_topic_score_codex":0.000049444487,"about_ca_topic_score_gemma":0.000014972237,"teacher_disagreement_score":0.9231218,"about_ca_system_score_codex":0.00024331002,"about_ca_system_score_gemma":0.00013429772,"threshold_uncertainty_score":0.9998962},"labels":[],"label_agreement":null},{"id":"W2964855005","doi":"10.1609/aiide.v15i1.5220","title":"On Hard Exploration for Reinforcement Learning: A Case Study in Pommerman","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; SAFER; Benchmark (surveying); Pruning; Computer science; Domain (mathematical analysis); Artificial intelligence; Machine learning; Computer security; Mathematics","score_opus":0.10090642247022633,"score_gpt":0.3290656216999939,"score_spread":0.2281591992297676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964855005","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":[0.62162346,0.000006368068,0.36430088,0.0013756428,0.0010458581,0.005140146,0.000009083136,0.00006843585,0.006430154],"genre_scores_gemma":[0.9984994,0.000019854066,0.00013697491,0.00015294252,0.000033617853,0.00032842648,0.000008486869,0.000023273004,0.00079705653],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972016,0.000033070133,0.0009362661,0.00087155355,0.00058574975,0.0003717155],"domain_scores_gemma":[0.997892,0.0002598853,0.0009066947,0.0003900403,0.00047113717,0.00008023074],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004155624,0.0004641125,0.0004886325,0.00033602054,0.00013605808,0.001112895,0.0010929399,0.00012590134,0.000009278445],"category_scores_gemma":[0.0004510971,0.00036902944,0.00018673702,0.00018292206,0.00009406785,0.001060794,0.0014369655,0.0008545113,0.000021692904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012254711,0.002159118,0.0033193883,0.000497966,0.00035258956,0.00003821356,0.049258772,0.69325376,0.00067512284,0.17542659,0.00014993615,0.073643066],"study_design_scores_gemma":[0.00025011264,0.004340426,0.00007851253,0.0013601258,0.00003039875,0.000018268498,0.020515444,0.9469361,0.012427785,0.013426339,0.000088259956,0.00052825594],"about_ca_topic_score_codex":0.000065079425,"about_ca_topic_score_gemma":0.0000071581876,"teacher_disagreement_score":0.3768759,"about_ca_system_score_codex":0.00028651636,"about_ca_system_score_gemma":0.00008491845,"threshold_uncertainty_score":0.99992406},"labels":[],"label_agreement":null},{"id":"W2965050397","doi":"10.24963/ijcai.2019/434","title":"On Principled Entropy Exploration in Policy Optimization","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Entropy (arrow of time); Mathematical optimization; Optimization problem; Convergence (economics); Set (abstract data type); Monotonic function; Constrained optimization problem; Multi-objective optimization; Descent (aeronautics); Machine learning; Algorithm; Mathematics; Economics; Engineering","score_opus":0.013976204612210875,"score_gpt":0.254103345513721,"score_spread":0.2401271409015101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965050397","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":[0.0034359817,6.6490793e-7,0.9735467,0.0009968863,0.0001394517,0.00019602141,2.619299e-8,0.000100251615,0.021584036],"genre_scores_gemma":[0.90405697,0.000007045667,0.09022417,0.000617407,0.000029819059,0.0000080147365,0.000005080038,0.000006448655,0.0050450386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993034,0.000034753808,0.00014906807,0.00017243893,0.00019744238,0.00014292586],"domain_scores_gemma":[0.99952716,0.00004362499,0.00005354339,0.00032190443,0.000027556196,0.000026194035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011899008,0.00006423348,0.00006545916,0.00020191053,0.000018852674,0.000090536305,0.00027779548,0.000031582076,0.00008496971],"category_scores_gemma":[0.00007346177,0.000057888505,0.000015542393,0.00037812997,0.000004411512,0.00062639336,0.00008157518,0.00006768735,0.00047939442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020519826,0.000007713348,0.00044543852,0.0000016438469,7.8536493e-7,3.4003958e-7,0.00012894797,0.707031,0.00004874916,0.29210365,0.000022484091,0.00020718898],"study_design_scores_gemma":[0.0003188381,0.00009341364,0.00046615882,0.0000086091895,2.4691815e-7,3.000674e-7,0.000008255121,0.9980679,0.00032261157,0.00038974118,0.00025580695,0.00006807403],"about_ca_topic_score_codex":0.000016449043,"about_ca_topic_score_gemma":0.000001240219,"teacher_disagreement_score":0.900621,"about_ca_system_score_codex":0.000097229386,"about_ca_system_score_gemma":0.000050270522,"threshold_uncertainty_score":0.61618054},"labels":[],"label_agreement":null},{"id":"W2965212561","doi":"","title":"Neural Graph Evolution: Towards Efficient Automatic Robot Design","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Robot; Graph; Artificial intelligence; Artificial neural network; Theoretical computer science; Machine learning","score_opus":0.05089747332137666,"score_gpt":0.3173870093774977,"score_spread":0.266489536056121,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2965212561","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":[0.015418723,0.000009225609,0.9432251,0.0029132508,0.0015249171,0.00037853295,0.000001105713,0.00046051675,0.036068656],"genre_scores_gemma":[0.97344095,0.0000057482403,0.019472,0.00014070094,0.00006767406,0.000047555055,0.000021111768,0.00001688628,0.006787351],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738294,0.00027512317,0.0004213848,0.0005807266,0.0010085638,0.00033125046],"domain_scores_gemma":[0.9982754,0.00031345309,0.0002816424,0.0005910952,0.0004280072,0.00011039103],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003845127,0.00021767525,0.00018855602,0.00041391473,0.00023010261,0.0005400017,0.0013209941,0.00007465209,0.0009237478],"category_scores_gemma":[0.00039874975,0.00021758105,0.0001252372,0.0004819162,0.00006915499,0.00045455,0.00027762662,0.0004975863,0.0013470969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072093276,0.000038562623,0.0023004557,0.000005024675,0.00003980055,0.0000067726887,0.0005979454,0.8749052,0.0005706135,0.11865961,0.00013092524,0.002737848],"study_design_scores_gemma":[0.00041837376,0.00018664905,0.01787419,0.00005651185,0.0000074126697,0.000019447387,0.00020463251,0.97933215,0.0001673986,0.0013204989,0.00018814203,0.00022456686],"about_ca_topic_score_codex":0.000052059793,"about_ca_topic_score_gemma":8.072806e-7,"teacher_disagreement_score":0.95802224,"about_ca_system_score_codex":0.0001883881,"about_ca_system_score_gemma":0.00019538618,"threshold_uncertainty_score":0.99998957},"labels":[],"label_agreement":null},{"id":"W2966234803","doi":"10.24963/ijcai.2019/445","title":"Hill Climbing on Value Estimates for Search-control in Dyna","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto; Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Hill climbing; Climbing; Reinforcement learning; Trajectory; Computer science; Bellman equation; Langevin dynamics; Value (mathematics); Sampling (signal processing); Artificial intelligence; Mathematical optimization; Mathematics; Machine learning; Statistics; Engineering","score_opus":0.03048606102777367,"score_gpt":0.29886017952237093,"score_spread":0.26837411849459725,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966234803","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":[0.00055841194,0.000026376048,0.9790287,0.0011937778,0.0012053521,0.0014711857,0.000003896317,0.00024820378,0.01626408],"genre_scores_gemma":[0.7895821,0.000010313899,0.20682266,0.0011559409,0.00011550129,0.000108947075,0.000027379947,0.000042160224,0.002135024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749696,0.00011983669,0.0004977122,0.0008212276,0.00047186002,0.0005923885],"domain_scores_gemma":[0.9971222,0.0012198668,0.00018532704,0.0012809039,0.000103124316,0.000088530556],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014216063,0.00032322897,0.0004651127,0.00033088797,0.000064449676,0.00042707045,0.0018599259,0.0002822005,0.000019837033],"category_scores_gemma":[0.00034127303,0.00029600578,0.00018038132,0.00009558348,0.00003169982,0.00017347283,0.001212877,0.00084436545,0.00019847357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012205954,0.000022475579,0.0011011485,0.00015796213,0.000029152661,0.0000033173826,0.00014923554,0.9108411,0.000024961448,0.08531212,0.00022890426,0.0021174091],"study_design_scores_gemma":[0.00077963906,0.00019000942,0.00060036004,0.00027425337,0.000009702925,0.0000010831656,0.000011652971,0.9945856,0.00021901749,0.0027994416,0.00020340928,0.00032587236],"about_ca_topic_score_codex":0.000102510574,"about_ca_topic_score_gemma":0.00000374755,"teacher_disagreement_score":0.78902364,"about_ca_system_score_codex":0.00020752182,"about_ca_system_score_gemma":0.00021382135,"threshold_uncertainty_score":0.9999492},"labels":[],"label_agreement":null},{"id":"W2966675798","doi":"10.24963/ijcai.2019/506","title":"Planning with Expectation Models","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Parametrization (atmospheric modeling); Mathematical optimization; Bellman equation; Function (biology); State (computer science); Artificial intelligence; Mathematics; Algorithm","score_opus":0.016672741621003975,"score_gpt":0.2247960668066918,"score_spread":0.20812332518568782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966675798","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":[0.017845314,0.0000038508197,0.8836523,0.00006845799,0.00006285409,0.00006644913,8.560996e-9,0.00014352363,0.09815723],"genre_scores_gemma":[0.8643167,2.566924e-7,0.13115303,0.00012543662,0.0000070477226,0.0000019879242,6.1200274e-7,0.0000034362815,0.0043915184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995086,0.00000819735,0.00006422522,0.0001329708,0.00017660095,0.000109385306],"domain_scores_gemma":[0.99965036,0.00002600741,0.000032560973,0.00024181596,0.00002667151,0.000022599163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004659899,0.000048197562,0.000046976147,0.00003970838,0.000024871106,0.00007771475,0.0002487342,0.000014955065,0.000027082793],"category_scores_gemma":[0.0000020906784,0.000035701705,0.000009112304,0.00011186206,0.0000048918046,0.000613972,0.000050492174,0.00004688035,0.00016546762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001273852,0.000001464737,0.0019182044,0.0000019932759,0.0000028745737,0.0000011209684,0.0006787791,0.93923986,0.00005581736,0.05785143,0.00006809401,0.00017908603],"study_design_scores_gemma":[0.00013818467,0.00007710301,0.0005978539,0.000010154774,6.103295e-7,0.000002917369,0.000083396975,0.9983399,0.0002803694,0.000271993,0.00013051332,0.00006698293],"about_ca_topic_score_codex":0.000003821785,"about_ca_topic_score_gemma":1.2103563e-7,"teacher_disagreement_score":0.84647137,"about_ca_system_score_codex":0.0000127279445,"about_ca_system_score_gemma":0.000017281427,"threshold_uncertainty_score":0.21268067},"labels":[],"label_agreement":null},{"id":"W2968035913","doi":"10.1109/med.2019.8798515","title":"Lamarckian Inheritance in Neuromodulated Multiobjective Evolutionary Neurocontrollers","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Neuroevolution; Artificial intelligence; Inheritance (genetic algorithm); Evolutionary algorithm; Computer science; Traverse; Artificial neural network; Biology","score_opus":0.006355943929348623,"score_gpt":0.2070230902286131,"score_spread":0.20066714629926447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2968035913","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":[0.2337034,0.00004773611,0.71107566,0.0014766303,0.0010871624,0.0010395969,5.279291e-7,0.000528191,0.05104111],"genre_scores_gemma":[0.98463374,0.000005245976,0.011199975,0.0005715626,0.000013830814,0.000011049124,0.0000013269552,0.000010545446,0.003552749],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987014,0.000097641256,0.00023864141,0.00039713868,0.00025436172,0.00031082766],"domain_scores_gemma":[0.99921393,0.000112735084,0.0000713563,0.00048746716,0.000059972754,0.00005455056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012490655,0.00013168856,0.00016051742,0.00016105428,0.00003900163,0.00006395438,0.0006039403,0.000053780044,0.0000669736],"category_scores_gemma":[0.00006281879,0.00012869982,0.00004642171,0.00055384036,0.000022596572,0.0006142598,0.00018678421,0.00023017933,0.00042589454],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014766977,0.00002891147,0.03776146,0.0000062256204,0.0000074189243,0.000021739766,0.00023854557,0.9514687,0.0014592294,0.007951553,0.0001598958,0.0008815526],"study_design_scores_gemma":[0.0008216095,0.00008672736,0.18982118,0.00000994714,6.3725327e-7,0.00000537692,0.00001694431,0.808287,0.000055232904,0.00015289416,0.0006165203,0.00012591308],"about_ca_topic_score_codex":0.000048952927,"about_ca_topic_score_gemma":0.000009472123,"teacher_disagreement_score":0.7509303,"about_ca_system_score_codex":0.000088879795,"about_ca_system_score_gemma":0.000055620727,"threshold_uncertainty_score":0.5474155},"labels":[],"label_agreement":null},{"id":"W2970384648","doi":"10.48550/arxiv.1912.04226","title":"Unsupervised Curricula for Visual Meta-Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Unsupervised learning; Artificial intelligence; Machine learning; Meta learning (computer science); Cluster analysis; Task (project management); Discriminative model; Trajectory","score_opus":0.06914127001221135,"score_gpt":0.2036564058526367,"score_spread":0.13451513584042535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970384648","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":[0.05299733,0.00001866848,0.9421731,0.000052016396,0.000276146,0.00047743332,3.4169273e-7,0.00025314072,0.0037518064],"genre_scores_gemma":[0.9816253,0.0000176957,0.0023300026,0.00016530053,0.00002973594,0.0000024717344,0.000010836226,0.000017373812,0.015801258],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984559,0.00008172745,0.00021456718,0.0006281437,0.00014760981,0.00047204367],"domain_scores_gemma":[0.998769,0.0001988647,0.00017346395,0.0005575621,0.00016079821,0.00014033553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003213865,0.0002433777,0.00032286174,0.0001828021,0.00020280221,0.000112483875,0.0009922818,0.000089931076,0.00021824257],"category_scores_gemma":[0.000049779126,0.00024070978,0.00033061573,0.0006067531,0.000041968215,0.0007799964,0.00038567788,0.00021696265,0.00049910846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013803228,0.000018750437,0.002225755,0.000023660106,0.00022752502,0.000010169501,0.00009056766,0.8944921,0.00012760854,0.10254791,0.000082529,0.00013965744],"study_design_scores_gemma":[0.0009814192,0.0003460206,0.00017452543,0.000011214946,0.00019326521,0.0000018396374,0.000066468114,0.9907917,0.00029453903,0.00033022588,0.006497884,0.00031094594],"about_ca_topic_score_codex":0.000016729755,"about_ca_topic_score_gemma":8.805177e-7,"teacher_disagreement_score":0.9398431,"about_ca_system_score_codex":0.000110204455,"about_ca_system_score_gemma":0.000060918097,"threshold_uncertainty_score":0.981586},"labels":[],"label_agreement":null},{"id":"W2970483889","doi":"10.48550/arxiv.1911.04448","title":"Real-Time Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Open Philanthropy Project","keywords":"Reinforcement learning; Markov decision process; Computer science; Action selection; Computation; Artificial intelligence; State (computer science); Action (physics); Markov process; Mathematical optimization; Machine learning; Algorithm; Mathematics","score_opus":0.008090322237890085,"score_gpt":0.22149011163154358,"score_spread":0.2133997893936535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970483889","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":[0.026358053,0.000063398606,0.9455719,0.0012151339,0.00023762119,0.0007886299,6.233034e-7,0.002104313,0.02366031],"genre_scores_gemma":[0.76409346,0.00020419603,0.18843386,0.0011085622,0.000105837,0.00015202111,0.000025385323,0.000081409176,0.04579527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966118,0.00017846057,0.000643055,0.0006898814,0.0007965804,0.0010802301],"domain_scores_gemma":[0.9972275,0.00018853441,0.00039451226,0.0017084166,0.00014823953,0.00033281572],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000982798,0.00041770193,0.0004330753,0.00046892627,0.00027987995,0.0004979157,0.0017730531,0.0002603341,0.00027396152],"category_scores_gemma":[0.00017044475,0.00043182797,0.00020621336,0.0007823051,0.00005222639,0.000980844,0.0008966241,0.0006903757,0.0015841885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017675073,0.00003063608,0.012473598,0.000027161359,0.000039731083,0.00002637773,0.0002993151,0.9031694,0.01890051,0.06075111,0.0013010314,0.0029634351],"study_design_scores_gemma":[0.00048342798,0.0003704877,0.005305356,0.00005764071,0.000011543996,0.000047521822,0.000029636292,0.9802313,0.0049355025,0.0003358562,0.007673186,0.00051857886],"about_ca_topic_score_codex":0.0016262933,"about_ca_topic_score_gemma":0.000017692564,"teacher_disagreement_score":0.7571381,"about_ca_system_score_codex":0.0005797642,"about_ca_system_score_gemma":0.00025285184,"threshold_uncertainty_score":0.9998134},"labels":[],"label_agreement":null},{"id":"W2970634945","doi":"","title":"Maximum Entropy Monte-Carlo Planning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"","keywords":"Softmax function; Computer science; Mathematical optimization; Monte Carlo method; Principle of maximum entropy; Entropy (arrow of time); Convergence (economics); Monte Carlo tree search; Rate of convergence; Mathematics; Algorithm; Artificial intelligence; Artificial neural network; Statistics","score_opus":0.015684304278766808,"score_gpt":0.24203487129328252,"score_spread":0.22635056701451572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970634945","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":[0.039503552,0.00019856813,0.94464624,0.00026397954,0.0023925544,0.0005497491,9.442412e-7,0.0007539804,0.011690449],"genre_scores_gemma":[0.9965496,0.0000014768184,0.001976555,0.00039107542,0.00007125986,0.000018031935,0.000007384701,0.000008920176,0.0009757107],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823874,0.000042880914,0.0006075,0.00017278882,0.00058934785,0.00034872128],"domain_scores_gemma":[0.9987784,0.00003831192,0.0005012694,0.0003946403,0.00020600767,0.00008138188],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00028309313,0.00017719997,0.00019822817,0.00019719609,0.00017528226,0.0015511676,0.0007138158,0.00008540272,0.000006665509],"category_scores_gemma":[0.000039365164,0.00015694971,0.000047028472,0.0003686353,0.000017383314,0.0069649857,0.00014379607,0.00022474406,0.0006029911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003989242,0.0000030571882,0.0027093282,0.00025273193,0.000005868183,0.0000013954925,0.0019840496,0.987396,0.00008236301,0.0018134041,0.0008049926,0.0049428],"study_design_scores_gemma":[0.00031503497,0.00006491468,0.00045116714,0.00014973729,0.0000027111882,0.00003740868,0.00031463557,0.98135096,0.000083841915,0.000014104373,0.017026778,0.00018871728],"about_ca_topic_score_codex":0.00001645132,"about_ca_topic_score_gemma":4.4437023e-8,"teacher_disagreement_score":0.95704603,"about_ca_system_score_codex":0.000083364204,"about_ca_system_score_gemma":0.000068126,"threshold_uncertainty_score":0.9994853},"labels":[],"label_agreement":null},{"id":"W2970673985","doi":"","title":"Learning Reward Machines for Partially Observable Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":67,"is_retracted":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; Observable; Computer science; Set (abstract data type); Artificial intelligence; Task (project management); Function (biology); Optimization problem; Learning automata; Representation (politics); Decomposition; Automaton; Mathematical optimization; Mathematics; Algorithm","score_opus":0.021000865689137876,"score_gpt":0.2534669585508525,"score_spread":0.23246609286171463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970673985","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":[0.009366598,0.00008347839,0.9795047,0.00027504176,0.0013953254,0.0010580488,4.1791813e-7,0.00082568574,0.0074906996],"genre_scores_gemma":[0.9865053,0.0000066014845,0.0042388174,0.00030930343,0.00012326949,0.00012674893,0.000076498676,0.000022216036,0.008591196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99739367,0.000094490904,0.0009842963,0.00028116454,0.00067813037,0.0005682698],"domain_scores_gemma":[0.99799085,0.00012883813,0.0009218098,0.00036360536,0.00048332085,0.000111576206],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088302436,0.00027890346,0.00033207246,0.00021388188,0.000553664,0.001821588,0.0007516076,0.00012572188,0.000011366171],"category_scores_gemma":[0.00025678906,0.0002555068,0.00010220126,0.00043769582,0.000022688797,0.0065847794,0.00019515668,0.0004129688,0.00029293817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015143391,0.00000347514,0.0026325784,0.00067961536,0.000012261616,3.4988363e-7,0.0017064933,0.98196477,0.00019342083,0.0029826306,0.00029981972,0.009509437],"study_design_scores_gemma":[0.0006109511,0.00037064916,0.00013670241,0.00017649913,0.000008109301,0.000015178179,0.0003079328,0.9319536,0.00019078488,0.000017856517,0.0659144,0.0002973376],"about_ca_topic_score_codex":0.000034991328,"about_ca_topic_score_gemma":4.5140496e-7,"teacher_disagreement_score":0.97713876,"about_ca_system_score_codex":0.00012179075,"about_ca_system_score_gemma":0.00013649907,"threshold_uncertainty_score":0.9999897},"labels":[],"label_agreement":null},{"id":"W2970912723","doi":"","title":"Gossip-based Actor-Learner Architectures for Deep Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Gossip; Asynchronous communication; Computer science; Reinforcement learning; Scalability; Distributed computing; Synchronization (alternating current); Gossip protocol; Artificial intelligence; Computer network","score_opus":0.03552543995273192,"score_gpt":0.18424288550916965,"score_spread":0.14871744555643773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970912723","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":[0.108047344,0.000010421346,0.8864327,0.00006926331,0.00025833747,0.00041432105,2.394353e-7,0.0002748595,0.0044925106],"genre_scores_gemma":[0.98742896,0.00000508367,0.0040328912,0.0002635875,0.00004190121,0.0000016509981,0.000008679677,0.000022902388,0.008194314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837977,0.000088704255,0.00019771849,0.0006490138,0.00015346307,0.00053130504],"domain_scores_gemma":[0.9984557,0.00030959045,0.00020850725,0.00075444405,0.00011864477,0.00015308906],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026350163,0.00024235115,0.00022420034,0.00023613694,0.0002436727,0.00012785225,0.0011409544,0.00011128522,0.00013251558],"category_scores_gemma":[0.00009017303,0.0002545663,0.0001924658,0.00050883694,0.00006478126,0.0002145139,0.00026885283,0.00033260992,0.00030507194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004666865,0.000014331474,0.0056536626,0.000037037295,0.000034635057,0.000011522573,0.00017352002,0.9529998,0.00018168015,0.04028652,0.000034380693,0.0005262506],"study_design_scores_gemma":[0.0011758953,0.00036631981,0.0007773066,0.000026014997,0.000019325556,0.0000013646453,0.00006662872,0.98931676,0.00047124497,0.00035345828,0.007094689,0.00033099687],"about_ca_topic_score_codex":0.000018083821,"about_ca_topic_score_gemma":0.0000035369005,"teacher_disagreement_score":0.8823998,"about_ca_system_score_codex":0.00015092455,"about_ca_system_score_gemma":0.00010311905,"threshold_uncertainty_score":0.99999064},"labels":[],"label_agreement":null},{"id":"W2971218263","doi":"","title":"SMILe: Scalable Meta Inverse Reinforcement Learning through Context-Conditional Policies","year":2019,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Meta learning (computer science); Scalability; Machine learning; Principle of maximum entropy; Context (archaeology); Task (project management)","score_opus":0.03388311419550946,"score_gpt":0.2615376253999302,"score_spread":0.22765451120442073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971218263","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":[0.0041957935,0.00018061294,0.9541455,0.00044470665,0.0011702264,0.00076425896,0.0000022146503,0.00069145527,0.03840524],"genre_scores_gemma":[0.99059904,0.000008758606,0.0013526244,0.0018026374,0.000076752935,0.00007141324,0.00009813909,0.000013503754,0.005977126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731076,0.00009596322,0.0009220708,0.0002425263,0.0009498176,0.00047885938],"domain_scores_gemma":[0.9981554,0.000087809836,0.0008239458,0.00041135843,0.0004256564,0.000095830095],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047951503,0.00029067489,0.00039510132,0.00022148629,0.00042599975,0.0015346046,0.00073236704,0.00011804399,0.00007511479],"category_scores_gemma":[0.00009300755,0.00024950225,0.00012769934,0.00056111347,0.00006343841,0.011470991,0.00023443345,0.00037447226,0.0010063123],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004263585,0.0000046554132,0.00030517156,0.00028649866,0.00007217233,6.324762e-7,0.0032740787,0.96989506,0.00006967596,0.023248775,0.0021869738,0.00065204455],"study_design_scores_gemma":[0.0005026505,0.0001204734,0.000120874305,0.00008205771,0.00003932692,0.000038609407,0.0012393942,0.94919413,0.0002847671,0.00006688205,0.048019275,0.00029157783],"about_ca_topic_score_codex":0.00020086204,"about_ca_topic_score_gemma":8.307445e-7,"teacher_disagreement_score":0.9864032,"about_ca_system_score_codex":0.00015133731,"about_ca_system_score_gemma":0.00015636816,"threshold_uncertainty_score":0.9999957},"labels":[],"label_agreement":null},{"id":"W2971273232","doi":"10.13140/rg.2.2.12370.50882","title":"The Option Keyboard: Combining Skills in Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"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":"Cumulant; Reinforcement learning; Computer science; Premise; Artificial intelligence; Machine learning; Formalism (music); Transfer of learning; Human–computer interaction; Mathematics","score_opus":0.022666124344261605,"score_gpt":0.17229140948524505,"score_spread":0.14962528514098344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971273232","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":[0.30138975,0.000008497666,0.688684,0.00006801392,0.00030477185,0.00018915487,2.8805838e-8,0.00011090947,0.009244878],"genre_scores_gemma":[0.9766018,0.00006507591,0.0003858418,0.00006885026,0.000012250431,4.718121e-7,0.0000020171335,0.000008774814,0.022854915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987655,0.00012511108,0.00019676717,0.0003891906,0.0001321841,0.00039124503],"domain_scores_gemma":[0.99887437,0.0002512959,0.00016487802,0.0005827343,0.000059593,0.00006710669],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004918929,0.000140559,0.00013491594,0.00014235551,0.00024818548,0.0001417494,0.0009841279,0.00006655777,0.000024335111],"category_scores_gemma":[0.000060452036,0.00013157411,0.000057121306,0.00067162304,0.000050675335,0.0006293,0.00042513982,0.00036480647,0.00052018545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006972976,0.000008116836,0.015135708,0.0000040984414,0.000009231213,0.000014965377,0.00018408678,0.78172183,0.000056982033,0.2024894,0.00001594389,0.0003526672],"study_design_scores_gemma":[0.0006537866,0.00014523807,0.0042710006,0.000034919045,0.0000043724945,0.0000017396168,0.00018978743,0.9908598,0.00006133061,0.00057958456,0.0030250694,0.00017338993],"about_ca_topic_score_codex":0.00003308531,"about_ca_topic_score_gemma":0.0000059578947,"teacher_disagreement_score":0.68829817,"about_ca_system_score_codex":0.00018423465,"about_ca_system_score_gemma":0.00004936534,"threshold_uncertainty_score":0.6686105},"labels":[],"label_agreement":null},{"id":"W2971484784","doi":"10.1609/aaai.v34i04.5784","title":"Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"University of Toronto; Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Vector Institute; Alberta Innovates; DeepMind","keywords":"Reinforcement learning; Bellman equation; Horizon; Temporal difference learning; Function (biology); Time horizon; Value (mathematics); Stability (learning theory); Computer science; Mathematics; Mathematical optimization; Artificial intelligence; Machine learning","score_opus":0.137803606700458,"score_gpt":0.36583601233052376,"score_spread":0.22803240563006577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2971484784","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":[0.0012528596,0.00004284571,0.985694,0.003555175,0.001568726,0.0018294469,0.0000048999123,0.00032335534,0.0057286774],"genre_scores_gemma":[0.81601405,0.00010357286,0.18140551,0.00020816048,0.00020149088,0.00026031476,0.000010822883,0.000056134177,0.001739939],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509823,0.00010157329,0.0015632721,0.0014257146,0.0009765446,0.00083464367],"domain_scores_gemma":[0.9949678,0.00047034703,0.002048054,0.00083178043,0.0014419977,0.00023999937],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016072018,0.0007546841,0.0009873573,0.00024469825,0.00047110103,0.0010354853,0.0061047943,0.0004161808,0.000057048095],"category_scores_gemma":[0.0025149002,0.0006222615,0.00048353252,0.00068382896,0.0003196237,0.00035644288,0.004362912,0.0019671516,0.000049655457],"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":[0.00014377727,0.00007317523,0.00014988845,0.0007220321,0.00010695253,4.861316e-7,0.0020765923,0.1817575,0.019545717,0.7056936,0.00025892098,0.08947136],"study_design_scores_gemma":[0.000043723987,0.000754941,0.000022151646,0.00061996485,0.00004665912,0.0000011078426,0.00023710214,0.719583,0.17616093,0.10118958,0.00082466815,0.0005161667],"about_ca_topic_score_codex":0.00007736299,"about_ca_topic_score_gemma":0.000002304761,"teacher_disagreement_score":0.8147612,"about_ca_system_score_codex":0.00021024363,"about_ca_system_score_gemma":0.0005084838,"threshold_uncertainty_score":0.9996229},"labels":[],"label_agreement":null},{"id":"W2972435663","doi":"10.65109/hlnw2204","title":"Safe Policy Improvement with an Estimated Baseline Policy","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Baseline (sea); Reinforcement learning; Bootstrapping (finance); Computer science; Variance (accounting); Control (management); Machine learning; Artificial intelligence; Econometrics; Mathematics; Economics; Political science; Accounting","score_opus":0.03920345239348902,"score_gpt":0.31655273234008885,"score_spread":0.27734927994659986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972435663","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":[0.00029634297,0.000010120374,0.9636696,0.019130081,0.00020539474,0.0006452226,0.000008407073,0.0010866578,0.014948195],"genre_scores_gemma":[0.23592003,0.000045509554,0.7498739,0.00892464,0.0010754208,0.00006947893,0.00021732438,0.000083814346,0.0037899076],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996626,0.00011159393,0.00059803185,0.001201361,0.0008037845,0.00065918517],"domain_scores_gemma":[0.9965884,0.00006635325,0.00039995843,0.002199894,0.00024675866,0.000498634],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038387018,0.000568525,0.00049261755,0.00047914885,0.00013489978,0.0007364164,0.0027491539,0.00022843249,0.00007820794],"category_scores_gemma":[0.00027937308,0.0004623307,0.000101663565,0.0008629679,0.000076778786,0.00036552365,0.0035912525,0.0008427817,0.00017840287],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021428086,0.000052522333,0.0000931694,0.00012194774,0.000087490545,0.000030667576,0.0003701131,0.9032653,0.00023345939,0.07659321,0.0007694544,0.018361256],"study_design_scores_gemma":[0.00044711278,0.0008281612,0.0003014703,0.00009264033,0.000019250709,0.000009026143,0.000014238759,0.99267817,0.0008480276,0.0020873884,0.0020885833,0.00058590836],"about_ca_topic_score_codex":0.0030612156,"about_ca_topic_score_gemma":0.00002626452,"teacher_disagreement_score":0.23562369,"about_ca_system_score_codex":0.0003764164,"about_ca_system_score_gemma":0.0023040965,"threshold_uncertainty_score":0.99978286},"labels":[],"label_agreement":null},{"id":"W2975017304","doi":"10.1109/cig.2019.8848040","title":"Using Simple Games to Evaluate Self-Organization Concepts: a Whack-a-mole Case Study","year":2019,"lang":"en","type":"article","venue":"2019 IEEE Conference on Games (CoG)","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Generality; Simple (philosophy); Hammer; Computer science; Task (project management); Industrial engineering; Engineering; Psychology; Epistemology; Mechanical engineering; Systems engineering","score_opus":0.05754343499664861,"score_gpt":0.34501022742724996,"score_spread":0.28746679243060136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975017304","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":[0.652534,0.000013421168,0.34354028,0.000117339674,0.0008607777,0.0015366472,0.0000033887297,0.00036216518,0.0010319417],"genre_scores_gemma":[0.9876723,0.000008872031,0.009941289,0.0006446501,0.00009072677,0.000024082783,0.0000072202415,0.000051585655,0.0015592156],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966779,0.00032223755,0.0005470947,0.0009581199,0.00085945573,0.0006352377],"domain_scores_gemma":[0.996981,0.00016390269,0.00032247088,0.001501952,0.00078001514,0.00025060878],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005868504,0.00042198395,0.00046552773,0.0002717427,0.00019700991,0.00074068725,0.0011832168,0.00012884251,0.00030751692],"category_scores_gemma":[0.00015621322,0.0004079929,0.00007128681,0.0008742132,0.000044246077,0.00077154476,0.00041176134,0.00032020392,0.0022685318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002874595,0.000510561,0.025184335,0.00006988024,0.00027469473,0.00044736062,0.02455481,0.9279928,0.007063492,0.0039280006,0.002324803,0.007620511],"study_design_scores_gemma":[0.0017617544,0.0017008688,0.0016740591,0.00012906513,0.00010723722,0.00022751192,0.0033805396,0.986476,0.0026635798,0.00010440494,0.0008705686,0.0009043863],"about_ca_topic_score_codex":0.00021001342,"about_ca_topic_score_gemma":0.00001886191,"teacher_disagreement_score":0.33513832,"about_ca_system_score_codex":0.00016481137,"about_ca_system_score_gemma":0.00040105244,"threshold_uncertainty_score":0.9998372},"labels":[],"label_agreement":null},{"id":"W2977481643","doi":"10.1609/aaai.v35i12.17276","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":121,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Artificial intelligence; Stability (learning theory); Machine learning; Encoder; Representation (politics); Noise (video); Code (set theory); Image (mathematics)","score_opus":0.07127289501225326,"score_gpt":0.2836056152858242,"score_spread":0.21233272027357092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977481643","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":[0.026604127,0.00006107363,0.96632326,0.0010355134,0.0007650839,0.00069865404,0.0000061655232,0.00016263651,0.0043434855],"genre_scores_gemma":[0.9547352,0.00012701021,0.044524524,0.00012867409,0.00007668362,0.000066492925,0.000010110199,0.00003510881,0.00029615138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950778,0.000056840698,0.0014677821,0.0013456775,0.001311992,0.0007399079],"domain_scores_gemma":[0.9958242,0.00034567807,0.0014696491,0.0012602955,0.00097078516,0.00012938531],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010049127,0.0006026833,0.0007198311,0.00034647665,0.00025905189,0.0012349851,0.006937353,0.00035493658,0.00008003823],"category_scores_gemma":[0.0036945636,0.00053576415,0.0002971207,0.00076006044,0.0002785183,0.0005825539,0.0079594115,0.0022027288,0.000021215697],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002481621,0.000072572795,0.0002966763,0.00013457432,0.000022126731,0.0000015397076,0.0027717804,0.90246224,0.008960551,0.07695018,0.000023631243,0.008279298],"study_design_scores_gemma":[0.00004771079,0.00010262488,0.000052804036,0.0009298519,0.000020297903,6.7806747e-7,0.0005437651,0.84065604,0.11447941,0.04271866,0.000004452451,0.000443702],"about_ca_topic_score_codex":0.0013683721,"about_ca_topic_score_gemma":0.000037265276,"teacher_disagreement_score":0.9281311,"about_ca_system_score_codex":0.00027688526,"about_ca_system_score_gemma":0.0006024126,"threshold_uncertainty_score":0.9998018},"labels":[],"label_agreement":null},{"id":"W2977878187","doi":"10.1007/978-3-030-23807-0_27","title":"Intrinsically Motivated Autonomy in Human-Robot Interaction: Human Perception of Predictive Information in Robots","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Robot; Perception; Human–computer interaction; Human–robot interaction; Autonomy; Baseline (sea); USable; Artificial intelligence; Competence (human resources); Psychology; Social psychology","score_opus":0.015830707686866598,"score_gpt":0.26033507202411815,"score_spread":0.24450436433725156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977878187","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":[0.0034868459,0.000010791266,0.98963386,0.00015748474,0.00092160533,0.0007890709,0.0000012966315,0.00009774418,0.0049012783],"genre_scores_gemma":[0.93456405,0.0000076184097,0.06477718,0.0002744677,0.00011261696,0.000011073191,0.000034566572,0.000020831449,0.00019758972],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962549,0.000077384946,0.0013029143,0.00087916077,0.00095783675,0.0005277919],"domain_scores_gemma":[0.9974694,0.00028016773,0.0007922227,0.0010296262,0.00034415253,0.00008439941],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092744996,0.00047677264,0.0006565895,0.0024009333,0.00011531013,0.000337901,0.002213887,0.00041047652,0.00003734487],"category_scores_gemma":[0.00011489346,0.0004893384,0.00010516547,0.00095222367,0.00040652812,0.0027320553,0.0011655067,0.0014263417,0.00004071423],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008961287,0.000028213053,0.0012741826,0.00006241843,0.0000069273397,0.000008112547,0.0029125435,0.9519469,0.00048330243,0.0049209795,0.0000029017706,0.038344566],"study_design_scores_gemma":[0.0007010736,0.00051169517,0.01879167,0.0011119547,0.0000048991456,0.000013469208,0.0000029863882,0.97320855,0.00044573823,0.0045843935,0.00012332156,0.0005002407],"about_ca_topic_score_codex":0.00011677415,"about_ca_topic_score_gemma":0.00006787047,"teacher_disagreement_score":0.9310772,"about_ca_system_score_codex":0.001468491,"about_ca_system_score_gemma":0.00064641464,"threshold_uncertainty_score":0.9997558},"labels":[],"label_agreement":null},{"id":"W2987502141","doi":"10.1609/aaai.v34i04.6027","title":"Gamma-Nets: Generalizing Value Estimation over Timescale","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Machine Intelligence Institute; Compute Canada","keywords":"Estimator; Reinforcement learning; Computer science; A priori and a posteriori; Bellman equation; Representation (politics); Function (biology); Value (mathematics); Artificial intelligence; Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics","score_opus":0.09424233049296664,"score_gpt":0.31212231732304635,"score_spread":0.2178799868300797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2987502141","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":[0.009524936,0.000035974113,0.9629599,0.008237336,0.001479892,0.0008963352,0.0000069333846,0.00032264236,0.016536066],"genre_scores_gemma":[0.94680613,0.000062307394,0.051615562,0.000680158,0.00017083088,0.000046333258,0.0000049986816,0.000037814254,0.00057584106],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963106,0.000041907042,0.0010432305,0.0010081279,0.0011132886,0.0004828514],"domain_scores_gemma":[0.99716735,0.00010976982,0.0012309863,0.0007080095,0.00062598457,0.00015789288],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005726881,0.0005061956,0.00053917535,0.00018579369,0.00022803893,0.0008937802,0.0045723678,0.00031388665,0.000079620455],"category_scores_gemma":[0.0007823629,0.0004283333,0.0002832534,0.0005868204,0.00025636103,0.00045702103,0.0031674397,0.0012103901,0.00020692818],"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":[0.00002339379,0.0000447695,0.000053029973,0.00018233008,0.000040427618,8.8064724e-7,0.0013427328,0.30253616,0.007771146,0.66599303,0.0005688923,0.0214432],"study_design_scores_gemma":[0.000018263225,0.00009716012,0.00006341063,0.00053689035,0.000026330508,0.0000017911638,0.000047739817,0.75027096,0.106623076,0.14182374,0.0001589209,0.000331731],"about_ca_topic_score_codex":0.00007476129,"about_ca_topic_score_gemma":0.0000013720143,"teacher_disagreement_score":0.9372812,"about_ca_system_score_codex":0.00015207169,"about_ca_system_score_gemma":0.00028356438,"threshold_uncertainty_score":0.99981683},"labels":[],"label_agreement":null},{"id":"W2990169293","doi":"10.1109/isncc.2019.8909159","title":"Finding better learning algorithms for self-driving cars: An overview of the LAOP platform","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Collège de Maisonneuve; Laboratoire Recherche Informatique Maisonneuve","funders":"","keywords":"Neuroevolution; Computer science; Artificial neural network; Context (archaeology); Artificial intelligence; Process (computing); Machine learning; Deep learning; Java; Algorithm","score_opus":0.06599057292254697,"score_gpt":0.3095288898413565,"score_spread":0.24353831691880956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990169293","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":[0.09613979,0.00003809439,0.89952445,0.00025896003,0.0005701771,0.00046299474,3.339028e-7,0.00020983412,0.0027953591],"genre_scores_gemma":[0.7520819,0.000019896725,0.24326678,0.00067166425,0.00009850139,0.000015260248,0.0000035539551,0.000029490693,0.003812956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986986,0.00005229567,0.00028778028,0.00028355504,0.0003516825,0.00032611354],"domain_scores_gemma":[0.9988129,0.00022273326,0.00021232694,0.00062536966,0.00007930343,0.000047361984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006093108,0.0001384437,0.00019143353,0.00006665714,0.00015126388,0.00014015741,0.0010976926,0.00006802233,0.000047548412],"category_scores_gemma":[0.000049071226,0.000097608754,0.000120048586,0.00026225523,0.000017000284,0.0007510988,0.00042826714,0.0002161679,0.00003166415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002398574,0.000052658164,0.12596019,0.00029905982,0.00012454668,0.0000011861101,0.0051207654,0.75848794,0.0016536396,0.06564736,0.00036920645,0.042281028],"study_design_scores_gemma":[0.00029459372,0.00016340258,0.006957582,0.00008656739,0.000010390737,0.0000036883534,0.000097761054,0.98340064,0.0016205767,0.00017538301,0.007035586,0.00015382942],"about_ca_topic_score_codex":0.000017178701,"about_ca_topic_score_gemma":0.0000029677922,"teacher_disagreement_score":0.6562577,"about_ca_system_score_codex":0.000053796553,"about_ca_system_score_gemma":0.000050819024,"threshold_uncertainty_score":0.39803696},"labels":[],"label_agreement":null},{"id":"W2990933479","doi":"10.48550/arxiv.1911.08610","title":"Efficient decorrelation of features using Gramian in Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Decorrelation; Regularization (linguistics); Computer science; Sample complexity; Artificial intelligence; Gramian matrix; Temporal difference learning; Computational complexity theory; Mathematical optimization; Machine learning; Mathematics; Algorithm","score_opus":0.053181348214927066,"score_gpt":0.20262543750929482,"score_spread":0.14944408929436775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990933479","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":[0.28136048,0.0000231868,0.7160642,0.000008535268,0.00048798596,0.00030267186,4.1697834e-7,0.00006728783,0.0016852245],"genre_scores_gemma":[0.9951616,0.000029221754,0.0032662887,0.00001572725,0.000019754583,3.2095022e-7,0.000016936536,0.000016980051,0.0014731621],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981567,0.0001715919,0.00037794598,0.00072732964,0.00020126926,0.00036514335],"domain_scores_gemma":[0.99809164,0.0001237227,0.0006595027,0.000906502,0.00014256708,0.000076042954],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041634275,0.00028420603,0.0003727415,0.000617131,0.000087569126,0.00007534272,0.0011649332,0.00030878794,0.000014238153],"category_scores_gemma":[0.000082242164,0.0003436511,0.0001437718,0.00069551484,0.00006427379,0.00015514137,0.001691139,0.0009771165,0.000036649464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015619464,0.000021331087,0.014856485,0.00010212595,0.000030459043,0.000029382734,0.0004811533,0.96594054,0.00005334891,0.018371016,0.0000065252807,0.00009202261],"study_design_scores_gemma":[0.00044507557,0.000077847246,0.0046762014,0.0002897453,0.00002995297,0.0000019895826,0.000084359854,0.99371594,0.00007214719,0.00026219722,0.000032435513,0.0003120993],"about_ca_topic_score_codex":0.00031186297,"about_ca_topic_score_gemma":0.0000111717845,"teacher_disagreement_score":0.71380115,"about_ca_system_score_codex":0.0005002284,"about_ca_system_score_gemma":0.00023299664,"threshold_uncertainty_score":0.99990153},"labels":[],"label_agreement":null},{"id":"W2991419354","doi":"10.1109/itsc.2019.8916928","title":"Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada)","funders":"","keywords":"Reinforcement learning; Abstraction; Computer science; Modular design; Hierarchy; Motion (physics); Motion planning; Artificial intelligence; State space; Action (physics); Set (abstract data type); Human–computer interaction; Robot","score_opus":0.03906097747933342,"score_gpt":0.29254376067269544,"score_spread":0.25348278319336204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991419354","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":[0.06295869,0.00006409093,0.9312754,0.00009807212,0.00023375075,0.00018116283,2.4841704e-8,0.00022817292,0.004960589],"genre_scores_gemma":[0.7072219,0.0000047078383,0.2891697,0.00019897155,0.000030388805,0.0000012149314,0.0000018042026,0.000012842303,0.0033584225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99844414,0.00006714398,0.00030340056,0.0003999095,0.0003576489,0.0004277513],"domain_scores_gemma":[0.9992129,0.00014151722,0.00012156695,0.00035636188,0.000042909778,0.00012470143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003649163,0.00017828259,0.00019855583,0.00015905699,0.00021017356,0.0003642311,0.00039347194,0.000074598756,0.00006371711],"category_scores_gemma":[0.00007128086,0.0001646126,0.000038906397,0.00020362134,0.000039960054,0.0005855584,0.00056686444,0.000452734,0.00008441533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003849759,0.0000048034785,0.020630725,0.000020962612,0.000014127892,0.000009441941,0.0006629816,0.97067994,0.0034919714,0.0033786441,0.000010582984,0.0010919526],"study_design_scores_gemma":[0.0005217836,0.0001199683,0.0025231992,0.000076481316,0.0000045874667,0.000032953674,0.0000823592,0.9948334,0.00031916492,0.000026894222,0.0012302354,0.00022894598],"about_ca_topic_score_codex":0.000026220243,"about_ca_topic_score_gemma":2.3464237e-7,"teacher_disagreement_score":0.64426327,"about_ca_system_score_codex":0.00005842707,"about_ca_system_score_gemma":0.00004773557,"threshold_uncertainty_score":0.6712707},"labels":[],"label_agreement":null},{"id":"W2991820108","doi":"10.48550/arxiv.1912.04002","title":"Learning Sparse Representations Incrementally in Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Machine learning; Cognitive science; Psychology","score_opus":0.0612828309903429,"score_gpt":0.21055536665514085,"score_spread":0.14927253566479795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2991820108","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":[0.06753138,0.000024011546,0.90785486,0.00006936129,0.0005966644,0.00063893956,3.0769758e-7,0.0003614106,0.022923099],"genre_scores_gemma":[0.97987974,0.00026936014,0.002854385,0.00008504728,0.000052209252,0.0000037934346,0.00007712847,0.00003943702,0.016738873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964746,0.00045586223,0.0005741652,0.0014609379,0.0003219294,0.0007124559],"domain_scores_gemma":[0.99725246,0.00025100642,0.0007034374,0.0014366767,0.00017643141,0.00018001147],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00070686615,0.00048388838,0.00049961085,0.00075890403,0.0002792307,0.00032153825,0.002274054,0.00035342644,0.00013266687],"category_scores_gemma":[0.00023224953,0.000630109,0.00024150981,0.00097240735,0.000095782845,0.0007904587,0.0045095566,0.0023052732,0.0005219895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020242624,0.000030395455,0.05136216,0.00007473503,0.0000744944,0.00018272006,0.0009842878,0.9279716,0.00003543781,0.019043533,0.00004542395,0.00017494704],"study_design_scores_gemma":[0.0008743195,0.0001637578,0.0034711726,0.00018736107,0.00004106343,0.000003975534,0.000554679,0.99267477,0.00004554641,0.0006979607,0.00066754693,0.00061783276],"about_ca_topic_score_codex":0.00050615123,"about_ca_topic_score_gemma":0.00006164165,"teacher_disagreement_score":0.9123484,"about_ca_system_score_codex":0.0007728848,"about_ca_system_score_gemma":0.00028824652,"threshold_uncertainty_score":0.9999964},"labels":[],"label_agreement":null},{"id":"W2995031981","doi":"10.48550/arxiv.1912.05109","title":"Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Estimator; Computer science; Variance (accounting); Function (biology); Bellman equation; Value (mathematics); Mathematical optimization; Artificial intelligence; Machine learning; Mathematics; Economics; Statistics","score_opus":0.10240831877352728,"score_gpt":0.2271524172624324,"score_spread":0.12474409848890512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995031981","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":[0.002664637,0.000052046027,0.98732394,0.00022582743,0.0014358892,0.0011537719,0.000005412601,0.0005287177,0.0066097723],"genre_scores_gemma":[0.9507377,0.00024631707,0.010879813,0.00023538547,0.00037132265,0.000007374077,0.00010086682,0.00006798996,0.037353225],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965197,0.00015318564,0.0004943637,0.0015662266,0.0002915866,0.0009749803],"domain_scores_gemma":[0.99638104,0.00035710994,0.00061700144,0.0019109463,0.00044592738,0.0002879511],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005327715,0.00063258794,0.0006388028,0.00069057225,0.0003734697,0.00045099837,0.0032389914,0.00051482266,0.000043916825],"category_scores_gemma":[0.0002552393,0.0007632017,0.00047961896,0.0007331167,0.00013052947,0.0007279983,0.0033901273,0.0012743811,0.00026983276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027020222,0.000025386502,0.00042212513,0.00023927506,0.00014337574,0.000038054524,0.00026028889,0.92640644,0.000011589468,0.07125249,0.0004752647,0.0006986847],"study_design_scores_gemma":[0.0011526367,0.0002642534,0.0001213808,0.00019132739,0.00008886177,0.000004292203,0.000070834816,0.98501796,0.000070462855,0.0015015401,0.010712084,0.00080437935],"about_ca_topic_score_codex":0.00016229255,"about_ca_topic_score_gemma":0.000004129451,"teacher_disagreement_score":0.9764441,"about_ca_system_score_codex":0.0008819566,"about_ca_system_score_gemma":0.0008205704,"threshold_uncertainty_score":0.9994819},"labels":[],"label_agreement":null},{"id":"W2995040055","doi":"","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Generalization; Artificial intelligence; Decomposition; State (computer science); Machine learning; Mathematics","score_opus":0.035859797675240924,"score_gpt":0.28773296694383693,"score_spread":0.251873169268596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995040055","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":[0.0033179766,0.000002275644,0.82088596,0.0045742323,0.000097303724,0.00022020335,0.000002427266,0.00018847494,0.17071116],"genre_scores_gemma":[0.9880551,0.0000277035,0.010564056,0.00035894677,0.000040243216,0.000027293534,0.000101880665,0.000009455542,0.0008152847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808735,0.00012880653,0.0004905353,0.0002948297,0.00078867783,0.00020981325],"domain_scores_gemma":[0.9980388,0.00032725467,0.000540937,0.00020565747,0.00076678913,0.00012052774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015253644,0.00018664148,0.00020588803,0.00022274333,0.00018872548,0.0002795904,0.00073898234,0.000049070877,0.0003145221],"category_scores_gemma":[0.00079910725,0.00017564466,0.00007086123,0.0003477122,0.00015617337,0.001181583,0.00019881927,0.00048153274,0.00012548313],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042433392,0.000012053047,0.0030236722,0.000011746066,0.00007806011,0.0000039936644,0.005840524,0.642129,0.00050258,0.3469694,0.00003193253,0.0013546122],"study_design_scores_gemma":[0.0009839728,0.0008597904,0.003833747,0.00015417289,0.000014567056,0.000009849221,0.0049645044,0.98224777,0.002497911,0.00019855196,0.003961774,0.00027336672],"about_ca_topic_score_codex":0.000027263706,"about_ca_topic_score_gemma":0.0000012737279,"teacher_disagreement_score":0.98473716,"about_ca_system_score_codex":0.0000481561,"about_ca_system_score_gemma":0.00020016517,"threshold_uncertainty_score":0.7162581},"labels":[],"label_agreement":null},{"id":"W2995372087","doi":"","title":"Learning the Arrow of Time for Problems in Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Arrow; Arrow of time; Computer science; Reinforcement learning; Markov decision process; Reachability; Artificial intelligence; Machine learning; Class (philosophy); Function (biology); Markov process; Selection (genetic algorithm); Process (computing); Theoretical computer science; Mathematics","score_opus":0.05955057235187068,"score_gpt":0.3172682931974696,"score_spread":0.2577177208455989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995372087","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":[0.007360958,0.000011021354,0.94549435,0.013171172,0.0002168591,0.0007088621,0.000001067367,0.00020374586,0.032831986],"genre_scores_gemma":[0.990382,0.000040953997,0.0021306237,0.0002251217,0.00008191261,0.00012148531,0.000056756526,0.00001920282,0.006941912],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977693,0.00023726911,0.0005993201,0.00044952228,0.0006563553,0.00028823118],"domain_scores_gemma":[0.9980472,0.0007191609,0.0004989118,0.0002456129,0.0004087607,0.00008036873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005441699,0.00018394878,0.00021994063,0.00019669112,0.00025170544,0.0002440646,0.001162859,0.000065185,0.00022476114],"category_scores_gemma":[0.0021369306,0.00016309008,0.000103936625,0.0004311133,0.00008864843,0.00040905343,0.0002710261,0.00079912547,0.00012073608],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002243277,0.000017358561,0.0066027334,0.000016681219,0.000042746477,0.0000015838665,0.0061372924,0.9505544,0.0030733885,0.031840567,0.00012703841,0.001563802],"study_design_scores_gemma":[0.00059210125,0.0005697722,0.0012608626,0.00008935545,0.000007452999,0.0000021325607,0.00071241014,0.9905544,0.0005023136,0.00043891705,0.005105117,0.00016518784],"about_ca_topic_score_codex":0.000049743172,"about_ca_topic_score_gemma":0.0000029029145,"teacher_disagreement_score":0.9830211,"about_ca_system_score_codex":0.00007002158,"about_ca_system_score_gemma":0.00012306492,"threshold_uncertainty_score":0.66506207},"labels":[],"label_agreement":null},{"id":"W2995509794","doi":"10.48550/arxiv.2002.06487","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":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":"Convergence (economics); Benchmark (surveying); Computer science; Variance (accounting); Generalization error; Generalization; Artificial intelligence; Inductive bias; Machine learning; Q-learning; Algorithm; Value (mathematics); Mathematics; Stability (learning theory); Multi-task learning; Reinforcement learning","score_opus":0.09264049702283787,"score_gpt":0.1833738516716606,"score_spread":0.09073335464882272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995509794","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":[0.05948207,0.000014807227,0.9376166,0.00049605,0.00006834623,0.0001260504,1.5894207e-7,0.00018067416,0.0020152337],"genre_scores_gemma":[0.9963404,0.000021299695,0.002697897,0.00014016296,0.000027307042,2.1749064e-7,0.0000021112423,0.000009737191,0.00076087506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988726,0.00023084562,0.00020750322,0.00033490063,0.00012856368,0.00022561518],"domain_scores_gemma":[0.9988005,0.00038142447,0.00031869888,0.00029390075,0.0001089685,0.00009651726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034919026,0.00013231025,0.00018020818,0.00007314641,0.00023769311,0.000079504556,0.0009065251,0.000058259393,0.000027519636],"category_scores_gemma":[0.0005287679,0.00011849723,0.00010055652,0.00080947566,0.00008543801,0.00040815776,0.000277817,0.00039463377,0.00009872568],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015784362,0.0000060714424,0.0059130993,0.000013205299,0.000024815705,0.000016724647,0.00072394527,0.93162537,0.00016175586,0.060936425,0.000029468634,0.0005333453],"study_design_scores_gemma":[0.00045127407,0.00016595847,0.0005072656,0.000016213544,0.00002451254,0.0000015011922,0.0002836241,0.9964485,0.00031209807,0.0002702047,0.0013936412,0.00012516593],"about_ca_topic_score_codex":0.000014857939,"about_ca_topic_score_gemma":5.585646e-7,"teacher_disagreement_score":0.9368583,"about_ca_system_score_codex":0.000036017977,"about_ca_system_score_gemma":0.00005027074,"threshold_uncertainty_score":0.4832177},"labels":[],"label_agreement":null},{"id":"W2996001434","doi":"10.48550/arxiv.1912.05128","title":"Marginalized State Distribution Entropy Regularization in Policy Optimization","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Regularization (linguistics); Entropy (arrow of time); Mathematical optimization; Econometrics; Mathematics; Economics; Computer science; Statistical physics; Mathematical economics; Political science; Physics; Artificial intelligence; Thermodynamics","score_opus":0.03583607267643475,"score_gpt":0.1904179922911267,"score_spread":0.15458191961469192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996001434","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":[0.004920812,0.000010489973,0.99305516,0.00017016544,0.0003866008,0.00047886258,0.000012848501,0.00018487043,0.0007801583],"genre_scores_gemma":[0.985463,0.00029812992,0.006070187,0.000056847624,0.000044667006,0.0000011062634,0.00055177737,0.000019593022,0.007494668],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981794,0.00023013391,0.0002811927,0.00079636235,0.0001478076,0.00036511145],"domain_scores_gemma":[0.99825895,0.000053297106,0.00041911978,0.0010050421,0.00017720897,0.000086398526],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026455664,0.00026526776,0.0002814445,0.00041821864,0.00007726478,0.00019800504,0.0011278535,0.00024110328,0.000019764935],"category_scores_gemma":[0.000099904275,0.00033639825,0.000103803366,0.0010993191,0.000051935374,0.00056385057,0.0012032111,0.0004481048,0.00006520991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002408646,0.00002373834,0.0021727495,0.000048270867,0.000019715457,0.000029815414,0.000097597615,0.8916856,0.0000067945675,0.10577171,0.000050083454,0.00006980251],"study_design_scores_gemma":[0.0007299251,0.000035418823,0.0011131018,0.000090985945,0.000016124459,0.0000011858021,0.0000087237795,0.99282336,0.00004686294,0.0045574075,0.00026594216,0.000310987],"about_ca_topic_score_codex":0.00013633123,"about_ca_topic_score_gemma":0.0000034923835,"teacher_disagreement_score":0.986985,"about_ca_system_score_codex":0.0009293835,"about_ca_system_score_gemma":0.0003863248,"threshold_uncertainty_score":0.9999088},"labels":[],"label_agreement":null},{"id":"W2996026485","doi":"10.48550/arxiv.1912.06875","title":"Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"","keywords":"Curse of dimensionality; Reinforcement learning; Linear-quadratic regulator; Convergence (economics); Mathematical optimization; State space; Quadratic equation; Computer science; Action (physics); Mathematics; Optimal control; Artificial intelligence","score_opus":0.05382236452644264,"score_gpt":0.20893269833253675,"score_spread":0.15511033380609413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996026485","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":[0.04424648,0.000084775056,0.95046985,0.00034668978,0.0029233668,0.0008287021,0.000012560527,0.00036537112,0.0007221961],"genre_scores_gemma":[0.9786056,0.000059057365,0.01360274,0.00028562424,0.00018809836,0.0000020826612,0.000053628624,0.000034904228,0.0071682557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997255,0.00016576084,0.00036225468,0.0013151233,0.0002505017,0.0006513337],"domain_scores_gemma":[0.99688447,0.0004658982,0.00032834653,0.0017554753,0.0003372121,0.00022857926],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003249212,0.0004771359,0.00056028797,0.00024084764,0.00018993969,0.0002657744,0.0032912432,0.00043804807,0.000022429507],"category_scores_gemma":[0.0002329169,0.0005327675,0.00041744608,0.00038645143,0.00018802674,0.00047461005,0.0023204323,0.0009765376,0.00018028732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042711727,0.000031091546,0.0008682985,0.00026868467,0.00012339487,0.000048336846,0.00010370048,0.81046176,0.000036823283,0.1873326,0.00059402286,0.00008855776],"study_design_scores_gemma":[0.0007583839,0.00014083058,0.0008060097,0.00015999681,0.00008379918,0.0000037987313,0.000025740643,0.9878789,0.00008740242,0.007348969,0.0020966502,0.00060952257],"about_ca_topic_score_codex":0.000031542004,"about_ca_topic_score_gemma":0.000006234972,"teacher_disagreement_score":0.9368671,"about_ca_system_score_codex":0.00036382917,"about_ca_system_score_gemma":0.00052959414,"threshold_uncertainty_score":0.9997124},"labels":[],"label_agreement":null},{"id":"W2996283994","doi":"10.48550/arxiv.2002.05822","title":"Frequency-based Search-control in Dyna","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Computer science; Reinforcement learning; Bellman equation; Benchmark (surveying); Artificial intelligence; Function (biology); Machine learning; Mathematical optimization; Mathematics","score_opus":0.014531650295161206,"score_gpt":0.23006169952479144,"score_spread":0.21553004922963023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996283994","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":[0.00413249,0.00019842463,0.96130234,0.03156829,0.000090498055,0.00070607045,0.000008207416,0.0011091239,0.0008845506],"genre_scores_gemma":[0.7310141,0.00001683265,0.2541306,0.014486477,0.00008660238,0.00013798766,0.000008606564,0.00003970234,0.00007909734],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967917,0.00026858517,0.00060004316,0.0006813643,0.0006658632,0.000992398],"domain_scores_gemma":[0.997935,0.00020543135,0.000172876,0.001075443,0.00010699453,0.0005042704],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00075153395,0.00035542008,0.00040928795,0.0004299697,0.00014990325,0.00036255814,0.0020260364,0.00023612185,0.000039338593],"category_scores_gemma":[0.00035112462,0.00037569655,0.00016663548,0.0013552207,0.00008830548,0.0006599383,0.00030695234,0.0008157521,0.0001091472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030148422,0.00007028075,0.045676403,0.00004193823,0.000020809708,0.00020789336,0.00042022168,0.8967614,0.0058625652,0.044291567,0.00066678104,0.0059499727],"study_design_scores_gemma":[0.0010577141,0.00021323403,0.009691426,0.000036595855,0.0000070217498,0.000010730721,0.000020322132,0.98425555,0.0030296938,0.00069359806,0.00060088764,0.00038324975],"about_ca_topic_score_codex":0.002180704,"about_ca_topic_score_gemma":0.0003009884,"teacher_disagreement_score":0.72688156,"about_ca_system_score_codex":0.00045639256,"about_ca_system_score_gemma":0.00054115494,"threshold_uncertainty_score":0.9998695},"labels":[],"label_agreement":null},{"id":"W2996347495","doi":"","title":"Exploring Model-based Planning with Policy Networks","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Benchmarking; Artificial neural network; Code (set theory); Artificial intelligence; Mathematical optimization; Sample (material); Optimization problem; Control (management); Action (physics); State space; Machine learning; Algorithm; Mathematics","score_opus":0.22710027386392856,"score_gpt":0.1933980817790889,"score_spread":0.033702192084839655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996347495","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":[0.02220945,0.0000048212087,0.9747429,0.00036394357,0.000040873878,0.00008043671,2.0499837e-7,0.000330567,0.002226816],"genre_scores_gemma":[0.99065995,0.000007087647,0.008249961,0.00083158666,0.000073312534,4.3881454e-7,0.0000016078249,0.000013954954,0.00016208117],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902254,0.00003412773,0.00009459595,0.0004362939,0.00007974777,0.00033268926],"domain_scores_gemma":[0.99920666,0.000054827608,0.00008565744,0.0003893312,0.00005141582,0.00021213434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000064486376,0.00015105557,0.00013196762,0.00011670942,0.00015574406,0.000083111525,0.00082416646,0.000038936887,0.0000033979588],"category_scores_gemma":[0.000023184744,0.00015861535,0.00004859286,0.0010879535,0.000048634098,0.000835464,0.00021210479,0.00022204843,0.000026408019],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024406098,0.000005624837,0.0023380353,0.000007363617,0.000013440083,0.00011474372,0.00028065481,0.9431092,0.0000075410176,0.05395639,0.00003150092,0.000111064095],"study_design_scores_gemma":[0.00044701397,0.00012380163,0.00016964009,0.000025858833,0.000009976005,9.601456e-7,0.000044892302,0.99869555,0.000059650032,0.00008199258,0.00014016547,0.00020050158],"about_ca_topic_score_codex":0.000012814956,"about_ca_topic_score_gemma":5.2728024e-7,"teacher_disagreement_score":0.96845055,"about_ca_system_score_codex":0.00007737594,"about_ca_system_score_gemma":0.00013148683,"threshold_uncertainty_score":0.64681464},"labels":[],"label_agreement":null},{"id":"W2997289589","doi":"10.1609/aaai.v34i04.5955","title":"Count-Based Exploration with the Successor Representation","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada","keywords":"Successor cardinal; Representation (politics); Norm (philosophy); Computer science; Sample complexity; Generalization; Reinforcement learning; Similarity (geometry); Artificial intelligence; State (computer science); Algorithm; Theoretical computer science; Mathematics","score_opus":0.05162394606866699,"score_gpt":0.263603992355036,"score_spread":0.21198004628636902,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997289589","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":[0.00076480047,0.0000024399205,0.94308275,0.052254923,0.000036399495,0.00013791812,6.455837e-8,0.00016758083,0.0035531227],"genre_scores_gemma":[0.9672119,0.0000010736148,0.02682899,0.005538013,0.000042484728,0.0000150686465,0.0000048104243,0.0000049861906,0.0003526612],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931234,0.000041028205,0.000088031076,0.00016368357,0.0003032058,0.00009168953],"domain_scores_gemma":[0.9994832,0.00007655641,0.000066039735,0.00026671728,0.000071651724,0.000035785564],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008799027,0.000056806683,0.0000472838,0.000014602285,0.00009578281,0.00023441114,0.00041919693,0.000013844007,0.000026006177],"category_scores_gemma":[0.000034323482,0.000032667842,0.000014242191,0.00034112687,0.000023614524,0.0006579149,0.000045426208,0.00006576136,0.000083717714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007721067,0.0000028276017,0.0006161197,0.000003493707,0.000004180695,0.0000017357098,0.0006617348,0.98279595,0.00014774552,0.012085125,0.003120122,0.00055325695],"study_design_scores_gemma":[0.00020630805,0.000107294334,0.0003525386,0.000002393597,0.0000029308608,3.565145e-7,0.00011649779,0.9921724,0.0031757962,0.000023563458,0.0037808968,0.000058986396],"about_ca_topic_score_codex":0.00001345574,"about_ca_topic_score_gemma":0.0000044107596,"teacher_disagreement_score":0.9664471,"about_ca_system_score_codex":0.000011101669,"about_ca_system_score_gemma":0.000041121977,"threshold_uncertainty_score":0.22604321},"labels":[],"label_agreement":null},{"id":"W2998461398","doi":"10.1609/aaai.v34i04.5784","title":"Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; DeepMind","keywords":"Reinforcement learning; Bellman equation; Horizon; Temporal difference learning; Function (biology); Time horizon; Value (mathematics); Stability (learning theory); Computer science; Function approximation; Mathematics; Mathematical optimization; Artificial intelligence; Machine learning; Artificial neural network","score_opus":0.05269488141129239,"score_gpt":0.32804208255578104,"score_spread":0.27534720114448863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998461398","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":[0.00013377279,0.000033836837,0.9890354,0.0017167857,0.00027307446,0.00044573718,1.8428199e-7,0.00057115156,0.0077900584],"genre_scores_gemma":[0.20670228,0.000011984073,0.7830129,0.0009232698,0.000098265344,0.000047970687,0.000011724982,0.000020730798,0.009170874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981241,0.00013159869,0.00042657048,0.00050230796,0.00030588394,0.00050953677],"domain_scores_gemma":[0.99869597,0.0003489527,0.00018983825,0.00040777627,0.0001245456,0.00023290855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005750986,0.00022336429,0.00027901825,0.00006150659,0.00024940015,0.00030628016,0.0010490832,0.00007581697,0.000104419436],"category_scores_gemma":[0.00049628183,0.00019837316,0.000111805144,0.00037315983,0.000030920313,0.00041832685,0.00052471756,0.0002813631,0.00007023827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020305515,0.000009763421,0.0008841428,0.00007300606,0.000035558605,0.000001721718,0.0008168794,0.8768551,0.0031739518,0.06458395,0.0015059486,0.052039694],"study_design_scores_gemma":[0.000395527,0.00095457863,0.00006612436,0.000011209561,0.000007884082,9.765346e-7,0.00006324314,0.9186433,0.0058343727,0.00023243838,0.07353801,0.00025232762],"about_ca_topic_score_codex":0.000023043724,"about_ca_topic_score_gemma":5.2680423e-7,"teacher_disagreement_score":0.20656851,"about_ca_system_score_codex":0.000057074896,"about_ca_system_score_gemma":0.00009123614,"threshold_uncertainty_score":0.80894226},"labels":[],"label_agreement":null},{"id":"W2998494185","doi":"10.1609/aaai.v34i04.6027","title":"Gamma-Nets: Generalizing Value Estimation over Timescale","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Machine Intelligence Institute; Compute Canada","keywords":"Reinforcement learning; Computer science; Estimator; Bellman equation; Abstraction; Artificial intelligence; Scalability; Function (biology); Set (abstract data type); Temporal difference learning; Machine learning; Value (mathematics); Representation (politics); Key (lock); Markov decision process; Mathematical optimization; Markov process; Mathematics; Statistics","score_opus":0.020430689637633725,"score_gpt":0.2437083033784362,"score_spread":0.22327761374080246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998494185","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":[0.0010388914,0.000016354137,0.97307515,0.0035611482,0.00013471342,0.00008552409,1.1877247e-7,0.00036169364,0.021726392],"genre_scores_gemma":[0.3201762,0.0000052837213,0.66807795,0.008259829,0.00010383752,0.000004334412,0.000005603736,0.000013880225,0.003353073],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990727,0.000033081433,0.00018314886,0.00024113251,0.00027919427,0.0001908007],"domain_scores_gemma":[0.9994971,0.000037411723,0.00006142011,0.00027026594,0.000026441943,0.00010734701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000098510085,0.00009645921,0.00009260619,0.000030957584,0.00007204395,0.00018920537,0.00049519434,0.00003811914,0.0001485187],"category_scores_gemma":[0.00006579402,0.00008930387,0.000040571,0.00024399259,0.000014826362,0.0005130352,0.00022431459,0.00009592414,0.0005179203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.2425544e-7,0.0000031159293,0.00018021316,0.0000065287036,0.0000060363973,0.000003022661,0.00029987883,0.9381354,0.00058169995,0.05027028,0.005904497,0.0046084872],"study_design_scores_gemma":[0.000146371,0.00004784989,0.00037316707,0.0000055930086,0.0000029384319,0.0000018455513,0.000004040523,0.98593205,0.0016142373,0.00023196617,0.011521073,0.000118847805],"about_ca_topic_score_codex":0.00001558984,"about_ca_topic_score_gemma":1.8156061e-7,"teacher_disagreement_score":0.3191373,"about_ca_system_score_codex":0.000027647111,"about_ca_system_score_gemma":0.000028420753,"threshold_uncertainty_score":0.66569906},"labels":[],"label_agreement":null},{"id":"W3000091990","doi":"10.1038/s41593-019-0574-1","title":"Causal evidence supporting the proposal that dopamine transients function as temporal difference prediction errors","year":2020,"lang":"en","type":"article","venue":"Nature Neuroscience","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":103,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; U.S. Department of Health and Human Services; Government of Canada; National Institutes of Health; Concordia University; National Institute on Drug Abuse; Canada Research Chairs","keywords":"Neuroscience; Dopamine; Temporal difference learning; Psychology; Function (biology); Cognitive psychology; Biology; Computer science; Artificial intelligence; Reinforcement learning","score_opus":0.03897630391855688,"score_gpt":0.28451362114193823,"score_spread":0.24553731722338135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000091990","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":[0.0876837,0.000099689925,0.88858366,0.018843617,0.0033087174,0.0006566096,0.00000296127,0.0005317965,0.00028927502],"genre_scores_gemma":[0.9903872,0.000020975423,0.0012501171,0.007816121,0.0001618046,0.00001651507,0.0000029981804,0.000014861976,0.00032937757],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629784,0.00019653566,0.00037538106,0.00096130924,0.0016006853,0.0005682534],"domain_scores_gemma":[0.9985157,0.00018670368,0.00032257335,0.0006104774,0.00012879059,0.00023573954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005878356,0.00027150416,0.00018278426,0.00007949703,0.0005849908,0.0004914911,0.0021563037,0.00016958307,0.000010580021],"category_scores_gemma":[0.001579824,0.00018861021,0.00008498042,0.0013246741,0.00026861366,0.0015663774,0.00038624645,0.00135561,0.00003122823],"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":[0.0004074202,0.00023967797,0.20747936,0.0003293765,0.000030418907,0.00037868347,0.008550133,0.3200912,0.40935615,0.027263064,0.0062432163,0.019631306],"study_design_scores_gemma":[0.00033200366,0.0013884401,0.120743215,0.00007884203,0.000026152182,0.00009026995,0.000072306364,0.86464995,0.008265145,0.00019972115,0.0037931665,0.00036078817],"about_ca_topic_score_codex":0.0000133992635,"about_ca_topic_score_gemma":0.000002878828,"teacher_disagreement_score":0.9027035,"about_ca_system_score_codex":0.000048897342,"about_ca_system_score_gemma":0.00026560196,"threshold_uncertainty_score":0.7691301},"labels":[],"label_agreement":null},{"id":"W3000711993","doi":"10.1109/ro-man46459.2019.8956320","title":"Incremental Estimation of Users’ Expertise Level","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Estimation; Engineering; Systems engineering","score_opus":0.03310113847019799,"score_gpt":0.2636222543227014,"score_spread":0.23052111585250343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000711993","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":[0.11026805,0.000003665475,0.8802183,0.00007889021,0.00015275482,0.000094276176,1.3842997e-7,0.000054998578,0.009128875],"genre_scores_gemma":[0.84610504,8.506673e-7,0.15200669,0.00010076526,0.000004004984,0.0000013515115,0.0000011449545,0.000002828464,0.001777348],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993768,0.000014110766,0.00015644438,0.000119881544,0.00023138321,0.00010141129],"domain_scores_gemma":[0.99953365,0.00002654424,0.00006748244,0.00031996105,0.000027735778,0.000024606941],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010292803,0.000054037555,0.0000732326,0.00005100714,0.000017168115,0.000032632193,0.00036227625,0.000022729282,0.00015698677],"category_scores_gemma":[0.000019147374,0.000048079986,0.000024713525,0.00011121772,0.00001206,0.000415053,0.00015742073,0.000036999474,0.00028536745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029386993,0.000020112793,0.00672097,0.000018938035,0.00001221881,6.424223e-7,0.0010049597,0.9263187,0.009132512,0.044107,0.0006103701,0.012050631],"study_design_scores_gemma":[0.00020772987,0.00006973699,0.006446984,0.00001085997,0.000001010234,0.0000013515809,0.000029554962,0.97285676,0.020179208,0.00005123717,0.000081199476,0.00006434005],"about_ca_topic_score_codex":0.000038610022,"about_ca_topic_score_gemma":5.849724e-7,"teacher_disagreement_score":0.735837,"about_ca_system_score_codex":0.000030675707,"about_ca_system_score_gemma":0.000020965643,"threshold_uncertainty_score":0.36679167},"labels":[],"label_agreement":null},{"id":"W3004681481","doi":"10.65109/lvmd6651","title":"Multi Type Mean Field Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Collège Boréal; University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Field (mathematics); Mean field theory; Type (biology); Core (optical fiber); Artificial intelligence; Game theory; Relaxation (psychology); Multi-agent system; Machine learning; Mathematics; Mathematical economics","score_opus":0.055785596669593734,"score_gpt":0.29388675866132424,"score_spread":0.2381011619917305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3004681481","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":[0.00006955554,0.00004610697,0.96042234,0.0021649834,0.0016113196,0.00035140011,9.784655e-8,0.0009179104,0.034416307],"genre_scores_gemma":[0.6451774,0.00010003202,0.32672352,0.0029558334,0.00024891246,0.000021557516,0.00004267765,0.000045026998,0.024685005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751323,0.00009640996,0.00053797377,0.00080662174,0.00061121245,0.0004345343],"domain_scores_gemma":[0.99801797,0.00014911767,0.00033367597,0.0011177306,0.00017878487,0.00020271518],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00025138186,0.00038255955,0.0003794027,0.00013020939,0.00012247247,0.00049578876,0.0022204597,0.00030736273,0.00030761462],"category_scores_gemma":[0.00041951906,0.00037117145,0.0001655945,0.00027408448,0.000023493818,0.00019533276,0.0053050276,0.0016061084,0.00080557214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005534522,0.000010619584,0.00014471996,0.00008257588,0.000063905114,0.000018751583,0.00092283497,0.9885295,0.0003399529,0.0049896105,0.0031426384,0.0017493266],"study_design_scores_gemma":[0.00021042711,0.00035225003,0.00004892216,0.00007624531,0.000015490206,0.0000023598138,0.00003458335,0.979453,0.0018029433,0.00014746483,0.017412625,0.00044367835],"about_ca_topic_score_codex":0.000092947565,"about_ca_topic_score_gemma":0.000004666922,"teacher_disagreement_score":0.64510787,"about_ca_system_score_codex":0.000115598625,"about_ca_system_score_gemma":0.00016698256,"threshold_uncertainty_score":0.9999724},"labels":[],"label_agreement":null},{"id":"W3008080228","doi":"10.1007/978-981-15-1773-0_17","title":"Revisited: Machine Intelligence in Heterogeneous Multi-Agent Systems","year":2020,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Reinforcement Learning in Robotics","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.014693134983030414,"score_gpt":0.22612211726262396,"score_spread":0.21142898227959356,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008080228","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":[0.0000016973761,0.007865815,0.98989844,0.00011778933,0.0004137891,0.00051666057,0.0000021449287,0.0003056851,0.00087799836],"genre_scores_gemma":[0.8815972,0.0019922298,0.11149243,0.00088655663,0.000667643,0.00008439357,0.000075475815,0.00041382856,0.0027902205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99709225,0.000035823236,0.0008518002,0.00085855956,0.00051927206,0.0006422875],"domain_scores_gemma":[0.99847424,0.00045590536,0.00018727485,0.0006612986,0.00004750536,0.0001737826],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021120149,0.0006297681,0.0007793076,0.0006764559,0.00003041522,0.00016822886,0.0012472234,0.00052679173,0.000013775841],"category_scores_gemma":[0.0005572332,0.0006415783,0.00015972204,0.0005772187,0.000019431016,0.0001027655,0.00033116262,0.0021595978,0.00007466092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044892245,0.000009263398,0.0000149682255,0.00014487741,0.000029373412,0.00052182877,0.00007776914,0.975689,0.00006670885,0.011423256,0.0000030480467,0.012015431],"study_design_scores_gemma":[0.00014441597,0.00013146453,0.000007796254,0.00042207583,0.000010572302,0.0000647334,6.4565015e-8,0.99415326,0.00023112635,0.0002557771,0.00398399,0.0005947067],"about_ca_topic_score_codex":0.000027690878,"about_ca_topic_score_gemma":0.0000061348856,"teacher_disagreement_score":0.8815955,"about_ca_system_score_codex":0.0006173385,"about_ca_system_score_gemma":0.000064682994,"threshold_uncertainty_score":0.99960357},"labels":[],"label_agreement":null},{"id":"W3009186063","doi":"","title":"Spatially-Distributed Interactive Behaviour Generation for Architecture-Scale Systems Based on Reinforcement Learning","year":2020,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Architecture; Scale (ratio); Computer science; Human–computer interaction; Distributed computing; Data science; Artificial intelligence; Geography; Cartography","score_opus":0.014137990150256935,"score_gpt":0.21692191390495366,"score_spread":0.20278392375469673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009186063","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":[0.03770031,0.000009877996,0.95921785,0.0005828068,0.0009476749,0.0010591031,0.0000241543,0.00018385774,0.00027437115],"genre_scores_gemma":[0.8380857,0.000016434382,0.030396314,0.000067504385,0.0001912076,0.000012388365,0.01033615,0.00006949383,0.12082477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802375,0.00013754192,0.00027609817,0.00063396344,0.0005921723,0.00033649412],"domain_scores_gemma":[0.998153,0.00010915746,0.00076755707,0.00046136524,0.00037177373,0.00013718418],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019111858,0.0003569202,0.0004826258,0.00033446617,0.0003522489,0.00014861852,0.0008682759,0.0002738756,0.000025178022],"category_scores_gemma":[0.000062048195,0.00042094337,0.00024865902,0.0002482994,0.000033323457,0.00026816802,0.00010421509,0.0005383576,0.00002556514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002180733,0.00003179236,0.000082862025,0.00023701867,0.00007102194,0.0000117452155,0.024195379,0.9722419,0.0016262218,0.0002607381,0.00048232955,0.000540924],"study_design_scores_gemma":[0.0009302092,0.0010410321,0.00019422939,0.00027878096,0.0001142808,7.69013e-7,0.007175112,0.9861505,0.0027180426,0.0000042830093,0.0009960675,0.00039668218],"about_ca_topic_score_codex":0.0030003963,"about_ca_topic_score_gemma":0.0010922919,"teacher_disagreement_score":0.9288215,"about_ca_system_score_codex":0.0002602228,"about_ca_system_score_gemma":0.00018353986,"threshold_uncertainty_score":0.9998242},"labels":[],"label_agreement":null},{"id":"W3010862467","doi":"10.48550/arxiv.2003.07417","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Generalization; Artificial neural network; Scalability; Machine learning","score_opus":0.03919345243744466,"score_gpt":0.17974001139860277,"score_spread":0.1405465589611581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010862467","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":[0.09268743,0.000046660924,0.9057804,0.000060709528,0.0003555008,0.00030507485,2.2976195e-7,0.00017538,0.0005886355],"genre_scores_gemma":[0.99827373,0.00018734048,0.00077353796,0.00014788102,0.000056958088,0.0000019106326,0.000054762677,0.000025498612,0.0004783617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99773276,0.00018372419,0.00043061242,0.00096854084,0.00014558563,0.0005387734],"domain_scores_gemma":[0.99873716,0.000058138434,0.00046849521,0.00056248065,0.00006287729,0.000110862835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034204757,0.00034311568,0.00034059322,0.0003451003,0.00012735018,0.00020625765,0.0013877433,0.0002689308,0.000009688617],"category_scores_gemma":[0.000054651522,0.0004483062,0.000075857715,0.0010135825,0.00004183584,0.0007189517,0.0022148641,0.0014302373,0.000009845211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014962491,0.000009570971,0.036603447,0.00007998082,0.000010599607,0.00007515311,0.00028941382,0.9595113,0.000031346695,0.002295549,0.000018810357,0.0010598626],"study_design_scores_gemma":[0.00051558326,0.000084073894,0.0017830796,0.0001320796,0.000010689031,0.0000014858005,0.00002914795,0.99687326,0.0000245146,0.000040285955,0.00007972252,0.00042609216],"about_ca_topic_score_codex":0.00037879206,"about_ca_topic_score_gemma":0.000029505098,"teacher_disagreement_score":0.9055863,"about_ca_system_score_codex":0.00053627806,"about_ca_system_score_gemma":0.00009514564,"threshold_uncertainty_score":0.99979687},"labels":[],"label_agreement":null},{"id":"W3011813374","doi":"10.1109/cdc40024.2019.9029898","title":"Approximate information state for partially observed systems","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Observable; Computer science; State (computer science); Reinforcement learning; Partially observable Markov decision process; Markov decision process; Benchmark (surveying); Markov process; Mathematical optimization; Constructive; Artificial intelligence; Theoretical computer science; Markov chain; Markov model; Machine learning; Mathematics; Algorithm","score_opus":0.026192144294298572,"score_gpt":0.2265800874326913,"score_spread":0.20038794313839275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011813374","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":[0.0031887619,0.0000051646593,0.9888303,0.00012613634,0.00080463826,0.0007514332,0.0000011031381,0.00026887158,0.006023575],"genre_scores_gemma":[0.88199204,0.0000057197144,0.106038965,0.00051717827,0.00003698633,0.000102181046,0.000033684937,0.000012308997,0.011260914],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906766,0.000020248992,0.00030712227,0.00012635844,0.0002284321,0.00025014865],"domain_scores_gemma":[0.99917763,0.00006782725,0.00014807847,0.00042596087,0.00013120218,0.000049283826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035016116,0.00009079047,0.00011736032,0.00005545865,0.000049486953,0.00046193064,0.00050646946,0.00003290782,0.0000085240745],"category_scores_gemma":[0.000029746994,0.00007651403,0.000040039133,0.00012648685,0.0000069501098,0.0017589286,0.00011788807,0.000050267736,0.0005093636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004183437,0.0000034547256,0.0006172283,0.00009963996,0.000010567173,1.0711462e-7,0.00029383256,0.9116805,0.00009245772,0.0853408,0.00091438007,0.00094285153],"study_design_scores_gemma":[0.00037030276,0.00009683673,0.00028993018,0.000012423006,0.0000016618992,0.0000010673189,0.000027576409,0.9782787,0.00045241613,0.00014626728,0.020208472,0.00011433946],"about_ca_topic_score_codex":0.000016544873,"about_ca_topic_score_gemma":6.463339e-7,"teacher_disagreement_score":0.88279134,"about_ca_system_score_codex":0.0000308784,"about_ca_system_score_gemma":0.000046343634,"threshold_uncertainty_score":0.6547008},"labels":[],"label_agreement":null},{"id":"W3012442074","doi":"10.1109/cdc40024.2019.9029788","title":"Q-Learning with Side Information in Multi-Agent Finite Games","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Human–computer interaction","score_opus":0.013505554646719783,"score_gpt":0.22893920249844577,"score_spread":0.21543364785172597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3012442074","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":[0.032834638,0.000003018962,0.9518789,0.00013505633,0.0000942273,0.00017485606,3.9303714e-8,0.00014663168,0.014732648],"genre_scores_gemma":[0.9063522,0.0000049743207,0.08904721,0.00036037888,0.0000040699906,0.000005571611,0.0000036230176,0.0000043016307,0.004217656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991654,0.00003457328,0.0002089025,0.00013031706,0.00024915507,0.00021161545],"domain_scores_gemma":[0.99944615,0.00009382742,0.00009920882,0.0002742534,0.000048207366,0.000038332884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00020297508,0.00009347058,0.000096884214,0.00016072927,0.000031627216,0.00017915953,0.0003395577,0.000034929544,0.000050455426],"category_scores_gemma":[0.00006639049,0.000073196396,0.000018192619,0.00028889353,0.000010965842,0.0014567268,0.00014473496,0.0001931904,0.0011103168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027083458,0.0000052194223,0.032500464,0.000010850471,0.0000034215723,0.0000015093303,0.0012453836,0.9613589,0.000018714927,0.001747814,0.000016815839,0.003088172],"study_design_scores_gemma":[0.00054517604,0.00014708254,0.019438632,0.00002940719,8.2941864e-7,0.0000021878648,0.00020154128,0.9734162,0.00014721774,0.000005741471,0.005944236,0.00012173263],"about_ca_topic_score_codex":0.000039725976,"about_ca_topic_score_gemma":0.000007047809,"teacher_disagreement_score":0.8735176,"about_ca_system_score_codex":0.00004434936,"about_ca_system_score_gemma":0.000039628983,"threshold_uncertainty_score":0.9996674},"labels":[],"label_agreement":null},{"id":"W3013464227","doi":"10.1109/ieeeconf44664.2019.9049021","title":"Decentralized Q-Learning with Constant Aspirations in Stochastic Games","year":2019,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Constant (computer programming); Mathematical optimization; State (computer science); Control (management); Information structure; Fictitious play; Complete information; Function (biology); Obstacle; Nash equilibrium; Artificial intelligence; Mathematical economics; Mathematics; Algorithm; Economics","score_opus":0.012778840513520693,"score_gpt":0.22521369905343583,"score_spread":0.21243485853991514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013464227","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":[0.02171635,0.00001581729,0.960365,0.00022796138,0.000087586915,0.00023473718,5.588271e-8,0.00015414786,0.017198373],"genre_scores_gemma":[0.9650533,0.0000029228959,0.03230764,0.00017133127,0.0000042359325,0.000006980653,0.0000014772075,0.0000070390183,0.002445063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901646,0.00004924922,0.00018512386,0.00023284325,0.00024488816,0.00027141505],"domain_scores_gemma":[0.99940467,0.00013297625,0.00007111941,0.00029067762,0.00004666291,0.000053911666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015488597,0.00010062163,0.00013186228,0.00011344036,0.00004431952,0.00014338546,0.00033058212,0.000030806008,0.00019157192],"category_scores_gemma":[0.00005316716,0.000079043195,0.000019444482,0.00036878008,0.00002922641,0.0003402178,0.0000877366,0.00018510524,0.00026131645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000043325763,0.000008654537,0.010776728,0.0000033011233,0.0000058221817,0.0000036033657,0.00026420085,0.9015005,0.000105307736,0.08692231,0.000017160706,0.00038808098],"study_design_scores_gemma":[0.0008248688,0.00019864518,0.0026933833,0.000047772734,0.0000025959107,0.000008474337,0.000110380795,0.9948853,0.00006997607,0.00010636116,0.00089294167,0.00015926613],"about_ca_topic_score_codex":0.000019332381,"about_ca_topic_score_gemma":0.000016869322,"teacher_disagreement_score":0.94333696,"about_ca_system_score_codex":0.000044595992,"about_ca_system_score_gemma":0.00009634489,"threshold_uncertainty_score":0.33587816},"labels":[],"label_agreement":null},{"id":"W3014454071","doi":"10.48550/arxiv.2004.00993","title":"Augmented Q Imitation Learning (AQIL)","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Reinforcement learning; Imitation; Artificial intelligence; Q-learning; Computer science; Process (computing); Convergence (economics); Machine learning; Unsupervised learning; Reinforcement; Learning classifier system; Sequence learning; Psychology; Social psychology","score_opus":0.10468339204744868,"score_gpt":0.19147103244595107,"score_spread":0.08678764039850238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3014454071","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":[0.0132013485,0.0000171823,0.9781753,0.00034098295,0.0006232806,0.00024636203,0.0000011781174,0.0006866609,0.0067077233],"genre_scores_gemma":[0.98970854,0.000083597624,0.0059545473,0.0001557525,0.0000748859,7.339598e-7,0.00004434255,0.000023809163,0.0039538005],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802095,0.00021010778,0.00023663824,0.0010240623,0.000161752,0.00034649603],"domain_scores_gemma":[0.9983465,0.00012226726,0.00039537772,0.0007893465,0.00016043682,0.00018607177],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019692261,0.00030860785,0.00028875988,0.00021747219,0.00020436673,0.00023074071,0.0017713824,0.00023959944,0.000037501162],"category_scores_gemma":[0.00014979429,0.00039273527,0.00018791488,0.00063928164,0.00006633316,0.0004242076,0.002460243,0.0011375672,0.00040691797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009965558,0.000012450859,0.0013013314,0.00005355648,0.00006758604,0.0001307758,0.00036915706,0.9286725,0.000054584085,0.06874577,0.00028190526,0.00030041204],"study_design_scores_gemma":[0.00034147644,0.00008572414,0.00082577567,0.00006725146,0.000046384615,0.000001603281,0.00008472204,0.9917948,0.00007661532,0.004518883,0.0017723517,0.0003843866],"about_ca_topic_score_codex":0.00003947306,"about_ca_topic_score_gemma":0.0000024101485,"teacher_disagreement_score":0.9765072,"about_ca_system_score_codex":0.00025109603,"about_ca_system_score_gemma":0.00017377516,"threshold_uncertainty_score":0.9998525},"labels":[],"label_agreement":null},{"id":"W3015100386","doi":"10.48550/arxiv.2004.00600","title":"Work in Progress: Temporally Extended Auxiliary Tasks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Computer science; Robustness (evolution); Reinforcement learning; Task (project management); Autoencoder; Trajectory; Sensitivity (control systems); Artificial intelligence; Machine learning; Algorithm; Deep learning; Engineering","score_opus":0.08161985637333861,"score_gpt":0.2053707032589729,"score_spread":0.12375084688563427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015100386","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":[0.018305605,0.000103740305,0.97485167,0.000855274,0.00073291495,0.00062433566,0.000002621289,0.00060484087,0.003918976],"genre_scores_gemma":[0.9843689,0.000070627844,0.013631293,0.00019908315,0.00007207219,0.0000023967395,0.000023936946,0.000028834747,0.001602855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727213,0.00021412104,0.0003648114,0.0014277735,0.00019997415,0.0005212089],"domain_scores_gemma":[0.99766165,0.00008738526,0.0003903702,0.0015179224,0.00010766742,0.00023502934],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030090287,0.00042212586,0.00045726035,0.00035394783,0.00009543377,0.00023220094,0.0033375765,0.00037404452,0.000030035237],"category_scores_gemma":[0.00006954189,0.0005090873,0.00020467835,0.001410508,0.000163828,0.0004496889,0.0041835057,0.0013297967,0.00022783337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004706188,0.000062555024,0.021248722,0.000096703436,0.00005809907,0.0013944575,0.0004119736,0.9401514,0.000002765758,0.03507608,0.0008159237,0.00063425914],"study_design_scores_gemma":[0.0006594707,0.000101354286,0.015809393,0.00032111286,0.000033926815,0.0000028865725,0.00005856272,0.9700271,0.000019192612,0.010626599,0.0015974895,0.0007429292],"about_ca_topic_score_codex":0.000041256746,"about_ca_topic_score_gemma":0.000007938605,"teacher_disagreement_score":0.9660633,"about_ca_system_score_codex":0.0002936165,"about_ca_system_score_gemma":0.00040224488,"threshold_uncertainty_score":0.9997361},"labels":[],"label_agreement":null},{"id":"W3015230978","doi":"10.48550/arxiv.2004.03761","title":"Adaptive Transformers in RL","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Transformer; Computer science; Computation; Replicate; Reinforcement learning; Artificial intelligence; Computer engineering; Machine learning; Voltage; Electrical engineering; Engineering; Algorithm","score_opus":0.1102922021503649,"score_gpt":0.18820508747018033,"score_spread":0.07791288531981543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015230978","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":[0.007019959,0.000017958315,0.9774019,0.00030443218,0.00040216933,0.00031235703,0.0000030791286,0.00022534313,0.014312774],"genre_scores_gemma":[0.99519116,0.00011231628,0.003557074,0.00017046458,0.000034022618,7.317403e-7,0.000008166357,0.00001673729,0.0009093448],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99818426,0.00011344478,0.00022650886,0.0009712993,0.00012190989,0.00038255105],"domain_scores_gemma":[0.99888873,0.0000820681,0.00016992366,0.0006282572,0.00006348939,0.00016755215],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015911013,0.00029764712,0.00033463517,0.00027917544,0.00006549135,0.00008750462,0.0018852275,0.00025198533,0.000026668444],"category_scores_gemma":[0.000027321015,0.0003702835,0.0001827974,0.0007834282,0.00008466337,0.00038875913,0.0011386416,0.0009992833,0.00017440408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020504913,0.000016543365,0.00077613903,0.00003433245,0.000038929003,0.00032832092,0.0005572415,0.92039317,0.000006954145,0.077362746,0.00009091105,0.00037420818],"study_design_scores_gemma":[0.0004438182,0.000087897926,0.00086598075,0.00007961897,0.00002203513,0.0000012773188,0.0001242096,0.99039125,0.000040060186,0.007093617,0.00046487869,0.00038533338],"about_ca_topic_score_codex":0.0001254275,"about_ca_topic_score_gemma":0.000031176394,"teacher_disagreement_score":0.98817116,"about_ca_system_score_codex":0.0003018099,"about_ca_system_score_gemma":0.00025863983,"threshold_uncertainty_score":0.9998749},"labels":[],"label_agreement":null},{"id":"W3015239645","doi":"10.1007/s12065-020-00394-9","title":"Neuromodulated multiobjective evolutionary neurocontrollers without speciation","year":2020,"lang":"en","type":"article","venue":"Evolutionary Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Neuroevolution; Computer science; Evolutionary algorithm; Artificial intelligence; Neuromodulation; Genetic algorithm; Artificial neural network; Mathematical optimization; Mathematics; Ecology; Biology","score_opus":0.026577096686810284,"score_gpt":0.24533899506254947,"score_spread":0.21876189837573917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015239645","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":[0.001589498,0.00016588578,0.98877203,0.004328551,0.00068714336,0.00050845236,0.0000045068664,0.0006444073,0.0032995096],"genre_scores_gemma":[0.96084446,0.000053541826,0.03659963,0.0016945296,0.0002989572,0.000027798547,0.000019332594,0.000023918521,0.00043785898],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973263,0.00020449271,0.0005353797,0.00077284785,0.00070293766,0.00045802523],"domain_scores_gemma":[0.998455,0.00020232907,0.00025656886,0.00051482307,0.00031531276,0.00025598265],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013576042,0.00028809565,0.0002572311,0.0001508143,0.0003198788,0.00010123906,0.0011901694,0.000105020285,0.00013255174],"category_scores_gemma":[0.0006077456,0.0003079376,0.00014052948,0.0009968095,0.00012150383,0.0011606347,0.00036470513,0.0004425909,0.0010729452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050924158,0.000042359046,0.0039312956,0.000010855451,0.00003360186,0.000026518224,0.0007821838,0.9759814,0.00071871205,0.014169039,0.0020910723,0.0021620176],"study_design_scores_gemma":[0.00021724794,0.000274492,0.028235637,0.000014987254,0.000009720702,0.000030374858,0.000056877183,0.9654311,0.00036185572,0.00096143084,0.004101014,0.00030524223],"about_ca_topic_score_codex":0.000020806261,"about_ca_topic_score_gemma":7.453703e-7,"teacher_disagreement_score":0.9592549,"about_ca_system_score_codex":0.0002180613,"about_ca_system_score_gemma":0.00018296704,"threshold_uncertainty_score":0.9999373},"labels":[],"label_agreement":null},{"id":"W3015837232","doi":"10.1109/icra40945.2020.9196879","title":"Learning to Drive Off Road on Smooth Terrain in Unstructured Environments Using an On-Board Camera and Sparse Aerial Images","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":true,"ca_institutions":"McGill University","funders":"","keywords":"Terrain; Computer science; Tree traversal; Artificial intelligence; Computer vision; Overhead (engineering); Aerial image; Image (mathematics); Remote sensing; Geology; Geography; Algorithm; Cartography","score_opus":0.027105756007752637,"score_gpt":0.27052294769151775,"score_spread":0.2434171916837651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015837232","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":[0.49478582,0.000009413104,0.5013603,0.0009022942,0.0009014083,0.00076149014,0.0000044623325,0.00014380607,0.0011309872],"genre_scores_gemma":[0.9258658,0.00002455651,0.07241248,0.0010643967,0.00021476187,0.000014678417,0.000024532641,0.000049369337,0.00032938214],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672985,0.00033969097,0.000496545,0.0013566146,0.00057608,0.0005012362],"domain_scores_gemma":[0.99846303,0.00007031145,0.00029343777,0.00085739425,0.000015513639,0.00030028707],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027545795,0.00053279067,0.000545515,0.00033517173,0.000137183,0.00053743046,0.0010976641,0.00026531555,0.00003544192],"category_scores_gemma":[0.00015351667,0.000529712,0.0000758712,0.00017979374,0.00008904947,0.00023430875,0.0022014691,0.0012951895,0.00003596953],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041252093,0.000024631754,0.0013732229,0.000016491387,0.000023944622,0.000037116613,0.0034839888,0.9754512,0.0030811846,0.0001721073,0.000044398825,0.016250497],"study_design_scores_gemma":[0.0008062261,0.0008536007,0.027875226,0.00022724453,0.000016414198,0.000004044651,0.00021638883,0.9663055,0.0017079026,0.00019534344,0.00097057363,0.0008215202],"about_ca_topic_score_codex":0.0004469597,"about_ca_topic_score_gemma":0.00001681149,"teacher_disagreement_score":0.43108,"about_ca_system_score_codex":0.00029030174,"about_ca_system_score_gemma":0.000103376224,"threshold_uncertainty_score":0.99971545},"labels":[],"label_agreement":null},{"id":"W3017390413","doi":"","title":"Active Roll-outs in MDP with Irreversible Dynamics","year":2019,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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":"Dynamics (music); Chemistry; Computer science; Physics","score_opus":0.009771959918208143,"score_gpt":0.21452481604992762,"score_spread":0.20475285613171948,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3017390413","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":[0.010465027,0.000098817654,0.8724319,0.0039869277,0.0003096286,0.00061059016,0.000012755209,0.00024554975,0.111838855],"genre_scores_gemma":[0.8396865,0.00014042022,0.1319537,0.00013029808,0.00001262099,0.000051746847,0.00027688371,0.000053454845,0.02769439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946821,0.0025443074,0.000500877,0.0010560747,0.00069529604,0.00052136875],"domain_scores_gemma":[0.9933142,0.0010969198,0.0006643721,0.0034809378,0.0012915389,0.00015203758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0028524962,0.00041464198,0.00047333867,0.00040149345,0.00018027822,0.0006597747,0.0034046627,0.00033009527,0.000053968866],"category_scores_gemma":[0.00052586466,0.00042487503,0.0001416955,0.0007618617,0.00015491342,0.00045138565,0.0033196046,0.0012384973,0.0001561037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045413613,0.0005490963,0.018165795,0.00038768438,0.0002035652,0.000037384078,0.020223137,0.64523154,0.00013150042,0.2880932,0.0008551131,0.026076566],"study_design_scores_gemma":[0.00076065736,0.0000012380771,0.005485735,0.0016793685,0.000020484586,0.000008669671,0.00012282954,0.98535115,0.0023742546,0.0014356137,0.0021920756,0.0005679097],"about_ca_topic_score_codex":0.0010733393,"about_ca_topic_score_gemma":0.0017821748,"teacher_disagreement_score":0.8292215,"about_ca_system_score_codex":0.00054798496,"about_ca_system_score_gemma":0.00065759977,"threshold_uncertainty_score":0.9998203},"labels":[],"label_agreement":null},{"id":"W3020277389","doi":"10.48550/arxiv.2004.12399","title":"Reinforcement Learning Generalization with Surprise Minimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Surprise; Generalization; Computer science; Reinforcement learning; Artificial intelligence; Robustness (evolution); Machine learning; Mathematics; Psychology","score_opus":0.06140952338521455,"score_gpt":0.1835702624956942,"score_spread":0.12216073911047964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3020277389","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":[0.0059951693,0.000013214819,0.98918253,0.00017409728,0.00028570244,0.00037437966,6.003239e-7,0.00051395607,0.003460377],"genre_scores_gemma":[0.985941,0.00016837493,0.009273266,0.0001620204,0.00007835034,0.0000014907058,0.00013547338,0.0000329693,0.0042070434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979971,0.00017349412,0.00027513746,0.000993243,0.00022076932,0.00034022643],"domain_scores_gemma":[0.99814296,0.000053280557,0.0005278075,0.00083663175,0.00025550055,0.00018381127],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014966035,0.00035501883,0.00030493047,0.00022798759,0.00022439913,0.0002630737,0.0012798966,0.00022195563,0.00004043587],"category_scores_gemma":[0.00006639107,0.00039309304,0.00010698674,0.0007883495,0.000063992265,0.0005063337,0.0014920146,0.0006480915,0.00008665998],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025915762,0.000010688163,0.0029013064,0.00007016387,0.0000732688,0.00009716191,0.00042467145,0.95247036,0.000013666344,0.04360986,0.0002130774,0.000089881076],"study_design_scores_gemma":[0.00048645996,0.00016382679,0.00028127214,0.000089666355,0.00006616267,0.0000023335506,0.00004365838,0.9964676,0.00010254574,0.0005241982,0.0013134333,0.000458864],"about_ca_topic_score_codex":0.00005172878,"about_ca_topic_score_gemma":0.000005017397,"teacher_disagreement_score":0.97994584,"about_ca_system_score_codex":0.00026013143,"about_ca_system_score_gemma":0.00025099432,"threshold_uncertainty_score":0.9998521},"labels":[],"label_agreement":null},{"id":"W3023876387","doi":"10.48550/arxiv.2005.01138","title":"Off-Policy Adversarial Inverse Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Adversarial system; Reinforcement learning; Computer science; Artificial intelligence; Imitation; Machine learning; Task (project management); Function (biology); Transfer of learning; Class (philosophy); Temporal difference learning; Psychology; Engineering","score_opus":0.0758925450107277,"score_gpt":0.2042774652760245,"score_spread":0.1283849202652968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3023876387","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":[0.0036114599,0.000015333511,0.9735701,0.00059858896,0.001086725,0.00044200203,0.0000017610797,0.0007698754,0.019904163],"genre_scores_gemma":[0.9860907,0.00031385507,0.0030920643,0.0005601126,0.00045786184,0.0000014659704,0.000053146032,0.000041476982,0.009389274],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688536,0.00025289785,0.00043000863,0.0014442578,0.00030247628,0.0006850081],"domain_scores_gemma":[0.99715275,0.00012812296,0.00063527183,0.0014649796,0.00019373737,0.00042513144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030916056,0.00055519346,0.000524039,0.0005010137,0.00032184305,0.0002937925,0.0031757469,0.00043504403,0.000092170696],"category_scores_gemma":[0.00035008197,0.00069817103,0.0003778779,0.0011037485,0.00015549645,0.00062673056,0.006497051,0.0018020258,0.0007598746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034508543,0.0000141246155,0.00044533465,0.00007339433,0.0001306117,0.00025690423,0.0006009127,0.87627757,0.000021853,0.1208723,0.00095054606,0.00032195446],"study_design_scores_gemma":[0.0008783149,0.00016836096,0.00009896317,0.00008420226,0.00007331225,0.0000030718825,0.00009152624,0.97988653,0.00005503536,0.0031130626,0.014888218,0.00065940374],"about_ca_topic_score_codex":0.0002836777,"about_ca_topic_score_gemma":0.000009207915,"teacher_disagreement_score":0.9824793,"about_ca_system_score_codex":0.000729367,"about_ca_system_score_gemma":0.0009102013,"threshold_uncertainty_score":0.99954695},"labels":[],"label_agreement":null},{"id":"W3024138969","doi":"10.48550/arxiv.2005.06223","title":"DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Canadian Animal Health Institute","funders":"","keywords":"Dream; Architecture; Robotics; Artificial intelligence; Computer science; Developmental robotics; Cognitive science; Engineering; Psychology; Robot; Art; Visual arts; Neuroscience","score_opus":0.10023880800136796,"score_gpt":0.20699681502897768,"score_spread":0.10675800702760972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3024138969","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":[0.0050336374,0.000007104178,0.9630212,0.00036341423,0.0002657976,0.00086709537,0.0000015214679,0.0003281455,0.030112084],"genre_scores_gemma":[0.82035714,0.00001555586,0.17688161,0.00034298864,0.00003802036,0.000003536925,0.000032051616,0.000033037424,0.0022960338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968197,0.00027522806,0.00037649358,0.0016971745,0.00021473886,0.0006167085],"domain_scores_gemma":[0.9983458,0.00010808233,0.0002742828,0.00083003764,0.0000831061,0.00035870337],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00035824304,0.00048525044,0.0005594664,0.00048621872,0.00019067856,0.0005521403,0.005667871,0.00029288788,0.000008882527],"category_scores_gemma":[0.00016646786,0.00059769326,0.00013420942,0.001519364,0.00006663294,0.00035338118,0.013631184,0.0019062872,0.00017030915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029649302,0.000069162714,0.0016004964,0.00006522169,0.000059298854,0.00017780783,0.0015226982,0.9466586,0.00003588602,0.049233314,0.00014877808,0.00039905927],"study_design_scores_gemma":[0.0006902008,0.00009445156,0.00162487,0.00011667802,0.000022602228,0.00001099595,0.00021664912,0.99196625,0.000039749113,0.003414081,0.0010562232,0.0007472277],"about_ca_topic_score_codex":0.00013193981,"about_ca_topic_score_gemma":0.000022743909,"teacher_disagreement_score":0.81532353,"about_ca_system_score_codex":0.0006088463,"about_ca_system_score_gemma":0.000621859,"threshold_uncertainty_score":0.99971193},"labels":[],"label_agreement":null},{"id":"W3025133396","doi":"10.65109/uazl2918","title":"META-Learning State-based Eligibility Traces for More Sample-Efficient Policy Evaluation","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Machine learning; Robustness (evolution); Artificial intelligence; Temporal difference learning; Sample (material); Q-learning; Bellman equation; Mathematical optimization; Mathematics","score_opus":0.16838999763150939,"score_gpt":0.39732922141276855,"score_spread":0.22893922378125917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3025133396","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":[0.0018168321,0.00011702862,0.98535115,0.008455601,0.0004274688,0.0025967127,0.000029422416,0.0007008961,0.0005049022],"genre_scores_gemma":[0.6565921,0.000009234598,0.34101385,0.00097275234,0.00015886109,0.000641136,0.0002732346,0.000045019282,0.00029385163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99499047,0.00049559335,0.0008926852,0.0014501392,0.0015912079,0.0005799084],"domain_scores_gemma":[0.9955316,0.0013288996,0.0007353912,0.0013780853,0.00079971616,0.00022627573],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0031457318,0.00053711305,0.00079258496,0.0003289531,0.00025546842,0.0007130731,0.0018060586,0.000228762,0.00012028363],"category_scores_gemma":[0.0037629257,0.00046530057,0.0006721194,0.0005118816,0.00009038871,0.00014425474,0.0012045907,0.00084979757,0.000034839486],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016614513,0.000039759707,0.00008924865,0.00022879617,0.00034500138,5.787188e-7,0.0009601591,0.9893518,0.0000325368,0.004577799,0.00015981578,0.0041978997],"study_design_scores_gemma":[0.0004881587,0.00015673944,0.00035581505,0.00002441262,0.0005706465,3.3392055e-7,0.000035719113,0.9912645,0.0008799984,0.0043049534,0.0014660433,0.00045264713],"about_ca_topic_score_codex":0.00039281772,"about_ca_topic_score_gemma":0.0000050336453,"teacher_disagreement_score":0.6547752,"about_ca_system_score_codex":0.0004914316,"about_ca_system_score_gemma":0.0019117562,"threshold_uncertainty_score":0.9997799},"labels":[],"label_agreement":null},{"id":"W3029466658","doi":"10.1109/tg.2020.2990865","title":"Winning Is Not Everything: Enhancing Game Development With Intelligent Agents","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Games","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Electronic Arts (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Benchmark (surveying); Hyperparameter; Human–computer interaction; Machine learning","score_opus":0.043264560459594814,"score_gpt":0.25315020327216015,"score_spread":0.20988564281256533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3029466658","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":[0.012040444,0.000011499924,0.9850659,0.001752984,0.0003353572,0.00019194772,7.1064846e-7,0.0003288576,0.0002723236],"genre_scores_gemma":[0.9299941,0.000011474784,0.06475358,0.0042316024,0.000029994053,0.000020662896,6.284172e-7,0.000024099705,0.0009338455],"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99814475,0.000040331466,0.00036388467,0.0004927666,0.0005979028,0.00036035507],"domain_scores_gemma":[0.99915016,0.000084732965,0.00011913767,0.00036543212,0.00008408595,0.00019644182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013153307,0.00024242776,0.00020572222,0.00012799271,0.00020987332,0.0002060691,0.00060521404,0.00006310402,0.00013083554],"category_scores_gemma":[0.0000090814765,0.00022031524,0.00007430963,0.0004516207,0.000038915998,0.00042175376,0.00000869578,0.0003856766,0.000336139],"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":[0.000031222855,0.000039942784,0.0000419503,0.000040132778,0.00008895238,0.000019768833,0.021363126,0.9440136,0.0010393162,0.000046992634,0.00016280083,0.03311221],"study_design_scores_gemma":[0.00043529013,0.00037638724,0.00017123859,0.00016157309,0.00002689011,0.0000179654,0.00030893495,0.43345147,0.5490253,0.0000057790508,0.0155395,0.00047968357],"about_ca_topic_score_codex":0.000007095074,"about_ca_topic_score_gemma":0.000003118732,"teacher_disagreement_score":0.9203123,"about_ca_system_score_codex":0.00012230217,"about_ca_system_score_gemma":0.00015520821,"threshold_uncertainty_score":0.89841944},"labels":[],"label_agreement":null},{"id":"W3034607397","doi":"","title":"An Optimistic Perspective on Offline Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada); University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Perspective (graphical); Artificial intelligence; Reinforcement; Machine learning; Psychology; Social psychology","score_opus":0.04466082375581626,"score_gpt":0.3204855486435333,"score_spread":0.27582472488771703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034607397","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":[0.0010088803,0.000011194637,0.8987529,0.008804753,0.0003144306,0.00016790492,7.591048e-7,0.0004824117,0.09045677],"genre_scores_gemma":[0.987827,0.000032112835,0.0073091597,0.0023239984,0.0002710194,0.000014404633,0.000081317914,0.000032690317,0.0021083124],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970936,0.00024443452,0.00042013868,0.0008665926,0.0009925388,0.0003826787],"domain_scores_gemma":[0.9983172,0.00017684915,0.00033432158,0.0004445173,0.00044911046,0.00027802537],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035730118,0.00034040876,0.0002611411,0.00021656958,0.0003052919,0.0005476592,0.0017003585,0.00008654805,0.0008736206],"category_scores_gemma":[0.0012997789,0.00033519752,0.000103355516,0.0002624735,0.000057045876,0.00052894175,0.0002948053,0.0014518903,0.00059282896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007535339,0.000029187295,0.00048476923,0.000004593856,0.00004354318,0.000027346403,0.0016120665,0.74410737,0.00047593834,0.24999066,0.000020371515,0.0031287782],"study_design_scores_gemma":[0.00065690133,0.0020554631,0.00023886896,0.00004920723,0.000008156555,0.0000065083877,0.00047414863,0.9927591,0.00023477108,0.0003573168,0.0028104163,0.000349149],"about_ca_topic_score_codex":0.00006817735,"about_ca_topic_score_gemma":0.00000241486,"teacher_disagreement_score":0.9868181,"about_ca_system_score_codex":0.00025192264,"about_ca_system_score_gemma":0.00010221856,"threshold_uncertainty_score":0.99991},"labels":[],"label_agreement":null},{"id":"W3034724428","doi":"10.48550/arxiv.2003.00203","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Reuse; Transfer of learning; Artificial intelligence; Robustness (evolution); Task (project management); Context (archaeology); Machine learning; Policy learning; Dynamics (music); Engineering","score_opus":0.053756362553908234,"score_gpt":0.20865636249188882,"score_spread":0.1548999999379806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034724428","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":[0.022869911,0.00004565073,0.97087216,0.00024479703,0.00029400302,0.00048179034,0.0000012185802,0.00020671556,0.004983768],"genre_scores_gemma":[0.9970974,0.0001852206,0.0014111346,0.0002538487,0.00009168592,0.0000019896065,0.000025850853,0.000032351738,0.0009005368],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971969,0.0002825388,0.0005661861,0.0010891835,0.00026856604,0.00059663417],"domain_scores_gemma":[0.9981632,0.00017722578,0.00028238256,0.0009919584,0.00013582094,0.0002493813],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028956225,0.0004822157,0.000644569,0.0006576093,0.00012573793,0.00009566186,0.0022499994,0.00039185028,0.00004547639],"category_scores_gemma":[0.00013419728,0.0005717609,0.0002796871,0.0010821264,0.00016721874,0.0003635395,0.0016907667,0.001156598,0.00004165679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054324475,0.000032690547,0.0010314793,0.000104467355,0.00009331005,0.0002440495,0.0024490163,0.90811867,0.00032744935,0.08713876,0.000028414743,0.00037735605],"study_design_scores_gemma":[0.0011447973,0.00026976847,0.00028595814,0.00014699381,0.00003566492,0.0000039923143,0.00013850689,0.9941552,0.0006039543,0.0019227215,0.000733573,0.00055886584],"about_ca_topic_score_codex":0.0004976864,"about_ca_topic_score_gemma":0.000045542358,"teacher_disagreement_score":0.9742275,"about_ca_system_score_codex":0.00045458126,"about_ca_system_score_gemma":0.00037550338,"threshold_uncertainty_score":0.99967337},"labels":[],"label_agreement":null},{"id":"W3034739078","doi":"10.1109/isorc49007.2020.00033","title":"Context-based learning for autonomous vehicles","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Computer science; Context (archaeology); Artificial intelligence; Control (management); Deep learning; Machine learning; Human–computer interaction","score_opus":0.03608482396398357,"score_gpt":0.25076122593306166,"score_spread":0.21467640196907808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034739078","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":[0.00064606103,0.00001652884,0.9891127,0.0069063306,0.00009052004,0.0001839125,1.4275005e-7,0.00056573574,0.002478122],"genre_scores_gemma":[0.86276144,5.2873384e-7,0.13069639,0.0053810617,0.00005211129,0.000013734516,0.000002795405,0.00001007799,0.0010818643],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991915,0.000025709438,0.00016858382,0.00024816304,0.00014570434,0.00022031751],"domain_scores_gemma":[0.9994148,0.00017858489,0.00006951771,0.00016996791,0.000060700513,0.00010642676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012357706,0.000094927695,0.00011703807,0.000028375429,0.00012233322,0.00016191996,0.0005386285,0.000037376853,0.000034955374],"category_scores_gemma":[0.00020008061,0.000088492096,0.00006742905,0.00014225334,0.000020683518,0.00018171823,0.000097831806,0.00012353383,0.00010025009],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006512699,0.00000510728,0.0007025203,0.000018814504,0.000008298009,0.0000018919698,0.00029980953,0.9441964,0.00046092027,0.034058046,0.0019272177,0.018314458],"study_design_scores_gemma":[0.0004066781,0.00024599538,0.000121224635,0.0000041255676,0.000002661419,3.6005096e-7,0.00002556586,0.9027553,0.0029249163,0.000043341908,0.093357965,0.00011183171],"about_ca_topic_score_codex":0.0000048933425,"about_ca_topic_score_gemma":4.038255e-7,"teacher_disagreement_score":0.8621154,"about_ca_system_score_codex":0.000021095011,"about_ca_system_score_gemma":0.000076606535,"threshold_uncertainty_score":0.3608603},"labels":[],"label_agreement":null},{"id":"W3034833014","doi":"","title":"OPtions as REsponses: Grounding behavioural hierarchies in multi-agent reinforcement learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Ground; Reinforcement; Artificial intelligence; Cognitive psychology; Human–computer interaction; Cognitive science; Psychology; Engineering; Social psychology; Electrical engineering","score_opus":0.12890161320820673,"score_gpt":0.34831895195492124,"score_spread":0.2194173387467145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034833014","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":[0.042711016,0.000034387576,0.93841386,0.007590912,0.0004968829,0.00028366433,0.000001386864,0.00041556617,0.010052343],"genre_scores_gemma":[0.98164696,0.000116995456,0.011560422,0.0008189139,0.00006977585,0.000035842982,0.00006433506,0.000027257598,0.005659487],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970029,0.0004487997,0.000606654,0.0006194619,0.0008693262,0.0004528459],"domain_scores_gemma":[0.9988338,0.00023667066,0.0003139128,0.00024806053,0.0001651907,0.00020239888],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000619512,0.00031274036,0.00026367692,0.0004825984,0.00032074036,0.00062288955,0.0013497509,0.00008738273,0.00045874753],"category_scores_gemma":[0.0012508037,0.00032673706,0.000115260256,0.0004164879,0.00006786067,0.00071611063,0.00062540505,0.0016090111,0.0004605243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008918352,0.0000338953,0.03874375,0.000008929851,0.000028981995,0.00008371561,0.0030773585,0.84504104,0.0010017927,0.1089869,0.00001038328,0.0028940644],"study_design_scores_gemma":[0.00097585435,0.0005449527,0.00797199,0.00012019101,0.0000058374967,0.00001633863,0.000418385,0.9857543,0.0001348113,0.00014154767,0.0035765057,0.00033924993],"about_ca_topic_score_codex":0.00026857335,"about_ca_topic_score_gemma":0.000016676806,"teacher_disagreement_score":0.93893594,"about_ca_system_score_codex":0.00025769367,"about_ca_system_score_gemma":0.00013355965,"threshold_uncertainty_score":0.99991846},"labels":[],"label_agreement":null},{"id":"W3035417664","doi":"10.48550/arxiv.2006.07262","title":"A Brief Look at Generalization in Visual Meta-Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Overfitting; Generalization; Computer science; Artificial intelligence; Meta learning (computer science); Scalability; Machine learning; Realization (probability); Artificial neural network; Task (project management); Mathematics","score_opus":0.1025356039800561,"score_gpt":0.2165601146297081,"score_spread":0.114024510649652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035417664","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":[0.019113174,0.000053379226,0.97620285,0.00017212483,0.00032508373,0.00042308826,7.656787e-7,0.00033230713,0.0033772138],"genre_scores_gemma":[0.98979944,0.00017891312,0.0016622255,0.00032887558,0.00006231951,0.00000325524,0.00007949876,0.000031437765,0.007854058],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972419,0.00029361318,0.00043900797,0.0012740623,0.00025754524,0.0004938566],"domain_scores_gemma":[0.99828714,0.00008972201,0.0005111401,0.00077902887,0.0001278837,0.00020505571],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003331037,0.0004606237,0.00060240884,0.00038344387,0.00018827541,0.00019781559,0.001565722,0.00029344347,0.00017125174],"category_scores_gemma":[0.000095521646,0.0005375319,0.00034894925,0.0008676859,0.00007325014,0.0004680164,0.004707737,0.000891294,0.00021231668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019607247,0.000019745297,0.003166078,0.000070875205,0.0003278719,0.00021384301,0.00046629165,0.9574779,0.000053809297,0.038026463,0.00011934518,0.000038123853],"study_design_scores_gemma":[0.0005590867,0.00011440807,0.00034777957,0.000040206964,0.0002632499,0.0000023566488,0.000019458013,0.99408036,0.00019304603,0.0007019557,0.0031656034,0.0005124724],"about_ca_topic_score_codex":0.00017433095,"about_ca_topic_score_gemma":0.000036351597,"teacher_disagreement_score":0.97454065,"about_ca_system_score_codex":0.00070804637,"about_ca_system_score_gemma":0.00020780815,"threshold_uncertainty_score":0.99970764},"labels":[],"label_agreement":null},{"id":"W3035954878","doi":"10.48550/arxiv.2006.13169","title":"Experience Replay with Likelihood-free Importance Weights","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Estimator; Temporal difference learning; Suite; Key (lock); Baseline (sea); Bellman equation; Function (biology); Sample (material); Artificial intelligence; Prioritization; Machine learning; Mathematical optimization; Statistics; Mathematics","score_opus":0.05575956341198271,"score_gpt":0.18530986196650417,"score_spread":0.12955029855452146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035954878","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":[0.06584028,0.0000387658,0.9241699,0.0003420003,0.000467422,0.00035296322,0.0000042539214,0.0006034378,0.008180994],"genre_scores_gemma":[0.97623014,0.000102106555,0.021313593,0.00036217738,0.00010205766,0.0000025320664,0.000013758351,0.000034205696,0.0018394192],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968989,0.000096505275,0.00031770914,0.0018287194,0.00028049047,0.000577715],"domain_scores_gemma":[0.9952148,0.00009392775,0.00054244295,0.003599651,0.00019045513,0.00035871723],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00015464393,0.0004868865,0.0004439806,0.000174113,0.00021860722,0.00025762618,0.005408953,0.00026179315,0.000052385592],"category_scores_gemma":[0.000088869325,0.00049155374,0.00017124976,0.00085052673,0.00019702686,0.000672549,0.0044334806,0.0009617372,0.00013524406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004930642,0.00003499731,0.020517554,0.00008598699,0.00010725353,0.0015373481,0.0013933913,0.84457475,0.000022731705,0.13056591,0.0010318693,0.00007892094],"study_design_scores_gemma":[0.00078239257,0.00022943362,0.0023124914,0.00018952531,0.000060951894,0.000018409799,0.00013477926,0.9744287,0.00028551702,0.01779676,0.0027715364,0.0009894669],"about_ca_topic_score_codex":0.0000620624,"about_ca_topic_score_gemma":0.000023374338,"teacher_disagreement_score":0.91038984,"about_ca_system_score_codex":0.00023276647,"about_ca_system_score_gemma":0.00036169172,"threshold_uncertainty_score":0.9999723},"labels":[],"label_agreement":null},{"id":"W3035992805","doi":"10.1109/icra48506.2021.9560922","title":"LEAF: Latent Exploration Along the Frontier","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Artificial intelligence; State (computer science); Reachability; Oracle; Robot; Set (abstract data type); Key (lock); Machine learning; Frontier; Task (project management); State space; Theoretical computer science; Algorithm; Mathematics; Geography","score_opus":0.04681003592202214,"score_gpt":0.25875255073531644,"score_spread":0.2119425148132943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035992805","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":[0.00065827544,0.00019201738,0.98414487,0.0047586146,0.0026594044,0.00027373072,1.8483772e-7,0.00023264451,0.0070802704],"genre_scores_gemma":[0.7029554,0.00042669688,0.2626959,0.0020514224,0.00043157325,0.00013034508,0.00009580461,0.00004106165,0.031171737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830544,0.00013164018,0.00033256627,0.00049342815,0.0005005827,0.00023637236],"domain_scores_gemma":[0.99796736,0.00006214325,0.00019016984,0.0015743516,0.0001584114,0.000047576938],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00038248862,0.00021289366,0.00019878693,0.0000571232,0.00013974009,0.001197305,0.001607786,0.0001577378,0.000109524175],"category_scores_gemma":[0.000062352265,0.00014029563,0.00014086685,0.00014833998,0.000032827138,0.00048370048,0.002969682,0.0006221343,0.00012505069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.346733e-7,0.000008657369,0.00039768172,0.00001959423,0.00004195247,0.00000937708,0.0013290112,0.9818004,0.000010711683,0.0073475675,0.0053791497,0.0036553887],"study_design_scores_gemma":[0.000081629005,0.000017083883,0.0011304636,0.00006286087,0.000014792588,0.0000032659934,0.00014948126,0.992424,0.00038722495,0.0007152383,0.0047714603,0.00024248243],"about_ca_topic_score_codex":0.00013373651,"about_ca_topic_score_gemma":0.000030056071,"teacher_disagreement_score":0.72144896,"about_ca_system_score_codex":0.00007473109,"about_ca_system_score_gemma":0.00017194056,"threshold_uncertainty_score":0.99983954},"labels":[],"label_agreement":null},{"id":"W3037098147","doi":"","title":"Efficient Planning under Partial Observability with Unnormalized Q Functions and Spectral Learning","year":2019,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Reinforcement Learning in Robotics","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 Montréal; McGill University","funders":"","keywords":"Observability; Sample complexity; Reinforcement learning; Computer science; Observable; Artificial intelligence; Sample (material); Plan (archaeology); Mathematical optimization; Algorithm; Machine learning; Mathematics","score_opus":0.09226570585973484,"score_gpt":0.3228543093033689,"score_spread":0.23058860344363405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037098147","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":[0.109572,0.0000070500905,0.8862106,0.00044977618,0.00039132632,0.00014326822,0.000009033293,0.000062048304,0.0031549],"genre_scores_gemma":[0.97965795,0.000013722637,0.019559382,0.00010601401,0.000041747782,0.0000066385655,0.000017100072,0.000007836894,0.00058959966],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855083,0.000079596786,0.00030991767,0.00040479726,0.00041234627,0.00024250899],"domain_scores_gemma":[0.9990212,0.00034368687,0.0001324221,0.0001882476,0.00021747834,0.00009701591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028345778,0.0001668376,0.00015707947,0.000098718774,0.00016892607,0.00043096044,0.00027480235,0.000050249313,0.00019129491],"category_scores_gemma":[0.00013078099,0.00014628438,0.000018327873,0.00012466432,0.00015281727,0.00014101877,0.00012170226,0.00030260914,0.00007784873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006777837,0.000021949658,0.0028507481,0.00000527925,0.000017455886,0.0000055779556,0.00034764202,0.5224936,0.0001866392,0.4695868,0.0000055971054,0.0044109323],"study_design_scores_gemma":[0.00007719956,0.00043646514,0.0025257303,0.00004891422,0.000007684236,0.00001365979,0.0008986883,0.9867063,0.0002249702,0.008710685,0.00015985957,0.00018985156],"about_ca_topic_score_codex":0.000033298133,"about_ca_topic_score_gemma":0.0000129313285,"teacher_disagreement_score":0.87008595,"about_ca_system_score_codex":0.00004427375,"about_ca_system_score_gemma":0.00007781546,"threshold_uncertainty_score":0.5965304},"labels":[],"label_agreement":null},{"id":"W3037179286","doi":"10.65109/rtpw2660","title":"Improving Performance in Reinforcement Learning by Breaking Generalization in Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Generalization; Scalability; Artificial neural network; Machine learning","score_opus":0.01277579907890778,"score_gpt":0.21482141115209308,"score_spread":0.2020456120731853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037179286","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":[0.025995284,0.00004364802,0.97173107,0.0004391352,0.00010920733,0.00016136306,1.4208e-8,0.0001476361,0.00137263],"genre_scores_gemma":[0.9939251,0.000026488844,0.0045331293,0.0011871569,0.000046493402,0.000008915561,0.000009632074,0.000012066831,0.0002510501],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985412,0.00006526783,0.00041677163,0.0003265101,0.00025402842,0.00039624734],"domain_scores_gemma":[0.99955416,0.000033575474,0.00014061815,0.00017299785,0.00002594138,0.00007269641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026295404,0.00014494278,0.00014737812,0.00009814017,0.00007589744,0.00017424025,0.00049254845,0.000061629915,0.000020132242],"category_scores_gemma":[0.00006183114,0.00014909705,0.000020517326,0.00070944626,0.000013114479,0.0008498296,0.00031802795,0.00037253258,0.000008749965],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039439537,0.0000030344518,0.035669383,0.000015489879,0.0000014177463,0.0000034385953,0.00049145916,0.95232415,0.00026086107,0.000520713,0.000047586862,0.010658524],"study_design_scores_gemma":[0.00038095305,0.0001287072,0.0018321351,0.000018326413,9.349348e-7,0.000001409286,0.000024557794,0.9969071,0.0001772597,6.900903e-7,0.0003531919,0.00017470679],"about_ca_topic_score_codex":0.000116197785,"about_ca_topic_score_gemma":0.000008129242,"teacher_disagreement_score":0.9679298,"about_ca_system_score_codex":0.00009697538,"about_ca_system_score_gemma":0.000021516948,"threshold_uncertainty_score":0.6080001},"labels":[],"label_agreement":null},{"id":"W3037476194","doi":"10.1609/icaps.v30i1.6750","title":"Symbolic Plans as High-Level Instructions for Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":63,"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; Agencia Nacional de Investigación y Desarrollo","keywords":"Reinforcement learning; Computer science; Maximization; Task (project management); State (computer science); Action (physics); Artificial intelligence; Machine learning; Mathematical optimization; Programming language; Mathematics","score_opus":0.06793028415246624,"score_gpt":0.2946574244530109,"score_spread":0.22672714030054467,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037476194","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":[0.631974,0.000017726205,0.34088063,0.012548323,0.0009165037,0.00049085054,0.000009777928,0.0010173516,0.012144868],"genre_scores_gemma":[0.97727597,0.000009280958,0.021878233,0.00045593496,0.00006897823,0.00001698385,0.000007237454,0.000010793738,0.00027659026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987517,0.0000063784855,0.00032850323,0.00029223488,0.00042616457,0.00019502173],"domain_scores_gemma":[0.99907196,0.00008251376,0.00034326722,0.00007169991,0.0003472561,0.00008329513],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020610711,0.0001560623,0.00016993974,0.0001040279,0.00025954598,0.0003147045,0.0009181796,0.00007120496,0.000009760322],"category_scores_gemma":[0.00057549065,0.00012935261,0.000055504366,0.00017914422,0.000047824444,0.00031554722,0.00027641022,0.00031048807,0.000006213363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004665603,0.0000074188,0.0025123565,0.000053907454,0.00007931708,4.933848e-7,0.0019802367,0.6440079,0.010483215,0.34025434,0.00016203463,0.0004121316],"study_design_scores_gemma":[0.0004229061,0.00018981256,0.0008624433,0.00029015454,0.000011807507,0.000011329817,0.0005378793,0.98829466,0.008106588,0.00087050715,0.000259129,0.00014280819],"about_ca_topic_score_codex":0.000012234156,"about_ca_topic_score_gemma":9.037417e-8,"teacher_disagreement_score":0.34530202,"about_ca_system_score_codex":0.000032683947,"about_ca_system_score_gemma":0.000067588786,"threshold_uncertainty_score":0.52748466},"labels":[],"label_agreement":null},{"id":"W3037571487","doi":"","title":"Value Preserving State-Action Abstractions","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Value (mathematics); State (computer science); Action (physics); Programming language; Machine learning","score_opus":0.23789144969792853,"score_gpt":0.3741205699300081,"score_spread":0.13622912023207956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037571487","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":[0.00045895242,0.0000041590097,0.9844529,0.0057595014,0.00062669814,0.000104616876,0.000034079207,0.000101426784,0.0084576765],"genre_scores_gemma":[0.9311973,0.0001494539,0.0673078,0.0008695347,0.00011987141,0.000008015429,0.000022242695,0.000009185019,0.000316607],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864423,0.00005265069,0.0003645326,0.00033326162,0.00042043376,0.0001848655],"domain_scores_gemma":[0.9990258,0.00025015272,0.00014646995,0.00017086495,0.00026365186,0.00014305608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001442417,0.00013869964,0.000113731236,0.00007962517,0.00014601345,0.00053624925,0.00056719553,0.00004300163,0.0003368287],"category_scores_gemma":[0.0004273273,0.00014337021,0.000024663055,0.000118376774,0.00007549416,0.0004266227,0.00014996395,0.00025542098,0.00036605637],"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":[0.000025579198,0.000021411079,0.000034426947,0.000007740223,0.000018669194,0.00001222256,0.00070641516,0.12787585,0.0008141842,0.80146074,0.00033162616,0.06869115],"study_design_scores_gemma":[0.000020251782,0.00016739749,0.0002276003,0.000015841924,0.0000037435768,0.000004462065,0.00026213285,0.92397344,0.0020682507,0.07173079,0.0013803872,0.00014571256],"about_ca_topic_score_codex":0.000051409577,"about_ca_topic_score_gemma":0.000018255516,"teacher_disagreement_score":0.93073833,"about_ca_system_score_codex":0.000037368096,"about_ca_system_score_gemma":0.000074777025,"threshold_uncertainty_score":0.58464676},"labels":[],"label_agreement":null},{"id":"W3037719421","doi":"10.65109/gjmw6851","title":"Neural Replicator Dynamics: Multiagent Learning via Hedging Policy Gradients","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Softmax function; Reinforcement learning; Computer science; Nash equilibrium; Mathematical optimization; Replicator equation; Convergence (economics); Gradient descent; Best response; Regret; Margin (machine learning); Artificial intelligence; Artificial neural network; Applied mathematics; Mathematical economics; Mathematics; Machine learning; Economics","score_opus":0.017980739523340793,"score_gpt":0.2518673730577505,"score_spread":0.2338866335344097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037719421","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":[0.008428235,0.000012653834,0.97890496,0.0075033284,0.00017314694,0.00016779381,2.0361932e-7,0.00076565915,0.0040440066],"genre_scores_gemma":[0.9661419,0.000005452227,0.029567532,0.0030949234,0.00016101371,0.0000072663147,0.00000647984,0.000021796337,0.0009936497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99824774,0.00007588849,0.00031705052,0.0005427436,0.00035068992,0.00046585576],"domain_scores_gemma":[0.9989693,0.00006185264,0.00010038418,0.000512222,0.000054269225,0.0003019467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014579941,0.00018829582,0.0001775875,0.00011436854,0.0002170338,0.00022612691,0.0010615379,0.000050573668,0.000031021016],"category_scores_gemma":[0.0002957576,0.00018026725,0.00009342973,0.0006284575,0.00003578193,0.00041806852,0.0006984731,0.00035217634,0.0003430731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044785693,0.000015092612,0.010469866,0.000023497787,0.000024223185,0.000021832298,0.0014085813,0.93746805,0.0005712582,0.02250263,0.00026161756,0.027228892],"study_design_scores_gemma":[0.00023933881,0.00012166066,0.0011941771,0.0000057126053,0.000003393012,0.000009051289,0.000048266706,0.9953075,0.00031148279,0.00003581058,0.002522107,0.00020150695],"about_ca_topic_score_codex":0.000081401064,"about_ca_topic_score_gemma":0.000001472901,"teacher_disagreement_score":0.95771366,"about_ca_system_score_codex":0.00014370058,"about_ca_system_score_gemma":0.00004501594,"threshold_uncertainty_score":0.7351085},"labels":[],"label_agreement":null},{"id":"W3037828233","doi":"10.48550/arxiv.1904.11439","title":"META-Learning State-based Eligibility Traces for More Sample-Efficient\\n Policy Evaluation","year":2019,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Robustness (evolution); Machine learning; Temporal difference learning; Artificial intelligence; Q-learning; Sample (material); TRACE (psycholinguistics)","score_opus":0.2079463326522307,"score_gpt":0.28507339274908255,"score_spread":0.07712706009685186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037828233","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":[0.10700364,0.00011143107,0.88613355,0.0005257711,0.0010641584,0.004275801,0.00009422439,0.00032544025,0.00046600663],"genre_scores_gemma":[0.9876084,0.00008989858,0.0083598355,0.00020930203,0.0001411431,0.000023995124,0.000245711,0.00008940477,0.0032323457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99078226,0.0016484559,0.0011929137,0.0038298862,0.0009953522,0.0015511547],"domain_scores_gemma":[0.9883607,0.003204662,0.0022180863,0.0034016022,0.0023194756,0.0004954783],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0056108367,0.0012700612,0.0016238212,0.0012730393,0.00096236373,0.0007600882,0.0037848833,0.00068217254,0.00035019388],"category_scores_gemma":[0.0026349449,0.0014486173,0.0017631707,0.0023148914,0.00055935356,0.000732894,0.0018838254,0.0016962299,0.0002129556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024893117,0.00022057195,0.0032532811,0.00053356116,0.0013641935,0.000010098505,0.0011724958,0.9748872,0.000023768354,0.01714876,0.00003053433,0.0011065975],"study_design_scores_gemma":[0.0025810928,0.00048823105,0.001432939,0.00011186285,0.0040030982,0.0000012414547,0.00024811487,0.98520035,0.00023865448,0.0030967714,0.00129683,0.001300839],"about_ca_topic_score_codex":0.00070459174,"about_ca_topic_score_gemma":0.000016132868,"teacher_disagreement_score":0.88060474,"about_ca_system_score_codex":0.0020975345,"about_ca_system_score_gemma":0.003921904,"threshold_uncertainty_score":0.9987963},"labels":[],"label_agreement":null},{"id":"W3037941652","doi":"10.65109/hmve9255","title":"Gifting in Multi-Agent Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Function (biology); Reinforcement; Appropriation; Space (punctuation); Resource (disambiguation); Action (physics); Mechanism (biology); Property (philosophy); Error-driven learning; Artificial intelligence; Psychology; Social psychology","score_opus":0.06128900177664424,"score_gpt":0.27539004644848986,"score_spread":0.21410104467184563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037941652","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":[0.0012711387,0.000015439413,0.9845991,0.0016476014,0.000104937324,0.00015028441,1.2149567e-8,0.00031339398,0.011898099],"genre_scores_gemma":[0.9030835,0.000009807051,0.093157195,0.00175293,0.000027525177,0.000006552085,0.0000015657976,0.000009584084,0.0019513459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985965,0.000057706162,0.0003538336,0.00032268863,0.00032268747,0.00034658375],"domain_scores_gemma":[0.9994483,0.000057157657,0.00009902498,0.00022875887,0.000034307646,0.00013243493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027452814,0.00013097688,0.00014852881,0.000075606455,0.00008263332,0.00014225295,0.00065726327,0.000041062463,0.00009314403],"category_scores_gemma":[0.00026350343,0.00012590727,0.000045129636,0.00045331378,0.000014995597,0.00036450717,0.00049697654,0.00031997217,0.00040298307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015253729,0.000005607278,0.005717473,0.000011475346,0.000004729784,0.000014999702,0.0018896256,0.98456913,0.00033150765,0.0055026878,0.00010256786,0.0018486936],"study_design_scores_gemma":[0.00045212152,0.00009998434,0.0010207022,0.000014489221,0.0000011695251,0.000001159939,0.00013684407,0.9906121,0.00061798317,0.000004394727,0.0068823933,0.00015666445],"about_ca_topic_score_codex":0.000028938513,"about_ca_topic_score_gemma":0.0000020268094,"teacher_disagreement_score":0.9018124,"about_ca_system_score_codex":0.0000619057,"about_ca_system_score_gemma":0.00003766949,"threshold_uncertainty_score":0.5179666},"labels":[],"label_agreement":null},{"id":"W3037991458","doi":"","title":"What can I do here? A Theory of Affordances in Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Affordance; Reinforcement learning; Computer science; Markov decision process; Embodied cognition; Context (archaeology); Dual (grammatical number); Function (biology); Artificial intelligence; Human–computer interaction; Cognitive science; Markov process; Mathematics; Psychology","score_opus":0.03236714438760317,"score_gpt":0.26857640851696307,"score_spread":0.23620926412935989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037991458","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":[0.0020007018,0.0004304921,0.97870994,0.00088605925,0.0011851317,0.0004843009,2.6040522e-7,0.00020777358,0.016095323],"genre_scores_gemma":[0.9663422,0.00095575704,0.028379548,0.00034661658,0.00006566236,0.000043601172,0.000015243181,0.000026266844,0.0038250685],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970017,0.00026391106,0.0008462834,0.0007382817,0.0007166125,0.00043320507],"domain_scores_gemma":[0.9979261,0.00024368531,0.00064412295,0.0009649104,0.00010317997,0.000118006195],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00092933816,0.00037170784,0.0005893979,0.00026802256,0.000056760982,0.0005854834,0.0022127677,0.00021411467,0.000103702834],"category_scores_gemma":[0.00020738819,0.00034771988,0.00014458525,0.00040498693,0.00009147065,0.0005212282,0.003687158,0.0011961472,0.00002805442],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011013482,0.000009263737,0.0006608165,0.00021858727,0.000043618562,0.000013619448,0.005261922,0.87572324,0.00003929733,0.11310543,0.000045268545,0.0048678922],"study_design_scores_gemma":[0.0004957881,0.0003372681,0.00035558722,0.0013691377,0.00001890036,0.0000032868336,0.0034947353,0.9718924,0.0013114419,0.018901134,0.0011410969,0.00067923043],"about_ca_topic_score_codex":0.0000789523,"about_ca_topic_score_gemma":0.000017637962,"teacher_disagreement_score":0.9643415,"about_ca_system_score_codex":0.00015429944,"about_ca_system_score_gemma":0.00033297448,"threshold_uncertainty_score":0.9998975},"labels":[],"label_agreement":null},{"id":"W3037998275","doi":"10.65109/fyqq1225","title":"Inducing Cooperation through Reward Reshaping based on Peer Evaluations in Deep Multi-Agent Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Selfishness; Reinforcement learning; Computer science; Function (biology); Task (project management); Action (physics); Artificial intelligence; Dual (grammatical number); Action selection; Value (mathematics); Machine learning; Psychology; Social psychology; Engineering","score_opus":0.1017844746347217,"score_gpt":0.33307506315892255,"score_spread":0.23129058852420084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037998275","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":[0.0009745428,0.000012396879,0.9833703,0.007298609,0.00017642726,0.00046644933,8.1710226e-8,0.00026917324,0.0074320408],"genre_scores_gemma":[0.8611854,0.0000046411315,0.13079889,0.0069703157,0.000053028576,0.000036058005,0.000024961922,0.000017729542,0.0009090014],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997384,0.00023716816,0.00054789643,0.00052383495,0.0009382867,0.0003687873],"domain_scores_gemma":[0.998897,0.00017271149,0.00016270152,0.00040776626,0.00025351509,0.00010627236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009165278,0.00020385004,0.00019032824,0.00014227456,0.00028241685,0.0002987857,0.0005243205,0.00008615158,0.00017663074],"category_scores_gemma":[0.0014738216,0.00020046037,0.000059024318,0.0007700015,0.000024441726,0.00070008426,0.00021376174,0.00051874574,0.00025535587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008582948,0.000018302302,0.0007841267,0.000014018058,0.0000069964854,0.000005405937,0.004148105,0.9889019,0.00046292887,0.004527057,0.00026585924,0.00085669593],"study_design_scores_gemma":[0.0009930742,0.00030171135,0.00047795844,0.00006837654,0.0000057741954,4.5442098e-7,0.00019892464,0.99373186,0.0013898014,0.000008697166,0.0025894984,0.00023386575],"about_ca_topic_score_codex":0.000058195223,"about_ca_topic_score_gemma":0.000014789457,"teacher_disagreement_score":0.86021084,"about_ca_system_score_codex":0.000251518,"about_ca_system_score_gemma":0.00015436526,"threshold_uncertainty_score":0.8174537},"labels":[],"label_agreement":null},{"id":"W3038104799","doi":"10.1109/lcsys.2020.3005886","title":"To Share or Not to Share? Performance Guarantees and the Asymmetric Nature of Cross-Robot Experience Transfer","year":2020,"lang":"en","type":"preprint","venue":"IEEE Control Systems Letters","topic":"Reinforcement Learning in Robotics","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":"Dynamic Systems Analysis (Canada); Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Research Foundation","keywords":"Robot; Computer science; Robotics; Transfer of learning; Artificial intelligence; Tracking (education); Bayesian probability; Transfer (computing); Inverse; Mathematics","score_opus":0.025791384409374694,"score_gpt":0.28392171397009963,"score_spread":0.25813032956072496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038104799","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":[0.12725812,0.00034451875,0.85493433,0.010551955,0.0034429245,0.0031320322,0.00008002776,0.00017540513,0.00008070506],"genre_scores_gemma":[0.9839941,0.000023519335,0.0009314533,0.013907626,0.00041752573,0.0005084114,0.000005569665,0.00004599889,0.00016577433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550134,0.0002951685,0.0011014201,0.0012171363,0.0012367782,0.00064818404],"domain_scores_gemma":[0.99690163,0.0006514814,0.00033080517,0.001528074,0.00032236197,0.0002656477],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00080851465,0.00060672197,0.001207487,0.00039214132,0.00022464554,0.0012193207,0.0037495587,0.00038172328,0.000007511375],"category_scores_gemma":[0.00046645594,0.00042086403,0.0002456077,0.00090880564,0.0001988655,0.00039631582,0.0006649792,0.0013258017,0.00004505137],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005913564,0.000008966238,0.0006255523,0.00086711225,0.00015375877,0.000031295713,0.007497463,0.98282564,0.0053707273,0.00038714477,0.0012118525,0.00042911957],"study_design_scores_gemma":[0.0044856644,0.00037592073,0.009156404,0.0019958972,0.0000873888,0.000050668936,0.00015914065,0.97770965,0.0023313633,0.000002586742,0.0024775253,0.0011678076],"about_ca_topic_score_codex":0.00013400169,"about_ca_topic_score_gemma":0.0000038884123,"teacher_disagreement_score":0.856736,"about_ca_system_score_codex":0.00013015373,"about_ca_system_score_gemma":0.00011901616,"threshold_uncertainty_score":0.99982435},"labels":[],"label_agreement":null},{"id":"W3038500004","doi":"10.1007/s12652-021-03489-y","title":"A conceptual framework for externally-influenced agents: an assisted reinforcement learning review","year":2021,"lang":"en","type":"article","venue":"Journal of Ambient Intelligence and Humanized Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Conceptual framework; Process (computing); Heuristic; Interoperability","score_opus":0.07417532899007453,"score_gpt":0.34930266685967293,"score_spread":0.2751273378695984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038500004","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":[0.011310199,0.004981975,0.9824118,0.00027368354,0.00060558587,0.00025103948,1.9446205e-7,0.000052596566,0.0001128965],"genre_scores_gemma":[0.65771836,0.004768054,0.33386227,0.0030463892,0.00033899315,0.0000046249597,0.0000060332054,0.000027175593,0.00022811974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968866,0.00021968836,0.0013814768,0.00038875258,0.0006869277,0.0004365618],"domain_scores_gemma":[0.9962841,0.00052918843,0.0013910563,0.00039760687,0.0011695161,0.00022851973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001496708,0.00025539505,0.0005749363,0.00014510573,0.00044087932,0.00046388686,0.0009345219,0.00009000811,0.000071219634],"category_scores_gemma":[0.0011214794,0.00023795661,0.00023251252,0.00035409545,0.000098444776,0.00072514196,0.00037178057,0.0006543312,0.0000069832],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004434408,0.0001099476,0.00035797007,0.00039412692,0.00018625495,0.0001172765,0.0050214217,0.6928859,0.0005419934,0.21966392,0.00017217385,0.0805047],"study_design_scores_gemma":[0.0012441336,0.0034167462,0.0009807079,0.01524396,0.00024149372,0.00095874147,0.002580619,0.94732904,0.0059379344,0.005189305,0.015883679,0.0009936212],"about_ca_topic_score_codex":0.000003091461,"about_ca_topic_score_gemma":5.30849e-7,"teacher_disagreement_score":0.64854956,"about_ca_system_score_codex":0.00010174036,"about_ca_system_score_gemma":0.0001893441,"threshold_uncertainty_score":0.9703589},"labels":[],"label_agreement":null},{"id":"W3038915804","doi":"10.48550/arxiv.2007.02151","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Gradient method; Mathematical optimization; Mathematical economics; Artificial intelligence; Mathematics; Engineering; Structural engineering","score_opus":0.084019057565281,"score_gpt":0.22943373992515428,"score_spread":0.1454146823598733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3038915804","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":[0.0007936066,0.000009513629,0.993703,0.00069361343,0.00030796145,0.00062900316,0.0000059368426,0.00033295652,0.0035243884],"genre_scores_gemma":[0.7467031,0.000041473748,0.24070615,0.00041683982,0.00032829904,0.00001012463,0.00012176964,0.000038445705,0.011633849],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976386,0.00018496093,0.00031064072,0.0011039198,0.00023551722,0.0005264016],"domain_scores_gemma":[0.99798536,0.00025029515,0.00048034007,0.0007657353,0.00028931137,0.00022895081],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003725591,0.00041090953,0.00040751565,0.00034912926,0.00033128707,0.00024121799,0.0015315437,0.00020155165,0.000024183955],"category_scores_gemma":[0.00014632594,0.00043924438,0.00023387284,0.0005688369,0.000078486315,0.00034111697,0.0016690937,0.00069526065,0.000024202738],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035530647,0.000008258074,0.0002061186,0.00006777054,0.0001227015,0.000016856959,0.0004377372,0.57319534,0.000005650074,0.4256883,0.00010675187,0.000108999964],"study_design_scores_gemma":[0.0007231524,0.00033100144,0.00024516834,0.000054770426,0.000078305646,0.000004298919,0.00008274635,0.9799717,0.00004948191,0.013531376,0.004456535,0.00047146718],"about_ca_topic_score_codex":0.00027142893,"about_ca_topic_score_gemma":0.000006017784,"teacher_disagreement_score":0.75299686,"about_ca_system_score_codex":0.000501142,"about_ca_system_score_gemma":0.00075636775,"threshold_uncertainty_score":0.9998059},"labels":[],"label_agreement":null},{"id":"W3039671729","doi":"10.48550/arxiv.2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Counterfactual thinking; Reinforcement learning; Computer science; Coda; Representation (politics); Artificial intelligence; Set (abstract data type); Causal structure; Sequence (biology); Machine learning; State space; Mathematics","score_opus":0.2323526430308347,"score_gpt":0.23812963320514827,"score_spread":0.005776990174313573,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3039671729","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":[0.03362774,0.000009059688,0.96419954,0.000103803504,0.00084413425,0.000291215,0.0000665858,0.00030227008,0.00055564486],"genre_scores_gemma":[0.9865797,0.00004108387,0.012311967,0.00014064823,0.000067981855,1.4343576e-7,0.00051176775,0.000026262069,0.00032045646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976895,0.00012166641,0.00028571117,0.0013481328,0.00021357898,0.00034143068],"domain_scores_gemma":[0.99692804,0.0000919355,0.00043526807,0.0022286093,0.00014070881,0.00017546945],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018679813,0.00034586305,0.00031673882,0.0001650672,0.00015869511,0.00035887974,0.00462954,0.00025242378,0.000028040862],"category_scores_gemma":[0.00006634178,0.0004350323,0.00009101578,0.00042055408,0.00009993385,0.0009852996,0.007518952,0.0007052384,0.0000908151],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001706642,0.000016387325,0.0010514009,0.000058842576,0.000099301666,0.00011648186,0.00020211532,0.98558605,0.000030734598,0.012479092,0.00014377569,0.00019877654],"study_design_scores_gemma":[0.00036371007,0.00004576068,0.00025454132,0.00006878744,0.00008350177,0.0000030011886,0.00011024666,0.99742913,0.000027323877,0.0010468903,0.00015131808,0.0004157597],"about_ca_topic_score_codex":0.00020473838,"about_ca_topic_score_gemma":0.000031867985,"teacher_disagreement_score":0.95295197,"about_ca_system_score_codex":0.00069918,"about_ca_system_score_gemma":0.00043486225,"threshold_uncertainty_score":0.99981016},"labels":[],"label_agreement":null},{"id":"W3040403450","doi":"10.48550/arxiv.2007.03151","title":"Curriculum learning for multilevel budgeted combinatorial problems","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Heuristics; Reinforcement learning; Solver; Combinatorial optimization; Mathematical optimization; Computer science; Speedup; Graph; Theoretical computer science; Mathematics; Artificial intelligence","score_opus":0.08203876657349847,"score_gpt":0.2036334493881823,"score_spread":0.12159468281468384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040403450","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":[0.00939756,0.000017390823,0.9852147,0.00015700498,0.0025675937,0.0009883434,0.0000041187877,0.00074247137,0.000910795],"genre_scores_gemma":[0.9911285,0.000039034978,0.0070129833,0.000062754356,0.00022457259,0.000006483411,0.000067644345,0.000042876043,0.0014151725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734765,0.00017017618,0.0003519028,0.0013890906,0.00018166544,0.0005595328],"domain_scores_gemma":[0.99776345,0.0001824011,0.0005627643,0.0008781843,0.00035621825,0.00025695094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002943707,0.00044975162,0.0004906838,0.00020989249,0.00032103056,0.00028233524,0.0025400375,0.0004103517,0.000013391703],"category_scores_gemma":[0.00033322294,0.00054490776,0.00033795173,0.0004974668,0.00008772866,0.0003781104,0.002863952,0.0012725338,0.000105940344],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010273396,0.000043716343,0.0020560005,0.00018542814,0.00009214598,0.000038179314,0.0002780319,0.86808145,0.000024443983,0.12867415,0.0003751133,0.00014107843],"study_design_scores_gemma":[0.0013036064,0.00021005986,0.00012890779,0.00011400688,0.000069755806,0.0000013689473,0.00005383789,0.97969973,0.000044645654,0.013310982,0.004466144,0.0005969384],"about_ca_topic_score_codex":0.000090417794,"about_ca_topic_score_gemma":0.0000022052309,"teacher_disagreement_score":0.98173094,"about_ca_system_score_codex":0.00025693508,"about_ca_system_score_gemma":0.00026328815,"threshold_uncertainty_score":0.99970025},"labels":[],"label_agreement":null},{"id":"W3040829104","doi":"10.48550/arxiv.2007.03749","title":"Sharp Analysis of Smoothed Bellman Error Embedding","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Reinforcement learning; Embedding; Bellman equation; Artificial neural network; Function (biology); Representation (politics); Horizon; Computer science; Nonlinear system; Algorithm; Mathematics; Discrete mathematics; Applied mathematics; Mathematical optimization; Physics; Artificial intelligence; Quantum mechanics; Geometry","score_opus":0.1156203499844863,"score_gpt":0.22891043717233997,"score_spread":0.11329008718785367,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040829104","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":[0.02727165,0.00001971977,0.96562123,0.00017311132,0.00028392105,0.00018510067,0.000010421497,0.00023811749,0.006196751],"genre_scores_gemma":[0.99313396,0.000041725634,0.005486444,0.0001038584,0.000032120748,3.827913e-7,0.000038252365,0.000018432147,0.0011448261],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789697,0.00013295676,0.0003581114,0.0010890376,0.00019009458,0.00033282803],"domain_scores_gemma":[0.99732786,0.0001240118,0.0006388791,0.0015581261,0.00016989885,0.00018124416],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002288927,0.00032158213,0.0006798676,0.000809146,0.00012606084,0.000098632634,0.002944174,0.0002412245,0.00010574607],"category_scores_gemma":[0.000076718505,0.0003888193,0.0005794804,0.002564791,0.00010066917,0.00026702633,0.0032823365,0.0006324863,0.00005726325],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000096076765,0.000020931924,0.0029694608,0.000071424256,0.0011164168,0.00008938624,0.00045924657,0.94320464,0.000028428689,0.05189941,0.00007591953,0.000055136177],"study_design_scores_gemma":[0.00020333778,0.000044184646,0.0017625014,0.00006203567,0.0009795061,4.262177e-7,0.00006597821,0.9949796,0.00008806476,0.0011633534,0.0002993123,0.00035165084],"about_ca_topic_score_codex":0.00010435679,"about_ca_topic_score_gemma":0.000014780073,"teacher_disagreement_score":0.96586233,"about_ca_system_score_codex":0.00015860389,"about_ca_system_score_gemma":0.00012005625,"threshold_uncertainty_score":0.99985635},"labels":[],"label_agreement":null},{"id":"W3040979139","doi":"10.48550/arxiv.2007.06184","title":"Efficient Planning in Large MDPs with Weak Linear Function Approximation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Markov decision process; Bellman equation; Oracle; Mathematical optimization; Computer science; Computation; Function (biology); Set (abstract data type); Time horizon; State (computer science); Core (optical fiber); Approximation algorithm; Expected value; Markov process; Algorithm; Mathematics","score_opus":0.06112267459238138,"score_gpt":0.19371696036882993,"score_spread":0.13259428577644855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040979139","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":[0.080325104,0.000013449934,0.91587293,0.00008080854,0.00030156848,0.00033649884,0.0000018088865,0.00027294245,0.0027948918],"genre_scores_gemma":[0.9931456,0.000006140441,0.006246763,0.000077083285,0.000056734916,0.0000012755663,0.00003359764,0.000018302586,0.0004145285],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825174,0.00011173875,0.00021850505,0.00089506106,0.00017253176,0.00035040628],"domain_scores_gemma":[0.9987444,0.000060137678,0.00030106868,0.000689603,0.000093751245,0.00011101168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000272104,0.00026963555,0.0002671098,0.00031535776,0.000117350544,0.00010504937,0.0009059134,0.00020354449,0.000010725703],"category_scores_gemma":[0.00003570544,0.0002928396,0.000077960554,0.0008397048,0.000038139704,0.00018094774,0.0011597861,0.0008251055,0.00008684491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053535958,0.000038490878,0.0054740165,0.00007778331,0.000030302086,0.00010075481,0.000490893,0.9543699,0.000009928704,0.039287917,0.000029549592,0.00003693064],"study_design_scores_gemma":[0.00068474177,0.00012242474,0.0035685888,0.00018050855,0.000030126615,0.0000017090213,0.00015070333,0.99413276,0.00001868033,0.0005212853,0.00027113207,0.00031731487],"about_ca_topic_score_codex":0.000022405307,"about_ca_topic_score_gemma":0.000005107099,"teacher_disagreement_score":0.91282046,"about_ca_system_score_codex":0.00023928922,"about_ca_system_score_gemma":0.00014891522,"threshold_uncertainty_score":0.9999524},"labels":[],"label_agreement":null},{"id":"W3041568888","doi":"10.48550/arxiv.2007.06049","title":"An Equivalence between Loss Functions and Non-Uniform Sampling in Experience Replay","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Equivalence (formal languages); Reinforcement learning; Function (biology); Mathematics; Computer science; Algorithm; Applied mathematics; Statistics; Discrete mathematics; Artificial intelligence","score_opus":0.13083770781811202,"score_gpt":0.2445806165634153,"score_spread":0.11374290874530327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041568888","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":[0.32996726,0.000006645383,0.6686628,0.000056473025,0.00019701899,0.00017988497,0.0000042862166,0.00014303137,0.00078262767],"genre_scores_gemma":[0.9906296,0.00008242221,0.008809366,0.000058807305,0.00007641125,0.0000015296229,0.000019390976,0.000016731929,0.0003057176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99771005,0.000081516824,0.00029848053,0.0013468266,0.00014378346,0.0004193533],"domain_scores_gemma":[0.99790704,0.00014963686,0.0002603363,0.0013190031,0.000086252614,0.0002777162],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002586107,0.00031158523,0.00034987179,0.00027859327,0.00020848628,0.00024637504,0.0019641249,0.00023901396,0.00001270957],"category_scores_gemma":[0.000069169975,0.00038663237,0.000077873,0.00075344584,0.00018112648,0.0009569177,0.0024716188,0.0008577104,0.000036490695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000835211,0.000013937363,0.0952823,0.000054265343,0.000017074386,0.00013539386,0.0014415852,0.8971105,0.000040871597,0.0056527187,0.0000058718606,0.00023713331],"study_design_scores_gemma":[0.0002989263,0.000120187724,0.02176746,0.00014132063,0.00002451639,0.0000048543916,0.000393633,0.97434103,0.000053383123,0.0022805317,0.00010371638,0.00047042908],"about_ca_topic_score_codex":0.0001664704,"about_ca_topic_score_gemma":0.000013433815,"teacher_disagreement_score":0.66066235,"about_ca_system_score_codex":0.00019633607,"about_ca_system_score_gemma":0.00015820394,"threshold_uncertainty_score":0.99985856},"labels":[],"label_agreement":null},{"id":"W3041828093","doi":"10.24963/ijcai.2020/706","title":"On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Montréal; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Samsung; Institut de Valorisation des Données; Waalse Gewest","keywords":"Overfitting; Observability; Reinforcement learning; Term (time); Context (archaeology); Representation (politics); Computer science; Artificial intelligence; State (computer science); Mathematics; Applied mathematics; Algorithm; Artificial neural network","score_opus":0.04988424548801556,"score_gpt":0.2554322823185893,"score_spread":0.2055480368305737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3041828093","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":[0.39616045,0.0000073689753,0.59423745,0.0018794416,0.000076652395,0.0003238435,7.3772e-8,0.00026129026,0.007053432],"genre_scores_gemma":[0.9894902,0.00000573568,0.009221252,0.0010037955,0.00003211116,0.000008826773,0.000002248651,0.000012995429,0.00022279772],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798816,0.000081700855,0.00043957448,0.0005592866,0.00051386654,0.00041740795],"domain_scores_gemma":[0.99884075,0.00040752706,0.00017341517,0.00034249655,0.00004807021,0.00018773926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053833047,0.00021800847,0.00024264616,0.00005948682,0.00012197071,0.0002420723,0.0003945359,0.00006413305,0.00007419045],"category_scores_gemma":[0.0005398792,0.0001784829,0.00003443185,0.0003821998,0.00005358955,0.0004909723,0.00028258565,0.0004957847,0.00004643618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051057857,0.000017525717,0.025971895,0.000039282324,0.000012033981,0.000019366698,0.0011637937,0.95968926,0.00008041883,0.01118461,0.000029881023,0.001740891],"study_design_scores_gemma":[0.0008422212,0.0009699839,0.037828293,0.00005993433,0.0000046580976,0.0000027776555,0.0001227762,0.9588709,0.0005785395,0.00007927073,0.0003936496,0.00024703474],"about_ca_topic_score_codex":0.000067674606,"about_ca_topic_score_gemma":0.0000071121485,"teacher_disagreement_score":0.5933298,"about_ca_system_score_codex":0.00007330739,"about_ca_system_score_gemma":0.00007586779,"threshold_uncertainty_score":0.7278321},"labels":[],"label_agreement":null},{"id":"W3045293119","doi":"10.48550/arxiv.2007.10916","title":"On the Convergence of Reinforcement Learning with Monte Carlo Exploring Starts","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Convergence (economics); Mathematical optimization; Bellman equation; Monte Carlo method; Computer science; Complement (music); Markov decision process; Function (biology); Stochastic approximation; Applied mathematics; Mathematics; Markov process; Artificial intelligence; Economics","score_opus":0.1503308442699026,"score_gpt":0.18248930565484367,"score_spread":0.03215846138494108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045293119","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":[0.17582498,0.00001019049,0.8207959,0.00021376432,0.00030771302,0.00034980557,7.947392e-7,0.00016513777,0.0023316978],"genre_scores_gemma":[0.9977723,0.00013843537,0.0006186785,0.00011509854,0.000028285998,0.0000032599953,0.0000028577308,0.000021568992,0.0012995356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980998,0.00016636428,0.00028089256,0.00079960085,0.000299866,0.00035349771],"domain_scores_gemma":[0.997648,0.0002747392,0.00054628577,0.0012059875,0.00018849314,0.0001364936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027438987,0.00034052707,0.0003454337,0.00014663837,0.00020846703,0.00009308876,0.002052031,0.00010297991,0.00004381278],"category_scores_gemma":[0.00010528796,0.0002853318,0.00014727912,0.00054006,0.00014401751,0.00033983722,0.001924921,0.0010399197,0.000051605188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004425055,0.000008933722,0.0013388455,0.00006488892,0.000103046004,0.00009035808,0.0009983582,0.8764602,0.000014052949,0.12078076,0.000068590874,0.000027701106],"study_design_scores_gemma":[0.000273838,0.00038163335,0.0002793435,0.00026355335,0.00004569818,9.799659e-7,0.0003136515,0.99674356,0.00041321758,0.0006468667,0.0003128876,0.0003247713],"about_ca_topic_score_codex":0.00013670327,"about_ca_topic_score_gemma":0.000005309287,"teacher_disagreement_score":0.8219473,"about_ca_system_score_codex":0.00016656192,"about_ca_system_score_gemma":0.00018880775,"threshold_uncertainty_score":0.9999599},"labels":[],"label_agreement":null},{"id":"W3046590403","doi":"10.1016/j.ibmed.2024.100137","title":"Reinforcement learning in large, structured action spaces: A simulation study of decision support for spinal cord injury rehabilitation","year":2024,"lang":"en","type":"article","venue":"Intelligence-Based Medicine","topic":"Reinforcement Learning in Robotics","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":"Parkwood Institute; Lawson Health Research Institute; Western University","funders":"","keywords":"Rehabilitation; Reinforcement; Reinforcement learning; Spinal cord injury; Action (physics); Physical medicine and rehabilitation; Psychology; Spinal cord; Computer science; Medicine; Artificial intelligence; Neuroscience; Social psychology","score_opus":0.05463180441145013,"score_gpt":0.39976203145658495,"score_spread":0.34513022704513485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046590403","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":[0.06275293,0.000049628463,0.93452847,0.00025368755,0.000962628,0.0012470311,6.815404e-7,0.00014051238,0.00006442978],"genre_scores_gemma":[0.98473597,0.00000922272,0.01485448,0.00006245957,0.00010011276,0.000065009546,0.000025328372,0.000017826538,0.00012958661],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973195,0.00011659319,0.0009693058,0.00048790837,0.0008029726,0.00030372426],"domain_scores_gemma":[0.9975431,0.0013935259,0.0002739761,0.00041510002,0.00029887073,0.00007545685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017011781,0.00021153342,0.00032628336,0.0008432833,0.00008895335,0.000064049265,0.0003714508,0.00009621832,0.00007726632],"category_scores_gemma":[0.0016634194,0.00017906495,0.000069871916,0.001096912,0.000063691856,0.00039468257,0.00006930427,0.00031808313,0.000008208588],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081890443,0.00006973951,0.0010840119,0.00023419027,0.000014488896,0.0000064564356,0.0022073227,0.85860974,0.00023120377,0.0017604424,0.000037764432,0.13492574],"study_design_scores_gemma":[0.00072764105,0.023515917,0.0011964039,0.0006857569,0.000029122752,0.0000011553775,0.0019329559,0.9682125,0.0007612547,0.0009398732,0.0018431137,0.00015433665],"about_ca_topic_score_codex":0.00006843692,"about_ca_topic_score_gemma":0.00004075117,"teacher_disagreement_score":0.92198306,"about_ca_system_score_codex":0.0002586713,"about_ca_system_score_gemma":0.00019276564,"threshold_uncertainty_score":0.73020566},"labels":[],"label_agreement":null},{"id":"W3047253995","doi":"10.1109/lwc.2020.3045005","title":"Faded-Experience Trust Region Policy Optimization for Model-Free Power Allocation in Interference Channel","year":2020,"lang":"en","type":"preprint","venue":"IEEE Wireless Communications Letters","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Memorization; Convergence (economics); Computer science; Interference (communication); Channel (broadcasting); Power (physics); Control (management); Artificial intelligence; Telecommunications; Mathematics; Economics","score_opus":0.07360881230310362,"score_gpt":0.30746428122084635,"score_spread":0.23385546891774273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047253995","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":[0.0019972925,0.000046205212,0.92406887,0.071639374,0.00041406445,0.0011869001,0.000012169319,0.00032166805,0.0003134311],"genre_scores_gemma":[0.8078355,0.0003790367,0.18722068,0.0033327476,0.000066370405,0.0009084496,0.00015925955,0.00005134724,0.000046574023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705976,0.00025534473,0.0009093373,0.0008916764,0.00039271795,0.00049114146],"domain_scores_gemma":[0.99231535,0.00024409422,0.0007272979,0.00631313,0.0002683004,0.00013183148],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00029392279,0.0004602508,0.00046943777,0.0006213177,0.0002942366,0.00046453648,0.010670396,0.00031631408,0.0000012807681],"category_scores_gemma":[0.00029436138,0.00055558933,0.0001700187,0.00082030846,0.00027355234,0.000720596,0.0039932104,0.0010776304,0.000007678871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013634461,0.00005275798,0.000036259677,0.00007440855,0.000022622395,0.0000012044109,0.007653694,0.9747513,0.00053692015,0.015523398,0.0007864839,0.0005473295],"study_design_scores_gemma":[0.00045423408,0.000039834074,0.000042392585,0.00032001908,0.000011697525,0.0000033320619,0.00011266192,0.99710137,0.00029481572,0.0010009542,0.00011151087,0.00050719036],"about_ca_topic_score_codex":0.00018469503,"about_ca_topic_score_gemma":0.000025159432,"teacher_disagreement_score":0.8058382,"about_ca_system_score_codex":0.00061796,"about_ca_system_score_gemma":0.00038986828,"threshold_uncertainty_score":0.9996896},"labels":[],"label_agreement":null},{"id":"W3072315125","doi":"10.1073/pnas.1907370117","title":"Fast reinforcement learning with generalized policy updates","year":2020,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Artificial intelligence; Machine learning; Generalization; Exploit; Mathematics","score_opus":0.03975041601643639,"score_gpt":0.28852758406207973,"score_spread":0.24877716804564334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3072315125","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":[0.4610352,0.0002539772,0.12346259,0.24717335,0.00011650923,0.0019661766,0.000005298393,0.00060777296,0.16537914],"genre_scores_gemma":[0.97648174,0.000016724789,0.021611523,0.001473641,0.0000822487,0.000004844334,9.7865154e-8,0.0000039190054,0.0003252908],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976212,0.000008244897,0.00032817398,0.00026998008,0.0015666264,0.00020577446],"domain_scores_gemma":[0.9990275,0.000059214017,0.00056783203,0.00001103851,0.00027000502,0.00006441613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006320578,0.000112347094,0.00015422306,0.00014633876,0.00025102263,0.000093611445,0.0019518046,0.00004351865,0.000009302796],"category_scores_gemma":[0.00052289176,0.000070396134,0.000054758824,0.0015968034,0.00044303737,0.0008462062,0.00047016458,0.00021467099,0.000003881366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008447074,0.0000052223454,0.002208882,0.000033994413,0.000015182869,8.465909e-9,0.0006487586,0.68963706,0.02221732,0.28472248,0.00030322385,0.0001994134],"study_design_scores_gemma":[0.00047233023,0.00034097323,0.0056860726,0.00009385088,0.000009927547,0.000008041959,0.0001802359,0.83713716,0.14947046,0.0047195,0.0016776354,0.00020382684],"about_ca_topic_score_codex":0.0000062581953,"about_ca_topic_score_gemma":6.5637273e-9,"teacher_disagreement_score":0.51544654,"about_ca_system_score_codex":0.000034679248,"about_ca_system_score_gemma":0.00008320865,"threshold_uncertainty_score":0.3626971},"labels":[],"label_agreement":null},{"id":"W3080779222","doi":"10.48550/arxiv.2008.11329","title":"Inverse Policy Evaluation for Value-based Sequential Decision-making","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Value (mathematics); Inverse; Computer science; Operations research; Mathematics; Machine learning","score_opus":0.14822902897177312,"score_gpt":0.27112859961845015,"score_spread":0.12289957064667703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080779222","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":[0.01020495,0.000008924301,0.98584175,0.00039251836,0.0009707796,0.0009965458,0.000010506429,0.00030346497,0.0012705451],"genre_scores_gemma":[0.9384265,0.000009679827,0.060485877,0.0006064738,0.00024767572,0.0000044234043,0.000043245243,0.00002904049,0.00014710527],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747133,0.00023424134,0.00031737468,0.0012119622,0.00034723684,0.00041786992],"domain_scores_gemma":[0.9971699,0.00048703045,0.0004872429,0.0012332952,0.0004418734,0.00018067578],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007062806,0.00035040465,0.000334063,0.000512802,0.000249167,0.00027968132,0.0021833235,0.00031152205,0.000042078053],"category_scores_gemma":[0.0009296778,0.00043770098,0.00035941397,0.00084727077,0.000082760744,0.00038947805,0.0017426858,0.0004978586,0.00011825096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051979387,0.000017741111,0.00017262288,0.00006899966,0.00005990549,0.000031193373,0.00013274851,0.91339254,0.00002005253,0.08405707,0.0004343551,0.0015608],"study_design_scores_gemma":[0.00090901385,0.000086897264,0.00012846367,0.00018360977,0.0001332608,8.5951416e-7,0.000017956758,0.934539,0.000048320497,0.063020445,0.0005403833,0.00039174638],"about_ca_topic_score_codex":0.000050902778,"about_ca_topic_score_gemma":0.000007491214,"teacher_disagreement_score":0.9282215,"about_ca_system_score_codex":0.0009351178,"about_ca_system_score_gemma":0.0018308671,"threshold_uncertainty_score":0.9998075},"labels":[],"label_agreement":null},{"id":"W3081310128","doi":"10.3390/electronics9091363","title":"A Survey of Multi-Task Deep Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Electronics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Forgetting; Deep learning; Transfer of learning; Task (project management); Active learning (machine learning); Machine learning; Engineering","score_opus":0.030447156903129203,"score_gpt":0.26008836771618027,"score_spread":0.22964121081305106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081310128","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":[0.0014392412,0.0012878027,0.9960057,0.00026465344,0.00007300463,0.00015346809,1.501246e-7,0.00015958422,0.00061635685],"genre_scores_gemma":[0.9895111,0.0002485661,0.009437524,0.000379784,0.000021362126,0.000005022069,0.000016651704,0.000017399525,0.00036259796],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982764,0.00015519117,0.00038540666,0.00030920215,0.00039963104,0.00047417413],"domain_scores_gemma":[0.99897975,0.00013089384,0.00024824298,0.0003570538,0.00016010995,0.00012396705],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000482457,0.0001580715,0.00022938623,0.00005419665,0.000092101225,0.00006429689,0.00090558,0.00006419059,0.00002447252],"category_scores_gemma":[0.0005540651,0.00016290358,0.00006416405,0.0006179765,0.000031330983,0.0002205878,0.00030823846,0.0004390373,0.00008331942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009056734,0.000011141992,0.0024876408,0.000018666215,0.000033234435,0.000002102329,0.0008525922,0.98825043,0.000827658,0.0024157502,0.00010243808,0.0049893125],"study_design_scores_gemma":[0.00042123935,0.0005545322,0.0022231676,0.0000068021914,0.000005804539,0.0000012681843,0.000010426885,0.9864545,0.0018674061,0.000008144958,0.008278321,0.00016839245],"about_ca_topic_score_codex":0.000024309333,"about_ca_topic_score_gemma":0.000020188085,"teacher_disagreement_score":0.98807186,"about_ca_system_score_codex":0.00008095564,"about_ca_system_score_gemma":0.00019520157,"threshold_uncertainty_score":0.6643016},"labels":[],"label_agreement":null},{"id":"W3083684068","doi":"10.2139/ssrn.4059578","title":"Visualizing the Loss Landscape of Actor Critic Methods with Applications in Inventory Optimization","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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":"McGill University; University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.012929530973607517,"score_gpt":0.30265001198992164,"score_spread":0.28972048101631415,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083684068","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":[0.0031903523,0.00054719223,0.9953893,0.0004005805,0.000053887903,0.00014457775,1.751305e-7,0.00001911367,0.00025484254],"genre_scores_gemma":[0.9623327,0.0002370832,0.037005667,0.000085684704,0.000039251147,0.000043990545,0.0000028724858,0.000014087393,0.00023865343],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982428,0.0003931855,0.00024525137,0.00013178855,0.00032374787,0.0006632472],"domain_scores_gemma":[0.9993138,0.00014083456,0.00021296782,0.00024738174,0.000057845056,0.000027171121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024102477,0.00007938903,0.000109536646,0.0001546585,0.00030744504,0.000054007116,0.0008053372,0.000017105915,0.000017634957],"category_scores_gemma":[0.000038303955,0.000058075835,0.000038492046,0.0006489047,0.00003503357,0.00021064028,0.00015520827,0.0010735563,5.520178e-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":[0.0000052254154,0.000021588696,0.0024766065,0.000003554945,0.000022027487,5.835941e-7,0.00049391267,0.8451501,0.000038314425,0.15074392,0.000003975975,0.0010401768],"study_design_scores_gemma":[0.00045920152,0.00038270728,0.00026287526,0.000011290029,0.000018299947,0.00019054223,0.002938284,0.983807,0.00008669184,0.0107326945,0.0009780573,0.00013235406],"about_ca_topic_score_codex":0.000012066706,"about_ca_topic_score_gemma":0.000014086167,"teacher_disagreement_score":0.9591424,"about_ca_system_score_codex":0.00040412438,"about_ca_system_score_gemma":0.00095039466,"threshold_uncertainty_score":0.46641272},"labels":[],"label_agreement":null},{"id":"W3087873943","doi":"10.48550/arxiv.2009.11997","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Task (project management); Computer science; Artificial intelligence; Machine learning; Control (management); Dynamics (music); Plan (archaeology); State (computer science); Robot; Engineering","score_opus":0.06297797963901723,"score_gpt":0.1813221165108317,"score_spread":0.11834413687181446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3087873943","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":[0.0062298533,0.00001680804,0.98473704,0.00020377025,0.00023447217,0.00042398003,9.947482e-7,0.0006789485,0.0074741547],"genre_scores_gemma":[0.9808407,0.000031558888,0.013935749,0.00037416973,0.00008011381,0.0000021632825,0.000046735702,0.00004380629,0.0046450337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734735,0.00014577946,0.00031474823,0.0013240548,0.00027661413,0.00059141964],"domain_scores_gemma":[0.99761254,0.00011934682,0.0005272669,0.001199516,0.00023542691,0.000305936],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002451865,0.00051833823,0.000496871,0.00020060745,0.00024154407,0.00028507956,0.002274841,0.0003270148,0.000028398485],"category_scores_gemma":[0.000048234386,0.0005571356,0.00020807423,0.0005819375,0.00014434617,0.00035191394,0.0020432028,0.0016707462,0.00009997964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067030494,0.000016301758,0.0012759317,0.00006733643,0.0001025592,0.00022580317,0.00021345934,0.96004915,0.0000053796066,0.037653487,0.00020968303,0.00011386828],"study_design_scores_gemma":[0.00090245827,0.00026584908,0.00005260227,0.00016671041,0.00009285304,0.0000019902473,0.000037578546,0.99645364,0.00004391177,0.0006774557,0.00064338325,0.0006615485],"about_ca_topic_score_codex":0.000030444808,"about_ca_topic_score_gemma":0.000004852947,"teacher_disagreement_score":0.9746108,"about_ca_system_score_codex":0.00028460557,"about_ca_system_score_gemma":0.00052335084,"threshold_uncertainty_score":0.999688},"labels":[],"label_agreement":null},{"id":"W3089723243","doi":"","title":"Learning Intrinsic Rewards as a Bi-Level Optimization Problem","year":2020,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Intrinsic motivation; Mathematical optimization; Mathematics; Psychology; Social psychology","score_opus":0.06927971827994504,"score_gpt":0.29235963903827544,"score_spread":0.22307992075833039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089723243","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":[0.0017441077,0.000026188905,0.9894383,0.004360224,0.00025217902,0.0004057195,7.745625e-7,0.00035664046,0.0034158616],"genre_scores_gemma":[0.87512684,0.00006660161,0.12310248,0.0012452804,0.00015427345,0.000032371507,0.000013197925,0.00002597584,0.000232998],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99717504,0.00020559815,0.00079756265,0.0006971014,0.00057220383,0.00055248995],"domain_scores_gemma":[0.9986991,0.00022883051,0.00024812508,0.00039802745,0.00021872524,0.00020714405],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00059359445,0.00026743743,0.00028843607,0.00022525236,0.00019228098,0.0003696927,0.0012260439,0.00013690312,0.00016362652],"category_scores_gemma":[0.0014169761,0.00027911065,0.00008541073,0.0017511689,0.0001121979,0.0005606853,0.0004332732,0.0006762156,0.0006226582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029797087,0.000026498941,0.00013916391,0.000019508203,0.000008003498,0.000025260935,0.004339095,0.87366813,0.00015487506,0.053313013,0.000035262747,0.06824138],"study_design_scores_gemma":[0.00005195508,0.0003956192,0.000017492499,0.000061402985,0.00000448466,0.000005598848,0.000560008,0.99076337,0.0021182273,0.004667889,0.0010343521,0.00031961416],"about_ca_topic_score_codex":0.00026137644,"about_ca_topic_score_gemma":0.000030173753,"teacher_disagreement_score":0.8733827,"about_ca_system_score_codex":0.00017400827,"about_ca_system_score_gemma":0.00022692952,"threshold_uncertainty_score":0.9999661},"labels":[],"label_agreement":null},{"id":"W3090658167","doi":"10.1109/ijcnn48605.2020.9207473","title":"Automatic Policy Decomposition through Abstract State Space Dynamic Specialization","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Computer science; Bottleneck; State space; Artificial intelligence; State (computer science); Q-learning; Space (punctuation); Bellman equation; Decomposition; Function (biology); Macro; Action (physics); Machine learning; Mathematical optimization; Algorithm; Mathematics","score_opus":0.018410848227613713,"score_gpt":0.3002906061636799,"score_spread":0.28187975793606623,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090658167","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":[0.0057182345,0.000006683702,0.97004044,0.009433285,0.00013278455,0.00016610416,7.013809e-7,0.0005418412,0.013959936],"genre_scores_gemma":[0.871002,0.000023818095,0.12614672,0.0022351188,0.000094574265,0.0000029592322,0.000014241898,0.000014116884,0.00046645777],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989144,0.000031462478,0.00026141407,0.00025454012,0.00030533367,0.00023284857],"domain_scores_gemma":[0.9994045,0.00004652914,0.00013849803,0.00027187183,0.00004947866,0.00008916189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007227125,0.00012725264,0.00012296482,0.00005884446,0.000097322576,0.0002731488,0.00046927648,0.000035648212,0.00017794054],"category_scores_gemma":[0.00006769437,0.00012363117,0.000044049106,0.0005371169,0.000022426546,0.0008614155,0.00014580016,0.000101755526,0.0005528627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023965422,0.000016401977,0.000091906346,0.000045908448,0.000017294095,0.000009754748,0.0032637906,0.92530763,0.0010456695,0.06058619,0.0011855976,0.00842746],"study_design_scores_gemma":[0.00017453027,0.00007005287,0.003154871,0.000013337342,0.0000029641167,0.0000034921343,0.000016399807,0.99232745,0.00067636213,0.0013746896,0.002040322,0.00014550694],"about_ca_topic_score_codex":0.00005531569,"about_ca_topic_score_gemma":0.000008421244,"teacher_disagreement_score":0.8652838,"about_ca_system_score_codex":0.00010906237,"about_ca_system_score_gemma":0.00009288621,"threshold_uncertainty_score":0.7106116},"labels":[],"label_agreement":null},{"id":"W3090693621","doi":"10.1109/ccta41146.2020.9206397","title":"Reinforcement Learning in Deep Structured Teams: Initial Results with Finite and Infinite Valued Features","year":2020,"lang":"en","type":"article","venue":"2020 IEEE Conference on Control Technology and Applications (CCTA)","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"","keywords":"Markov chain; Convergence (economics); Variable-order Markov model; Linear model; Quadratic equation; Linear regression; Orthonormal basis; Reinforcement learning; State (computer science)","score_opus":0.012479337956139673,"score_gpt":0.24442315684276597,"score_spread":0.2319438188866263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090693621","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":[0.0044968026,0.00008858137,0.9784164,0.013459769,0.000030722233,0.0008429344,0.0000048665474,0.00040931214,0.0022506067],"genre_scores_gemma":[0.9927349,0.00010828636,0.0056372895,0.0010863851,0.000049679093,0.0002471947,0.000015136067,0.000013213708,0.00010791234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982878,0.000070319955,0.00039729982,0.0006792534,0.0002240021,0.00034133266],"domain_scores_gemma":[0.99884444,0.00021088256,0.00025382347,0.0004453149,0.00012046786,0.00012504986],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016664305,0.0002680115,0.00033912814,0.00030261822,0.00025875756,0.00016396165,0.0005924539,0.00025720958,0.000006872709],"category_scores_gemma":[0.00021614117,0.00023995437,0.00002319002,0.0009402892,0.00029287106,0.00019127669,0.00015166754,0.0008893973,0.000016383245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005117355,0.00003499932,0.00245234,0.000053878866,0.000104144296,0.0000361778,0.0011879643,0.5205735,0.0022633155,0.41167766,0.00011516265,0.06098911],"study_design_scores_gemma":[0.0048121233,0.0012034582,0.0017751247,0.000071456736,0.000033052762,0.000023050856,0.00033207572,0.9833694,0.00088904105,0.0029158024,0.0041187974,0.0004565937],"about_ca_topic_score_codex":0.000005930837,"about_ca_topic_score_gemma":0.000019023535,"teacher_disagreement_score":0.9882381,"about_ca_system_score_codex":0.000027228196,"about_ca_system_score_gemma":0.000109412846,"threshold_uncertainty_score":0.97850555},"labels":[],"label_agreement":null},{"id":"W3090903721","doi":"10.1109/ijcnn48605.2020.9207681","title":"Noisy Importance Sampling Actor-Critic: An Off-Policy Actor-Critic With Experience Replay","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Sample (material); Set (abstract data type); Truncation (statistics); Convergence (economics); Noise (video); Domain (mathematical analysis); Sampling (signal processing); Artificial intelligence; Machine learning; Mathematics; Computer vision","score_opus":0.05571278835542469,"score_gpt":0.31350621939963186,"score_spread":0.25779343104420716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090903721","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":[0.091855906,0.000045141904,0.8993433,0.0027381247,0.00018065533,0.00026792454,0.0000016049781,0.0007777444,0.0047895988],"genre_scores_gemma":[0.88255733,0.000020225498,0.111076236,0.0055623157,0.00032203586,0.000023603905,0.000007092916,0.000038900962,0.00039225962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968058,0.000076243516,0.0005322509,0.0009995747,0.0007828479,0.0008033037],"domain_scores_gemma":[0.9975183,0.00018705305,0.00016770836,0.0013316256,0.00020138579,0.00059391366],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019723707,0.00036995864,0.00035319815,0.00011671923,0.00027973455,0.0006276738,0.0019407484,0.00010054665,0.00014550064],"category_scores_gemma":[0.0005311033,0.0003162923,0.00007361844,0.00093958626,0.00017654483,0.002128865,0.00040531333,0.00039278835,0.00009305318],"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":[0.00023036552,0.0003794852,0.091419,0.00049803004,0.00021010588,0.0006656198,0.07424849,0.3510602,0.054575197,0.40307146,0.002288886,0.021353144],"study_design_scores_gemma":[0.0016371253,0.0022022233,0.011236805,0.00018296672,0.000033080094,0.00017195065,0.0027036092,0.93617463,0.014970538,0.0004256313,0.02803646,0.0022249748],"about_ca_topic_score_codex":0.00008108923,"about_ca_topic_score_gemma":0.000014639046,"teacher_disagreement_score":0.79070145,"about_ca_system_score_codex":0.00011837348,"about_ca_system_score_gemma":0.00031547845,"threshold_uncertainty_score":0.9999289},"labels":[],"label_agreement":null},{"id":"W3092156990","doi":"10.1613/jair.1.12440","title":"Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":172,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto; Government of Canada; Canadian Institute for Advanced Research; Vector Institute; Microsoft Research","keywords":"Reinforcement learning; Computer science; Exploit; Counterfactual thinking; Function (biology); Artificial intelligence; Finite-state machine; Machine learning; Algorithm; Psychology","score_opus":0.11135646365839093,"score_gpt":0.37456319042376984,"score_spread":0.26320672676537893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092156990","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":[0.06806064,0.00015789071,0.92873454,0.001028922,0.001010319,0.00024387274,3.459332e-7,0.000037465066,0.00072603417],"genre_scores_gemma":[0.99426854,0.00007585859,0.004872578,0.000072218565,0.00029848824,0.000010804528,0.0000023579717,0.000020014844,0.00037911648],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373543,0.0011042604,0.0013322252,0.00034333527,0.0027351072,0.00074965606],"domain_scores_gemma":[0.9975918,0.00059155555,0.0005737434,0.00041055115,0.0006643192,0.000168032],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007680622,0.00017345697,0.00030790365,0.0014290118,0.000805173,0.0003705154,0.0017137097,0.00007099303,0.0004823425],"category_scores_gemma":[0.001497566,0.00016676656,0.000117506665,0.0022836195,0.00009991034,0.00084128464,0.0010280012,0.003419774,0.00003401743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014681228,0.000035701716,0.0008341765,0.000019261199,0.000020086492,0.000106313535,0.0027744533,0.92033166,0.0039795213,0.011725918,0.00014596795,0.059880152],"study_design_scores_gemma":[0.00011376082,0.002815373,0.00019751508,0.00010261924,0.000006892068,0.00013793625,0.007290337,0.9629144,0.0040428042,0.016538832,0.0055752303,0.00026430975],"about_ca_topic_score_codex":0.00008558952,"about_ca_topic_score_gemma":0.000014398291,"teacher_disagreement_score":0.9262079,"about_ca_system_score_codex":0.00072259223,"about_ca_system_score_gemma":0.00042333384,"threshold_uncertainty_score":0.9988794},"labels":[],"label_agreement":null},{"id":"W3092954297","doi":"10.48550/arxiv.2010.09163","title":"D2RL: Deep Dense Architectures in Reinforcement Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Suite; Computer science; Artificial intelligence; Benchmark (surveying); Deep learning; Architecture; Variety (cybernetics); Artificial neural network; Reinforcement; Unsupervised learning; Generative grammar; Machine learning; Human–computer interaction; Engineering","score_opus":0.06018814793559971,"score_gpt":0.19460360121575873,"score_spread":0.13441545328015903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092954297","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":[0.041554045,0.00003908504,0.9515387,0.00023219603,0.00035843303,0.00038606607,4.1483634e-7,0.0004278347,0.0054632355],"genre_scores_gemma":[0.9940503,0.00009680992,0.0036864066,0.00025518303,0.00007199157,0.0000017327685,0.000017721983,0.00003168964,0.001788164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972414,0.0002693043,0.0003935561,0.0012699651,0.00022655887,0.0005992307],"domain_scores_gemma":[0.99797463,0.0001787002,0.00040088917,0.0011108674,0.000091825976,0.00024307202],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003050217,0.00045577425,0.00045896007,0.00048551316,0.0001585642,0.00021168667,0.0025089518,0.00030340205,0.000048891256],"category_scores_gemma":[0.00019705485,0.0005502815,0.00019394055,0.00081785466,0.000100111116,0.00018662578,0.0040922402,0.001971247,0.00019203285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002830944,0.000014576123,0.0032314542,0.000087667926,0.000056642028,0.0006080861,0.0010263175,0.9683433,0.000030640524,0.026154066,0.00004480738,0.0003741367],"study_design_scores_gemma":[0.0005137653,0.00013350589,0.0011571452,0.000119079676,0.000029111558,0.0000048681595,0.00007475728,0.9917208,0.00008499139,0.004850613,0.000765635,0.00054573256],"about_ca_topic_score_codex":0.00014645653,"about_ca_topic_score_gemma":0.000040911607,"teacher_disagreement_score":0.95249623,"about_ca_system_score_codex":0.00037328675,"about_ca_system_score_gemma":0.00021539864,"threshold_uncertainty_score":0.9996949},"labels":[],"label_agreement":null},{"id":"W3093511015","doi":"10.3390/s20215991","title":"Policy-Gradient and Actor-Critic Based State Representation Learning for Safe Driving of Autonomous Vehicles","year":2020,"lang":"en","type":"article","venue":"Sensors","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Computer science; Representation (politics); Artificial intelligence; Reinforcement learning; Perception; Scheme (mathematics); Object (grammar); Function (biology); Deep learning; Machine learning; Simulation; Mathematics; Psychology; Law","score_opus":0.02501525026013139,"score_gpt":0.2744572081329379,"score_spread":0.24944195787280649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093511015","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":[0.4318157,0.000009886445,0.565416,0.0022391148,0.000056064968,0.00018947941,8.7509244e-7,0.000099461926,0.00017344615],"genre_scores_gemma":[0.97458154,0.000008388082,0.024966499,0.0002078198,0.000042264168,0.000004331711,0.0000038527196,0.0000131098695,0.00017219334],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989592,0.000083245366,0.00025750353,0.00027765325,0.00019003419,0.00023237044],"domain_scores_gemma":[0.9991188,0.00035575463,0.00015185302,0.00018547897,0.0000786345,0.00010946114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015095144,0.000105670944,0.00016406055,0.000101610734,0.00010419398,0.000083783736,0.00020961693,0.000030439367,0.0000021275782],"category_scores_gemma":[0.0006978499,0.000111169844,0.000052012318,0.00024807823,0.000053943073,0.00015574452,0.000096283205,0.00011396141,0.0000038081466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009572901,0.000005728949,0.0052505,0.00006641902,0.000013279156,0.0000027369802,0.0026462597,0.9796364,0.0051826322,0.0015447965,0.000025231026,0.005616461],"study_design_scores_gemma":[0.00036176952,0.00020566046,0.0062427707,0.00002507352,0.000007051584,0.0000013116498,0.0001284568,0.9820435,0.010159535,0.00013798272,0.00057407946,0.00011282169],"about_ca_topic_score_codex":0.000035910285,"about_ca_topic_score_gemma":0.000001343438,"teacher_disagreement_score":0.54276586,"about_ca_system_score_codex":0.000034043074,"about_ca_system_score_gemma":0.00006947983,"threshold_uncertainty_score":0.45333746},"labels":[],"label_agreement":null},{"id":"W3093827687","doi":"10.22215/etd/2016-11612","title":"Multi-Robot Learning in the Guarding a Territory Game","year":2016,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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","funders":"","keywords":"Guard (computer science); Reinforcement learning; Computer science; A priori and a posteriori; Robot; Artificial intelligence; Game theory; Human–computer interaction; Mathematical economics; Mathematics; Epistemology","score_opus":0.02150014991520405,"score_gpt":0.2836851225046714,"score_spread":0.2621849725894674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093827687","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":[0.0013109035,0.000102982194,0.9493154,0.0003188714,0.0014314282,0.0003424822,1.5692503e-7,0.0002842168,0.04689355],"genre_scores_gemma":[0.68377423,0.00011774997,0.048125625,0.0005862686,0.00043734018,0.00012634876,0.00008892038,0.00008021327,0.26666328],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979354,0.00023012263,0.00040744653,0.00046548067,0.0005493537,0.0004121808],"domain_scores_gemma":[0.9987161,0.0002893627,0.00026469943,0.0006298039,0.000060159793,0.000039874427],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006913375,0.0002768736,0.00025239852,0.0002774863,0.0001461341,0.00034520618,0.0018928979,0.00022509816,0.000044381486],"category_scores_gemma":[0.0001942943,0.00017319027,0.00012252603,0.00024147097,0.000021210813,0.00037466496,0.00011098041,0.0007933286,0.00025493783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000518822,0.00021184944,0.010458243,0.0006074892,0.00023330686,0.00031761234,0.07223138,0.72430545,0.011319997,0.020465143,0.0045644073,0.15523325],"study_design_scores_gemma":[0.0019575388,0.00031262045,0.054640196,0.0016717925,0.00004499264,0.0000324083,0.0045519215,0.8818487,0.0010393155,0.00025140474,0.051788013,0.0018610872],"about_ca_topic_score_codex":0.00007427563,"about_ca_topic_score_gemma":0.00007266763,"teacher_disagreement_score":0.9011898,"about_ca_system_score_codex":0.00009784588,"about_ca_system_score_gemma":0.00012167397,"threshold_uncertainty_score":0.7062494},"labels":[],"label_agreement":null},{"id":"W3093967600","doi":"10.48550/arxiv.2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perception; Psychology; Data science; Sociology; Computer science","score_opus":0.11056369047256379,"score_gpt":0.24066389574610228,"score_spread":0.1301002052735385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093967600","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":[0.055228923,0.000011962264,0.940413,0.0028610048,0.00020617012,0.00049832073,0.000007061451,0.00017894148,0.000594623],"genre_scores_gemma":[0.9963109,0.00012034138,0.0021938717,0.0001578109,0.00016067181,0.0000027181795,0.000034953395,0.0000152438015,0.0010035268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987163,0.00007580306,0.00015649127,0.0007618116,0.00008392542,0.00020567248],"domain_scores_gemma":[0.9991953,0.000047038397,0.00019172624,0.00029194335,0.00017915384,0.00009487531],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001550967,0.00021506187,0.0002465497,0.00009017943,0.00036530333,0.00024606363,0.00048251008,0.0002602652,0.0000067412875],"category_scores_gemma":[0.000025250642,0.00026750145,0.000075245276,0.00020573437,0.00009150902,0.00038234817,0.0010299665,0.00034687942,0.0000101367905],"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":[0.00004790146,0.000041979692,0.0010146126,0.0004346662,0.00011500268,0.000030574913,0.00667821,0.27665496,0.00039902137,0.71263385,0.0010810124,0.0008681951],"study_design_scores_gemma":[0.0007232334,0.0002120683,0.0022467177,0.000037832277,0.00007918345,9.4564246e-7,0.00035199267,0.97570336,0.000014663269,0.018025152,0.0022188458,0.0003860271],"about_ca_topic_score_codex":0.000025289839,"about_ca_topic_score_gemma":0.000016801534,"teacher_disagreement_score":0.94108194,"about_ca_system_score_codex":0.00013581026,"about_ca_system_score_gemma":0.00008722548,"threshold_uncertainty_score":0.9999777},"labels":[],"label_agreement":null},{"id":"W3093980962","doi":"","title":"Incremental Policy Gradients for Online Reinforcement Learning Control","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Term (time); Control (management); Artificial intelligence; Econometrics; Machine learning; Economics","score_opus":0.01937927747768515,"score_gpt":0.280628564126172,"score_spread":0.26124928664848684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3093980962","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":[0.0020344977,0.000023549366,0.9893067,0.0016317465,0.0002896818,0.0003052549,0.000001569662,0.00023110828,0.006175878],"genre_scores_gemma":[0.88809127,0.000022264121,0.09365478,0.0027146249,0.0002113648,0.000029950645,0.00006831945,0.000018380908,0.015189056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982815,0.00006245689,0.0003850806,0.00037736952,0.00039605505,0.0004975579],"domain_scores_gemma":[0.99891496,0.00014662952,0.00013913792,0.00044802882,0.00021394159,0.00013728093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002550713,0.00017601528,0.00020631703,0.00013446172,0.0002356201,0.00020604252,0.00056353456,0.000056324945,0.00007487219],"category_scores_gemma":[0.0003960844,0.00017130544,0.00012648554,0.0003852242,0.000027725919,0.0003635795,0.0003220808,0.00017510497,0.00005168159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011799015,0.000054538206,0.0009916845,0.000023463153,0.000077347,0.000011969454,0.00018070747,0.8638425,0.0016388516,0.124328785,0.00079658144,0.008041798],"study_design_scores_gemma":[0.0022234563,0.0002909016,0.0006056829,0.000018186469,0.000012711236,0.000019500481,0.0000651437,0.96114564,0.0027356618,0.00027366518,0.03236457,0.00024490588],"about_ca_topic_score_codex":0.000035814235,"about_ca_topic_score_gemma":0.0000057091747,"teacher_disagreement_score":0.89565194,"about_ca_system_score_codex":0.00016854145,"about_ca_system_score_gemma":0.00021986154,"threshold_uncertainty_score":0.69856334},"labels":[],"label_agreement":null},{"id":"W3097732461","doi":"10.48550/arxiv.2011.02565","title":"Diversity-Enriched Option-Critic","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Diversity (politics); Political science; Law","score_opus":0.1188464807474624,"score_gpt":0.19455811583723112,"score_spread":0.07571163508976872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3097732461","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":[0.01827444,0.000027091894,0.9756382,0.00049927074,0.00093173306,0.00027108216,0.000004174575,0.0006316476,0.0037223657],"genre_scores_gemma":[0.9923994,0.000112204325,0.004595284,0.00038219077,0.00010230688,4.5602732e-7,0.00002357244,0.00001980636,0.0023647752],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977147,0.0001797828,0.00022237378,0.0012343958,0.00020954262,0.00043918003],"domain_scores_gemma":[0.99777246,0.00014614547,0.00025420377,0.0013377597,0.00019153682,0.0002979242],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00020063887,0.00037017695,0.00037900393,0.0002470369,0.00074748835,0.00018486743,0.003624486,0.00030172922,0.00004655113],"category_scores_gemma":[0.00011432284,0.00047869887,0.00027482508,0.0007171641,0.00011869181,0.0005332265,0.018954366,0.0010767162,0.00046923506],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000771249,0.000020923073,0.0019345306,0.00007074173,0.000076793,0.00033835068,0.00052311906,0.7850764,0.000013927178,0.21154961,0.00033796096,0.000049936403],"study_design_scores_gemma":[0.000397885,0.00006438467,0.0015967846,0.000046459558,0.00008978425,0.0000031359252,0.00007135291,0.9696517,0.000016898688,0.026854493,0.00067952136,0.00052761583],"about_ca_topic_score_codex":0.000115201845,"about_ca_topic_score_gemma":0.0000044136837,"teacher_disagreement_score":0.97412497,"about_ca_system_score_codex":0.00030210704,"about_ca_system_score_gemma":0.00018623869,"threshold_uncertainty_score":0.99976647},"labels":[],"label_agreement":null},{"id":"W3098974658","doi":"","title":"Promoting Coordination through Policy Regularization in Multi-Agent Deep Reinforcement Learning","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"McGill University; Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Regularization (linguistics); Predictability; Action selection; Artificial intelligence; Machine learning; Action (physics); Mathematics","score_opus":0.014284941918207643,"score_gpt":0.2518850997686436,"score_spread":0.23760015785043595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098974658","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":[0.011063734,0.00010423513,0.9822093,0.0027453764,0.00016957389,0.0013436973,2.6905187e-7,0.0007872606,0.0015765558],"genre_scores_gemma":[0.83461607,0.000055054992,0.1571299,0.0008941086,0.00005567097,0.00018352592,0.00003226018,0.000049731756,0.0069837086],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99674934,0.0002566543,0.0007809322,0.00065775274,0.0006563184,0.00089901435],"domain_scores_gemma":[0.9980805,0.00010202507,0.0005183038,0.00097508234,0.00017309666,0.00015102186],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010589613,0.00036250896,0.00035395744,0.00072568713,0.0002411509,0.00041488002,0.0010306896,0.00026609536,0.000022049428],"category_scores_gemma":[0.0005488249,0.00039765026,0.00011820956,0.0015976429,0.0000397071,0.0015472084,0.00061764097,0.0006554033,0.000087565866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009538604,0.00006309537,0.025686232,0.000049115923,0.00001611104,0.000011353809,0.0026232963,0.8661646,0.0036631913,0.09651799,0.000020612068,0.0051748245],"study_design_scores_gemma":[0.0008982678,0.0002065534,0.009545413,0.000113361566,0.000006157691,0.000021798269,0.000096295,0.9817286,0.004907825,0.00097406784,0.001101135,0.0004005378],"about_ca_topic_score_codex":0.002084565,"about_ca_topic_score_gemma":0.00015038777,"teacher_disagreement_score":0.8250794,"about_ca_system_score_codex":0.0013595456,"about_ca_system_score_gemma":0.00027549212,"threshold_uncertainty_score":0.99984753},"labels":[],"label_agreement":null},{"id":"W3099478911","doi":"10.1007/978-3-030-61577-2_13","title":"Experiments and Applications of Emotional Human-Robot Interaction Systems","year":2020,"lang":"en","type":"book-chapter","venue":"Studies in computational intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Robot; Human–robot interaction; Human–computer interaction; Computer science; Process (computing); Natural (archaeology); Artificial intelligence; Social robot; Scheme (mathematics); Psychology; Robot control; Mobile robot; Mathematics","score_opus":0.1618150848356296,"score_gpt":0.3963985655761806,"score_spread":0.234583480740551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3099478911","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":[0.000003739794,0.0021954472,0.96498984,0.000113497605,0.0004792042,0.00045314373,0.0000064876767,0.000052027546,0.03170662],"genre_scores_gemma":[0.8812717,0.001783974,0.080041684,0.00031079954,0.0006658523,0.0003001262,0.00017802928,0.00009246976,0.035355315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800235,0.000031538755,0.00079845503,0.00051013747,0.0005232498,0.00013428387],"domain_scores_gemma":[0.9983022,0.00048314602,0.0005155011,0.0002493079,0.00039870918,0.00005114257],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015883161,0.00026348303,0.00041633387,0.0002615817,0.00012500976,0.000058832346,0.00052227016,0.00010006472,0.000014233336],"category_scores_gemma":[0.000046363242,0.0002850957,0.00006541327,0.000119989294,0.0003087522,0.00019773793,0.0005930648,0.00032748465,0.000043571952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001657628,0.000008063382,0.000013436576,0.000117770884,0.000077333636,0.0000034481704,0.00044145188,0.5023737,0.0000024002668,0.49566218,0.00008253188,0.0012160579],"study_design_scores_gemma":[0.00021057038,0.00034096444,0.00010326409,0.0017764148,0.000039194576,0.00005771043,0.0008195853,0.76025337,0.000086796346,0.2254418,0.010084924,0.0007854206],"about_ca_topic_score_codex":0.0000074968716,"about_ca_topic_score_gemma":0.0000012063135,"teacher_disagreement_score":0.88494813,"about_ca_system_score_codex":0.00017400179,"about_ca_system_score_gemma":0.000060909555,"threshold_uncertainty_score":0.9999601},"labels":[],"label_agreement":null},{"id":"W3100366369","doi":"10.1561/2200000071","title":"An Introduction to Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"Foundations and Trends® in Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1251,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Deep learning; Generalization; Field (mathematics); Robotics; Machine learning; Robot; Mathematics","score_opus":0.013791966264077308,"score_gpt":0.29059655087526653,"score_spread":0.27680458461118923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3100366369","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":[0.013426917,0.000017287995,0.9794482,0.0025599366,0.00034168665,0.00009515802,8.263303e-8,0.00024108436,0.0038696725],"genre_scores_gemma":[0.9653999,0.000009713721,0.03051879,0.00014071446,0.00045557972,0.000017227205,0.00007971851,0.000017958613,0.0033603928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983198,0.00017664705,0.00034700645,0.00052248186,0.00026723748,0.0003668279],"domain_scores_gemma":[0.9991729,0.000053946176,0.00013353479,0.000395868,0.00010380679,0.00013990697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006109281,0.00018258173,0.00016554564,0.0007663849,0.00067427766,0.0004633143,0.00035980638,0.000055968598,0.00035950387],"category_scores_gemma":[0.00019925229,0.00018858866,0.00003091576,0.001161934,0.00006312553,0.00086342805,0.00022096345,0.00048054193,0.00011713419],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008118957,0.000016488098,0.009627651,0.0000036023387,0.000009371041,0.0000018044703,0.001973486,0.8689428,0.00018322474,0.016332166,0.000045726272,0.102855556],"study_design_scores_gemma":[0.00031117775,0.0006187988,0.012213887,0.000009345769,0.0000061184674,0.000011085561,0.00009163598,0.9279959,0.000039725506,0.00009041178,0.058399454,0.0002124618],"about_ca_topic_score_codex":0.0001537651,"about_ca_topic_score_gemma":0.00016753,"teacher_disagreement_score":0.95197296,"about_ca_system_score_codex":0.000088445886,"about_ca_system_score_gemma":0.000017120268,"threshold_uncertainty_score":0.76904225},"labels":[],"label_agreement":null},{"id":"W3101152497","doi":"","title":"On Efficiency in Hierarchical Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning","score_opus":0.02283141343365988,"score_gpt":0.25049009276771156,"score_spread":0.22765867933405168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101152497","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":[0.0060408525,0.000028153298,0.9810825,0.0013187159,0.00030837383,0.00033815383,1.3746444e-7,0.0004015244,0.010481587],"genre_scores_gemma":[0.99764395,0.0000024206233,0.0005362935,0.0016070133,0.000051666742,0.000023846304,0.000010342907,0.000007135075,0.00011734029],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791044,0.0000875898,0.0007551874,0.00020598462,0.0006884954,0.00035230472],"domain_scores_gemma":[0.9991436,0.000079073405,0.0003502994,0.00019100345,0.00010010063,0.00013589906],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033624176,0.00017798178,0.00019908238,0.00021952418,0.00019833709,0.00079868885,0.00064010354,0.00007611387,0.000004831317],"category_scores_gemma":[0.00032596895,0.00015954212,0.00003924947,0.00078741345,0.000029058658,0.0027212803,0.00014486998,0.00052977074,0.00022672514],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009961518,0.00000478628,0.00017214062,0.00015348596,0.0000015557808,0.0000027164785,0.0035753844,0.9793579,0.000026569998,0.0106050065,0.00017792352,0.0059125833],"study_design_scores_gemma":[0.00042770375,0.00029702866,0.00011082216,0.0001100609,0.000001186209,0.000007322609,0.00015307739,0.99499357,0.00007002713,0.000013773307,0.0036414727,0.0001739602],"about_ca_topic_score_codex":0.000009821619,"about_ca_topic_score_gemma":8.9901725e-8,"teacher_disagreement_score":0.9916031,"about_ca_system_score_codex":0.00009271195,"about_ca_system_score_gemma":0.000084588995,"threshold_uncertainty_score":0.77017754},"labels":[],"label_agreement":null},{"id":"W3101675824","doi":"","title":"CoinDICE: Off-Policy Confidence Interval Estimation","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Confidence interval; Reinforcement learning; Computer science; Embedding; Bellman equation; Mathematical optimization; Function (biology); Confidence region; Algorithm; Mathematics; Applied mathematics; Statistics; Artificial intelligence","score_opus":0.07032887715500136,"score_gpt":0.20192292744749268,"score_spread":0.13159405029249133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3101675824","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":[0.017392734,0.0000077890945,0.97676957,0.0011232283,0.00010292431,0.00010329973,6.904588e-7,0.00026217283,0.0042375773],"genre_scores_gemma":[0.99426,0.000021681999,0.0038247406,0.000999577,0.000052417683,1.5458441e-7,0.0000027125525,0.000007209543,0.00083147327],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905044,0.000063634274,0.00013954334,0.0004099747,0.000099156736,0.00023722491],"domain_scores_gemma":[0.9991456,0.00007995684,0.0001334472,0.0003829654,0.000074645,0.00018334312],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010416673,0.00012701825,0.00013217724,0.00010941066,0.00011757007,0.00010360377,0.0010731865,0.00005771015,0.000042723845],"category_scores_gemma":[0.00018478408,0.00014942455,0.00006456151,0.0008904632,0.00008178687,0.0008156629,0.00039068068,0.00018234519,0.00059748197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007143488,0.0000060523876,0.00056179916,0.000010041216,0.000010869319,0.000056581775,0.00037564256,0.7262908,0.00004340593,0.27160582,0.00027781093,0.00075399794],"study_design_scores_gemma":[0.00031611268,0.000118903255,0.0006363726,0.000016102702,0.000009692705,0.000004191549,0.00005335715,0.99587744,0.00019244068,0.0013128399,0.0013055592,0.00015700383],"about_ca_topic_score_codex":0.00003423336,"about_ca_topic_score_gemma":0.0000016470788,"teacher_disagreement_score":0.9768673,"about_ca_system_score_codex":0.00009113267,"about_ca_system_score_gemma":0.00013070884,"threshold_uncertainty_score":0.7679621},"labels":[],"label_agreement":null},{"id":"W3102849613","doi":"10.48550/arxiv.2011.03125","title":"LBGP: Learning Based Goal Planning for Autonomous Following in Front","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Trajectory; Planner; Computer science; Robot; Reinforcement learning; Artificial intelligence; Front (military); Deep learning; Human–computer interaction; Simulation; Engineering","score_opus":0.08554689636773007,"score_gpt":0.2142208071226572,"score_spread":0.12867391075492712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3102849613","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":[0.02507342,0.000036611727,0.9713694,0.00017132594,0.0007985538,0.000533886,0.0000022355869,0.0004634895,0.0015511037],"genre_scores_gemma":[0.97696185,0.0000044661715,0.021467624,0.00017632099,0.00007744805,0.0000041129574,0.000039767823,0.000037278438,0.0012311174],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750775,0.00016592223,0.000344762,0.001260957,0.00014386488,0.00057671644],"domain_scores_gemma":[0.9983324,0.00035234983,0.00035756401,0.0007115768,0.00006479319,0.00018134396],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00043257687,0.00039283925,0.0005058768,0.0003775965,0.00021240608,0.00023236973,0.001924835,0.00032838754,0.000011263037],"category_scores_gemma":[0.00022455507,0.0005155399,0.0003883221,0.00031641976,0.000039189938,0.000361302,0.0015270226,0.0012465753,0.000050961877],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003097303,0.00001807275,0.008948252,0.00009435082,0.00005898168,0.00042143062,0.0008164566,0.98543906,0.000023114133,0.0039267736,0.00008388235,0.0001386631],"study_design_scores_gemma":[0.0010593875,0.00012818347,0.00095911213,0.00023772169,0.000047521342,6.568849e-7,0.00011960608,0.9942006,0.00004153155,0.0012622458,0.0014197669,0.0005236893],"about_ca_topic_score_codex":0.000075443335,"about_ca_topic_score_gemma":0.0000086286755,"teacher_disagreement_score":0.95188844,"about_ca_system_score_codex":0.0005021594,"about_ca_system_score_gemma":0.00042906773,"threshold_uncertainty_score":0.99972963},"labels":[],"label_agreement":null},{"id":"W3103290077","doi":"","title":"Learning Agent Representations for Ice Hockey","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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 Waterloo; Simon Fraser University","funders":"","keywords":"Ice hockey; Computer science; Artificial intelligence; Physical medicine and rehabilitation","score_opus":0.04542303430578692,"score_gpt":0.2864625706532663,"score_spread":0.24103953634747938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103290077","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":[0.00090004946,0.000049499373,0.9928561,0.0020679545,0.00046018092,0.00049734086,0.0000013139284,0.00056717463,0.0026004054],"genre_scores_gemma":[0.98941684,0.0000035077423,0.008622762,0.0012061528,0.00016025639,0.00009783705,0.00004608873,0.000010254442,0.00043631785],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985535,0.000052195825,0.0005785152,0.00017934728,0.00038639503,0.00025004437],"domain_scores_gemma":[0.99879986,0.000082473416,0.00048292562,0.0001843993,0.00032868105,0.000121664234],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00022623687,0.00013451294,0.00015399448,0.0000911451,0.00042078592,0.0013014158,0.0005138456,0.000056346482,0.00000206016],"category_scores_gemma":[0.00037806583,0.00012885277,0.00005612269,0.000446806,0.000019188898,0.0044907406,0.00010881945,0.00018761752,0.000101576],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004873108,0.000002391796,0.00018468,0.0003344762,0.0000063645393,4.3048652e-7,0.0065198215,0.977268,0.0000903442,0.0022463019,0.0024083157,0.010934005],"study_design_scores_gemma":[0.00029335727,0.00011839075,0.00007301492,0.000036613565,0.0000057116986,0.000008609643,0.0008192462,0.95224786,0.00016213898,0.000008578631,0.04608553,0.00014092562],"about_ca_topic_score_codex":0.000010712584,"about_ca_topic_score_gemma":9.941041e-8,"teacher_disagreement_score":0.98851675,"about_ca_system_score_codex":0.000044485754,"about_ca_system_score_gemma":0.00007558681,"threshold_uncertainty_score":0.99973536},"labels":[],"label_agreement":null},{"id":"W3103898737","doi":"10.1109/tro.2022.3192969","title":"Joint Estimation of Expertise and Reward Preferences From Human Demonstrations","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Robotics","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Robot; Leverage (statistics); Computer science; Human–robot interaction; Artificial intelligence; Set (abstract data type); Function (biology); Machine learning; Human–computer interaction; Human behavior; Space (punctuation)","score_opus":0.036868723667860044,"score_gpt":0.2569113578331829,"score_spread":0.22004263416532288,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103898737","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":[0.013509567,0.000022532544,0.9852003,0.00032108396,0.0004362165,0.00016951558,0.000012116191,0.00011014453,0.00021855641],"genre_scores_gemma":[0.8724741,0.000015049782,0.12725714,0.00005384907,0.000008379052,0.000030319612,0.0000058067585,0.000008297644,0.00014709808],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987566,0.00010109575,0.00036399203,0.00025485465,0.00037598322,0.00014750172],"domain_scores_gemma":[0.999245,0.000097604745,0.00015331728,0.00039880935,0.000042631706,0.00006264387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012765247,0.00012223597,0.00015931297,0.0001571028,0.0005374268,0.000070154674,0.00031727873,0.000039136,0.000065934495],"category_scores_gemma":[0.0000065842,0.00013291309,0.00005543521,0.00025932924,0.00007340992,0.0002594326,0.000010848765,0.00026192045,0.0000049999408],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030243789,0.00007377893,0.000026610265,0.000006467481,0.000023565992,0.0000012647293,0.0009618808,0.98749995,0.0009994423,0.0018675686,0.000030611845,0.008505857],"study_design_scores_gemma":[0.00025104883,0.0003120199,0.0003822339,0.000022261025,0.000029571718,0.0000041436174,0.00015438427,0.9906264,0.0068655666,0.0011914808,0.000012586505,0.00014829593],"about_ca_topic_score_codex":0.00009893607,"about_ca_topic_score_gemma":0.000016045266,"teacher_disagreement_score":0.8589645,"about_ca_system_score_codex":0.000067810004,"about_ca_system_score_gemma":0.000058159054,"threshold_uncertainty_score":0.54200387},"labels":[],"label_agreement":null},{"id":"W3103966376","doi":"","title":"Value-driven Hindsight Modelling","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Hindsight bias; Leverage (statistics); Computer science; Reinforcement learning; Machine learning; Artificial intelligence; Bellman equation; Exploit; Function (biology); Representation (politics); Mathematical optimization; Mathematics","score_opus":0.03967133682234385,"score_gpt":0.2352821196128032,"score_spread":0.19561078279045935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103966376","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":[0.00072096667,0.000074031035,0.9920077,0.001341783,0.0004454891,0.0002241824,6.6292387e-7,0.00061617617,0.00456905],"genre_scores_gemma":[0.98457634,0.000003455125,0.013544164,0.0016102116,0.00013802866,0.000014070611,0.000012358638,0.0000090310195,0.00009235185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983612,0.000046206456,0.0006012482,0.00017148587,0.0005517049,0.00026817835],"domain_scores_gemma":[0.9989947,0.000027593414,0.00040960417,0.00022713275,0.00019588454,0.00014507178],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00015023112,0.00016139516,0.0001779936,0.000095895775,0.00024356683,0.0013797302,0.0007470396,0.000073620286,0.0000022734198],"category_scores_gemma":[0.000041722484,0.0001450934,0.000045979155,0.000470494,0.00002054869,0.006555713,0.00013998958,0.00022488677,0.0002334532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000020499963,0.0000016745657,0.000046412602,0.00019224404,0.0000039309434,0.0000010447297,0.0035029429,0.9871282,0.00003445769,0.0057809185,0.00059280265,0.0027133161],"study_design_scores_gemma":[0.00019085154,0.00004973335,0.000006788403,0.00005670924,0.0000038133949,0.000012550819,0.00011789497,0.98568624,0.00011192113,0.0000134669335,0.013580696,0.00016931626],"about_ca_topic_score_codex":0.000010171196,"about_ca_topic_score_gemma":2.319524e-8,"teacher_disagreement_score":0.98385537,"about_ca_system_score_codex":0.00004749471,"about_ca_system_score_gemma":0.00007753161,"threshold_uncertainty_score":0.9996569},"labels":[],"label_agreement":null},{"id":"W3104132897","doi":"","title":"Deep Reinforcement and InfoMax Learning","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Infomax; Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Representation (politics); Machine learning; Mutual information; Baseline (sea); Channel (broadcasting)","score_opus":0.05192380332967931,"score_gpt":0.1673757088892988,"score_spread":0.11545190555961951,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3104132897","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":[0.017869579,0.000016982714,0.97359043,0.00030141562,0.000060245417,0.00009568706,3.9961908e-8,0.000247451,0.007818173],"genre_scores_gemma":[0.9960166,0.00006297465,0.0019012339,0.000596428,0.000028679888,1.6728812e-7,0.0000017055847,0.000007861526,0.0013843386],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906915,0.00004976272,0.00013104516,0.00040249314,0.000086384316,0.000261177],"domain_scores_gemma":[0.9992947,0.00006377595,0.00010336534,0.0002679393,0.000051929408,0.00021831333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009845094,0.0001374282,0.00013085242,0.00007042507,0.0001845201,0.000106061205,0.0005803494,0.0000549786,0.00004012889],"category_scores_gemma":[0.00008245998,0.00015771162,0.00004578442,0.0005082201,0.000060921055,0.0006302348,0.0005637366,0.00023713535,0.00016331395],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007515727,0.0000026416071,0.004511823,0.000011895173,0.00001631314,0.000055573728,0.00054198265,0.89205444,0.000038879818,0.10228428,0.000055523964,0.00041914277],"study_design_scores_gemma":[0.00042380946,0.00017944297,0.0006293469,0.000007375989,0.000011372205,0.0000030014048,0.00013320052,0.993696,0.000066215514,0.00018916554,0.0044772746,0.00018382826],"about_ca_topic_score_codex":0.000010924371,"about_ca_topic_score_gemma":9.63969e-7,"teacher_disagreement_score":0.97814703,"about_ca_system_score_codex":0.000043281198,"about_ca_system_score_gemma":0.000030593503,"threshold_uncertainty_score":0.64312935},"labels":[],"label_agreement":null},{"id":"W3105702366","doi":"","title":"Variational Policy Gradient Method for Reinforcement Learning with General Utilities","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Mathematical optimization; Reinforcement learning; Convexity; Markov decision process; Q-learning; Mathematics; Gradient descent; Gradient method; Computer science; Applied mathematics; Convergence (economics); Markov process; Artificial neural network; Artificial intelligence; Finance","score_opus":0.03067472875020712,"score_gpt":0.28240915646595416,"score_spread":0.25173442771574706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3105702366","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":[0.00018417867,0.000027589014,0.9940392,0.002340293,0.00021501824,0.0005975977,0.0000017852935,0.00038875462,0.0022055805],"genre_scores_gemma":[0.8497978,0.0000030154674,0.14564249,0.0027433482,0.0004729659,0.0002205666,0.00011620056,0.000019748231,0.0009838685],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802727,0.00007504048,0.0006796217,0.00021598744,0.00062688213,0.00037518743],"domain_scores_gemma":[0.9985284,0.000087405315,0.00060967536,0.00017749936,0.00044580712,0.00015117532],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003908071,0.00021468659,0.0002306061,0.00018609843,0.0004415797,0.0011346277,0.00048525445,0.000065905835,0.0000028577765],"category_scores_gemma":[0.000204691,0.00017793616,0.00005660672,0.00054182095,0.000027478896,0.0037101367,0.000105979496,0.00020175068,0.000019133104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020774958,0.0000023857144,0.00007636803,0.00035227,0.000015745156,3.097567e-7,0.005143465,0.92963755,0.000027746575,0.058748037,0.0003705171,0.005604844],"study_design_scores_gemma":[0.0005867178,0.0003543159,0.000057955123,0.000049157283,0.000008537547,0.000022125187,0.00039684342,0.96853465,0.00011464507,0.000032982898,0.02963061,0.00021148135],"about_ca_topic_score_codex":0.000055384247,"about_ca_topic_score_gemma":2.1555022e-7,"teacher_disagreement_score":0.8496136,"about_ca_system_score_codex":0.00012850702,"about_ca_system_score_gemma":0.0002931137,"threshold_uncertainty_score":0.9999023},"labels":[],"label_agreement":null},{"id":"W3107153805","doi":"10.1038/s41586-020-2939-8","title":"Autonomous navigation of stratospheric balloons using reinforcement learning","year":2020,"lang":"en","type":"article","venue":"Nature","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":272,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Google (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Controller (irrigation); Obstacle avoidance; Process (computing); Obstacle; Reinforcement; Real-time computing; Artificial intelligence; Simulation; Engineering","score_opus":0.018149712530883974,"score_gpt":0.2613037861494292,"score_spread":0.24315407361854519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107153805","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":[0.025581006,0.00013415054,0.97076565,0.0004715101,0.00019465903,0.0001373047,2.227059e-7,0.00016625038,0.0025492555],"genre_scores_gemma":[0.9481514,0.0000037951008,0.05093965,0.0007097254,0.00005836394,0.0000012400361,0.0000066567873,0.000009954401,0.000119213124],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885154,0.000041819356,0.00027080148,0.00023846896,0.00039739892,0.00019997131],"domain_scores_gemma":[0.99931306,0.000035307814,0.00023466318,0.00022847936,0.00010854708,0.000079931044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012541971,0.00012332149,0.00015318599,0.000026887577,0.00009266581,0.00007274236,0.00055201136,0.00036472557,0.000026676275],"category_scores_gemma":[0.00010208714,0.0001238732,0.00006203735,0.0005112364,0.000025860241,0.00034734918,0.00019038051,0.0014803092,0.000015521036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031120487,0.0000038459248,0.0005735282,0.000034708748,0.000015690033,0.0000039842503,0.00065516547,0.9834239,0.004911462,0.0093812365,0.00007731764,0.0009160832],"study_design_scores_gemma":[0.00019528813,0.00014559882,0.00034339738,0.00003555523,0.00000919907,0.000004364529,0.00005334196,0.9915751,0.0041712713,0.000032554904,0.0033050547,0.0001292555],"about_ca_topic_score_codex":0.000006870286,"about_ca_topic_score_gemma":1.1588034e-7,"teacher_disagreement_score":0.9225704,"about_ca_system_score_codex":0.000054587326,"about_ca_system_score_gemma":0.000110049776,"threshold_uncertainty_score":0.6431289},"labels":[],"label_agreement":null},{"id":"W3107258301","doi":"10.48550/arxiv.2012.01418","title":"Team Optimal Control of Coupled Subsystems with Mean-Field Sharing","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Control theory (sociology); Optimal control; Dynamic programming; State (computer science); Mean field theory; Computer science; Controller (irrigation); Mathematical optimization; Field (mathematics); Stochastic control; Mathematics; Control (management); Algorithm; Artificial intelligence","score_opus":0.05192717160608362,"score_gpt":0.18326112596299296,"score_spread":0.13133395435690934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107258301","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":[0.048045754,0.000021609512,0.94788724,0.000093582785,0.00028654156,0.00043695414,0.00000281433,0.00023747544,0.0029880102],"genre_scores_gemma":[0.99575496,0.000021972213,0.0033514109,0.000093462586,0.0000574961,0.0000010941225,0.000006136124,0.000022851284,0.00069062616],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980421,0.000071197035,0.00032667714,0.0009884823,0.0002175455,0.00035398902],"domain_scores_gemma":[0.9975209,0.00018585905,0.0005898989,0.001290431,0.00023123116,0.00018165671],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025564767,0.00033610058,0.00057432294,0.00018560085,0.00009265332,0.00013129401,0.0026296852,0.00023920454,0.000019132634],"category_scores_gemma":[0.000053868887,0.00034894433,0.00017689401,0.000482467,0.00007975043,0.00031966515,0.001594904,0.0007303435,0.00003447574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086623986,0.000020884156,0.006927663,0.00016594808,0.00020230809,0.00013372509,0.00036871026,0.94779545,0.00008976341,0.04414788,0.00004618871,0.000014877342],"study_design_scores_gemma":[0.0010399594,0.0003038911,0.00020087218,0.00021425971,0.000101317186,0.000004674474,0.000101419784,0.9970984,0.00024233776,0.0002536914,0.00007603484,0.00036317323],"about_ca_topic_score_codex":0.00021463001,"about_ca_topic_score_gemma":0.000012184249,"teacher_disagreement_score":0.9477092,"about_ca_system_score_codex":0.00013300606,"about_ca_system_score_gemma":0.00021359777,"threshold_uncertainty_score":0.9998962},"labels":[],"label_agreement":null},{"id":"W3108136459","doi":"10.48550/arxiv.2011.12363","title":"C-Learning: Horizon-Aware Cumulative Accessibility Estimation","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reachability; Reinforcement learning; Computer science; Time horizon; Generalization; Motion planning; Sample (material); Reliability (semiconductor); Set (abstract data type); Path (computing); Horizon; Code (set theory); Monotonic function; Machine learning; Mathematical optimization; Artificial intelligence; Robot; Theoretical computer science; Mathematics","score_opus":0.09698605659490178,"score_gpt":0.23354127048946952,"score_spread":0.13655521389456773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108136459","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":[0.037345972,0.000008428484,0.9572458,0.00022304234,0.00056625344,0.00040616552,0.0000035361118,0.0007836184,0.0034171445],"genre_scores_gemma":[0.99061465,0.000030586936,0.0076894173,0.00006072491,0.00007448796,0.0000012024002,0.00006293448,0.000025669468,0.0014403027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99716544,0.00033568483,0.0003439317,0.0015298125,0.00022621667,0.00039891194],"domain_scores_gemma":[0.99733704,0.0002231008,0.0006287542,0.0012903756,0.0002706499,0.00025008828],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031696731,0.00042396545,0.00043220675,0.00020529593,0.0002768781,0.0003509566,0.0025856385,0.00035915963,0.00005129537],"category_scores_gemma":[0.00031547714,0.000506621,0.00023887468,0.00082713313,0.00012408715,0.00087798666,0.0040282155,0.0014820569,0.00026927554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016671213,0.000022701772,0.003124472,0.0001002644,0.000065771994,0.00009481475,0.00045886144,0.96864825,0.0000054690827,0.026425874,0.00012096207,0.00091586856],"study_design_scores_gemma":[0.0003109514,0.0001897844,0.0026220228,0.00007909796,0.000053746102,0.0000011395692,0.00007158538,0.9810181,0.00005803748,0.014905555,0.00020882275,0.00048114586],"about_ca_topic_score_codex":0.00005637703,"about_ca_topic_score_gemma":0.000002647844,"teacher_disagreement_score":0.9532687,"about_ca_system_score_codex":0.00040609788,"about_ca_system_score_gemma":0.0003286168,"threshold_uncertainty_score":0.9997385},"labels":[],"label_agreement":null},{"id":"W3108183475","doi":"","title":"Skill Transfer via Partially Amortized Hierarchical Planning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Suite; Reinforcement learning; Leverage (statistics); Task (project management); Adaptation (eye); Knowledge transfer; Amortization; Transfer of learning; Artificial intelligence; Machine learning; Human–computer interaction; Knowledge management","score_opus":0.08606900475964419,"score_gpt":0.20635410698759374,"score_spread":0.12028510222794955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108183475","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":[0.03056204,0.000022690476,0.9645582,0.0004124644,0.0006832249,0.00033843293,0.000003627302,0.00063306786,0.0027862545],"genre_scores_gemma":[0.99272,0.000037276193,0.0057898937,0.00040395898,0.00013936636,0.0000012732598,0.000027198137,0.00003339385,0.00084761594],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722666,0.00023295215,0.00037560266,0.0013615092,0.00023115963,0.0005721352],"domain_scores_gemma":[0.9979867,0.00016453794,0.0001555753,0.00120421,0.00010461237,0.0003844042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023208509,0.00044367646,0.0005157822,0.00021545436,0.00019178992,0.000222511,0.0027340066,0.00037503606,0.000058479043],"category_scores_gemma":[0.00006234707,0.00052096794,0.00034157475,0.0005653143,0.00014959511,0.0003539903,0.0019348508,0.001503999,0.00021138573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000475529,0.000029039436,0.001329384,0.000060294075,0.000119601915,0.00082660664,0.0007895793,0.95582724,0.00008341215,0.040516976,0.00014485183,0.00022544625],"study_design_scores_gemma":[0.0006794745,0.00010807859,0.0013746688,0.00009513821,0.00007914156,0.000005552916,0.000018825962,0.9872864,0.00015967888,0.008519003,0.0010975648,0.00057650404],"about_ca_topic_score_codex":0.000026348174,"about_ca_topic_score_gemma":0.0000038200264,"teacher_disagreement_score":0.96215796,"about_ca_system_score_codex":0.00015115878,"about_ca_system_score_gemma":0.0002723711,"threshold_uncertainty_score":0.9997242},"labels":[],"label_agreement":null},{"id":"W3110289401","doi":"10.1017/9781009302180.029","title":"Dynamic Programming Algorithms","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Computer science; Dynamic programming; Algorithm","score_opus":0.017629680580646116,"score_gpt":0.2132394704960128,"score_spread":0.19560978991536668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110289401","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":[5.710408e-7,0.00013830086,0.36499748,0.000025869324,0.0005911918,0.00028645748,0.000013068105,0.0005892728,0.63335776],"genre_scores_gemma":[0.000099583485,0.00006280355,0.013892848,0.000037194543,0.00006434076,9.043658e-7,0.000029467064,0.000060800783,0.98575205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979887,0.000019074245,0.00023751495,0.00082576857,0.000494158,0.00043478765],"domain_scores_gemma":[0.99836385,0.000057778536,0.00020919689,0.001047403,0.00013530986,0.00018643735],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00012639703,0.00045526095,0.0003627278,0.00032390025,0.00019004931,0.00035895657,0.001809785,0.00036535694,0.0000020419552],"category_scores_gemma":[0.0000058943756,0.00053577364,0.0002774251,0.000023076136,0.00017600013,0.00021396008,0.0016470662,0.0008675484,0.0001576607],"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":[0.000004041691,0.000002776033,1.5188995e-7,0.00012759463,0.0001500658,0.0008023479,0.000060290713,0.0010865934,0.000003685623,0.98324805,0.0038649782,0.010649405],"study_design_scores_gemma":[0.00016791365,0.000067229135,8.726553e-7,0.00025836166,0.00011308707,0.000034104367,0.00000773705,0.11889973,0.000015092298,0.000029964924,0.8799071,0.0004988555],"about_ca_topic_score_codex":0.000025928794,"about_ca_topic_score_gemma":4.902367e-7,"teacher_disagreement_score":0.98321813,"about_ca_system_score_codex":0.0003865183,"about_ca_system_score_gemma":0.00014237799,"threshold_uncertainty_score":0.99970937},"labels":[],"label_agreement":null},{"id":"W3112448993","doi":"10.1109/smc42975.2020.9283018","title":"Motion Path Planning of Two Robot Arms in a Common Workspace","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Regina","funders":"","keywords":"Workspace; Motion planning; Computer science; Reinforcement learning; Discretization; Robot; Path (computing); Artificial intelligence; Context (archaeology); Kinematics; Collision; Q-learning; Mathematics; Physics","score_opus":0.03983504067494486,"score_gpt":0.2884268183005159,"score_spread":0.24859177762557105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112448993","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":[0.0113493875,0.000017430242,0.9836185,0.0016093861,0.00007035335,0.00008919336,6.4460615e-8,0.000098726596,0.0031469637],"genre_scores_gemma":[0.86519176,0.000001740704,0.13438761,0.0003217803,0.000017767023,0.0000016572427,0.0000012191589,0.00000454214,0.00007193227],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99916667,0.000047124264,0.0002311548,0.0001821339,0.00020904753,0.0001638583],"domain_scores_gemma":[0.9995285,0.00006592804,0.000103068865,0.00022334547,0.000020791005,0.000058340953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016017727,0.000079854144,0.0001490891,0.000056985813,0.000019003674,0.000047481637,0.0004493639,0.000030886986,0.000012459292],"category_scores_gemma":[0.00003624639,0.000074139345,0.000028091601,0.00042924142,0.000016167698,0.0002474112,0.00020147652,0.0001663115,0.000020158646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002907732,0.000008956833,0.04075411,0.000010696713,0.0000028945794,0.0000061738724,0.002192242,0.9474192,0.0002867482,0.0077644624,0.00011371041,0.0014378813],"study_design_scores_gemma":[0.00031525234,0.00007990753,0.009446296,0.000044786597,0.0000013305255,0.0000010555412,0.00010741305,0.9890719,0.0006136168,0.00019543663,0.000040293107,0.000082701896],"about_ca_topic_score_codex":0.00003650939,"about_ca_topic_score_gemma":0.0000027140352,"teacher_disagreement_score":0.8538424,"about_ca_system_score_codex":0.000021099053,"about_ca_system_score_gemma":0.000015931668,"threshold_uncertainty_score":0.30233148},"labels":[],"label_agreement":null},{"id":"W3117215073","doi":"10.1613/jair.1.13673","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","year":2022,"lang":"en","type":"review","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":180,"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 Montréal; McGill University","funders":"Canada Excellence Research Chairs, Government of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Scope (computer science); Artificial intelligence; Bridging (networking); Taxonomy (biology); Function (biology); Management science; Engineering","score_opus":0.3537488428002021,"score_gpt":0.4758490705427069,"score_spread":0.12210022774250484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117215073","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.0065416e-7,0.77820694,0.21891998,0.00052476174,0.0002594229,0.0006263192,5.310488e-7,0.000022355927,0.0014395799],"genre_scores_gemma":[0.000022682036,0.9961339,0.0023335703,0.000035721077,0.00026991448,0.000038758735,0.0000027447945,0.00003634514,0.0011263136],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.991866,0.0020305645,0.0021806557,0.00054974464,0.0026036752,0.00076934847],"domain_scores_gemma":[0.994913,0.0014653233,0.0014997768,0.0006523895,0.0011390637,0.00033047862],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011670991,0.00040194986,0.0019207925,0.0012123233,0.00054469967,0.0005758179,0.0028780478,0.00017370595,0.00082472817],"category_scores_gemma":[0.004848099,0.00032041266,0.00059954304,0.0020118703,0.00036375853,0.00055065117,0.0017772833,0.004585868,0.000089810805],"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":[0.0000065930994,0.000044040913,1.5608255e-7,0.0066800583,0.00017054469,0.00011215822,0.0011332469,0.0029217277,2.7907194e-7,0.020102127,0.000697781,0.9681313],"study_design_scores_gemma":[0.00001913925,0.0012939177,1.0135547e-7,0.008857085,0.00021327876,0.00039244752,0.0010838101,0.0036426836,0.0000040186956,0.0005308807,0.983661,0.0003016187],"about_ca_topic_score_codex":0.000016946318,"about_ca_topic_score_gemma":7.451476e-7,"teacher_disagreement_score":0.98296326,"about_ca_system_score_codex":0.00067045697,"about_ca_system_score_gemma":0.0018342834,"threshold_uncertainty_score":0.9999248},"labels":[],"label_agreement":null},{"id":"W3118340619","doi":"10.1109/ssci47803.2020.9308403","title":"Objective Comparison and Selection in Mono- and Multi-Objective Evolutionary Neurocontrollers","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Evolutionary algorithm; Mathematical optimization; Multi-objective optimization; Computer science; Pareto principle; Selection (genetic algorithm); Compatibility (geochemistry); Objectivity (philosophy); Mathematics; Artificial intelligence; Engineering","score_opus":0.023410978597037852,"score_gpt":0.2552927826432486,"score_spread":0.23188180404621075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118340619","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":[0.031815764,0.00009958332,0.96555936,0.0009007689,0.00004410724,0.0003211276,2.3664866e-7,0.00013322009,0.0011258507],"genre_scores_gemma":[0.9604049,0.000017023609,0.03896643,0.00047434962,0.000019743775,0.000010859408,4.202335e-7,0.0000059292815,0.0001003787],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99903387,0.000092416696,0.00018921046,0.0003693497,0.00013483451,0.00018033282],"domain_scores_gemma":[0.99961054,0.00012430608,0.00006798205,0.000056958823,0.000047260888,0.000092962546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008599626,0.000118430835,0.00017690742,0.000093526076,0.00009411645,0.00008135787,0.00013852905,0.00004831579,0.0000039330985],"category_scores_gemma":[0.00011040921,0.00011577872,0.000018015968,0.00035171106,0.000043691514,0.0004375214,0.00017275842,0.00022050043,0.000007622403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007023223,0.00004655185,0.2049849,0.000018586477,0.00003387519,0.0000065079817,0.006637686,0.77893454,0.0014099907,0.0034811078,0.00034630558,0.0040297415],"study_design_scores_gemma":[0.00084337464,0.00019508305,0.21284048,0.000004163244,0.0000028847712,0.000004350423,0.00022442853,0.7855794,0.000098654076,0.000039386578,0.00007181375,0.00009598218],"about_ca_topic_score_codex":0.00009935467,"about_ca_topic_score_gemma":0.000026158943,"teacher_disagreement_score":0.9285891,"about_ca_system_score_codex":0.00005545559,"about_ca_system_score_gemma":0.000037368212,"threshold_uncertainty_score":0.4721319},"labels":[],"label_agreement":null},{"id":"W3118394271","doi":"10.1609/aaai.v35i11.17166","title":"Solving Common-Payoff Games with Approximate Policy Iteration","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Montréal; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Stochastic game; Scalability; Artificial intelligence; Common knowledge (logic); Scale (ratio); Mathematical optimization; Mathematical economics; Mathematics","score_opus":0.04921359465533086,"score_gpt":0.28882868471805523,"score_spread":0.23961509006272436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118394271","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":[0.05475348,0.000029343833,0.8946324,0.010190126,0.00038560043,0.0004826482,0.0000023229773,0.00023126429,0.03929281],"genre_scores_gemma":[0.98322034,0.000023057386,0.015366871,0.00040376408,0.00007933892,0.000016566384,0.0000011581399,0.00001498072,0.0008738977],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99801266,0.00002512185,0.00049694185,0.0004675861,0.0006163224,0.0003813361],"domain_scores_gemma":[0.99808264,0.00009105094,0.00042468755,0.0004299217,0.0008891513,0.00008257645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003355165,0.0002292444,0.00026105775,0.0001382842,0.00026123674,0.00071418384,0.0014857013,0.0000733031,0.000037828202],"category_scores_gemma":[0.00042767354,0.00016739278,0.00008342806,0.0010215257,0.00020532978,0.00065760995,0.00049597415,0.00032851324,0.00004412198],"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":[0.000023928356,0.00006564477,0.00050281716,0.000056044,0.0000199446,0.0000018230029,0.0017463339,0.011428122,0.021778071,0.94376254,0.00007548477,0.02053924],"study_design_scores_gemma":[0.000031679578,0.00016410468,0.00017402173,0.0003138223,0.000010184348,0.000018537934,0.00038159036,0.46851817,0.49532336,0.03469945,0.00014162951,0.00022345406],"about_ca_topic_score_codex":0.000029145422,"about_ca_topic_score_gemma":0.0000082182505,"teacher_disagreement_score":0.9284669,"about_ca_system_score_codex":0.000067743924,"about_ca_system_score_gemma":0.00027602114,"threshold_uncertainty_score":0.6886891},"labels":[],"label_agreement":null},{"id":"W3119430014","doi":"10.65109/bwtd6573","title":"Partially Observable Mean Field Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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; University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Scalability; Field (mathematics); Visibility; Artificial intelligence; Observable; Mathematical optimization; Set (abstract data type); Q-learning; Machine learning; Mathematics","score_opus":0.03734177779240893,"score_gpt":0.2667191034409659,"score_spread":0.22937732564855695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119430014","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":[0.0007617536,0.000104408544,0.9355256,0.001206399,0.0016770343,0.0003035944,7.35744e-8,0.00066947856,0.059751675],"genre_scores_gemma":[0.76361537,0.0002772615,0.17441276,0.002675423,0.0002871252,0.00007939186,0.000088505716,0.0000508412,0.05851331],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661106,0.00016794707,0.00072475546,0.0009507975,0.000885438,0.0006599927],"domain_scores_gemma":[0.99707174,0.00022133443,0.00039649723,0.001845574,0.00027286613,0.00019196242],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006065843,0.00043369937,0.00048761777,0.00012709739,0.00022714326,0.0014601297,0.002263511,0.00038683054,0.00076639024],"category_scores_gemma":[0.0003058395,0.00043961252,0.00027503175,0.00026658608,0.000025415899,0.00044911273,0.006255826,0.0016131555,0.00016533714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025034237,0.000012168117,0.00051615154,0.00010070578,0.00008239926,0.00004378608,0.0009222799,0.9855374,0.000064417545,0.009231206,0.0015982466,0.0018887112],"study_design_scores_gemma":[0.00019136768,0.00015689262,0.000093409406,0.00020380573,0.000023416937,0.000005546986,0.00011486883,0.9811945,0.0035749266,0.00018951947,0.013695036,0.00055673136],"about_ca_topic_score_codex":0.00030557538,"about_ca_topic_score_gemma":0.00004087904,"teacher_disagreement_score":0.7628536,"about_ca_system_score_codex":0.0001445154,"about_ca_system_score_gemma":0.0004913425,"threshold_uncertainty_score":0.99980557},"labels":[],"label_agreement":null},{"id":"W3119528129","doi":"10.1109/ssci47803.2020.9308450","title":"Self-Adaptation of Meta-Parameters for Lamarckian-Inherited Neuromodulated Neurocontrollers in the Pursuit-Evasion Game","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Evolutionary algorithm; Adaptation (eye); Computer science; Evolutionary computation; Set (abstract data type); Pursuit-evasion; Evolution strategy; Selection (genetic algorithm); Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.10416389623534689,"score_gpt":0.26003691895567027,"score_spread":0.15587302272032338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119528129","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":[0.026192429,0.000025169626,0.96301085,0.009194274,0.000102143014,0.0010762936,9.1942513e-7,0.00016162987,0.0002362897],"genre_scores_gemma":[0.916223,0.000010752608,0.080543794,0.0030920769,0.000012509417,0.000057721925,0.000005390856,0.000013328794,0.000041442367],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982876,0.00024692572,0.0004297553,0.00033171094,0.0004595079,0.0002445054],"domain_scores_gemma":[0.9987124,0.0005454719,0.00020748461,0.00038175777,0.00009506658,0.000057789704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004946963,0.000160176,0.00030610073,0.000097154654,0.000043735774,0.00014305871,0.0011874102,0.000051490755,0.00000772477],"category_scores_gemma":[0.0003038997,0.0001094731,0.0001831787,0.0008048427,0.000024036024,0.0003320964,0.00010907744,0.00015559612,0.0000069706643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003538868,0.000030104631,0.00005770241,0.000034265184,0.00010470754,0.0000048329503,0.002399334,0.9925355,0.001354179,0.0021761078,0.00016604208,0.0011018862],"study_design_scores_gemma":[0.0010085293,0.0004680166,0.0006881303,0.0000029502967,0.00009563637,0.000001989318,0.00010713191,0.9950855,0.00046886547,0.00006985794,0.0018966034,0.00010681765],"about_ca_topic_score_codex":0.000026974425,"about_ca_topic_score_gemma":0.000004627332,"teacher_disagreement_score":0.89003056,"about_ca_system_score_codex":0.000015047946,"about_ca_system_score_gemma":0.000037516173,"threshold_uncertainty_score":0.44641832},"labels":[],"label_agreement":null},{"id":"W3120394327","doi":"10.1007/s10515-021-00313-x","title":"Faults in deep reinforcement learning programs: a taxonomy and a detection approach","year":2021,"lang":"en","type":"article","venue":"Automated Software Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Fonds de Recherche du Québec-Société et Culture; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Categorization; Artificial intelligence; Fault detection and isolation; Software; Machine learning; Software engineering; Programming language","score_opus":0.012062613245359722,"score_gpt":0.20269778829536153,"score_spread":0.1906351750500018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3120394327","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":[0.016615938,0.00013992796,0.97998655,0.000008905316,0.00013692341,0.00026747634,2.980257e-8,0.0027366988,0.00010753094],"genre_scores_gemma":[0.7958848,0.00001465701,0.20384744,0.000015884243,0.000016104108,0.00012238575,0.000011316884,0.000018785218,0.000068642985],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986405,0.000039527156,0.0003059131,0.00038534956,0.00022797941,0.00040075206],"domain_scores_gemma":[0.99940395,0.00008277166,0.00007715905,0.00028317023,0.00006535836,0.00008759039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002110985,0.00019473935,0.0001911775,0.00019111193,0.000084131025,0.00017936887,0.00021752168,0.00010235668,0.0000021771787],"category_scores_gemma":[0.00035729128,0.00022261818,0.000037765763,0.0007347932,0.000013191951,0.00043593827,0.00025340886,0.0003510063,0.000007650413],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011901728,0.000012211718,0.0021347518,0.00008569149,0.00001968221,0.00003456164,0.00048311986,0.98300326,0.00022360381,0.00016301016,0.0000014214744,0.013837511],"study_design_scores_gemma":[0.0003720941,0.00005631621,0.00275767,0.00008155998,0.0000049697164,0.00006679403,0.00006961809,0.99474657,0.0006674416,0.000001995088,0.0009373189,0.00023766952],"about_ca_topic_score_codex":0.000016421718,"about_ca_topic_score_gemma":0.0000029642204,"teacher_disagreement_score":0.77926886,"about_ca_system_score_codex":0.00012910468,"about_ca_system_score_gemma":0.000040999646,"threshold_uncertainty_score":0.90781057},"labels":[],"label_agreement":null},{"id":"W3123244128","doi":"10.1109/lars/sbr/wre51543.2020.9306954","title":"Deep Reinforcement Learning Applied to IEEE Very Small Size Soccer Strategy","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Curriculum; Robot; Heuristic; Context (archaeology); Adversary; Machine learning","score_opus":0.033649539412251794,"score_gpt":0.24077473726701018,"score_spread":0.20712519785475839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3123244128","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":[0.001136942,0.0000057527486,0.9171335,0.0011608086,0.0001930754,0.00033576685,3.026075e-8,0.00055096974,0.079483144],"genre_scores_gemma":[0.9346162,0.000005549684,0.052112654,0.008017865,0.00016298782,0.000026981137,0.000002482536,0.000025337615,0.0050299237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979286,0.000042453332,0.0004198978,0.00055833324,0.00048654096,0.0005641672],"domain_scores_gemma":[0.9987743,0.00017665174,0.00012228459,0.0004603033,0.000076917044,0.00038956292],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021513664,0.00025797638,0.00025007754,0.000059810827,0.00018186113,0.00038768587,0.0011727534,0.00008570146,0.00042406542],"category_scores_gemma":[0.00013284321,0.00024782505,0.000082247316,0.00052211864,0.000025167965,0.0002502075,0.00049494003,0.0003798399,0.0016322031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013953439,0.0000059491795,0.00009732052,0.000018550132,0.000025427802,0.000007921572,0.0010027763,0.9758001,0.0019404894,0.016193204,0.0009627316,0.0039315918],"study_design_scores_gemma":[0.00042187376,0.00040005724,0.00024555917,0.000007703684,0.000008205816,0.0000016347071,0.0001773153,0.98780954,0.0032645704,0.000056276625,0.007235914,0.00037133705],"about_ca_topic_score_codex":0.00002108546,"about_ca_topic_score_gemma":0.0000042375655,"teacher_disagreement_score":0.93347925,"about_ca_system_score_codex":0.00007506745,"about_ca_system_score_gemma":0.00008983157,"threshold_uncertainty_score":0.9999974},"labels":[],"label_agreement":null},{"id":"W3126150352","doi":"10.48550/arxiv.2102.03718","title":"An Analysis of Frame-skipping in Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Frame (networking); Task (project management); Inertia; Offset (computer science); Consistency (knowledge bases); Action (physics); Artificial intelligence; Machine learning; Algorithm","score_opus":0.05482070555975511,"score_gpt":0.20925271551283764,"score_spread":0.15443200995308254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126150352","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":[0.3022441,0.00001893473,0.6963251,0.000010834955,0.0001448846,0.00011580015,4.1725627e-7,0.00008802232,0.00105189],"genre_scores_gemma":[0.99510187,0.00013736395,0.004011222,0.00004254106,0.000015845719,6.561197e-7,0.00007222542,0.000014138103,0.0006041603],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755,0.0002995363,0.0004826298,0.00105037,0.00021767861,0.00039978605],"domain_scores_gemma":[0.9972567,0.00013293147,0.0006104424,0.0016320759,0.00023137892,0.00013647611],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053777883,0.00030170113,0.0006772297,0.0014033222,0.00009251407,0.00018202799,0.0019653256,0.0003059907,0.00008617321],"category_scores_gemma":[0.00010186248,0.000394245,0.00030180273,0.0029353204,0.00007422347,0.00057680917,0.0019224384,0.0010121681,0.000007071609],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068685636,0.000038062917,0.04177734,0.000056032248,0.00044615738,0.00012591382,0.0010978393,0.941169,0.000095285235,0.015085568,0.0000012542133,0.00010062525],"study_design_scores_gemma":[0.00023187614,0.000085184736,0.00996433,0.00013440974,0.00032116094,4.2971564e-7,0.00048470587,0.988154,0.000105090905,0.00013332246,0.000027862561,0.0003576356],"about_ca_topic_score_codex":0.0005733774,"about_ca_topic_score_gemma":0.00009599322,"teacher_disagreement_score":0.69285774,"about_ca_system_score_codex":0.0003472419,"about_ca_system_score_gemma":0.00023893482,"threshold_uncertainty_score":0.9998509},"labels":[],"label_agreement":null},{"id":"W3126457215","doi":"10.1007/s00521-023-09096-6","title":"hammer: Multi-level coordination of reinforcement learning agents via learned messaging","year":2023,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Representation (politics); Artificial intelligence; Information sharing; Distributed computing; Artificial neural network; Embodied agent; Human–computer interaction; Machine learning; Embodied cognition; World Wide Web","score_opus":0.07241711314584617,"score_gpt":0.32680994064118757,"score_spread":0.2543928274953414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126457215","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":[0.01014149,0.000024878578,0.98796254,0.00056368206,0.0000638088,0.0002772573,3.6902884e-7,0.00039727864,0.0005687212],"genre_scores_gemma":[0.9876514,0.000016768732,0.010340302,0.00008166159,0.000032418266,0.000021015738,0.000023177714,0.00001243123,0.0018208356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987166,0.00006146014,0.00035230184,0.0003325569,0.00026342712,0.0002736539],"domain_scores_gemma":[0.99910104,0.00016089389,0.0002568111,0.00030381625,0.000106278596,0.00007114965],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036733627,0.00013210296,0.00015651234,0.00017872486,0.00044895327,0.0000945825,0.00039449707,0.00004454948,0.0000032883236],"category_scores_gemma":[0.00005352496,0.00013880189,0.000046245754,0.00077101326,0.000051259147,0.00016303213,0.00041466544,0.00022097013,0.000034404016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.565068e-7,0.000009674683,0.0017963665,0.00003449903,0.000014051385,5.1802897e-7,0.000322388,0.93127435,0.0012484823,0.005253341,0.00008775407,0.059957724],"study_design_scores_gemma":[0.00030283196,0.0000398495,0.008993527,0.000021981492,0.000009649002,0.000003967132,0.000062143365,0.9869428,0.0003968534,0.000079676254,0.0030171897,0.00012950874],"about_ca_topic_score_codex":0.000024288327,"about_ca_topic_score_gemma":4.4013078e-7,"teacher_disagreement_score":0.9776222,"about_ca_system_score_codex":0.000019242683,"about_ca_system_score_gemma":0.000016931648,"threshold_uncertainty_score":0.5660177},"labels":[],"label_agreement":null},{"id":"W3127407414","doi":"","title":"Planning from Pixels using Inverse Dynamics Models","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Task (project management); Heuristic; Computer science; Focus (optics); Artificial intelligence; Machine learning; Dynamics (music); Engineering; Psychology","score_opus":0.19904125336702247,"score_gpt":0.21294462833526798,"score_spread":0.013903374968245508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127407414","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":[0.07053713,0.000020666103,0.9248285,0.00007556336,0.00077534746,0.00021874839,0.00001975671,0.00043836527,0.003085903],"genre_scores_gemma":[0.95557404,0.000032128508,0.043511372,0.00025081716,0.000104654384,2.671004e-7,0.00007101514,0.00003565941,0.00042002447],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99762934,0.00013983663,0.00029263747,0.0013106357,0.00018584928,0.00044171754],"domain_scores_gemma":[0.9976785,0.00012856883,0.0004430972,0.0013628725,0.00012106614,0.00026586745],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013571518,0.00042551025,0.00044233285,0.00023908154,0.00020150855,0.0002840875,0.0027362136,0.00038030586,0.0000176829],"category_scores_gemma":[0.000039729566,0.00055685634,0.00022471754,0.00055317633,0.00009774091,0.00081804494,0.004663016,0.0010886525,0.00007821038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011777026,0.000011641937,0.0010715518,0.00003244771,0.00010706081,0.00040076746,0.0005812463,0.9390701,0.000022732633,0.058561023,0.00008680721,0.000042834665],"study_design_scores_gemma":[0.00031443816,0.000025090629,0.00006278549,0.00015540002,0.000085019456,0.0000017342609,0.00012614923,0.9539625,0.00001846574,0.044667747,0.000052592248,0.00052805716],"about_ca_topic_score_codex":0.0004590805,"about_ca_topic_score_gemma":0.000013151795,"teacher_disagreement_score":0.88503695,"about_ca_system_score_codex":0.00062521454,"about_ca_system_score_gemma":0.00030900902,"threshold_uncertainty_score":0.99968827},"labels":[],"label_agreement":null},{"id":"W3127605640","doi":"10.1007/s00521-021-06375-y","title":"Improving reinforcement learning with human assistance: an argument for human subject studies with HIPPO Gym","year":2021,"lang":"en","type":"preprint","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; University of Alberta; Alberta Machine Intelligence Institute; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Amazon Web Services; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Human–computer interaction; Subject (documents); Parsing; World Wide Web","score_opus":0.04079369190192602,"score_gpt":0.3265417845465773,"score_spread":0.2857480926446513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127605640","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":[0.12894407,0.00022714,0.8687284,0.00015324297,0.000073083494,0.0012667907,0.0000010288572,0.00039974006,0.0002065259],"genre_scores_gemma":[0.9418553,0.000016749927,0.056751627,0.0001142876,0.00022655031,0.0004608188,0.0001598193,0.000044963046,0.00036989056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971564,0.00010614869,0.0005530705,0.0012179735,0.00045349827,0.00051292946],"domain_scores_gemma":[0.99744105,0.00018947397,0.0007597557,0.0010093517,0.00045266352,0.00014769052],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004650394,0.00047467946,0.0005274272,0.00013462154,0.0018950746,0.0010117956,0.0007969283,0.000118733406,0.0000014524679],"category_scores_gemma":[0.000023360848,0.00040469744,0.00008224559,0.00026422198,0.00015354982,0.00022553394,0.001158517,0.0008609045,5.855324e-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":[0.00000719402,0.00003628207,0.0011768542,0.00046600835,0.00013121605,0.0000039610527,0.0012627275,0.9811525,0.0006907405,0.006926401,0.000012149759,0.00813399],"study_design_scores_gemma":[0.00092304114,0.0012021967,0.0013924104,0.0005301041,0.00015480377,0.00002448457,0.0012776215,0.9921394,0.0006385593,0.0002804533,0.0005450806,0.00089183165],"about_ca_topic_score_codex":0.000060512717,"about_ca_topic_score_gemma":0.0000385089,"teacher_disagreement_score":0.8129112,"about_ca_system_score_codex":0.0001632875,"about_ca_system_score_gemma":0.00011952979,"threshold_uncertainty_score":0.9998405},"labels":[],"label_agreement":null},{"id":"W3127742036","doi":"10.48550/arxiv.2103.00336","title":"Transformers with Competitive Ensembles of Independent Mechanisms","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transformer; Computer science; Engineering; Electrical engineering; Voltage","score_opus":0.041398407696539664,"score_gpt":0.17015250408307234,"score_spread":0.12875409638653268,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127742036","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":[0.045234576,0.00001867996,0.94678724,0.000039077237,0.00026160132,0.00026454896,0.0000048603565,0.0001102049,0.007279206],"genre_scores_gemma":[0.98567605,0.00012697554,0.0133448,0.00004464114,0.000010745021,6.8651576e-7,0.000020170686,0.000018219916,0.00075773644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982504,0.00012453919,0.00023621251,0.0008291081,0.00023774688,0.00032195382],"domain_scores_gemma":[0.99832505,0.00009266674,0.00034323282,0.0008092762,0.00030353293,0.00012622465],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018623221,0.00031326184,0.0004348802,0.00023724858,0.00008940401,0.000100448764,0.0013441051,0.00023294461,0.000048829934],"category_scores_gemma":[0.000011892289,0.0003318405,0.00018937897,0.0004909225,0.00012758693,0.00033269267,0.00091060455,0.00058896886,0.0000105438885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020423042,0.000035385994,0.00027568382,0.00009478956,0.00015767252,0.00025243848,0.0005209451,0.7481564,0.00015234848,0.25023705,0.0000032610692,0.00009355439],"study_design_scores_gemma":[0.001311167,0.00044199935,0.0010082071,0.0006861295,0.00021241537,0.000023026107,0.002436347,0.97857624,0.0094822645,0.0048123933,0.00010185795,0.00090797566],"about_ca_topic_score_codex":0.00010697752,"about_ca_topic_score_gemma":0.00006643016,"teacher_disagreement_score":0.9404414,"about_ca_system_score_codex":0.00015959886,"about_ca_system_score_gemma":0.0004102703,"threshold_uncertainty_score":0.99991333},"labels":[],"label_agreement":null},{"id":"W3128954025","doi":"10.1609/aaai.v35i9.16964","title":"Variance Penalized On-Policy and Off-Policy Actor-Critic","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Variance (accounting); Convergence (economics); Computer science; Reinforcement learning; Estimator; Moment (physics); Markov decision process; Expected return; Mathematical optimization; Minimum-variance unbiased estimator; Variance risk premium; Econometrics; Mathematics; Artificial intelligence; Markov process; Statistics; Economics","score_opus":0.06320478828266483,"score_gpt":0.3209269653549211,"score_spread":0.25772217707225625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128954025","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":[0.11767061,0.0002723778,0.5485516,0.088036336,0.00212472,0.0017890168,0.000019482195,0.0006838129,0.24085203],"genre_scores_gemma":[0.99178976,0.0002425677,0.0041885185,0.0013987412,0.00020650326,0.00001734412,5.683319e-7,0.000018098015,0.0021379085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99758285,0.00004077296,0.0005688279,0.0006314793,0.00067971885,0.00049634645],"domain_scores_gemma":[0.9978811,0.00026948258,0.00034584076,0.00051212806,0.0008358033,0.00015564832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041922487,0.00028821718,0.0003397127,0.00022324189,0.00027315307,0.00058293436,0.001742806,0.00010928893,0.00006527623],"category_scores_gemma":[0.003357226,0.00023572409,0.000112133675,0.0012559044,0.00034562414,0.00044806467,0.00071199454,0.00042913455,0.00010760384],"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":[0.000027233616,0.000068349334,0.000059841113,0.000049783015,0.000017991153,0.0000021322521,0.00085644546,0.0012596492,0.01703515,0.9495255,0.00008077407,0.031017167],"study_design_scores_gemma":[0.00012247088,0.0004073449,0.00045913164,0.0006618314,0.000022020466,0.00003741721,0.00042273986,0.22510956,0.5230493,0.24702008,0.0021306123,0.0005575013],"about_ca_topic_score_codex":0.00005235013,"about_ca_topic_score_gemma":0.0000034440277,"teacher_disagreement_score":0.87411916,"about_ca_system_score_codex":0.00010338892,"about_ca_system_score_gemma":0.0005669993,"threshold_uncertainty_score":0.96125495},"labels":[],"label_agreement":null},{"id":"W3130235457","doi":"10.1109/candarw51189.2020.00031","title":"FPGA Acceleration of ROS2-Based Reinforcement Learning Agents","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Field-programmable gate array; Robot; Artificial neural network; Robotics; Artificial intelligence; Embedded system; Latency (audio); Robot learning; Mobile robot","score_opus":0.05309554792447842,"score_gpt":0.2673577872631097,"score_spread":0.2142622393386313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130235457","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":[0.0015635532,0.000004348768,0.98239857,0.0012934717,0.000094240444,0.0001530112,5.260179e-8,0.00020324097,0.014289486],"genre_scores_gemma":[0.9691684,0.0000032614896,0.027771452,0.0016240154,0.000031737145,0.0000047193503,0.000008522688,0.000008015349,0.0013798364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874294,0.000046749774,0.0003446748,0.00023042777,0.00044093482,0.00019429576],"domain_scores_gemma":[0.9993152,0.000048471808,0.00018908037,0.00025847502,0.00008931344,0.00009946037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015859505,0.00011238759,0.00014019353,0.000057971534,0.00008240022,0.00010530679,0.0005752437,0.00004209343,0.00023083563],"category_scores_gemma":[0.00012794879,0.000106293126,0.00006076563,0.00033336764,0.000020364994,0.00037485268,0.00019195424,0.00014843338,0.000114276714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049674686,0.0000061165542,0.0010327804,0.000023304967,0.000008948826,0.0000015061812,0.00035626165,0.98830634,0.0011678154,0.0070693176,0.0006899027,0.0013327355],"study_design_scores_gemma":[0.00036648737,0.00027842826,0.00045617108,0.000009964758,0.0000039017445,2.2106342e-7,0.000022017737,0.97081566,0.023695953,0.0000073724264,0.0042334017,0.00011043062],"about_ca_topic_score_codex":0.000010343803,"about_ca_topic_score_gemma":2.119961e-7,"teacher_disagreement_score":0.9676049,"about_ca_system_score_codex":0.000029692706,"about_ca_system_score_gemma":0.00006374557,"threshold_uncertainty_score":0.4334508},"labels":[],"label_agreement":null},{"id":"W3130843035","doi":"","title":"Conservative Safety Critics for Exploration","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Task (project management); Suite; Upper and lower bounds; Artificial intelligence; Machine learning; Mathematical optimization; Engineering; Mathematics; Law","score_opus":0.11749702201540502,"score_gpt":0.379141317792146,"score_spread":0.261644295776741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130843035","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":[0.00038618478,0.0000055406927,0.9230995,0.020756116,0.0007723424,0.00017681353,0.00000884677,0.00016544528,0.054629173],"genre_scores_gemma":[0.91065323,0.00007504399,0.063025914,0.00085632846,0.0001613198,0.00012611448,0.00037160687,0.000018582341,0.024711857],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984492,0.00014256693,0.00034237228,0.00042550347,0.0004452711,0.0001950974],"domain_scores_gemma":[0.997215,0.0007006772,0.00017196058,0.0003388001,0.0015064784,0.00006711167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002116543,0.00013028337,0.00012903499,0.00012538106,0.00031064372,0.00047878874,0.0005230504,0.000056929937,0.00022313885],"category_scores_gemma":[0.0020706852,0.00014762346,0.000086422544,0.0002454846,0.00007975584,0.00083432184,0.00014779862,0.00026327826,0.000106882755],"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":[0.000014894974,0.00003472692,0.00064505904,0.000005101281,0.000046703546,0.000009367834,0.0012168812,0.25148338,0.0006253039,0.7428561,0.000745949,0.0023165403],"study_design_scores_gemma":[0.0006166069,0.00011281522,0.0011096634,0.000056398963,0.0000094078,0.000011231806,0.0016148782,0.95872253,0.0027204065,0.015282397,0.019538995,0.0002046517],"about_ca_topic_score_codex":0.000015437403,"about_ca_topic_score_gemma":0.00001086767,"teacher_disagreement_score":0.91026706,"about_ca_system_score_codex":0.00009041642,"about_ca_system_score_gemma":0.0002562981,"threshold_uncertainty_score":0.601991},"labels":[],"label_agreement":null},{"id":"W3131011999","doi":"","title":"Memory-based Deep Reinforcement Learning for POMDP.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Markov decision process; Observable; Artificial intelligence; Component (thermodynamics); Noise (video); Feature engineering; Process (computing); Robotics; Feature (linguistics); Machine learning; Deep learning; Markov process; Markov chain; Markov model; Robot; Mathematics","score_opus":0.06249373525342344,"score_gpt":0.19857316350256013,"score_spread":0.13607942824913669,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131011999","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":[0.0042553307,0.000051894593,0.99010146,0.00013110957,0.00096190773,0.0006587199,7.95083e-7,0.0004497361,0.0033890316],"genre_scores_gemma":[0.9745155,0.00005227962,0.017614841,0.0002903337,0.000097586824,0.000006522434,0.00014819448,0.000041856587,0.007232896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971863,0.00017562706,0.00038475252,0.0013661188,0.00022723028,0.0006599824],"domain_scores_gemma":[0.9968781,0.00029413227,0.00054379465,0.0016190833,0.0004362953,0.00022858339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044961678,0.0004763023,0.0004887805,0.00033632122,0.00037385622,0.0004336127,0.0022677947,0.00038362676,0.000091362825],"category_scores_gemma":[0.00020539148,0.0005998844,0.00047768006,0.0005639443,0.00009036101,0.00041153343,0.0021322463,0.0007412893,0.00005626447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023279466,0.000027115957,0.00030789818,0.00019255473,0.00011040387,0.00012513057,0.00024366193,0.9853114,0.000034311703,0.013123415,0.00010678212,0.00039406845],"study_design_scores_gemma":[0.000926878,0.00015136368,0.000059043672,0.00014987258,0.000092063565,0.0000019567713,0.0001536456,0.9952304,0.0005944819,0.00047847818,0.0015285764,0.0006332674],"about_ca_topic_score_codex":0.000057134268,"about_ca_topic_score_gemma":0.000012026143,"teacher_disagreement_score":0.9724866,"about_ca_system_score_codex":0.00045262606,"about_ca_system_score_gemma":0.00054711517,"threshold_uncertainty_score":0.99964523},"labels":[],"label_agreement":null},{"id":"W3131546278","doi":"10.1609/aaai.v35i13.17378","title":"How RL Agents Behave When Their Actions Are Modified","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Action (physics); Supervisor; Markov decision process; Computer science; Process (computing); Q-learning; Reinforcement; Control (management); Risk analysis (engineering); Intervention (counseling); Artificial intelligence; Markov process; Psychology; Business; Social psychology; Mathematics; Political science; Law","score_opus":0.21135287046727055,"score_gpt":0.31668126810195774,"score_spread":0.10532839763468718,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131546278","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":[0.05571116,0.0000633569,0.9059023,0.015615534,0.0036529226,0.0014215622,0.000024037832,0.00037411,0.017234962],"genre_scores_gemma":[0.9893325,0.0001282937,0.007306213,0.00025478165,0.000153774,0.000093699666,0.0000059996773,0.000036961403,0.0026877928],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963326,0.00005284521,0.0008017552,0.0011696497,0.001046528,0.00059665943],"domain_scores_gemma":[0.99529064,0.00012153169,0.0015338406,0.0011686273,0.001717315,0.00016806145],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00049038435,0.00060678733,0.0006643537,0.00025534292,0.00036779972,0.0025167111,0.0055483845,0.00042182434,0.0000692743],"category_scores_gemma":[0.0007517709,0.00048638496,0.00043460366,0.0005008172,0.0003354616,0.00063922274,0.004000958,0.0016391806,0.00004560231],"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":[0.00006652023,0.0005364755,0.00060507515,0.00065064407,0.00034856735,0.000007825822,0.014489085,0.14426711,0.014783339,0.786023,0.0015455832,0.036676772],"study_design_scores_gemma":[0.000038806676,0.00015402395,0.00033166344,0.0016176982,0.00006816451,0.000007401172,0.003357694,0.7408228,0.18178494,0.07070894,0.00033385793,0.00077398657],"about_ca_topic_score_codex":0.00005976595,"about_ca_topic_score_gemma":0.000015530059,"teacher_disagreement_score":0.93362135,"about_ca_system_score_codex":0.00018255612,"about_ca_system_score_gemma":0.00034111732,"threshold_uncertainty_score":0.9998321},"labels":[],"label_agreement":null},{"id":"W3132054471","doi":"10.48550/arxiv.2102.08607","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Convexity; Truncation (statistics); Variance (accounting); Convergence (economics); Term (time); Mathematics; Variance reduction; Applied mathematics; Reinforcement learning; Mathematical optimization; Function (biology); Sample (material); Computer science; Statistics; Economics; Physics; Artificial intelligence; Monte Carlo method","score_opus":0.06947985645106997,"score_gpt":0.22228006022886093,"score_spread":0.15280020377779097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132054471","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":[0.10960469,0.000022891598,0.88834965,0.00028540287,0.00041634715,0.00023472955,0.000005119303,0.00005654306,0.001024654],"genre_scores_gemma":[0.9812689,0.00015664574,0.017934997,0.00016324403,0.000028405928,8.6997466e-7,0.0000036215101,0.000010381334,0.0004329611],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981287,0.000334392,0.00023421056,0.00082901085,0.0001608655,0.0003127932],"domain_scores_gemma":[0.9968296,0.001131019,0.0003643816,0.001394115,0.00017104056,0.000109842855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005012422,0.00025298455,0.00031510074,0.00021897088,0.00017375586,0.000104311,0.0017377513,0.00014630702,0.00003743876],"category_scores_gemma":[0.0006085421,0.0002290288,0.00014445152,0.00088980957,0.00018896155,0.00013686849,0.0020676,0.0004926563,0.000007713011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004577769,0.00002291858,0.00015066583,0.000032033204,0.000035633733,0.000015106474,0.00046211196,0.59049976,0.0000946938,0.40857565,0.00001967917,0.000087177395],"study_design_scores_gemma":[0.00020427497,0.00009417254,0.0007046755,0.00011610392,0.00003612772,0.0000034461364,0.00012652017,0.97725815,0.0012300233,0.019894907,0.0000738236,0.00025777885],"about_ca_topic_score_codex":0.000561559,"about_ca_topic_score_gemma":0.0000054149737,"teacher_disagreement_score":0.87166417,"about_ca_system_score_codex":0.00013470852,"about_ca_system_score_gemma":0.00039620133,"threshold_uncertainty_score":0.93395233},"labels":[],"label_agreement":null},{"id":"W3132089310","doi":"10.1109/iros45743.2020.9341019","title":"Learning Domain Randomization Distributions for Training Robust Locomotion Policies","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Context (archaeology); Machine learning; Task (project management); Generalization; Extrapolation; Domain (mathematical analysis); Interpolation (computer graphics); Range (aeronautics); Mathematics; Statistics; Engineering","score_opus":0.05326927639304079,"score_gpt":0.25799983112925,"score_spread":0.2047305547362092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132089310","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":[0.0007372155,0.0000055021605,0.9887339,0.007565741,0.00010336715,0.0003478607,0.0000012647746,0.0004249464,0.0020801888],"genre_scores_gemma":[0.7170074,0.0000051091624,0.28178692,0.0004903669,0.00014477971,0.000034959412,0.00006855028,0.0000115538005,0.00045032968],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902177,0.000073646836,0.0002477261,0.00022712472,0.00017261915,0.00025714125],"domain_scores_gemma":[0.9993808,0.00018627619,0.00011232885,0.00013389532,0.00008943059,0.00009723442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029847593,0.00010756906,0.00015304053,0.000047016965,0.00032767956,0.00022514773,0.000335899,0.0000474113,0.000021942142],"category_scores_gemma":[0.00047335523,0.000102221034,0.000080871316,0.00036363478,0.000028436583,0.00040503617,0.00009678172,0.00012708151,0.000022610679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011807602,0.0000041704607,0.000097938726,0.000010075803,0.000009814865,2.827917e-7,0.0026634159,0.8902642,0.00025694337,0.104279816,0.0005021542,0.0018993792],"study_design_scores_gemma":[0.0017276678,0.00015370669,0.00010572784,0.00000884429,0.0000068034246,0.0000018863619,0.00041629604,0.98846495,0.0002862322,0.0005634004,0.0081327995,0.00013168673],"about_ca_topic_score_codex":0.000004194711,"about_ca_topic_score_gemma":7.779673e-7,"teacher_disagreement_score":0.7162702,"about_ca_system_score_codex":0.00003947231,"about_ca_system_score_gemma":0.000044073684,"threshold_uncertainty_score":0.4168453},"labels":[],"label_agreement":null},{"id":"W3132255199","doi":"","title":"C-Learning: Horizon-Aware Cumulative Accessibility Estimation","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reachability; Reinforcement learning; Computer science; Motion planning; Time horizon; Generalization; Sample (material); Reliability (semiconductor); Set (abstract data type); Path (computing); Code (set theory); Field (mathematics); Machine learning; Artificial intelligence; Mathematical optimization; Robot; Theoretical computer science; Mathematics","score_opus":0.06374053049019669,"score_gpt":0.3772116194799136,"score_spread":0.31347108898971693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132255199","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":[0.020225877,0.000006459585,0.89342767,0.0039435094,0.00079655397,0.00015637891,0.000002503164,0.00042897474,0.081012055],"genre_scores_gemma":[0.97135603,0.00003110097,0.012156782,0.00011341897,0.00009398664,0.000039764178,0.00021089103,0.000017435967,0.015980579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971392,0.00040647484,0.00048110067,0.00075668225,0.0009282992,0.00028824815],"domain_scores_gemma":[0.99726117,0.00053255307,0.00036736001,0.0005558718,0.0011598624,0.00012319292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034270828,0.00021784953,0.00019677951,0.00022128073,0.00043905055,0.00089830207,0.0009341544,0.00009922024,0.00087126],"category_scores_gemma":[0.0023883507,0.00023661328,0.00012043117,0.0005405361,0.000084212006,0.001143502,0.00043106053,0.00081205025,0.00041206976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010917045,0.000066484194,0.009806041,0.0000071433046,0.00006589598,0.00003526615,0.0015221755,0.8531891,0.0004937368,0.1201723,0.00018793823,0.014442975],"study_design_scores_gemma":[0.00037727278,0.00016579941,0.015191111,0.00006286294,0.00000947195,0.000016807517,0.0006901455,0.9762689,0.0011984883,0.0042728744,0.0015055772,0.00024070371],"about_ca_topic_score_codex":0.000032049236,"about_ca_topic_score_gemma":0.0000047842477,"teacher_disagreement_score":0.95113015,"about_ca_system_score_codex":0.00017644178,"about_ca_system_score_gemma":0.00031734203,"threshold_uncertainty_score":0.96488094},"labels":[],"label_agreement":null},{"id":"W3132477017","doi":"","title":"Non-Linear Rewards For Successor Features","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Successor cardinal; Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Feature (linguistics); Function (biology); Term (time); Mathematics","score_opus":0.01908450848725854,"score_gpt":0.2887595636198263,"score_spread":0.26967505513256773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132477017","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":[0.00037029877,0.00003238827,0.9764017,0.0023103992,0.0005102907,0.00011576278,5.3202984e-7,0.00014154558,0.020117119],"genre_scores_gemma":[0.15871532,0.000013582099,0.75493187,0.0021287494,0.00022677168,0.000024961026,0.000015101701,0.000016738868,0.08392692],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991258,0.000012902818,0.00014337283,0.000268893,0.00021269372,0.00023637166],"domain_scores_gemma":[0.9991013,0.000095198295,0.000044250613,0.00050933444,0.00019006769,0.000059848237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015497474,0.00008984643,0.000112694535,0.000035819652,0.00010116601,0.00017053972,0.00055323297,0.00005302762,0.00004747259],"category_scores_gemma":[0.00013056565,0.00007824143,0.00007475284,0.00023034381,0.000015334848,0.00024210438,0.00023338484,0.00009076601,0.000055938475],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014118537,0.0000722903,0.0015661446,0.00013374718,0.00009616573,0.00006328967,0.00079179695,0.6197046,0.0031631617,0.26632282,0.09543263,0.012639211],"study_design_scores_gemma":[0.0004855062,0.000090219924,0.0013318673,0.000014240874,0.0000070628857,0.000019097148,0.00003151549,0.8906911,0.037348203,0.0005970856,0.06916698,0.00021708837],"about_ca_topic_score_codex":0.0000080013015,"about_ca_topic_score_gemma":0.0000048548322,"teacher_disagreement_score":0.2709865,"about_ca_system_score_codex":0.000020154566,"about_ca_system_score_gemma":0.00009315435,"threshold_uncertainty_score":0.31905928},"labels":[],"label_agreement":null},{"id":"W3133261350","doi":"","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Task (project management); Computer science; Perception; Benchmark (surveying); Social intelligence; Human–computer interaction; Artificial intelligence; Human intelligence; Intelligent agent; Knowledge management; Data science; Psychology; Engineering; Social psychology","score_opus":0.07150864535425586,"score_gpt":0.22592537345845154,"score_spread":0.15441672810419568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133261350","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":[0.1901025,0.000010105666,0.8076829,0.0011881092,0.00007780163,0.000119224154,0.0000012171985,0.00006723416,0.0007509597],"genre_scores_gemma":[0.99525875,0.000056665234,0.0014859006,0.0001250627,0.000055125187,6.526108e-7,0.000008155811,0.0000058620267,0.0030038322],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993307,0.000048021593,0.00008056272,0.00034262423,0.000048953953,0.00014911129],"domain_scores_gemma":[0.9995224,0.000038438,0.000056213674,0.00016057237,0.00017299702,0.000049403574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010630517,0.00008603956,0.000100452125,0.000043258755,0.0003482694,0.00012187474,0.000148539,0.000073592826,0.000010758061],"category_scores_gemma":[0.000019079096,0.00010517032,0.000031409214,0.00025898192,0.000052370997,0.00050543196,0.00016020161,0.00008013416,0.0000069474536],"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":[0.0000152268485,0.000040787116,0.0022138888,0.000057628495,0.000034658922,0.00003509952,0.0027809315,0.04489533,0.0019165567,0.9464908,0.0004690234,0.0010500296],"study_design_scores_gemma":[0.001515732,0.00025282882,0.009148941,0.000019570054,0.00005206428,0.0000058243095,0.0012630379,0.9714877,0.0002142944,0.008796099,0.006897051,0.00034683538],"about_ca_topic_score_codex":0.0000072290277,"about_ca_topic_score_gemma":0.000023494544,"teacher_disagreement_score":0.9376947,"about_ca_system_score_codex":0.000059741553,"about_ca_system_score_gemma":0.00004489171,"threshold_uncertainty_score":0.42887214},"labels":[],"label_agreement":null},{"id":"W3134156689","doi":"10.48550/arxiv.2103.00107","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Convergence (economics); Lambda; Algorithm; Function (biology); Computer science; Mathematics; Artificial intelligence; Physics; Economics; Quantum mechanics","score_opus":0.07805414104499778,"score_gpt":0.20661398747231488,"score_spread":0.1285598464273171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134156689","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":[0.010863432,0.0001069606,0.9819923,0.00012255217,0.0006937198,0.0006254183,0.0000012288444,0.0004676792,0.0051267343],"genre_scores_gemma":[0.97268313,0.00023852827,0.015792537,0.00013580418,0.00021097582,0.000005154887,0.00009827048,0.00004774079,0.010787872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968472,0.00019303916,0.00047389124,0.0015294793,0.00023321636,0.00072315725],"domain_scores_gemma":[0.996762,0.000299577,0.0006836021,0.0015662498,0.0004753721,0.00021322108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006551612,0.0004994103,0.0005649615,0.00027734876,0.0004744309,0.0006192318,0.002225643,0.00036420708,0.00005043736],"category_scores_gemma":[0.00029740806,0.0006388715,0.00047582758,0.00048475846,0.00006776971,0.00066861935,0.0038405354,0.0011850498,0.000040593535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000135031505,0.000011650251,0.0005230828,0.00027915955,0.00012422784,0.00011623959,0.00051476265,0.9608516,0.00004705261,0.036172725,0.000060842736,0.0012851185],"study_design_scores_gemma":[0.00056062185,0.0000789101,0.000084646264,0.0003724652,0.00009305465,0.000005159633,0.0001914085,0.9948368,0.00012835284,0.0015066777,0.0014784884,0.00066339807],"about_ca_topic_score_codex":0.00004124794,"about_ca_topic_score_gemma":0.0000026626203,"teacher_disagreement_score":0.96619976,"about_ca_system_score_codex":0.00043602573,"about_ca_system_score_gemma":0.00037187428,"threshold_uncertainty_score":0.99960625},"labels":[],"label_agreement":null},{"id":"W3134456772","doi":"10.48550/arxiv.2103.03216","title":"Continuous Coordination As a Realistic Scenario for Lifelong Learning","year":2021,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Lifelong learning; Computer science; Reinforcement learning; Testbed; Benchmark (surveying); Task (project management); Artificial intelligence; Engineering","score_opus":0.01464353487020289,"score_gpt":0.2543663899315203,"score_spread":0.23972285506131738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3134456772","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":[0.0063239285,0.0008966964,0.9813519,0.0053519523,0.00091677613,0.002103689,0.000013094818,0.0020496335,0.0009922914],"genre_scores_gemma":[0.59075886,0.00021459367,0.39800814,0.0017355469,0.00036299886,0.0014980612,0.00041736287,0.00014728784,0.006857144],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949713,0.0004086651,0.0010814444,0.0014488754,0.0008723103,0.0012174255],"domain_scores_gemma":[0.99487287,0.0005883575,0.0011378743,0.0021211726,0.0008632784,0.00041646848],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0016706077,0.0007780836,0.0009817872,0.00071733963,0.0005863003,0.0023911025,0.0024393601,0.001000492,0.00002054716],"category_scores_gemma":[0.002986751,0.00090991944,0.0005251477,0.00065618125,0.000102086786,0.0005922665,0.0027629677,0.0021194564,0.000020811038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041568852,0.00011745327,0.0044155405,0.0003471465,0.00018031303,0.0001571045,0.0011262479,0.9224471,0.0008029299,0.05302052,0.0027845302,0.0145595595],"study_design_scores_gemma":[0.00059961656,0.0003034988,0.0024579137,0.00049097894,0.00009260793,0.00012150135,0.0001351218,0.98619765,0.0013809643,0.0026407938,0.0046278117,0.00095151924],"about_ca_topic_score_codex":0.006452071,"about_ca_topic_score_gemma":0.00048526318,"teacher_disagreement_score":0.5844349,"about_ca_system_score_codex":0.0012051318,"about_ca_system_score_gemma":0.0014928114,"threshold_uncertainty_score":0.99933517},"labels":[],"label_agreement":null},{"id":"W3136163870","doi":"10.48550/arxiv.2011.13897","title":"Latent Skill Planning for Exploration and Transfer","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Leverage (statistics); Suite; Task (project management); Adaptation (eye); Amortization; Knowledge transfer; Transfer of learning; Artificial intelligence; Machine learning; Human–computer interaction; Knowledge management","score_opus":0.14792688945634863,"score_gpt":0.19303798547250298,"score_spread":0.045111096016154345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136163870","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":[0.038362697,0.000009131836,0.96046543,0.0005671534,0.000058964524,0.00013911458,6.1678213e-7,0.00010950832,0.00028735606],"genre_scores_gemma":[0.9966606,0.000018980349,0.0027228121,0.00032215173,0.000025215342,3.8572455e-7,0.0000028004283,0.000005513583,0.00024153368],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99945116,0.00001926973,0.00007317731,0.0002809999,0.000036476456,0.00013889284],"domain_scores_gemma":[0.9996635,0.000052029383,0.000023028377,0.00013148232,0.00003738905,0.00009262328],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005863132,0.00007774146,0.00008010323,0.000038695143,0.00009958383,0.00005473074,0.00025352166,0.000035823992,0.0000036415895],"category_scores_gemma":[0.000019001825,0.00008673711,0.0000342373,0.00020742817,0.000022518292,0.00064601103,0.00006765663,0.00006624301,0.000013084873],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014326751,0.0000041421354,0.0010154421,0.000013426288,0.000010553277,0.000014361679,0.0013033032,0.91105753,0.00009248418,0.08618052,0.00008239188,0.00021153163],"study_design_scores_gemma":[0.00046747166,0.00014265276,0.00030659582,0.000008715294,0.000011226315,6.418433e-7,0.00009812376,0.9966184,0.0002706959,0.00094716693,0.0010178847,0.00011046056],"about_ca_topic_score_codex":0.0000018807509,"about_ca_topic_score_gemma":3.4126782e-7,"teacher_disagreement_score":0.9582979,"about_ca_system_score_codex":0.000017333015,"about_ca_system_score_gemma":0.000015321511,"threshold_uncertainty_score":0.35370368},"labels":[],"label_agreement":null},{"id":"W3136181012","doi":"10.1109/access.2021.3065710","title":"A Hybrid Multi-Task Learning Approach for Optimizing Deep Reinforcement Learning Agents","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Machine learning; Field (mathematics); Multi-task learning; Deep learning; Engineering","score_opus":0.0610404448592446,"score_gpt":0.314948900322499,"score_spread":0.2539084554632544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136181012","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":[0.002067663,0.000114452,0.99292564,0.00008263794,0.0007487669,0.00049961987,3.099339e-7,0.00042254908,0.003138366],"genre_scores_gemma":[0.71650964,0.00006695959,0.27734897,0.0004110755,0.00016509232,0.00014573116,0.00007254886,0.00005419055,0.0052258237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99688154,0.00018558971,0.0005941663,0.0008757195,0.00061988074,0.00084309245],"domain_scores_gemma":[0.9981209,0.00020768176,0.0004047782,0.0007150714,0.0003539771,0.00019758542],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00061847764,0.00034855556,0.00038408593,0.0001887106,0.0007125878,0.0013598885,0.0018626758,0.00009993956,0.000035621408],"category_scores_gemma":[0.00043921592,0.00037628118,0.00021564809,0.00048750686,0.00004622333,0.0015183243,0.0008916667,0.00064789905,0.000039619823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009208357,0.00004408321,0.0007452704,0.000100957994,0.00007889352,0.000035846188,0.00066158327,0.9927038,0.0006136471,0.0003745431,0.00027133047,0.0043608686],"study_design_scores_gemma":[0.0011666785,0.00010099528,0.00010526442,0.00004827808,0.000028959998,0.00003182616,0.00010273197,0.98437685,0.008048291,0.000022234699,0.005520173,0.00044770035],"about_ca_topic_score_codex":0.000018949793,"about_ca_topic_score_gemma":8.9170214e-7,"teacher_disagreement_score":0.71557665,"about_ca_system_score_codex":0.00016277864,"about_ca_system_score_gemma":0.00014501288,"threshold_uncertainty_score":0.9998689},"labels":[],"label_agreement":null},{"id":"W3136492000","doi":"10.1177/1059712321999421","title":"Affordance as general value function: a computational model","year":2021,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Reinforcement Learning in Robotics","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 Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Affordance; Computer science; Perception; Reinforcement learning; Artificial intelligence; Action (physics); Function (biology); Cognitive science; Perspective (graphical); Explication; Value (mathematics); Scalability; Human–computer interaction; Machine learning; Psychology; Epistemology","score_opus":0.030329927443571846,"score_gpt":0.2752280964595858,"score_spread":0.24489816901601394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136492000","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":[0.023524102,0.000057055066,0.97179973,0.00022046966,0.00038527406,0.00013105104,0.000002570163,0.00014998745,0.0037297579],"genre_scores_gemma":[0.529314,0.0000027008339,0.4602872,0.0007571842,0.000053689542,0.000046565587,0.000018230417,0.000013359198,0.00950704],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857944,0.000051563264,0.00021631688,0.00041491783,0.0004769393,0.00026082215],"domain_scores_gemma":[0.99909145,0.000045582707,0.000090324305,0.00039309033,0.00028199668,0.00009753622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009151616,0.00015144216,0.00013833457,0.00005121762,0.00017349915,0.00013292303,0.00037661745,0.000058717007,0.000066584646],"category_scores_gemma":[0.0000215966,0.00016432216,0.00008856886,0.00029933575,0.000047846865,0.0004655253,0.00026015614,0.00017949352,0.00022673854],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049791465,0.00003862474,0.00023479665,0.000001239104,0.000010096373,0.00004641952,0.00008672596,0.7375884,0.0003496949,0.26001796,0.0002834872,0.0013375763],"study_design_scores_gemma":[0.0003282483,0.00012174005,0.004632491,0.000009447794,0.000026918722,0.00005761553,0.000020443296,0.9899372,0.00060746557,0.0034772991,0.0005819716,0.00019916109],"about_ca_topic_score_codex":0.000007716307,"about_ca_topic_score_gemma":0.000001439911,"teacher_disagreement_score":0.5115125,"about_ca_system_score_codex":0.00008597457,"about_ca_system_score_gemma":0.00032962995,"threshold_uncertainty_score":0.6700863},"labels":[],"label_agreement":null},{"id":"W3136541527","doi":"10.1287/moor.2022.1331","title":"Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability","year":2022,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Markov decision process; Partially observable Markov decision process; Convergence (economics); Bellman equation; Mathematical optimization; Mathematics; Limit (mathematics); Stability (learning theory); Filter (signal processing); Q-learning; Reinforcement learning; Optimal control; Ergodicity; Markov chain; Applied mathematics; Computer science; Markov process; Artificial intelligence; Machine learning","score_opus":0.19567375944599658,"score_gpt":0.3990674966197256,"score_spread":0.20339373717372905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136541527","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":[0.39721042,0.000033147935,0.6012613,0.00039701484,0.000025123765,0.0005194405,0.000011562002,0.000019796256,0.0005222084],"genre_scores_gemma":[0.84846663,0.000015476182,0.15093961,0.000007739051,0.000004391635,0.00005756113,0.0000054234306,0.00000872486,0.0004944034],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786466,0.0003533252,0.00055161986,0.00021309368,0.00077874825,0.00023856176],"domain_scores_gemma":[0.9971887,0.0013538742,0.0001229222,0.00058061763,0.00070591114,0.000048009573],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033846025,0.00008664653,0.00025961894,0.00017740947,0.00048180527,0.00007525148,0.00067778386,0.00003345328,0.00014438451],"category_scores_gemma":[0.0013360075,0.000085584754,0.000060181825,0.0005070648,0.00035227102,0.0002130654,0.00094873604,0.00030288304,0.0000015644682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008553389,0.00014149214,0.00035567614,0.00039549542,0.000028111099,1.5474824e-7,0.009657264,0.9354561,0.005158649,0.048685305,0.0000337799,0.00007942629],"study_design_scores_gemma":[0.00023771393,0.0004406867,0.0003147298,0.000018865876,0.000005949748,0.0000015047887,0.0027147103,0.9825591,0.012241159,0.001310095,0.00008233423,0.00007314459],"about_ca_topic_score_codex":0.000106996165,"about_ca_topic_score_gemma":0.000004428844,"teacher_disagreement_score":0.45125625,"about_ca_system_score_codex":0.00004904203,"about_ca_system_score_gemma":0.00027590743,"threshold_uncertainty_score":0.37057054},"labels":[],"label_agreement":null},{"id":"W3139073295","doi":"10.48550/arxiv.2103.07945","title":"Learning One Representation to Optimize All Rewards","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Computer science; Representation (politics); Markov decision process; Artificial intelligence; Reinforcement learning; A priori and a posteriori; Range (aeronautics); Machine learning; Markov process; Mathematics","score_opus":0.12253217452495434,"score_gpt":0.22301649940082927,"score_spread":0.10048432487587493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3139073295","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":[0.054315798,0.000017343968,0.9376177,0.00032504785,0.0006632416,0.00031844256,8.1354506e-7,0.000422308,0.006319299],"genre_scores_gemma":[0.93461627,0.0001667716,0.054311763,0.0002753396,0.000086664055,0.0000017223416,0.000053080577,0.000028980849,0.010459392],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972544,0.00032118932,0.00029449855,0.0014273752,0.0002466041,0.000455945],"domain_scores_gemma":[0.9973011,0.00015011345,0.0003266416,0.0016294866,0.00032901662,0.0002636487],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037662245,0.00031831537,0.0004019037,0.00033409387,0.00017281734,0.00046844312,0.0019226425,0.00028535642,0.000082354774],"category_scores_gemma":[0.000289331,0.00043734274,0.00022712721,0.0008789368,0.000046507783,0.0005165689,0.004456491,0.0010361477,0.00018160918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014516349,0.000030948955,0.0010873049,0.000039186172,0.00012225521,0.00024691192,0.0010062137,0.9899661,0.00008932516,0.006825799,0.00019910155,0.0003723718],"study_design_scores_gemma":[0.00034206125,0.000102036014,0.00087240426,0.00014652587,0.00007120627,0.0000038760195,0.00025349917,0.9960559,0.0003164761,0.00048330068,0.0008534401,0.0004992512],"about_ca_topic_score_codex":0.00020005852,"about_ca_topic_score_gemma":0.000010135249,"teacher_disagreement_score":0.88330597,"about_ca_system_score_codex":0.00035282492,"about_ca_system_score_gemma":0.0002302582,"threshold_uncertainty_score":0.99980783},"labels":[],"label_agreement":null},{"id":"W3142824457","doi":"10.1142/s2737480721500059","title":"Path Following Control for UAV Using Deep Reinforcement Learning Approach","year":2021,"lang":"en","type":"article","venue":"Guidance Navigation and Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Computer science; Path (computing); Convergence (economics); Motion planning; Function (biology); Artificial intelligence; Control (management); Trajectory; Q-learning; Action (physics); Domain (mathematical analysis); Mathematical optimization; Algorithm; Control theory (sociology); Mathematics; Robot","score_opus":0.016363631021404385,"score_gpt":0.25880171570533134,"score_spread":0.24243808468392694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142824457","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":[0.004908539,0.0005948928,0.99277085,0.00024274421,0.00030662902,0.0005090731,6.8628225e-7,0.00013044021,0.00053612766],"genre_scores_gemma":[0.94072914,0.000008898717,0.057885047,0.0007759301,0.00010368207,0.000077921635,0.00002426529,0.000016438686,0.00037868656],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982008,0.00012992868,0.00045196537,0.00044802664,0.00036978628,0.00039949946],"domain_scores_gemma":[0.9988798,0.000185011,0.00025630815,0.00032858472,0.00024062516,0.00010968946],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006322405,0.0001961099,0.00030525844,0.00005060954,0.0004404229,0.00035008838,0.00026778088,0.000091115,0.0000041898325],"category_scores_gemma":[0.00025088512,0.0002022427,0.00015110226,0.00023481669,0.000028920791,0.0005051638,0.00006777137,0.00019753087,0.000004162292],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017350718,0.0000125346505,0.002607439,0.000056052362,0.000074213945,0.000008429655,0.0003591731,0.9762392,0.005622292,0.01106612,0.00001429992,0.0039228993],"study_design_scores_gemma":[0.0037665206,0.00008369336,0.00028141146,0.000081522434,0.00005169453,0.00001623382,0.00012537962,0.99344254,0.00041221117,0.00018968395,0.0013156548,0.00023344484],"about_ca_topic_score_codex":0.000006756693,"about_ca_topic_score_gemma":1.7634282e-7,"teacher_disagreement_score":0.9358206,"about_ca_system_score_codex":0.00008349238,"about_ca_system_score_gemma":0.00010756909,"threshold_uncertainty_score":0.8247218},"labels":[],"label_agreement":null},{"id":"W3143003892","doi":"10.3390/app11073068","title":"New Approach in Human-AI Interaction by Reinforcement-Imitation Learning","year":2021,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Imitation; Action (physics); Artificial intelligence; Process (computing); Asynchronous communication; Psychology; Social psychology","score_opus":0.032627967572635294,"score_gpt":0.2980415984961594,"score_spread":0.2654136309235241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3143003892","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":[0.0031367703,0.000021344837,0.8681174,0.00034935345,0.00015451084,0.0001095382,3.585717e-8,0.00009375992,0.12801729],"genre_scores_gemma":[0.9436489,0.000009146657,0.050746333,0.00043160134,0.00003793322,0.000015136244,0.000017720513,0.0000059053637,0.005087352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821955,0.00006132944,0.00031659432,0.00052287895,0.00054517284,0.00033445077],"domain_scores_gemma":[0.9993831,0.00009720734,0.0001531083,0.00025063992,0.00004296048,0.00007296333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065814273,0.0001284392,0.00013630642,0.00016726159,0.0003442016,0.0005679623,0.0006796431,0.000055684483,0.00007587433],"category_scores_gemma":[0.000058901645,0.0001302049,0.00003125461,0.001178146,0.000069343965,0.0008858094,0.0002343036,0.00031173407,0.000079882055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013821701,0.000013409169,0.00054918375,0.000006830862,0.000003975551,0.0000014804502,0.0010859697,0.8786363,0.010457657,0.101531096,0.0026622072,0.005050478],"study_design_scores_gemma":[0.0005737732,0.00009423082,0.00043787883,0.000027487107,0.0000048894203,0.000008753385,0.0016942053,0.96790147,0.015356002,0.001792942,0.011748085,0.00036031412],"about_ca_topic_score_codex":0.000045417557,"about_ca_topic_score_gemma":0.000004760884,"teacher_disagreement_score":0.9405121,"about_ca_system_score_codex":0.00008321628,"about_ca_system_score_gemma":0.00015928394,"threshold_uncertainty_score":0.54768735},"labels":[],"label_agreement":null},{"id":"W3144252049","doi":"","title":"RL Unplugged: A Collection of Benchmarks for Offline Reinforcement Learning.","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning","score_opus":0.025197425025171277,"score_gpt":0.25185865706341515,"score_spread":0.22666123203824387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3144252049","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":[0.0009418303,0.00005837385,0.9936435,0.00077700685,0.00042845216,0.00073677266,0.0000011580432,0.00023039007,0.0031824647],"genre_scores_gemma":[0.9944941,0.000006487978,0.0044579874,0.00042000288,0.00009866466,0.000076474775,0.000093732866,0.00000902856,0.00034352264],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801695,0.000050156104,0.0009835968,0.00017205786,0.0005154193,0.00026181608],"domain_scores_gemma":[0.998063,0.00007552397,0.0009936513,0.00018384267,0.0005769756,0.00010696602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003764953,0.0001754518,0.00027096702,0.00016680014,0.00027126225,0.0003930593,0.0004740007,0.000092561735,0.00000697671],"category_scores_gemma":[0.00033364107,0.00016468884,0.000077151846,0.0007095922,0.00003135724,0.0029027387,0.00010555898,0.0002010849,0.000014126306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028476385,0.000004536911,0.00017630498,0.0008822675,0.000011748379,1.6385184e-7,0.003461677,0.98687774,0.00018746061,0.0016628017,0.0027197807,0.0039870553],"study_design_scores_gemma":[0.0006391085,0.0004868511,0.000040506126,0.00009088617,0.000009874927,0.000006872939,0.000305868,0.9728975,0.000961313,0.0000058378864,0.024392968,0.00016236276],"about_ca_topic_score_codex":0.000018496889,"about_ca_topic_score_gemma":2.1687758e-7,"teacher_disagreement_score":0.99355227,"about_ca_system_score_codex":0.000072783216,"about_ca_system_score_gemma":0.00014573293,"threshold_uncertainty_score":0.6715816},"labels":[],"label_agreement":null},{"id":"W3152801112","doi":"10.48550/arxiv.2104.08543","title":"Planning with Expectation Models for Control","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Guelph","funders":"","keywords":"Reinforcement learning; Variance (accounting); Computer science; Bellman equation; Function (biology); Feature (linguistics); Artificial intelligence; Sample (material); Action (physics); Stochastic modelling; Control (management); Mathematical optimization; Mathematics; Statistics","score_opus":0.0911888882141892,"score_gpt":0.19578933152223352,"score_spread":0.10460044330804431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3152801112","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":[0.019441241,0.000031953863,0.978292,0.00004664736,0.00026514288,0.00042655884,0.0000027466792,0.0002046288,0.0012890778],"genre_scores_gemma":[0.973547,0.000010540718,0.025408553,0.00008503882,0.000043646243,0.0000038350518,0.000030569594,0.000018341238,0.00085252075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986008,0.00006719126,0.00015306221,0.0007839938,0.00010456339,0.000290429],"domain_scores_gemma":[0.9984336,0.00016781785,0.00026903205,0.0007695253,0.00026985313,0.000090210626],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013380026,0.00023316137,0.00027451478,0.00015706419,0.00014694879,0.00023304988,0.0009564363,0.00016792706,0.0000047139274],"category_scores_gemma":[0.00002426631,0.0002572865,0.00012494263,0.0002557884,0.000041846015,0.00058534724,0.00044618695,0.00032342607,0.000004005882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003494075,0.000013373481,0.0005709289,0.00005154636,0.00009632091,0.00009649772,0.000685914,0.95811087,0.0000073542483,0.040251777,0.000037082602,0.000043398522],"study_design_scores_gemma":[0.00093454245,0.00009110289,0.00013778139,0.00013843199,0.00006325228,0.0000028111758,0.00026841005,0.99554193,0.000039260463,0.0024380416,0.000035675563,0.0003087325],"about_ca_topic_score_codex":0.000019432806,"about_ca_topic_score_gemma":0.0000032711112,"teacher_disagreement_score":0.95410573,"about_ca_system_score_codex":0.00014621933,"about_ca_system_score_gemma":0.00023119358,"threshold_uncertainty_score":0.99998796},"labels":[],"label_agreement":null},{"id":"W3153326893","doi":"","title":"Approximate Multi-Agent Fitted Q Iteration.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Computation; Reinforcement learning; Mathematical optimization; Computer science; Function (biology); Property (philosophy); Mathematics; Applied mathematics; Algorithm; Artificial intelligence","score_opus":0.09705536036995745,"score_gpt":0.20003257660552953,"score_spread":0.10297721623557209,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153326893","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":[0.027280647,0.00004674159,0.9698055,0.00008695504,0.0009790083,0.00029687095,0.0000031069922,0.00038689547,0.0011142689],"genre_scores_gemma":[0.9540498,0.000114631635,0.038465995,0.00019142767,0.00005450157,0.0000015013576,0.0000777806,0.000022311337,0.0070219953],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99786663,0.00017810958,0.00027201683,0.0011431697,0.00014968737,0.00039039287],"domain_scores_gemma":[0.99754435,0.00006448375,0.00031040923,0.0016519136,0.0002653556,0.00016350787],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021083138,0.00034204873,0.00032012683,0.00022699001,0.00019752,0.00055373646,0.0018515651,0.00027903845,0.00007388366],"category_scores_gemma":[0.00006220125,0.0004164275,0.00022405069,0.00057277473,0.000065223016,0.00052529556,0.0030929667,0.0006806307,0.00012745972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031802922,0.000052180512,0.0009994535,0.000072096576,0.00007846316,0.0003298648,0.0004212445,0.9813967,0.00004545814,0.016322838,0.00015909417,0.00011946448],"study_design_scores_gemma":[0.00041611056,0.00002259642,0.0007388131,0.00009661823,0.000038474936,0.0000045524594,0.00006546156,0.9972306,0.00018057322,0.0003011295,0.00047751004,0.00042755305],"about_ca_topic_score_codex":0.00004324085,"about_ca_topic_score_gemma":0.000008269858,"teacher_disagreement_score":0.9313395,"about_ca_system_score_codex":0.00025887467,"about_ca_system_score_gemma":0.0002277037,"threshold_uncertainty_score":0.99982876},"labels":[],"label_agreement":null},{"id":"W3156545714","doi":"10.1177/10597123221095880","title":"What’s a good prediction? Challenges in evaluating an agent’s knowledge","year":2022,"lang":"en","type":"article","venue":"Adaptive Behavior","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta; Canada Research Chairs; DeepMind; Alberta Machine Intelligence Institute; Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Knowledge management; Cognitive science; Machine learning; Psychology","score_opus":0.19113708756580008,"score_gpt":0.36126874226963157,"score_spread":0.1701316547038315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156545714","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":[0.6806553,0.00869062,0.2719027,0.0016065013,0.015074707,0.00442031,0.00002797382,0.0017375404,0.015884332],"genre_scores_gemma":[0.99084234,0.00009975864,0.0067914054,0.000047630754,0.000063958025,0.0006733878,0.000010706163,0.000022109434,0.0014487109],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977512,0.00046851582,0.0003222412,0.00054921926,0.00055922306,0.00034963895],"domain_scores_gemma":[0.99898094,0.000086723936,0.00013364495,0.00061868667,0.000087717155,0.00009230536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010048498,0.00016489197,0.00016466022,0.00021767826,0.00029692746,0.00014541326,0.0009173243,0.00004261714,0.000109928595],"category_scores_gemma":[0.0000283433,0.00018858252,0.000055313125,0.00039623067,0.00003216326,0.0014253091,0.00077763834,0.00041448526,0.000044131037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038997765,0.0016249804,0.014812547,0.000019857795,0.000038864317,0.00016182724,0.045023523,0.5101568,0.0010037154,0.049923975,0.00017441643,0.37702048],"study_design_scores_gemma":[0.0011071995,0.0030821466,0.17652054,0.00004997241,0.000042238735,0.000047320216,0.009659877,0.8057382,0.00010050688,0.0001933353,0.0030276221,0.00043105963],"about_ca_topic_score_codex":0.000021404196,"about_ca_topic_score_gemma":0.000038844195,"teacher_disagreement_score":0.37658942,"about_ca_system_score_codex":0.0003293278,"about_ca_system_score_gemma":0.00014365741,"threshold_uncertainty_score":0.7690172},"labels":[],"label_agreement":null},{"id":"W3157293568","doi":"10.48550/arxiv.2104.13877","title":"Autoregressive Dynamics Models for Offline Policy Evaluation and\\n Optimization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Autoregressive model; Computer science; Conditional independence; Covariance; Feed forward; Artificial intelligence; Econometrics; Mathematics; Statistics","score_opus":0.08714489944938392,"score_gpt":0.2331941443887187,"score_spread":0.14604924493933477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157293568","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":[0.0030847027,0.0000511023,0.9947155,0.00022326171,0.00035577815,0.00066989375,0.0000099694635,0.00014843751,0.0007413602],"genre_scores_gemma":[0.90920407,0.0002246643,0.08896544,0.00008286817,0.000086892134,0.0000046348337,0.0003153012,0.00002205293,0.001094102],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983852,0.00013660824,0.0002104828,0.0008439531,0.00016271108,0.00026102524],"domain_scores_gemma":[0.9978157,0.00011213079,0.00037973202,0.0008123722,0.0007746838,0.000105348096],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037098446,0.00024850786,0.00025980247,0.00031289016,0.00016527639,0.0002640205,0.00078392815,0.00027606002,0.00000873186],"category_scores_gemma":[0.00019609848,0.000306267,0.000120854806,0.000369033,0.0000623681,0.00065278047,0.0013291029,0.0002843202,0.0000019292838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007649695,0.000014878804,0.00004737743,0.00005773851,0.00005120805,0.000008026879,0.00022001927,0.87199235,0.0000011166147,0.1269061,0.000016431482,0.0006771166],"study_design_scores_gemma":[0.00055648707,0.00004220908,0.000035121313,0.00009453867,0.000098747194,0.000002229702,0.00006507335,0.98932666,0.00000980292,0.009473529,0.0000091323245,0.00028645337],"about_ca_topic_score_codex":0.000059600392,"about_ca_topic_score_gemma":0.000012483245,"teacher_disagreement_score":0.90611935,"about_ca_system_score_codex":0.000664002,"about_ca_system_score_gemma":0.00072234735,"threshold_uncertainty_score":0.99993896},"labels":[],"label_agreement":null},{"id":"W3157951743","doi":"10.1109/iros51168.2021.9636440","title":"Seeing All the Angles: Learning Multiview Manipulation Policies for Contact-Rich Tasks from Demonstrations","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Viewpoints; Computer science; Task (project management); Artificial intelligence; Perspective (graphical); Human–computer interaction; Robot; Variety (cybernetics); Computer vision","score_opus":0.11316112666620681,"score_gpt":0.3296329576508928,"score_spread":0.21647183098468598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3157951743","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":[0.00963269,0.0004488769,0.9811292,0.0019638934,0.002309669,0.00053130573,0.000020625863,0.00007285046,0.0038908618],"genre_scores_gemma":[0.9917901,0.0006106756,0.0024104596,0.00033321933,0.00036082996,0.00011474797,0.00019172601,0.000020487681,0.004167767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755514,0.00024353295,0.00068478566,0.0005794065,0.0006063893,0.0003307288],"domain_scores_gemma":[0.99779886,0.00062879856,0.00039811063,0.0004156698,0.00065006944,0.000108472035],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004474945,0.0002849108,0.00031921413,0.00012789878,0.0004163394,0.0014139108,0.0006828125,0.00012565182,0.00011638924],"category_scores_gemma":[0.00026772026,0.00023054272,0.00012626292,0.00018317177,0.000060508846,0.00040364676,0.00016938252,0.00036369107,0.00005683004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014047037,0.00006306654,0.0033220693,0.00004410574,0.00028017207,0.000015625857,0.0029066019,0.5436469,0.0048627006,0.43937737,0.0004973869,0.004969971],"study_design_scores_gemma":[0.0002838819,0.000109447625,0.0014475385,0.0003920851,0.00003470649,0.00002288138,0.0020189448,0.9830259,0.0014685316,0.000526008,0.010379903,0.00029017928],"about_ca_topic_score_codex":0.00032220123,"about_ca_topic_score_gemma":0.00007957849,"teacher_disagreement_score":0.9821574,"about_ca_system_score_codex":0.00013619933,"about_ca_system_score_gemma":0.0001422513,"threshold_uncertainty_score":0.9996227},"labels":[],"label_agreement":null},{"id":"W3158681970","doi":"10.48550/arxiv.2104.13844","title":"A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Reinforcement learning; Bellman equation; Temporal difference learning; Function approximation; Hyperparameter; Nonlinear system; Mean squared error; Artificial neural network; Mathematical optimization; Function (biology); Computer science; Approximation error; Linear approximation; Value (mathematics); Mathematics; Applied mathematics; Algorithm; Artificial intelligence; Machine learning; Statistics","score_opus":0.07410652224032353,"score_gpt":0.2396721545053905,"score_spread":0.165565632265067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158681970","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":[0.074842185,0.0000374751,0.9221404,0.00015566638,0.00034308547,0.0011508983,0.0000012962615,0.00029696207,0.0010320386],"genre_scores_gemma":[0.9554626,0.00015434228,0.038141772,0.00012774754,0.00006963983,0.000016921582,0.00020335555,0.00003728954,0.0057863337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971901,0.00029303355,0.0005036896,0.0011933827,0.00020664571,0.00061315467],"domain_scores_gemma":[0.9977406,0.0001591883,0.00058112026,0.0010910209,0.00028834507,0.00013968423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005141936,0.00043214494,0.00050976383,0.0008221802,0.0002389627,0.000301125,0.0014615017,0.0003647853,0.000018590288],"category_scores_gemma":[0.00042191034,0.0005435501,0.00022750747,0.0012833441,0.00006593793,0.00055782264,0.00196636,0.0008190741,0.000016812211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032063475,0.00003541446,0.00044472172,0.00017370291,0.000076560085,0.00006306239,0.0009351832,0.92471206,0.000057873684,0.072880834,0.000044076172,0.00054446876],"study_design_scores_gemma":[0.0013468363,0.00014828972,0.0004009516,0.0002441731,0.000050870505,0.000002987484,0.00009520162,0.99517125,0.00015872519,0.0013609984,0.0004915494,0.00052814645],"about_ca_topic_score_codex":0.0005714744,"about_ca_topic_score_gemma":0.000045197885,"teacher_disagreement_score":0.88399863,"about_ca_system_score_codex":0.00085947197,"about_ca_system_score_gemma":0.000950857,"threshold_uncertainty_score":0.9997016},"labels":[],"label_agreement":null},{"id":"W3158744994","doi":"","title":"Adaptive Approximate Policy Iteration","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Regret; Reinforcement learning; Markov decision process; Computer science; Ergodic theory; Tilde; Q-learning; Bellman equation; Mathematical optimization; Novelty; Function (biology); Upper and lower bounds; Function approximation; Scheme (mathematics); Adaptive learning; Online learning; Markov process; Artificial intelligence; Mathematics; Machine learning; Discrete mathematics; Statistics","score_opus":0.12021544814826839,"score_gpt":0.3511960815700123,"score_spread":0.2309806334217439,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158744994","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":[0.00008508697,0.000008749351,0.98135227,0.0028589198,0.0004974633,0.00007111095,0.000035069395,0.00005395017,0.015037394],"genre_scores_gemma":[0.8424873,0.00015984153,0.15530764,0.0007249446,0.00015284416,0.000009368199,0.000053884483,0.000007843561,0.0010963891],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864715,0.00007656644,0.00033511597,0.0003460521,0.00039953124,0.00019556332],"domain_scores_gemma":[0.9987803,0.00020632753,0.00011633941,0.00023399475,0.00057960424,0.0000834514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016539128,0.00013955445,0.000121223864,0.000141355,0.00012729106,0.00064157083,0.00038892587,0.000052413692,0.00016738952],"category_scores_gemma":[0.0005157425,0.00014307199,0.000024860585,0.00020452964,0.00008975077,0.00030151842,0.00016345923,0.00016744527,0.0001424571],"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":[0.000014157055,0.000030506182,0.00001054938,0.0000031639377,0.000015975294,0.00003319847,0.000436227,0.014712465,0.0005218173,0.87718695,0.00007788377,0.1069571],"study_design_scores_gemma":[0.000019944508,0.000092125956,0.000049112732,0.000024681849,0.0000025320742,0.000016336066,0.00020883752,0.7741322,0.0041827084,0.22088665,0.00025998312,0.00012491088],"about_ca_topic_score_codex":0.000023050074,"about_ca_topic_score_gemma":0.00001693015,"teacher_disagreement_score":0.84240216,"about_ca_system_score_codex":0.000059839957,"about_ca_system_score_gemma":0.00022177721,"threshold_uncertainty_score":0.6186682},"labels":[],"label_agreement":null},{"id":"W3159115098","doi":"10.3758/s13415-021-00902-z","title":"Correction to: A win-win situation: Does familiarity with a social robot modulate feedback monitoring and learning?","year":2021,"lang":"en","type":"article","venue":"Cognitive Affective & Behavioral Neuroscience","topic":"Reinforcement Learning in Robotics","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 Victoria","funders":"","keywords":"Robot; Psychology; Computer science; Artificial intelligence","score_opus":0.02750281265872729,"score_gpt":0.29861624191581393,"score_spread":0.27111342925708665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159115098","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":[0.57017434,0.0000079838555,0.42794818,0.00009481388,0.0011885632,0.00029703995,0.0000017216838,0.00014810606,0.00013922509],"genre_scores_gemma":[0.9961962,0.000009233189,0.0024594085,0.00017334463,0.00010914727,0.000058973223,0.000003169098,0.000022122616,0.00096839573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9969616,0.0004476875,0.0002167804,0.0011533728,0.00069419044,0.00052638067],"domain_scores_gemma":[0.99841756,0.00031764273,0.00016735714,0.0002264791,0.00066623505,0.00020475031],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033715522,0.0003137685,0.00027973083,0.00015285502,0.0011122026,0.00066253246,0.0003630843,0.000072250885,0.0000042955126],"category_scores_gemma":[0.0007115918,0.00027760986,0.00006688277,0.0015598534,0.00032023893,0.0012067863,0.00057665986,0.0007168491,0.000015959946],"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":[0.00016485648,0.0005411945,0.51801497,0.000040094677,0.000020537473,0.0005168068,0.012656358,0.08103023,0.2763891,0.00022945735,0.000055566208,0.11034086],"study_design_scores_gemma":[0.0006620342,0.0011640581,0.8975691,0.00015893235,0.000047315923,0.00007674004,0.0009231473,0.055010073,0.043845627,0.000024585946,0.00003897886,0.0004793894],"about_ca_topic_score_codex":0.00008338045,"about_ca_topic_score_gemma":0.000028932447,"teacher_disagreement_score":0.42602184,"about_ca_system_score_codex":0.00013249589,"about_ca_system_score_gemma":0.00015824204,"threshold_uncertainty_score":0.99996763},"labels":[],"label_agreement":null},{"id":"W3160261777","doi":"10.1016/j.automatica.2021.109693","title":"On the convergence of reinforcement learning with Monte Carlo Exploring Starts","year":2021,"lang":"en","type":"article","venue":"Automatica","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; European Commission; Ontario Ministry of Research, Innovation and Science; Canada Research Chairs; Government of Canada; Pacific Institute for the Mathematical Sciences","keywords":"Reinforcement learning; Mathematical optimization; Convergence (economics); Bellman equation; Monte Carlo method; Computer science; Markov decision process; Complement (music); Function (biology); Mathematics; Markov process; Artificial intelligence; Economics","score_opus":0.035769155301195114,"score_gpt":0.22203931889189224,"score_spread":0.18627016359069712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160261777","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":[0.16269836,0.000026697773,0.82825214,0.0010341412,0.00021586029,0.00018933321,1.2688311e-7,0.00020614915,0.007377182],"genre_scores_gemma":[0.9889933,0.000019289602,0.0094956225,0.00020284843,0.000010870395,0.000029304405,6.4779897e-7,0.000010450277,0.0012377069],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853665,0.000101676975,0.00029634897,0.0002230979,0.0005850117,0.00025724038],"domain_scores_gemma":[0.9984942,0.00042019566,0.00018072224,0.00071147963,0.00013922996,0.000054141394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028721808,0.00013161646,0.0001679348,0.000045056124,0.0001580727,0.00008870125,0.00051744585,0.000023110613,0.000117902375],"category_scores_gemma":[0.00026522935,0.0000888127,0.000046301288,0.0003554056,0.00005971401,0.00028113154,0.00023495665,0.00020522588,0.00006121305],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030771712,0.000009692558,0.00031440583,0.00002930467,0.000036979407,0.000020977226,0.0019757464,0.92439216,0.0001589668,0.0724264,0.0001467173,0.00048556254],"study_design_scores_gemma":[0.00017463676,0.000262665,0.00078358065,0.0001829261,0.000010400682,0.0000074264,0.0003528261,0.9884984,0.0087275505,0.00013120106,0.0007356891,0.00013269465],"about_ca_topic_score_codex":0.000012991118,"about_ca_topic_score_gemma":0.0000014714991,"teacher_disagreement_score":0.8262949,"about_ca_system_score_codex":0.000038064303,"about_ca_system_score_gemma":0.000106254636,"threshold_uncertainty_score":0.36216772},"labels":[],"label_agreement":null},{"id":"W3160504906","doi":"10.35840/2631-5106/4131","title":"Curriculum-Based Deep Reinforcement Learning for Adaptive Robotics: A Mini-Review","year":2021,"lang":"en","type":"article","venue":"International Journal of Robotic Engineering","topic":"Reinforcement Learning in Robotics","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":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Artificial intelligence; Robotics; Computer science; Automation; Autonomous learning; Autonomous agent; Deep learning; Machine learning; Human–computer interaction; Robot; Engineering; Psychology","score_opus":0.014732341695832863,"score_gpt":0.26142427901113857,"score_spread":0.2466919373153057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160504906","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":[0.00003211025,0.0025671343,0.99305546,0.0019358165,0.002113858,0.00013962832,1.4187943e-7,0.000049683524,0.00010617054],"genre_scores_gemma":[0.35604775,0.00085956504,0.6414999,0.0007746397,0.00046294412,0.000016627273,0.000016595886,0.00003784679,0.00028415007],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978589,0.000041721793,0.0007903172,0.00020424947,0.0008180706,0.00028673257],"domain_scores_gemma":[0.9973457,0.00028476518,0.00053609215,0.00022011629,0.0014809727,0.00013237627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047317208,0.00020249581,0.00035503594,0.000231611,0.000050699404,0.000161233,0.0010230044,0.00005347754,0.000028747114],"category_scores_gemma":[0.0010990064,0.00019969288,0.00030445494,0.00025908815,0.000014235407,0.00046576717,0.00016270981,0.0003629114,0.000010157264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041555863,0.000028272987,0.00015282955,0.00012431368,0.0001989216,0.00011960305,0.00005307162,0.9909496,0.00015229725,0.0067784865,0.000172447,0.001266044],"study_design_scores_gemma":[0.0006941361,0.00019164133,0.000037014917,0.0017725192,0.00005635632,0.0002107998,0.000027041935,0.99374217,0.00041902982,0.00003062736,0.0026175063,0.00020118292],"about_ca_topic_score_codex":0.0000017849445,"about_ca_topic_score_gemma":4.630603e-7,"teacher_disagreement_score":0.35601565,"about_ca_system_score_codex":0.00025147016,"about_ca_system_score_gemma":0.00023673728,"threshold_uncertainty_score":0.8143239},"labels":[],"label_agreement":null},{"id":"W3162022061","doi":"10.48550/arxiv.2105.08692","title":"Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Task (project management); Composition (language); Generalization; Resource (disambiguation); Team composition; Artificial intelligence; Human–computer interaction; Distributed computing; Knowledge management; Mathematics; Engineering","score_opus":0.06769760757836442,"score_gpt":0.21858040990177732,"score_spread":0.1508828023234129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162022061","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":[0.023013366,0.000046442397,0.97362864,0.00007131085,0.0010621455,0.0008852641,0.0000028394586,0.00040613243,0.0008838606],"genre_scores_gemma":[0.96904373,0.00016511732,0.023940014,0.00013196767,0.00004581179,0.000007940095,0.00033815386,0.00004082617,0.0062864283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971899,0.00020305015,0.0004324716,0.0013434745,0.00021810844,0.0006130267],"domain_scores_gemma":[0.9974009,0.00017378743,0.00058032206,0.0012583263,0.0003773726,0.00020932559],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039639277,0.00048972503,0.00048813864,0.00031465827,0.00045520754,0.00041702163,0.0016824577,0.00037761926,0.00003515217],"category_scores_gemma":[0.00006323248,0.0006161746,0.00040815474,0.000407882,0.00008630912,0.0004983219,0.00250511,0.0010022422,0.00006878167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023806966,0.00006855232,0.0006606443,0.00017752346,0.00017216316,0.000075025055,0.00042613936,0.9907507,0.0002704658,0.007090853,0.00010270791,0.00018143951],"study_design_scores_gemma":[0.0011041681,0.00014943865,0.0004105151,0.00021287512,0.000113746624,0.0000063298216,0.00019872205,0.9959755,0.00023773481,0.00012459955,0.0008250265,0.00064134406],"about_ca_topic_score_codex":0.000059729937,"about_ca_topic_score_gemma":0.000012873806,"teacher_disagreement_score":0.9496886,"about_ca_system_score_codex":0.0008150958,"about_ca_system_score_gemma":0.00027460608,"threshold_uncertainty_score":0.99962896},"labels":[],"label_agreement":null},{"id":"W3164770271","doi":"10.1007/s00521-021-06104-5","title":"Lucid dreaming for experience replay: refreshing past states with the current policy","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Army Research Office; Defense Advanced Research Projects Agency; Office of Naval Research; Future of Life Institute; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Lockheed Martin; Robert Bosch (Australia) Pty; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; State (computer science); Reinforcement learning; Work (physics); Dream; Artificial intelligence; Programming language; Psychology","score_opus":0.018890258616053722,"score_gpt":0.30805375499472293,"score_spread":0.2891634963786692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164770271","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":[0.024030656,0.00017173655,0.9707156,0.0045013535,0.00004676335,0.0002474944,0.0000012790367,0.00012286067,0.00016225125],"genre_scores_gemma":[0.9753448,0.000019834697,0.023574932,0.0005722154,0.0002714881,0.00008271238,0.0000114605355,0.000009512303,0.00011307047],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990786,0.000033666904,0.00015912383,0.0003463282,0.0001476126,0.00023469116],"domain_scores_gemma":[0.99892604,0.0003352689,0.000114595816,0.00045057968,0.00011714436,0.00005638801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012860209,0.00010327186,0.000091293296,0.00003267394,0.0007677443,0.00036971798,0.0003869843,0.000014483779,2.6900773e-7],"category_scores_gemma":[0.000035159173,0.00007380029,0.000026012849,0.00039574283,0.00006834753,0.00012739745,0.00025466163,0.00016797044,0.000001360228],"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":[0.000004018198,0.00003101252,0.0013955766,0.00005825404,0.000015228351,0.0000019648621,0.00485848,0.43132246,0.0005592902,0.06989637,0.00070906396,0.4911483],"study_design_scores_gemma":[0.00016735864,0.000041903855,0.001081146,0.000034703327,0.00000615434,0.000032130716,0.00031459593,0.93424404,0.00058552594,0.00037784645,0.06296715,0.00014743177],"about_ca_topic_score_codex":0.000011644807,"about_ca_topic_score_gemma":0.0000017411063,"teacher_disagreement_score":0.9513141,"about_ca_system_score_codex":0.000020404512,"about_ca_system_score_gemma":0.000051554343,"threshold_uncertainty_score":0.59049463},"labels":[],"label_agreement":null},{"id":"W3165914412","doi":"","title":"Pretraining Reward-Free Representations for Data-Efficient Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"HEC Montréal; Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Cognitive psychology; Machine learning; Human–computer interaction; Psychology; Social psychology","score_opus":0.12765188971660188,"score_gpt":0.378776401532506,"score_spread":0.2511245118159041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165914412","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":[0.0008749011,0.000021466141,0.90021336,0.0074079116,0.0011776414,0.0004214643,0.000014820151,0.00042820166,0.08944021],"genre_scores_gemma":[0.884539,0.00008089446,0.07542964,0.00031830842,0.0002937571,0.00021019648,0.0015566044,0.000047988906,0.037523605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995858,0.00029929535,0.0007976148,0.0012754073,0.0012451452,0.0005245395],"domain_scores_gemma":[0.9947122,0.0010996283,0.00052508555,0.0021307473,0.0013519109,0.00018047068],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008302111,0.0003024425,0.00028405094,0.00035329827,0.00081384525,0.0010657,0.0030433177,0.000116176496,0.0005129276],"category_scores_gemma":[0.007916275,0.0003422202,0.00016458235,0.0005912839,0.00010713934,0.00083207974,0.0017102647,0.0007976589,0.000142205],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001893182,0.00005730783,0.0012436332,0.00001230989,0.00013139876,0.000021764694,0.001854016,0.8096831,0.0006250926,0.18109268,0.0019920226,0.0032677483],"study_design_scores_gemma":[0.0010382213,0.0001482398,0.00081856316,0.00010611192,0.000030466645,0.000030169562,0.001398453,0.9768035,0.00060787913,0.0015335903,0.017138638,0.00034619044],"about_ca_topic_score_codex":0.00005232038,"about_ca_topic_score_gemma":0.000010187309,"teacher_disagreement_score":0.88366413,"about_ca_system_score_codex":0.00017402685,"about_ca_system_score_gemma":0.0004939393,"threshold_uncertainty_score":0.9999713},"labels":[],"label_agreement":null},{"id":"W3165994454","doi":"","title":"Reinforcement Learning as One Big Sequence Modeling Problem","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Sequence (biology); Transformer; Artificial intelligence; Markov chain; Sequence learning; Markov decision process; Machine learning; Markov process; Mathematics; Engineering","score_opus":0.1422045581090734,"score_gpt":0.21029973663436013,"score_spread":0.06809517852528674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165994454","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":[0.03559203,0.000054315155,0.95108634,0.00010875614,0.0005572976,0.00041533745,6.046955e-7,0.00056874135,0.011616559],"genre_scores_gemma":[0.9760955,0.00048822793,0.014352688,0.00018740202,0.0000992047,0.0000028556674,0.00005322665,0.000039813054,0.008681077],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653673,0.00023921493,0.00048818372,0.0016282788,0.00037140047,0.0007361824],"domain_scores_gemma":[0.9969291,0.000090781374,0.0005136204,0.0017279115,0.00046209453,0.00027646092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00052171695,0.0005165364,0.00051965093,0.00037109153,0.00039095888,0.0006120431,0.0026512793,0.000407518,0.00007861171],"category_scores_gemma":[0.00012250498,0.0006750432,0.00028496012,0.00087808946,0.00009166819,0.0006661874,0.005272694,0.0017952475,0.00016650333],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009556486,0.000027719238,0.00026781484,0.0001494269,0.00013253673,0.00032216046,0.0005886379,0.95332646,0.00011510148,0.044526916,0.000010433062,0.00052325864],"study_design_scores_gemma":[0.00035992285,0.0001123742,0.000008865636,0.00047723626,0.00007368211,0.000007187196,0.00019790577,0.9935911,0.00016218473,0.004130645,0.00017546913,0.00070342404],"about_ca_topic_score_codex":0.00056144694,"about_ca_topic_score_gemma":0.0000130684575,"teacher_disagreement_score":0.9405035,"about_ca_system_score_codex":0.0006059037,"about_ca_system_score_gemma":0.00068037614,"threshold_uncertainty_score":0.9995701},"labels":[],"label_agreement":null},{"id":"W3167624337","doi":"","title":"Sparse Feature Selection Makes Batch Reinforcement Learning More Sample Efficient","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Minimax; Estimator; Reinforcement learning; Lasso (programming language); Upper and lower bounds; Covariance; Divergence (linguistics); Computer science; Sample size determination; Feature selection; Mathematical optimization; Dimension (graph theory); Mathematics; Function (biology); Model selection; Algorithm; Artificial intelligence; Statistics","score_opus":0.030037715410598808,"score_gpt":0.29334601178244984,"score_spread":0.26330829637185105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167624337","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":[0.006057122,0.00003912461,0.9648504,0.0059568346,0.0008455479,0.00014659061,0.0000019547022,0.00041996426,0.021682423],"genre_scores_gemma":[0.9597772,0.000070098446,0.019682739,0.00056783634,0.00018435717,0.000020262623,0.00020984073,0.00003025486,0.019457433],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970066,0.00024724094,0.0004025318,0.00071699906,0.0011563391,0.0004702859],"domain_scores_gemma":[0.9982356,0.0002822117,0.00033786206,0.0003489208,0.00065555266,0.00013984823],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00043875852,0.0003343341,0.00026169227,0.00026817058,0.00044665087,0.0007172424,0.00088574365,0.0001332196,0.0009744776],"category_scores_gemma":[0.0011350842,0.00033919566,0.00014063902,0.0004849642,0.00004844215,0.000303351,0.00047509553,0.001496152,0.00021527961],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023233959,0.000035048437,0.007213074,0.000011183286,0.00005333046,0.000034682365,0.00059444114,0.9012622,0.0016394008,0.08434716,0.00013374389,0.004652457],"study_design_scores_gemma":[0.000519483,0.00019557403,0.0015424713,0.00011221183,0.000010420127,0.000050006474,0.00019056747,0.9698751,0.0016232672,0.00017360017,0.025367519,0.00033979327],"about_ca_topic_score_codex":0.00010434557,"about_ca_topic_score_gemma":0.000012651226,"teacher_disagreement_score":0.95372003,"about_ca_system_score_codex":0.00025990183,"about_ca_system_score_gemma":0.0002058634,"threshold_uncertainty_score":0.9999388},"labels":[],"label_agreement":null},{"id":"W3167763832","doi":"10.21428/594757db.8472938b","title":"General Deep Reinforcement Learning in NES Games","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Acadia University","funders":"","keywords":"Reinforcement learning; Domain (mathematical analysis); Computer science; Video game; Artificial intelligence; Entertainment; Field (mathematics); Deep learning; Domain knowledge; Focus (optics); Hyperparameter; Human–computer interaction; Multimedia","score_opus":0.015724029213907236,"score_gpt":0.2488639597852059,"score_spread":0.23313993057129867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167763832","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":[0.0042670486,0.000061261795,0.93342143,0.00073205505,0.00023710249,0.00006040801,6.7299415e-9,0.00018177275,0.06103889],"genre_scores_gemma":[0.80927914,0.000064591346,0.14008544,0.0009447923,0.00006661564,0.000010529815,0.000006961735,0.000011311819,0.049530618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863166,0.00008356136,0.00029924395,0.0003123328,0.0003228559,0.00035032356],"domain_scores_gemma":[0.9993075,0.00006676875,0.00006778513,0.0004132283,0.000077789446,0.0000669065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022568928,0.00012341331,0.00014834532,0.000106870684,0.000083608116,0.0002173239,0.00044712023,0.000049978717,0.0002696391],"category_scores_gemma":[0.0001067517,0.00011965184,0.00005309073,0.00047148854,0.00002076562,0.00038631962,0.00044285046,0.00025622727,0.00010471316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.945127e-7,0.000006800605,0.007720022,0.0000061515575,0.0000061095666,0.00004643699,0.00030825255,0.9276136,0.0003470455,0.059244465,0.00014372324,0.0045567686],"study_design_scores_gemma":[0.00028238317,0.00004233002,0.005346089,0.000012964014,0.0000015874533,0.0000129232,0.00007949282,0.98387706,0.0014841863,0.00016648728,0.008533145,0.00016137627],"about_ca_topic_score_codex":0.000031759748,"about_ca_topic_score_gemma":0.000018948536,"teacher_disagreement_score":0.8050121,"about_ca_system_score_codex":0.00007251823,"about_ca_system_score_gemma":0.000115756106,"threshold_uncertainty_score":0.48792604},"labels":[],"label_agreement":null},{"id":"W3167916533","doi":"10.48550/arxiv.2106.02617","title":"Be Considerate: Objectives, Side Effects, and Deciding How to Act","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Discretion; Agency (philosophy); Contemplation; Risk analysis (engineering); Work (physics); Computer science; Psychology; Business; Engineering; Political science; Sociology; Law","score_opus":0.054087394248674765,"score_gpt":0.19593051251140975,"score_spread":0.141843118262735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167916533","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":[0.15075414,0.00008951465,0.84527594,0.00039321624,0.0005960802,0.0003686947,0.000001466624,0.00021059357,0.002310353],"genre_scores_gemma":[0.9839828,0.00015713616,0.013703237,0.0004507643,0.000051184466,0.0000013170674,0.000008132451,0.000023489421,0.0016219165],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763894,0.00027246625,0.00015692966,0.0013349176,0.00014681996,0.00044992444],"domain_scores_gemma":[0.99751526,0.0006254578,0.00020542923,0.0011503531,0.0002034333,0.00030003674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027354548,0.000386712,0.000448666,0.00030000327,0.00024828542,0.000821198,0.001040503,0.00026359464,0.0000066732514],"category_scores_gemma":[0.00044419494,0.00047119052,0.00013636713,0.00057565706,0.000088713845,0.0005399366,0.005431427,0.000701974,0.000015499143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011440763,0.000018496668,0.0023022187,0.00016441057,0.00014838844,0.0010511056,0.0007721188,0.9737259,0.0003511043,0.020591637,0.00024443155,0.0006187289],"study_design_scores_gemma":[0.0009575209,0.00020935766,0.007608238,0.0006147488,0.00014951514,0.000041951862,0.00049033674,0.9812596,0.0037663376,0.002793012,0.0008197097,0.0012896921],"about_ca_topic_score_codex":0.000071292794,"about_ca_topic_score_gemma":0.000030696985,"teacher_disagreement_score":0.8332287,"about_ca_system_score_codex":0.0002649589,"about_ca_system_score_gemma":0.00031828863,"threshold_uncertainty_score":0.999774},"labels":[],"label_agreement":null},{"id":"W3168124941","doi":"10.48550/arxiv.2106.00922","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Backup; Reinforcement learning; Computer science; Algorithm; Bootstrapping (finance); Artificial intelligence; Task (project management); Machine learning; Tree (set theory); Collision; Function (biology); Temporal difference learning; Mathematics; Econometrics","score_opus":0.10285944847924657,"score_gpt":0.26344388981984024,"score_spread":0.1605844413405937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168124941","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":[0.27247244,0.000018837545,0.7254957,0.00017579155,0.00036411977,0.00021875871,0.0000037037084,0.00015947374,0.0010911651],"genre_scores_gemma":[0.9972942,0.0001169417,0.0016556844,0.000092284616,0.000121734825,9.624212e-7,0.000051024985,0.000018884472,0.0006482915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743426,0.0006324625,0.0003672694,0.0009006056,0.00031142408,0.00035400054],"domain_scores_gemma":[0.99721277,0.00034629944,0.00055171957,0.0014558025,0.00029180752,0.00014160694],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005362726,0.00029652828,0.00041162467,0.00032027927,0.00034922134,0.00021615153,0.0019203002,0.00033369593,0.000018766366],"category_scores_gemma":[0.00021666336,0.0002762739,0.00020030636,0.0010113784,0.00014975814,0.00033549688,0.0016232108,0.0013490559,0.000022437698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016523643,0.000122052275,0.011380605,0.000027704973,0.000057340916,0.00002676237,0.0012540818,0.97583854,0.000048740436,0.00991462,0.00017568821,0.0011373298],"study_design_scores_gemma":[0.00023364926,0.0003778896,0.004304321,0.00014302715,0.000039863753,0.0000017251369,0.0005644931,0.9928299,0.00038281563,0.0002471162,0.00064977485,0.00022542733],"about_ca_topic_score_codex":0.00010472339,"about_ca_topic_score_gemma":0.00000558241,"teacher_disagreement_score":0.72482175,"about_ca_system_score_codex":0.00030753325,"about_ca_system_score_gemma":0.000405116,"threshold_uncertainty_score":0.99996895},"labels":[],"label_agreement":null},{"id":"W3168260200","doi":"10.48550/arxiv.2106.11779","title":"Emphatic Algorithms for Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Temporal difference learning; Artificial intelligence; Weighting; Convergence (economics); Context (archaeology); Algorithm; Machine learning; Stability (learning theory); Lambda; Function (biology)","score_opus":0.06650257069781514,"score_gpt":0.20297120362475468,"score_spread":0.13646863292693956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168260200","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":[0.0029751384,0.00003090353,0.9920002,0.0001019513,0.00030930695,0.00017588449,1.6535743e-7,0.00020896921,0.004197453],"genre_scores_gemma":[0.96270275,0.000051988023,0.018095665,0.00019884952,0.00004924288,0.0000013857714,0.000013892774,0.000014778887,0.018871443],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866194,0.00007507734,0.00018854368,0.0005495238,0.00011247479,0.0004124233],"domain_scores_gemma":[0.99871594,0.00019363828,0.00014122561,0.0005824125,0.00023186248,0.00013490362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021423092,0.00016746577,0.0001797246,0.00010870765,0.00030669212,0.00013611105,0.0007002781,0.00007483185,0.00006609229],"category_scores_gemma":[0.00015312387,0.0002013277,0.00014078835,0.00066898897,0.000043996286,0.0005581033,0.00038322806,0.00017012314,0.00011675978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005329089,0.000013834029,0.00054767507,0.00002035439,0.00003899623,0.00009481871,0.00017979436,0.88284844,0.000059023758,0.1151683,0.00007799817,0.00094543974],"study_design_scores_gemma":[0.00072378473,0.00012779696,0.00013457151,0.000019484327,0.000027801725,0.000008551938,0.00016862263,0.9913324,0.0006555593,0.0012680521,0.005290443,0.00024292883],"about_ca_topic_score_codex":0.000007382428,"about_ca_topic_score_gemma":0.0000034143027,"teacher_disagreement_score":0.97390455,"about_ca_system_score_codex":0.00014470164,"about_ca_system_score_gemma":0.00012002595,"threshold_uncertainty_score":0.8209905},"labels":[],"label_agreement":null},{"id":"W3169135197","doi":"10.1109/iccma53594.2021.00018","title":"Hyperspace Neighbor Penetration Approach to Dynamic Programming for Model-Based Reinforcement Learning Problems with Slowly Changing Variables in a Continuous State Space","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Telus (Canada)","funders":"","keywords":"Reinforcement learning; Hyperspace; Computer science; Grid; Mathematical optimization; State variable; Computation; Tile; Theoretical computer science; Algorithm; Mathematics; Artificial intelligence; Geometry; Physics","score_opus":0.016641044675257805,"score_gpt":0.2406334646722556,"score_spread":0.2239924199969978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169135197","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":[0.0026264598,0.000055424523,0.98911285,0.00050507294,0.00017323987,0.005069082,0.000001175907,0.0004763478,0.0019803336],"genre_scores_gemma":[0.41805273,0.000008102662,0.576707,0.00011464382,0.000017460741,0.001226155,0.0001560279,0.0000622307,0.0036556583],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954761,0.00014325255,0.00072985375,0.0015706893,0.00083855423,0.0012414966],"domain_scores_gemma":[0.9974677,0.00015949641,0.00060602085,0.0010436369,0.000510167,0.000213007],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014178273,0.000694528,0.0007585516,0.000839469,0.0002613038,0.0016751518,0.001131373,0.000264549,0.000002818472],"category_scores_gemma":[0.00016504405,0.00066547876,0.0001594304,0.0010842341,0.000040860185,0.00048494563,0.0010600257,0.0009458706,0.0000023143361],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004502416,0.00008079837,0.00022268001,0.00086772937,0.0000711528,0.0000059055437,0.006207671,0.9863061,0.00019189459,0.0039292444,0.0000075669814,0.0020642842],"study_design_scores_gemma":[0.0011107579,0.00046718036,0.000022448581,0.000906328,0.00003771372,0.0000043839527,0.000811489,0.9953241,0.00020658883,0.000060922343,0.00019045564,0.0008576331],"about_ca_topic_score_codex":0.0001826845,"about_ca_topic_score_gemma":0.000089773406,"teacher_disagreement_score":0.41542625,"about_ca_system_score_codex":0.0006666534,"about_ca_system_score_gemma":0.0009893567,"threshold_uncertainty_score":0.99957967},"labels":[],"label_agreement":null},{"id":"W3169292790","doi":"10.48550/arxiv.2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance\\n Sampling with the Successor Representation","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Successor cardinal; Reinforcement learning; Representation (politics); Computer science; Sampling (signal processing); Artificial intelligence; Bridge (graph theory); Variety (cybernetics); Machine learning; Simple random sample; Reinforcement; State (computer science); Mathematics; Algorithm; Sociology; Psychology; Political science; Social psychology; Detector; Law","score_opus":0.09879524359877373,"score_gpt":0.22533058249091992,"score_spread":0.1265353388921462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169292790","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":[0.054128233,0.000078867524,0.9315495,0.00037725942,0.00044628535,0.0019169593,5.1987206e-7,0.0002467262,0.011255667],"genre_scores_gemma":[0.9665712,0.00033740717,0.021977581,0.0003808456,0.00015937639,0.000022066582,0.00013395534,0.00008395544,0.010333579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99278575,0.00087147445,0.00090284337,0.0032620432,0.00081400125,0.0013639026],"domain_scores_gemma":[0.9929694,0.00047361085,0.0016361354,0.0033686059,0.0010086733,0.000543555],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013602221,0.0010482679,0.0010149713,0.00050065323,0.0015515332,0.0017627804,0.0041476875,0.00041346913,0.00021254127],"category_scores_gemma":[0.0002659425,0.00096674956,0.0004835717,0.0036637762,0.00036013735,0.0012717581,0.0045669195,0.0023265576,0.00009515963],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003110582,0.00008440832,0.008741038,0.0002033785,0.00051063363,0.00021510481,0.0055587334,0.96616817,0.000038055947,0.017836327,0.00004327904,0.00028981213],"study_design_scores_gemma":[0.0014623429,0.00031395827,0.0019302926,0.00032602597,0.00039726167,0.000035654546,0.0053635743,0.98775154,0.000068399415,0.00009661892,0.0010718707,0.0011824825],"about_ca_topic_score_codex":0.0003955124,"about_ca_topic_score_gemma":0.00006806635,"teacher_disagreement_score":0.912443,"about_ca_system_score_codex":0.00093588396,"about_ca_system_score_gemma":0.0006831262,"threshold_uncertainty_score":0.99997514},"labels":[],"label_agreement":null},{"id":"W3169514089","doi":"","title":"EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","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":"Google (Canada); University of Alberta; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Backup; Heuristic; Operator (biology); Online and offline; Offline learning; Simple (philosophy); Artificial intelligence; Generative grammar; Machine learning; Mathematical optimization; Theoretical computer science; Online learning; Mathematics","score_opus":0.028410596128182336,"score_gpt":0.3196032698915692,"score_spread":0.29119267376338687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169514089","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":[0.06487779,0.00013123598,0.92544115,0.0030999323,0.0006934142,0.00039564192,0.000022545002,0.00034963008,0.004988674],"genre_scores_gemma":[0.97107464,0.00008260257,0.022862865,0.0005726183,0.00019692627,0.000053324817,0.00042429983,0.000034165125,0.0046985573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978267,0.0002624973,0.0003843544,0.00067882217,0.0004998803,0.0003477224],"domain_scores_gemma":[0.997979,0.00067221076,0.00023702676,0.00027391256,0.00070853165,0.00012933543],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037418384,0.00028381663,0.00030607512,0.00019076999,0.00032112285,0.00055451365,0.00063367386,0.000097463846,0.0002814477],"category_scores_gemma":[0.0021620232,0.0002823384,0.00009557708,0.0002334735,0.00005185902,0.00040226904,0.00049032335,0.0008313278,0.00003970401],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001456156,0.00020750155,0.02372496,0.00007704897,0.00032617935,0.00013507901,0.0018937858,0.6653191,0.011180749,0.23271516,0.00031285908,0.06396199],"study_design_scores_gemma":[0.0011287298,0.00047655034,0.002694733,0.00011040271,0.000012496554,0.00003676293,0.00023077738,0.9731099,0.0012288381,0.00078764017,0.019862179,0.00032099665],"about_ca_topic_score_codex":0.00003610417,"about_ca_topic_score_gemma":0.00002570941,"teacher_disagreement_score":0.90619683,"about_ca_system_score_codex":0.00009253198,"about_ca_system_score_gemma":0.00012794844,"threshold_uncertainty_score":0.99996287},"labels":[],"label_agreement":null},{"id":"W3170371439","doi":"10.1609/aaai.v36i7.20758","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research; Vector Institute; University of Toronto; Université de Montréal","funders":"Compute Canada","keywords":"Reinforcement learning; Bellman equation; Computer science; Context (archaeology); Function (biology); Task (project management); Class (philosophy); Value (mathematics); Likelihood function; Maximum likelihood; Reinforcement; Control (management); Artificial intelligence; Mathematical optimization; Machine learning; Estimation theory; Mathematics; Statistics; Economics; Algorithm","score_opus":0.03202434377017425,"score_gpt":0.25509131036248905,"score_spread":0.2230669665923148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170371439","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":[0.03704292,0.0000029813411,0.95712763,0.001463551,0.00018524933,0.00054694584,0.0000013044051,0.00014930878,0.0034801029],"genre_scores_gemma":[0.99562156,0.0000023378516,0.0033778893,0.00036586422,0.00001925195,0.00011741691,0.000002808745,0.000019191091,0.00047368807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972706,0.00004160403,0.0005912123,0.0005050915,0.00115396,0.00043752146],"domain_scores_gemma":[0.998147,0.000090743946,0.0007406122,0.00036778775,0.0005671874,0.000086673404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055293244,0.00026545074,0.00027754466,0.00019476424,0.00072619546,0.00021000477,0.0018235629,0.00004680949,0.000100701705],"category_scores_gemma":[0.00017383682,0.00020429914,0.00011307263,0.0007932207,0.00014559805,0.00033186813,0.00049781904,0.00063250377,0.000015845671],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010499733,0.00004678458,0.00036179318,0.000014014278,0.000014922531,2.1926395e-7,0.0003722357,0.62460357,0.0070026047,0.36588094,0.000019889818,0.0015779913],"study_design_scores_gemma":[0.00012468887,0.0007809984,0.00008664717,0.000057972367,0.000021199881,0.000002063063,0.00021099768,0.9391222,0.054885328,0.0044011064,0.000076492965,0.00023029659],"about_ca_topic_score_codex":0.000022665394,"about_ca_topic_score_gemma":0.0000012349301,"teacher_disagreement_score":0.95857865,"about_ca_system_score_codex":0.00016792052,"about_ca_system_score_gemma":0.00018050984,"threshold_uncertainty_score":0.8331077},"labels":[],"label_agreement":null},{"id":"W3171711942","doi":"10.1109/syscon48628.2021.9447080","title":"Optimization of Deep Reinforcement Learning with Hybrid Multi-Task Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Task (project management); Machine learning; Deep learning; Learning classifier system; Robot learning; Multi-task learning; Active learning (machine learning); Engineering; Robot","score_opus":0.013230727267571582,"score_gpt":0.2300208503905229,"score_spread":0.21679012312295132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171711942","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":[0.00059075165,0.0000448829,0.98953575,0.00010179662,0.0000938935,0.00012060864,2.8832321e-8,0.00023393148,0.009278357],"genre_scores_gemma":[0.61998,0.000035597925,0.37310356,0.00007859772,0.000014119292,0.000005580424,0.000019535903,0.000015595277,0.006747434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982653,0.00012543626,0.0003943989,0.00037684903,0.00051110913,0.00032685196],"domain_scores_gemma":[0.9987063,0.000103296705,0.00029062264,0.000432835,0.0003787439,0.00008823395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027264684,0.00017720334,0.00022412355,0.0001136777,0.00018954079,0.00015145866,0.00041480837,0.000042356274,0.0002070989],"category_scores_gemma":[0.0002307743,0.00015879443,0.000060608687,0.00048807097,0.000045799385,0.0005070736,0.0003362988,0.00032783224,0.000030956307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054655525,0.000019155452,0.0021337306,0.000025513957,0.0000376192,0.000024358007,0.0004242641,0.99299157,0.00034758696,0.0021592292,0.000011711288,0.0018198157],"study_design_scores_gemma":[0.000647247,0.0002502481,0.00014681848,0.00004168994,0.000012912515,0.000030811207,0.0001981589,0.9900589,0.0075975857,0.0000031169866,0.0008055586,0.00020698154],"about_ca_topic_score_codex":0.000015128642,"about_ca_topic_score_gemma":0.000002503468,"teacher_disagreement_score":0.61938924,"about_ca_system_score_codex":0.000057097735,"about_ca_system_score_gemma":0.00010963527,"threshold_uncertainty_score":0.64754486},"labels":[],"label_agreement":null},{"id":"W3172545192","doi":"10.1007/978-3-031-26889-2_19","title":"Least-Restrictive Multi-agent Collision Avoidance via Deep Meta Reinforcement Learning and Optimal Control","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Reinforcement Learning in Robotics","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 Regina; Simon Fraser University","funders":"","keywords":"Reinforcement learning; Collision avoidance; Computer science; Collision; Function (biology); Interrupt; Trajectory; Artificial intelligence; Autonomous agent; Control (management); Control theory (sociology); Computer security","score_opus":0.023811569614677456,"score_gpt":0.24225485058398818,"score_spread":0.21844328096931073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172545192","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":[0.000008331048,0.011935026,0.98392797,0.00007602413,0.0011346298,0.0011640986,0.0000017253856,0.00017746771,0.0015747112],"genre_scores_gemma":[0.9644711,0.0033063616,0.0045747906,0.00018237674,0.00055975403,0.00013749712,0.00004230524,0.00014094614,0.026584866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967689,0.00018609199,0.00086201576,0.0009564947,0.0006054567,0.00062105746],"domain_scores_gemma":[0.9973953,0.0010900645,0.0006824888,0.0005017766,0.00014710892,0.00018329806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084180734,0.0006938701,0.0011470204,0.00029971387,0.0003250814,0.0004915037,0.0004857269,0.00066720945,0.000006947585],"category_scores_gemma":[0.0001372381,0.0005854881,0.00017238263,0.00019005756,0.00011489915,0.00018977768,0.00045904928,0.0014320494,0.000013911262],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022285456,0.000004240243,0.00013055203,0.00011068659,0.00040862462,0.000071323106,0.00030514825,0.99279404,0.0000041234907,0.0030905777,0.000024418934,0.0030339723],"study_design_scores_gemma":[0.0008864863,0.00027938845,0.00004244147,0.0004005769,0.00022589388,0.000034215045,0.0000071800187,0.9941675,0.0000020054697,0.00009852597,0.0033005893,0.0005551848],"about_ca_topic_score_codex":0.00009486178,"about_ca_topic_score_gemma":0.000037709822,"teacher_disagreement_score":0.9793532,"about_ca_system_score_codex":0.0001621543,"about_ca_system_score_gemma":0.000044733846,"threshold_uncertainty_score":0.99965966},"labels":[],"label_agreement":null},{"id":"W3173549437","doi":"10.1609/aaai.v35i13.17378","title":"How RL Agents Behave When Their Actions Are Modified","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Action (physics); Supervisor; Markov decision process; Computer science; Process (computing); Risk analysis (engineering); Reinforcement; Control (management); Intervention (counseling); Artificial intelligence; Q-learning; Machine learning; Markov process; Psychology; Social psychology; Business; Economics; Mathematics","score_opus":0.0900760941624977,"score_gpt":0.27071665494807196,"score_spread":0.18064056078557425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173549437","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":[0.0016177059,0.000016601858,0.95917094,0.005132262,0.0004631737,0.00007225038,8.8901885e-7,0.0002160268,0.033310127],"genre_scores_gemma":[0.8201033,0.000015903634,0.05330507,0.0009189518,0.000066867666,0.000010867899,0.000008459774,0.000011652729,0.12555893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990732,0.000047157402,0.000115022405,0.0002849151,0.0002442464,0.00023544276],"domain_scores_gemma":[0.99896383,0.00005135052,0.000072738,0.0007014385,0.00012631241,0.00008433627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006834111,0.000112091424,0.00011154203,0.00005042958,0.00015153602,0.00053657655,0.0005446892,0.000054678403,0.0001153479],"category_scores_gemma":[0.000058258353,0.00009655443,0.000073033596,0.00019201479,0.000019847284,0.0004705749,0.00035774658,0.00015039802,0.00011767899],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037171303,0.00020112519,0.004175682,0.00004265894,0.00020704434,0.00018792025,0.0040174676,0.72301215,0.0030111633,0.18757544,0.060847364,0.01671829],"study_design_scores_gemma":[0.00031895825,0.000043359003,0.004632968,0.0000229012,0.0000107732885,0.000024153745,0.0006068277,0.92935395,0.007039158,0.0011269931,0.056531653,0.0002882962],"about_ca_topic_score_codex":0.000008233896,"about_ca_topic_score_gemma":0.000010290427,"teacher_disagreement_score":0.9058659,"about_ca_system_score_codex":0.00004479664,"about_ca_system_score_gemma":0.000056288787,"threshold_uncertainty_score":0.517422},"labels":[],"label_agreement":null},{"id":"W3175558129","doi":"10.1609/aaai.v35i12.17276","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Artificial intelligence; Stability (learning theory); Machine learning; Encoder; Representation (politics); Noise (video); Code (set theory); Image (mathematics)","score_opus":0.019185411067575067,"score_gpt":0.23646707892105248,"score_spread":0.2172816678534774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3175558129","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":[0.0020790168,0.00008132191,0.9859313,0.0004868007,0.00018214056,0.00010740226,6.640364e-7,0.00024809825,0.010883253],"genre_scores_gemma":[0.62021077,0.000026709591,0.3755634,0.00034909957,0.000033643064,0.000010068444,0.000019661125,0.00001538164,0.0037712827],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979848,0.0000757864,0.00044484495,0.0005542304,0.0004433271,0.00049697957],"domain_scores_gemma":[0.9982879,0.0003288337,0.00013281047,0.0010452485,0.00011216377,0.00009301617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003401872,0.00018896157,0.00021210685,0.00012909986,0.00014907384,0.00034982266,0.0011935416,0.000071384115,0.0001303387],"category_scores_gemma":[0.0010400225,0.00019034494,0.000072068826,0.00051730964,0.00003073042,0.00063246675,0.0014830191,0.0003685573,0.00004491041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001690143,0.00001546216,0.0021739518,0.0000080294285,0.0000058361734,0.000015945852,0.00038931405,0.9806615,0.002360051,0.011521217,0.00012842046,0.0027185709],"study_design_scores_gemma":[0.0005247236,0.000044830806,0.0005192518,0.00002398881,0.0000037374293,0.0000018464276,0.00007204143,0.9921091,0.0048250454,0.001455438,0.00018166407,0.0002383008],"about_ca_topic_score_codex":0.0007857587,"about_ca_topic_score_gemma":0.00003856934,"teacher_disagreement_score":0.6181317,"about_ca_system_score_codex":0.00012655393,"about_ca_system_score_gemma":0.00021019233,"threshold_uncertainty_score":0.77620417},"labels":[],"label_agreement":null},{"id":"W3176022961","doi":"10.1145/3449639.3459348","title":"On the impact of tangled program graph marking schemes under the atari reinforcement learning benchmark","year":2021,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Computer science; Reinforcement learning; Benchmark (surveying); Graph; Adaptation (eye); Heuristic; Scheme (mathematics); Theoretical computer science; Modularity (biology); Artificial intelligence; Node (physics); Machine learning; Engineering; Mathematics","score_opus":0.0203845929356071,"score_gpt":0.25870910566226896,"score_spread":0.23832451272666186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176022961","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":[0.485411,0.00026007008,0.5096315,0.0015560169,0.00012008737,0.00049440964,6.3791884e-7,0.000049503513,0.0024767693],"genre_scores_gemma":[0.98910797,0.00007118179,0.010523454,0.00006554956,0.000019105431,0.000020789774,0.0000030235062,0.0000063171706,0.00018258253],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865264,0.000050405866,0.000351429,0.0002523281,0.00048267885,0.0002105274],"domain_scores_gemma":[0.9984017,0.00028561204,0.00042770922,0.00017915794,0.0006672573,0.00003858799],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030989267,0.0001571557,0.00015463482,0.000056338013,0.00041493404,0.00014587535,0.0006484287,0.00004595846,0.000027658094],"category_scores_gemma":[0.00017271335,0.00008685522,0.000118032825,0.00053487415,0.00024747595,0.00015361371,0.00048033532,0.00024061443,0.0000015241643],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013160773,0.000031987936,0.0066471575,0.00003553395,0.00008193805,1.821034e-7,0.0006361585,0.8923682,0.0007604103,0.09556028,0.0004590458,0.0034059258],"study_design_scores_gemma":[0.00019205136,0.00024519349,0.093818106,0.00013080114,0.000019417632,0.000015636118,0.0004044256,0.8874738,0.00045046303,0.017078497,0.00006346132,0.00010809758],"about_ca_topic_score_codex":0.000020501882,"about_ca_topic_score_gemma":2.8698906e-7,"teacher_disagreement_score":0.50369704,"about_ca_system_score_codex":0.00004791707,"about_ca_system_score_gemma":0.0001996233,"threshold_uncertainty_score":0.3541853},"labels":[],"label_agreement":null},{"id":"W3176342773","doi":"","title":"OptiDICE: Offline Policy Optimization via Stationary Distribution Correction Estimation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Hyperparameter; Reinforcement learning; Benchmark (surveying); Computer science; Bootstrapping (finance); Set (abstract data type); Mathematical optimization; Online and offline; Offline learning; Artificial intelligence; Machine learning; Mathematics; Online learning; Econometrics","score_opus":0.034880791229417715,"score_gpt":0.20066294963608636,"score_spread":0.16578215840666866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176342773","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":[0.0032080887,0.000019876308,0.99380904,0.00021024732,0.0014521834,0.00031149684,0.000012065451,0.0003910868,0.0005859036],"genre_scores_gemma":[0.95317805,0.00019414068,0.04205262,0.00007006776,0.00012772692,0.0000019859824,0.00269607,0.000020287685,0.0016590283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981261,0.00020021742,0.0003227757,0.0008564479,0.00020085489,0.00029362232],"domain_scores_gemma":[0.99786603,0.00010802641,0.0005183455,0.00087044144,0.0005092291,0.00012792517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024027313,0.00029347086,0.00025162284,0.00030090671,0.00026774794,0.00028753,0.00076450367,0.00031335896,0.000038867587],"category_scores_gemma":[0.00021973187,0.0003914194,0.0001397656,0.001198011,0.000065846856,0.0010618322,0.0010145738,0.000534193,0.000036153713],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011927107,0.000047975078,0.00020941884,0.000046873778,0.00004367856,0.000038780847,0.00012789111,0.9874752,0.00000926454,0.01044939,0.00023405858,0.0013055011],"study_design_scores_gemma":[0.00029677284,0.000052928477,0.0007525767,0.00009723399,0.00004981052,0.0000105652725,0.000044675722,0.99747753,0.000083827515,0.0007105625,0.00007963572,0.00034390754],"about_ca_topic_score_codex":0.00022494103,"about_ca_topic_score_gemma":0.0000062037325,"teacher_disagreement_score":0.9517564,"about_ca_system_score_codex":0.000931338,"about_ca_system_score_gemma":0.0005667425,"threshold_uncertainty_score":0.9998538},"labels":[],"label_agreement":null},{"id":"W3176644733","doi":"10.1016/j.jprocont.2021.06.004","title":"Online reinforcement learning for a continuous space system with experimental validation","year":2021,"lang":"en","type":"article","venue":"Journal of Process Control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; State space; Artificial intelligence; Machine learning; Heuristic; Trajectory; Asynchronous communication; Mathematics","score_opus":0.012318515279714703,"score_gpt":0.2662024340434771,"score_spread":0.2538839187637624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176644733","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":[0.016952839,0.00026388394,0.98152095,0.00044858127,0.00025098468,0.00025575122,3.9840023e-7,0.000047333226,0.0002592696],"genre_scores_gemma":[0.98084927,0.000003902843,0.018228153,0.000107919026,0.0001920225,0.000014748754,0.000003965759,0.000015210607,0.0005848281],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836564,0.000075656935,0.0005530326,0.00018001534,0.0005744759,0.00025118707],"domain_scores_gemma":[0.9974665,0.00013771538,0.00096189376,0.00017920378,0.0011510921,0.00010358574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039985412,0.00015156863,0.00036466532,0.000102356484,0.00013587679,0.00024645386,0.00039313044,0.000048431117,0.000008192088],"category_scores_gemma":[0.00019603771,0.00011997329,0.00010416942,0.00020441382,0.000019968644,0.00063271413,0.00003806313,0.00023600592,0.0000022232591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013249491,0.00006479533,0.0004470805,0.000114970615,0.000116541676,0.0000650903,0.0006871404,0.9926145,0.0026978569,0.0026508954,0.000059441223,0.00034920624],"study_design_scores_gemma":[0.006315806,0.0018651284,0.000069254034,0.0004098555,0.000070954986,0.0005058831,0.002770472,0.9479387,0.03845737,0.000012418028,0.0013654911,0.00021867275],"about_ca_topic_score_codex":0.0000012803885,"about_ca_topic_score_gemma":4.1639055e-7,"teacher_disagreement_score":0.9638964,"about_ca_system_score_codex":0.00014365125,"about_ca_system_score_gemma":0.00033561487,"threshold_uncertainty_score":0.48923686},"labels":[],"label_agreement":null},{"id":"W3176880374","doi":"10.1109/lra.2021.3093551","title":"A Sim-to-Real Pipeline for Deep Reinforcement Learning for Autonomous Robot Navigation in Cluttered Rough Terrain","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":84,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Traverse; Terrain; Reinforcement learning; Robot; Pipeline (software); Artificial intelligence; Computer science; Computer vision; Point (geometry); Mobile robot; Trajectory; Geography; Mathematics; Cartography","score_opus":0.01694845159004387,"score_gpt":0.26733563832348006,"score_spread":0.2503871867334362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176880374","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":[0.007852049,0.000011474693,0.9766116,0.013914068,0.00053377234,0.0008387378,0.0000010649644,0.00018769012,0.00004952416],"genre_scores_gemma":[0.7057514,0.000010474908,0.29053578,0.0027777755,0.0001558136,0.00015257754,0.00017119013,0.00003171467,0.00041322544],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997997,0.00007629301,0.000659862,0.0005080188,0.00028278772,0.00047606946],"domain_scores_gemma":[0.9988467,0.00027593222,0.00026087242,0.0003244483,0.0001777475,0.00011428802],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048340816,0.00023871631,0.00029237714,0.000201134,0.0002359925,0.00037306343,0.00029101473,0.00009665285,0.0000026166024],"category_scores_gemma":[0.00016710868,0.0002680089,0.00009426251,0.00036329866,0.000026644517,0.00046242133,0.00010353127,0.00017124185,0.000007440198],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010556152,0.00001819746,0.00014115545,0.00009421139,0.000016793172,0.000006045904,0.0013961623,0.9822825,0.007529847,0.0022750439,0.00038062254,0.0058488403],"study_design_scores_gemma":[0.0012266351,0.00012497578,0.00061590195,0.000107947824,0.000016873033,0.000009100382,0.000051754912,0.9950338,0.0013759525,0.00017259578,0.0009547368,0.000309726],"about_ca_topic_score_codex":0.000027357803,"about_ca_topic_score_gemma":0.000016115706,"teacher_disagreement_score":0.6978994,"about_ca_system_score_codex":0.00020153735,"about_ca_system_score_gemma":0.00007190674,"threshold_uncertainty_score":0.99997723},"labels":[],"label_agreement":null},{"id":"W3177370677","doi":"10.1609/aaai.v35i18.17927","title":"Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract)","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Dependency grammar; Python (programming language); Interpretability; Dependency (UML); GRASP; Modular design; Backtracking; Artificial intelligence; Algorithm; Programming language","score_opus":0.08900379891208272,"score_gpt":0.31973577856656876,"score_spread":0.23073197965448605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177370677","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":[0.10536665,0.00006145634,0.8494557,0.0013262271,0.001280114,0.00052117516,6.008367e-7,0.00023787768,0.041750215],"genre_scores_gemma":[0.99030316,0.00007767408,0.007880482,0.00018566275,0.00007822754,0.0000110824385,8.4209967e-7,0.000023228291,0.0014396287],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99644375,0.000028589438,0.0009917694,0.0006930002,0.0012228182,0.00062009157],"domain_scores_gemma":[0.99722934,0.00012678244,0.0008073674,0.0004971907,0.0012017406,0.00013756315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074304285,0.00034158633,0.00036606344,0.00016042356,0.0005145564,0.00072554545,0.0023429208,0.00013522673,0.00021444829],"category_scores_gemma":[0.0007625604,0.00029577606,0.00020985836,0.00082428,0.00017934912,0.0007608246,0.001268049,0.000777412,0.00013240999],"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":[0.000018312294,0.0001022205,0.0009582368,0.000085213185,0.00004984361,0.000006326128,0.002353576,0.36555412,0.10511229,0.5135895,0.0000470513,0.012123292],"study_design_scores_gemma":[0.000045514007,0.00014610114,0.00033518646,0.00047463624,0.000024288272,0.000017092872,0.0009487725,0.56889176,0.41472834,0.013875921,0.00014777391,0.00036459867],"about_ca_topic_score_codex":0.00004215307,"about_ca_topic_score_gemma":0.000003149584,"teacher_disagreement_score":0.8849365,"about_ca_system_score_codex":0.00016768188,"about_ca_system_score_gemma":0.00030983603,"threshold_uncertainty_score":0.99994946},"labels":[],"label_agreement":null},{"id":"W3177464508","doi":"","title":"On the Sample Complexity of Batch Reinforcement Learning with Policy-Induced Data.","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Omega; Sample complexity; Horizon; Markov decision process; Upper and lower bounds; Time horizon; Function (biology); Exponential function; Combinatorics; Mathematics; Sample (material); Finite set; Binary logarithm; Markov process; Mathematical optimization; Physics; Computer science; Statistics; Artificial intelligence; Mathematical analysis; Quantum mechanics","score_opus":0.20235586642382825,"score_gpt":0.2316189306737228,"score_spread":0.029263064249894555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177464508","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":[0.087876,0.000004784752,0.90726787,0.00041725088,0.00016931276,0.00035022877,0.0000064380124,0.00012996893,0.0037781654],"genre_scores_gemma":[0.9947361,0.00004469818,0.004012981,0.0001940611,0.000049629965,8.897345e-7,0.00014921984,0.000022450702,0.0007899732],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974472,0.00033771578,0.0003228466,0.0011067409,0.00034510408,0.00044042934],"domain_scores_gemma":[0.99438626,0.000682585,0.0006573736,0.0038692502,0.00027785584,0.00012669599],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005658471,0.0003741085,0.00043712844,0.00023953774,0.00031202871,0.00021856444,0.00462987,0.0001775959,0.000083595085],"category_scores_gemma":[0.00044108543,0.0003157268,0.00012622996,0.0009466784,0.00027600984,0.00036712253,0.006742943,0.0012119075,0.000021541102],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021513748,0.00002466563,0.0005463802,0.000046085413,0.00012450313,0.000032425873,0.00030601618,0.7372183,0.00001880531,0.2615461,0.000057617635,0.000057522364],"study_design_scores_gemma":[0.000367147,0.00023587212,0.00056067196,0.00022537864,0.000053104282,0.0000025947163,0.0002906253,0.99448186,0.00028465793,0.0029115258,0.00022466708,0.00036186594],"about_ca_topic_score_codex":0.0017836564,"about_ca_topic_score_gemma":0.00007829229,"teacher_disagreement_score":0.9068601,"about_ca_system_score_codex":0.00025647797,"about_ca_system_score_gemma":0.00071313255,"threshold_uncertainty_score":0.9999295},"labels":[],"label_agreement":null},{"id":"W3181012797","doi":"10.1609/aaai.v36i6.20660","title":"Learning Expected Emphatic Traces for Deep RL","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Computer science; Weighting; Scalability; Convergence (economics); Stability (learning theory); Artificial intelligence; Machine learning; Sampling (signal processing); Sample (material); Artificial neural network; Baseline (sea); Key (lock); Variance (accounting); Algorithm; Computer vision","score_opus":0.0655002341992619,"score_gpt":0.2902482295044936,"score_spread":0.22474799530523168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181012797","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":[0.091606244,0.00004368549,0.8926318,0.0035686225,0.0010841232,0.0012226625,0.000002703561,0.0003269036,0.009513237],"genre_scores_gemma":[0.99204814,0.000009932454,0.006508832,0.00015527305,0.00004874566,0.00017328125,0.0000011100364,0.000018223214,0.0010364663],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977809,0.000039514318,0.00056905934,0.00048152698,0.0007126877,0.00041629848],"domain_scores_gemma":[0.9983725,0.0002468976,0.0005734891,0.00027179322,0.00046566586,0.00006968242],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007094426,0.00021363918,0.00025656927,0.00016628974,0.00079804484,0.00028437338,0.0026881082,0.000047430007,0.00014723788],"category_scores_gemma":[0.0006209271,0.00018273028,0.00015412315,0.00078358257,0.00014701733,0.00035745243,0.0007129615,0.00045341795,0.000025233001],"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":[0.000072801246,0.000105438296,0.00022069649,0.000053722302,0.000027258375,4.1280157e-7,0.0077080564,0.16648324,0.014964776,0.77292114,0.00011804516,0.037324395],"study_design_scores_gemma":[0.000047813675,0.00077281223,0.00005795711,0.00004996344,0.000014969077,0.000005343334,0.0039449753,0.85548747,0.11093242,0.027844137,0.0005891024,0.0002530302],"about_ca_topic_score_codex":0.000011272876,"about_ca_topic_score_gemma":0.0000017597255,"teacher_disagreement_score":0.9004419,"about_ca_system_score_codex":0.00009219248,"about_ca_system_score_gemma":0.00009647871,"threshold_uncertainty_score":0.7451524},"labels":[],"label_agreement":null},{"id":"W3181841583","doi":"10.1109/crv52889.2021.00018","title":"Uncertainty-Aware Policy Sampling and Mixing for Safe Interactive Imitation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Université de Montréal","funders":"","keywords":"Computer science; Trajectory; Process (computing); Imitation; Interactivity; Harm; Robot; Benchmark (surveying); Mixing (physics); Interleaving; Sampling (signal processing); Function (biology); Artificial intelligence; Human–computer interaction; Machine learning; Multimedia; Computer vision; Programming language","score_opus":0.03195446967103175,"score_gpt":0.31911333008798,"score_spread":0.2871588604169482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181841583","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":[0.0030072853,0.00002893744,0.9922154,0.0015403499,0.0001487034,0.00011588488,3.5689527e-7,0.00011195239,0.002831127],"genre_scores_gemma":[0.7595336,0.000020466,0.23690876,0.0004996445,0.00010327379,0.000013057072,0.000017374758,0.000011595222,0.0028922497],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908817,0.000057503083,0.00018446748,0.000298687,0.00013887111,0.00023230404],"domain_scores_gemma":[0.9987265,0.0007225855,0.00009624572,0.00017252444,0.00022356553,0.00005856201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019945535,0.00010336241,0.0001188844,0.000107353815,0.00022932014,0.00031395146,0.00017258416,0.000041056333,0.000012086628],"category_scores_gemma":[0.0008421664,0.00010380329,0.00004356788,0.0002617598,0.000018196246,0.0004835437,0.00022080244,0.00015767867,0.000008107192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005960718,0.0000060130665,0.0007631931,0.000030286667,0.00002434385,0.0000022648285,0.0020628967,0.90980726,0.0010212539,0.054718465,0.000039432507,0.03151864],"study_design_scores_gemma":[0.00030679203,0.0000692175,0.000823593,0.00004635977,0.0000053440926,0.000012033925,0.00104395,0.9892213,0.0014078676,0.0011528058,0.005763009,0.00014773927],"about_ca_topic_score_codex":0.000046296413,"about_ca_topic_score_gemma":0.000008272917,"teacher_disagreement_score":0.7565263,"about_ca_system_score_codex":0.000089452,"about_ca_system_score_gemma":0.00012427312,"threshold_uncertainty_score":0.42329755},"labels":[],"label_agreement":null},{"id":"W3184031856","doi":"10.22215/etd/2021-14448","title":"Several Reinforcement Learning Methods in Mean-Field Games with Binary Action Spaces","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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","funders":"","keywords":"Reinforcement learning; Action (physics); Convergence (economics); Computer science; Binary number; Task (project management); Field (mathematics); Artificial intelligence; Population; Binary classification; Machine learning; Space (punctuation); Mathematical optimization; Mathematics; Engineering; Support vector machine","score_opus":0.027511521246958562,"score_gpt":0.3446213576646282,"score_spread":0.31710983641766965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184031856","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":[0.003991433,0.00010888808,0.9421174,0.00018096717,0.0008599422,0.0002834029,3.5829032e-8,0.0002328754,0.05222509],"genre_scores_gemma":[0.0988836,0.00048872293,0.5817887,0.00037623468,0.00013337447,0.00009577617,0.00036616233,0.000076958175,0.31779045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973592,0.00030129048,0.0005179646,0.00067710824,0.0006861981,0.00045824394],"domain_scores_gemma":[0.9983836,0.0003232471,0.00044220683,0.000581339,0.00018307853,0.000086535045],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061743637,0.00040800145,0.00045840885,0.00046867662,0.00014998383,0.0004918473,0.0006564724,0.00032245935,0.00031060522],"category_scores_gemma":[0.00014343616,0.0003588552,0.00010724488,0.00067131897,0.000014391866,0.0007771869,0.00016045493,0.0011111505,0.00003054893],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005466135,0.00001655553,0.0003198291,0.00016239681,0.000069780006,0.000046748326,0.0034859537,0.9771668,0.0006041426,0.0024384384,0.00026408196,0.015370619],"study_design_scores_gemma":[0.0006291447,0.0009307212,0.0013425859,0.00063968473,0.00004395629,0.000018597404,0.0071340287,0.9658023,0.016112866,0.00004214637,0.0064247814,0.0008791706],"about_ca_topic_score_codex":0.00036089148,"about_ca_topic_score_gemma":0.0003751661,"teacher_disagreement_score":0.36032864,"about_ca_system_score_codex":0.00018812872,"about_ca_system_score_gemma":0.00032393055,"threshold_uncertainty_score":0.99988633},"labels":[],"label_agreement":null},{"id":"W3185313117","doi":"","title":"Exploration-Driven Representation Learning in Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Representation (politics); Machine learning","score_opus":0.06580708750621926,"score_gpt":0.32819784165969396,"score_spread":0.2623907541534747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185313117","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":[0.007037508,0.00003059396,0.91318405,0.0048840875,0.0006748372,0.00017648071,3.554308e-7,0.0004046244,0.07360747],"genre_scores_gemma":[0.97355795,0.00026492847,0.0063918666,0.00028560645,0.000118811455,0.000040267383,0.00023591075,0.000028473887,0.019076178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965946,0.00054764666,0.00066659437,0.00074107875,0.0010281331,0.0004219278],"domain_scores_gemma":[0.99832416,0.0002912615,0.00042184285,0.000361478,0.0004928169,0.000108446],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005312223,0.00028961938,0.00028285137,0.0004522982,0.00030638,0.00068533205,0.0008472953,0.00011175832,0.00068110065],"category_scores_gemma":[0.001559316,0.00032449153,0.00009533347,0.0006283116,0.00004042054,0.0013252757,0.00051010837,0.0016566284,0.0003468063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020857851,0.000029293744,0.02576623,0.000007653563,0.000034003697,0.000094575094,0.0013157493,0.88823676,0.0019613563,0.07560354,0.000024885285,0.00690512],"study_design_scores_gemma":[0.0007856997,0.0002286176,0.0020729452,0.00014611954,0.0000048905467,0.00001899382,0.000533653,0.9865861,0.0009962178,0.0007037591,0.0075984686,0.0003245672],"about_ca_topic_score_codex":0.000115119816,"about_ca_topic_score_gemma":0.000041896492,"teacher_disagreement_score":0.9665204,"about_ca_system_score_codex":0.00025385272,"about_ca_system_score_gemma":0.00019859475,"threshold_uncertainty_score":0.9999207},"labels":[],"label_agreement":null},{"id":"W3185541071","doi":"","title":"Contextual Policy Transfer in Reinforcement Learning Domains via Deep Mixtures-of-Experts","year":2021,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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; Robustness (evolution); Machine learning; Artificial intelligence; Transfer of learning; Reuse; Context (archaeology); Task (project management); Bayesian probability; Engineering","score_opus":0.03181191723208893,"score_gpt":0.2972237819968313,"score_spread":0.2654118647647424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185541071","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":[0.017802097,0.00014352263,0.9778465,0.00074098824,0.00034482637,0.0003008406,5.034385e-7,0.0000747107,0.0027460174],"genre_scores_gemma":[0.99531746,0.00009237086,0.0037506698,0.00040663997,0.00008703486,0.00002862503,0.000013035425,0.000018654568,0.00028549664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963885,0.00032359466,0.0012738063,0.0006292852,0.0006361855,0.0007486546],"domain_scores_gemma":[0.9983697,0.00047789974,0.00013978027,0.000650998,0.00022674644,0.00013489752],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074074406,0.00030707652,0.00046274083,0.0005450668,0.00011423979,0.00013132862,0.00096059655,0.00017908815,0.00014912555],"category_scores_gemma":[0.0008757324,0.00032296003,0.00013099263,0.0018989161,0.00019478127,0.0003611309,0.00026179734,0.0005549738,0.00005069255],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038712933,0.000085955246,0.00032359496,0.000022522665,0.000013332588,0.000098004755,0.0068125525,0.83334583,0.0065737306,0.11676473,0.0000063364614,0.035914686],"study_design_scores_gemma":[0.0001554912,0.00022840472,0.0000757289,0.00013222086,0.0000041434664,0.000015143939,0.0010162907,0.9247836,0.06667003,0.0057767914,0.0007781904,0.00036398173],"about_ca_topic_score_codex":0.0011149034,"about_ca_topic_score_gemma":0.0012899691,"teacher_disagreement_score":0.9775154,"about_ca_system_score_codex":0.00036058045,"about_ca_system_score_gemma":0.00037812046,"threshold_uncertainty_score":0.9999223},"labels":[],"label_agreement":null},{"id":"W3185619002","doi":"10.48550/arxiv.2107.08114","title":"Decentralized Multi-Agent Reinforcement Learning for Task Offloading Under Uncertainty","year":2021,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Marl; Computer science; Robustness (evolution); Task (project management); Curse of dimensionality; Artificial intelligence; Machine learning; Distributed computing; Engineering","score_opus":0.0788413178322847,"score_gpt":0.3097153766254181,"score_spread":0.23087405879313339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185619002","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":[0.06713107,0.00038579182,0.92716384,0.00059903815,0.0027578175,0.0012137385,0.0000016553638,0.0005178554,0.0002291901],"genre_scores_gemma":[0.94196135,0.000453547,0.051492143,0.0008679179,0.00019670743,0.00026054637,0.0003273023,0.00008859766,0.004351903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99510497,0.00026437084,0.0011208468,0.0015123853,0.0007875211,0.0012098807],"domain_scores_gemma":[0.9962274,0.00036151946,0.000870203,0.0017329777,0.00048283214,0.0003250938],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088755856,0.0007406188,0.0008183559,0.00023954384,0.0005277461,0.0007569962,0.002126041,0.0004811972,0.0001064899],"category_scores_gemma":[0.0006115683,0.00077884225,0.00058757217,0.00036897414,0.00009196931,0.0004043013,0.0033619325,0.0014382182,0.000111977264],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016191143,0.000045655856,0.0129257515,0.00023843569,0.0002925723,0.000020344054,0.0012416027,0.9824925,0.0010394285,0.000793536,0.00025885415,0.0006351398],"study_design_scores_gemma":[0.0015385704,0.00013436376,0.0038753115,0.00045635903,0.000103035985,0.000006206993,0.0002874042,0.98311955,0.00095250143,0.00005086023,0.00857944,0.0008963919],"about_ca_topic_score_codex":0.00015356473,"about_ca_topic_score_gemma":0.000016488686,"teacher_disagreement_score":0.8756717,"about_ca_system_score_codex":0.0008019626,"about_ca_system_score_gemma":0.0005982336,"threshold_uncertainty_score":0.99946624},"labels":[],"label_agreement":null},{"id":"W3187079608","doi":"10.24963/ijcai.2021/562","title":"Symbolic Dynamic Programming for Continuous State MDPs with Linear Program Transitions","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Toronto","funders":"","keywords":"Discretization; Computer science; Piecewise linear function; Dynamic programming; Linear programming; Mathematical optimization; Operator (biology); Bellman equation; Piecewise; State (computer science); Algorithm; Mathematics","score_opus":0.010607059097889362,"score_gpt":0.2697420779943324,"score_spread":0.2591350188964431,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187079608","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":[0.003955292,0.00002880415,0.99226403,0.001054062,0.00010186589,0.000911455,0.0000021644887,0.0007360329,0.00094627443],"genre_scores_gemma":[0.1820418,0.0000068935487,0.8122968,0.0001916936,0.000020223488,0.0002524989,0.000038627266,0.000022649125,0.005128828],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986577,0.000033252694,0.00023674432,0.00037827503,0.0002430117,0.00045100367],"domain_scores_gemma":[0.9990157,0.00006530359,0.00007162853,0.00044890246,0.0002956747,0.00010277797],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013935888,0.00015609029,0.00019223371,0.000060148832,0.00017562212,0.0003330501,0.00034937984,0.000041106643,0.000010530716],"category_scores_gemma":[0.000027049186,0.00013089784,0.000079862424,0.00046260434,0.000053521668,0.00028647215,0.00006246797,0.00013652821,0.000017529253],"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":[0.00003038736,0.00050126284,0.0005660296,0.00022322308,0.0002403406,0.00014325517,0.003176115,0.46081796,0.00058904925,0.02956704,0.0002057463,0.50393957],"study_design_scores_gemma":[0.00077531877,0.00069039373,0.00022236418,0.000048157664,0.000024287954,0.0000607046,0.0001627406,0.97269666,0.0008167618,0.00014620293,0.02408211,0.00027428853],"about_ca_topic_score_codex":0.000006137231,"about_ca_topic_score_gemma":0.00004095222,"teacher_disagreement_score":0.5118787,"about_ca_system_score_codex":0.000033719698,"about_ca_system_score_gemma":0.00016937705,"threshold_uncertainty_score":0.5337859},"labels":[],"label_agreement":null},{"id":"W3190031629","doi":"10.48550/arxiv.2108.02827","title":"An Elementary Proof that Q-learning Converges Almost Surely","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Q-learning; Function (biology); Bellman equation; Field (mathematics); Computer science; State (computer science); Value (mathematics); Elementary proof; Mathematical economics; Artificial intelligence; Connection (principal bundle); Mathematics; Discrete mathematics; Algorithm; Machine learning; Pure mathematics","score_opus":0.07020033359668047,"score_gpt":0.19847805084323028,"score_spread":0.1282777172465498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190031629","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":[0.18528916,0.00006591523,0.8112801,0.00009058247,0.00086334837,0.00031041692,0.0000027300034,0.0003925172,0.0017052825],"genre_scores_gemma":[0.9912462,0.00020809795,0.0051329075,0.00019100176,0.00008424607,0.0000014262484,0.00016072017,0.00003867298,0.0029366873],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968442,0.00045882337,0.00028647284,0.0015378797,0.0002719188,0.0006007556],"domain_scores_gemma":[0.9971231,0.00012473238,0.00046877202,0.0017600087,0.0002479718,0.00027541656],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004660072,0.00047336725,0.0004558873,0.00027048035,0.0003223728,0.00052046025,0.0027887009,0.00034195933,0.0002125287],"category_scores_gemma":[0.000045784403,0.0005860093,0.00023955641,0.0005535472,0.000120292396,0.0010904158,0.0029273173,0.0013778481,0.00006077253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011470095,0.000063432766,0.04191835,0.00008962476,0.00014678514,0.00056321576,0.00051023264,0.94885796,0.00006920415,0.007295718,0.00014568867,0.0003282969],"study_design_scores_gemma":[0.0004436305,0.00016901013,0.0034495993,0.00014594442,0.000084494815,0.00000921614,0.00063601654,0.9914979,0.0010173953,0.0004838559,0.0013376004,0.0007253876],"about_ca_topic_score_codex":0.000223966,"about_ca_topic_score_gemma":0.000038052724,"teacher_disagreement_score":0.80614716,"about_ca_system_score_codex":0.00028744593,"about_ca_system_score_gemma":0.0003727326,"threshold_uncertainty_score":0.9996591},"labels":[],"label_agreement":null},{"id":"W3191161744","doi":"10.1109/iwcmc51323.2021.9498960","title":"Safe Driving of Autonomous Vehicles through State Representation Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Toronto Metropolitan University","funders":"","keywords":"Autoencoder; Computer science; Reinforcement learning; Representation (politics); Artificial intelligence; Perception; Scheme (mathematics); Object (grammar); Function (biology); Deep learning; Simulation; Mathematics","score_opus":0.023431499770939335,"score_gpt":0.2786308688831665,"score_spread":0.2551993691122272,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191161744","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":[0.036625672,0.000032775522,0.9359323,0.0003583257,0.00015644415,0.00004968375,6.850824e-8,0.00014874022,0.026696011],"genre_scores_gemma":[0.79827607,0.000039782022,0.19042528,0.00009453738,0.00001657339,0.000001932473,0.0000035946434,0.000007822727,0.011134439],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988312,0.0001110116,0.00030582893,0.0002699065,0.0002872488,0.0001947934],"domain_scores_gemma":[0.9990583,0.00018677344,0.0001661159,0.00040438757,0.00015160261,0.000032820524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001801364,0.00008449273,0.00014097772,0.000039446146,0.000094676805,0.000119471886,0.00032241314,0.000029913648,0.0000748614],"category_scores_gemma":[0.00022247007,0.00008567618,0.000054339056,0.00036909137,0.000030841336,0.00060782494,0.00033673574,0.00015003777,0.000045847664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.089254e-7,0.000011939503,0.012137861,0.00001266213,0.000019363473,0.000015687989,0.0017933177,0.9523181,0.006048015,0.017050097,0.00013182494,0.010460237],"study_design_scores_gemma":[0.00025726782,0.00006710633,0.011052638,0.000035912417,0.000005891208,0.000013590309,0.00029863822,0.8808304,0.101386614,0.001486077,0.004394969,0.00017089651],"about_ca_topic_score_codex":0.000049056023,"about_ca_topic_score_gemma":0.0000047293174,"teacher_disagreement_score":0.7616504,"about_ca_system_score_codex":0.000032571814,"about_ca_system_score_gemma":0.00009776758,"threshold_uncertainty_score":0.34937733},"labels":[],"label_agreement":null},{"id":"W3191305580","doi":"10.1109/isscs52333.2021.9497411","title":"Inverted Pendulum Control with a Robotic Arm using Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Windsor","funders":"","keywords":"Inverted pendulum; Reinforcement learning; Pendulum; Computer science; Benchmark (surveying); Double inverted pendulum; Robot; Control theory (sociology); Position (finance); Inertial measurement unit; Artificial intelligence; Simulation; Control (management); Engineering; Physics; Mechanical engineering; Nonlinear system; Geology","score_opus":0.019758795675198365,"score_gpt":0.23581916117171545,"score_spread":0.21606036549651708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191305580","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":[0.0011212197,0.000047309975,0.9863355,0.00035950769,0.00021775947,0.00020415633,2.1508463e-8,0.00031549478,0.011398985],"genre_scores_gemma":[0.8960489,0.000008558586,0.097982846,0.0010660453,0.000042755717,0.000007869063,0.000005822529,0.000023158222,0.004814018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977461,0.00014481525,0.00039243198,0.0004994956,0.000640898,0.00057627365],"domain_scores_gemma":[0.9985329,0.00012226302,0.00019989522,0.0006735926,0.0002960112,0.00017537142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025665842,0.00025153835,0.00030903617,0.0001227616,0.00029164634,0.00040794743,0.0005724616,0.000075598575,0.000342632],"category_scores_gemma":[0.00013941414,0.00021726784,0.00007887823,0.0006760742,0.00005454158,0.0006098441,0.0003017164,0.00038493625,0.00010297254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007967031,0.00002252902,0.0017087999,0.000017513694,0.00008075013,0.00010956081,0.00027617154,0.9848679,0.000724778,0.011579819,0.00003101303,0.0005732122],"study_design_scores_gemma":[0.0013028784,0.00025203134,0.00020248079,0.000052020594,0.000038814673,0.0001203493,0.00016563188,0.99572533,0.0012026083,0.00004264094,0.0005730454,0.0003221545],"about_ca_topic_score_codex":0.000059780814,"about_ca_topic_score_gemma":0.000018138055,"teacher_disagreement_score":0.8949277,"about_ca_system_score_codex":0.00015026073,"about_ca_system_score_gemma":0.0002693021,"threshold_uncertainty_score":0.8859925},"labels":[],"label_agreement":null},{"id":"W3193711978","doi":"10.65109/lixm5646","title":"Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Huawei Technologies (Canada)","funders":"","keywords":"Curriculum; Cornerstone; Computer science; Diversity (politics); Benchmark (surveying); Variety (cybernetics); Process (computing); Reinforcement learning; Component (thermodynamics); Human–computer interaction; Artificial intelligence; Psychology; Pedagogy; Sociology","score_opus":0.02883001515941496,"score_gpt":0.3124728168870807,"score_spread":0.2836428017276657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193711978","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":[0.0010668571,0.000054666856,0.9791616,0.0011549294,0.001257292,0.00025520864,0.000001639273,0.00043660775,0.016611177],"genre_scores_gemma":[0.86487013,0.00004202433,0.08701781,0.00054211554,0.0002187003,0.000056872203,0.000015173213,0.00002692505,0.04721024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978324,0.00013329592,0.00040166941,0.00058621797,0.0004967591,0.00054962776],"domain_scores_gemma":[0.99818444,0.00048541345,0.00009974367,0.0005793068,0.00045878603,0.00019231127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003599529,0.00019922879,0.00026455813,0.00011617714,0.00038149967,0.000672661,0.0006784498,0.00007787741,0.00017808465],"category_scores_gemma":[0.0004822423,0.00018718066,0.00014703991,0.0004943792,0.000053820546,0.00052145374,0.000576369,0.00025643012,0.0001956022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038095852,0.00013194463,0.025132604,0.00032942058,0.00009124534,0.00015903937,0.0009407702,0.51798993,0.00028759227,0.42947337,0.022900123,0.002560133],"study_design_scores_gemma":[0.00035053346,0.000075427626,0.0005574963,0.00005946629,0.000020734637,0.000011086039,0.00082965026,0.963612,0.0009994443,0.000047482263,0.033169355,0.00026727424],"about_ca_topic_score_codex":0.00038979,"about_ca_topic_score_gemma":0.000030546016,"teacher_disagreement_score":0.8921438,"about_ca_system_score_codex":0.00012213751,"about_ca_system_score_gemma":0.00012304181,"threshold_uncertainty_score":0.76330054},"labels":[],"label_agreement":null},{"id":"W3194918255","doi":"10.1016/j.eng.2021.04.027","title":"Actor–Critic Reinforcement Learning and Application in Developing Computer-Vision-Based Interface Tracking","year":2021,"lang":"en","type":"article","venue":"Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Interface (matter); Context (archaeology); Process (computing); Artificial intelligence; Noise (video); Tracking (education); Control (management); Object (grammar); Machine learning; Computer vision","score_opus":0.009053442320821347,"score_gpt":0.251530277148817,"score_spread":0.24247683482799565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194918255","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":[0.012960406,0.00012328348,0.9860858,0.00028159007,0.00018424261,0.00009568119,3.3003143e-8,0.00019153774,0.00007743981],"genre_scores_gemma":[0.853858,0.000014457441,0.14597471,0.000066861765,0.000030050629,0.000009705714,0.0000037904351,0.000013053195,0.000029377145],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893177,0.000027528735,0.00027590146,0.0003039339,0.00019273636,0.0002681103],"domain_scores_gemma":[0.999443,0.00018575223,0.000052910098,0.00020705129,0.00005668874,0.000054593882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023210458,0.00014056379,0.00014677746,0.00014526106,0.00006835313,0.00021150472,0.00021629615,0.00004973601,0.0000027465976],"category_scores_gemma":[0.00009776016,0.00016805078,0.000023824228,0.00037718043,0.0000098069595,0.00031650305,0.00020625905,0.00026806537,0.000007444001],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.9376586e-7,0.000003545295,0.0008625887,0.00006977327,0.0000046101914,0.000013429245,0.00021717256,0.9866917,0.0029376764,0.0028929666,0.0000025618722,0.0063032904],"study_design_scores_gemma":[0.00023134994,0.000032109652,0.0025195507,0.0002421356,0.0000017665225,0.000009759385,0.000015391472,0.9886268,0.005913385,0.0000070409305,0.0022137125,0.00018699557],"about_ca_topic_score_codex":0.000005198043,"about_ca_topic_score_gemma":0.0000019521533,"teacher_disagreement_score":0.84089756,"about_ca_system_score_codex":0.00014208836,"about_ca_system_score_gemma":0.000057750807,"threshold_uncertainty_score":0.68529123},"labels":[],"label_agreement":null},{"id":"W3196801835","doi":"10.48550/arxiv.2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Machine learning; Error-driven learning; Component (thermodynamics); Psychology; Social psychology","score_opus":0.18719629604214041,"score_gpt":0.27015657521499553,"score_spread":0.08296027917285512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196801835","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":[0.024335425,0.000046013018,0.97339785,0.000017974264,0.00038104085,0.0002272307,4.3661043e-7,0.00008625224,0.0015077498],"genre_scores_gemma":[0.9680552,0.00023146367,0.030358806,0.000018766037,0.000010305647,0.0000011634672,0.00006536915,0.000014358341,0.0012445754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99708146,0.0012283381,0.00046063366,0.0007786827,0.00015099718,0.00029991873],"domain_scores_gemma":[0.9975648,0.00037206127,0.0005935967,0.001025691,0.0003631738,0.000080678794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017711894,0.00025426206,0.00045114293,0.00042752933,0.000065378554,0.000117881325,0.0012689881,0.0002485692,0.000031345815],"category_scores_gemma":[0.0004888544,0.00032563007,0.00011036143,0.0012297317,0.000059522634,0.0006423161,0.002407808,0.0008384475,0.000009720517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000105500585,0.000022500615,0.010231903,0.000077817465,0.000043574193,0.000051515857,0.0007504982,0.9817227,0.00007707986,0.006370243,0.000007546066,0.000634084],"study_design_scores_gemma":[0.00030862584,0.00007777757,0.00915333,0.00015803345,0.000016377033,5.3981864e-7,0.00015759066,0.989032,0.00043233167,0.0003411409,0.00003937295,0.000282923],"about_ca_topic_score_codex":0.0011126692,"about_ca_topic_score_gemma":0.00014500979,"teacher_disagreement_score":0.94371974,"about_ca_system_score_codex":0.0002581415,"about_ca_system_score_gemma":0.0003485068,"threshold_uncertainty_score":0.9999196},"labels":[],"label_agreement":null},{"id":"W3197466741","doi":"10.48550/arxiv.2109.03331","title":"CyGIL: A Cyber Gym for Training Autonomous Agents over Emulated Network Systems","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Training (meteorology); Computer science; Cyber-physical system; Computer network; Computer security; Operating system; Physics","score_opus":0.1234854113982818,"score_gpt":0.21512399704081328,"score_spread":0.09163858564253148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197466741","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":[0.049794476,0.00009176245,0.94311684,0.00002731338,0.0031159534,0.00079924916,0.000007047859,0.0004769436,0.0025703975],"genre_scores_gemma":[0.98625,0.00004811915,0.006037511,0.000141718,0.00026764264,0.000005405829,0.00008646094,0.000052166914,0.007110971],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969318,0.00020456512,0.00043742787,0.001425822,0.00018360355,0.00081678823],"domain_scores_gemma":[0.99710244,0.00024613793,0.00056942506,0.001568988,0.00027488338,0.00023813311],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004548551,0.0004852561,0.0006341176,0.00020691934,0.00031245366,0.0006252154,0.002036397,0.0005003658,0.000042394204],"category_scores_gemma":[0.00007177515,0.0006036844,0.00040071819,0.0006982058,0.00006931671,0.00045177346,0.0021138282,0.0007147585,0.00003255115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012659468,0.000023958894,0.00084823166,0.00012128736,0.0002831376,0.00026800463,0.0007254291,0.96825117,0.0000044379262,0.028527156,0.0007955711,0.00013897798],"study_design_scores_gemma":[0.0007023285,0.000057788322,0.0008282007,0.0003237893,0.00011782688,0.000007471836,0.00013278055,0.9930261,0.000004113962,0.00059104915,0.003592085,0.0006164918],"about_ca_topic_score_codex":0.00013066265,"about_ca_topic_score_gemma":0.000010873553,"teacher_disagreement_score":0.93707937,"about_ca_system_score_codex":0.00047098956,"about_ca_system_score_gemma":0.00046242806,"threshold_uncertainty_score":0.9996415},"labels":[],"label_agreement":null},{"id":"W3200155431","doi":"10.48550/arxiv.2109.05110","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Computer science; Algorithm; Artificial intelligence; Machine learning","score_opus":0.10666805785520882,"score_gpt":0.25010017098736903,"score_spread":0.1434321131321602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200155431","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":[0.24545015,0.00003423461,0.75338715,0.000110420115,0.00016145757,0.00020577622,0.0000016000903,0.00006695217,0.0005822254],"genre_scores_gemma":[0.9967994,0.00017822855,0.0025809265,0.000053143092,0.000085769956,0.0000013848795,0.000038949547,0.000013704329,0.0002484736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975035,0.00069549744,0.00038328857,0.0008043913,0.00028456983,0.00032872253],"domain_scores_gemma":[0.99803156,0.00016458571,0.00041821852,0.0012300431,0.000060322724,0.000095292715],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005774845,0.00026129984,0.00037877864,0.00031897053,0.00014001025,0.00014383368,0.0019539385,0.0002753405,0.000017527933],"category_scores_gemma":[0.000066436245,0.00026177737,0.00015747781,0.0006251022,0.00011760716,0.00036230212,0.0012564153,0.0012474976,0.0000134714555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006481029,0.00013254129,0.080898635,0.00002723566,0.000032088305,0.00006436291,0.0027447129,0.9131388,0.00001515584,0.0010601298,0.000019922443,0.001859953],"study_design_scores_gemma":[0.00028967945,0.00020441932,0.03585044,0.000058794845,0.000031542757,0.000003890819,0.0008950622,0.961792,0.000053415868,0.00020772571,0.0004082876,0.00020472228],"about_ca_topic_score_codex":0.00016245912,"about_ca_topic_score_gemma":0.000013062886,"teacher_disagreement_score":0.7513493,"about_ca_system_score_codex":0.00032916863,"about_ca_system_score_gemma":0.00021356424,"threshold_uncertainty_score":0.99998343},"labels":[],"label_agreement":null},{"id":"W3201099806","doi":"10.1109/lra.2021.3139145","title":"Learning Selective Communication for Multi-Agent Path Finding","year":2021,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"","keywords":"Computer science; Overhead (engineering); Imitation; Reinforcement learning; Artificial intelligence; Path (computing); Focus (optics); Simple (philosophy); Scheme (mathematics); Machine learning; Telecommunications network; Distributed computing; Computer network; Mathematics","score_opus":0.03388270364324859,"score_gpt":0.28015295791465555,"score_spread":0.24627025427140697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201099806","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":[0.0100318445,0.000043485157,0.98623323,0.0030477496,0.00025175785,0.00017277352,5.389846e-7,0.00017232096,0.000046282745],"genre_scores_gemma":[0.5175215,0.000040801417,0.48131567,0.00082992116,0.000028911854,0.000016643478,0.000021067175,0.0000118260305,0.000213666],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990408,0.000110443005,0.00023241244,0.00024229991,0.0001674819,0.00020657151],"domain_scores_gemma":[0.9991868,0.00019136579,0.00017443245,0.00026708446,0.00013137513,0.000048933765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026664807,0.00011444107,0.00012782753,0.00007345909,0.00038248408,0.00030634715,0.00022170972,0.000048792055,0.0000015345986],"category_scores_gemma":[0.00012230285,0.00012538613,0.000048151094,0.00021287095,0.000027017473,0.00034379584,0.000089797344,0.0001693894,0.000008038716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[7.404927e-7,0.000012907325,0.000603686,0.000026747868,0.000021878881,0.0000021120738,0.0011028436,0.9854792,0.0060035563,0.004177393,0.0003360714,0.0022328652],"study_design_scores_gemma":[0.00039356964,0.000034267257,0.0025912074,0.000047273395,0.000011771623,0.000007954215,0.000061326886,0.9941434,0.0019781617,0.000051234005,0.0005295276,0.00015030448],"about_ca_topic_score_codex":0.0000028573438,"about_ca_topic_score_gemma":0.0000012993012,"teacher_disagreement_score":0.5074896,"about_ca_system_score_codex":0.00007351528,"about_ca_system_score_gemma":0.00003764358,"threshold_uncertainty_score":0.51130974},"labels":[],"label_agreement":null},{"id":"W3201820699","doi":"10.1109/tpami.2022.3215769","title":"Continuous-Time Fitted Value Iteration for Robust Policies","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Toronto","funders":"","keywords":"Bellman equation; Discretization; Reinforcement learning; Leverage (statistics); Optimal control; Mathematical optimization; Computer science; Robustness (evolution); Dynamic programming; Mathematics; Artificial intelligence","score_opus":0.020695523465835194,"score_gpt":0.26019000160666267,"score_spread":0.23949447814082747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3201820699","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":[0.00087838527,0.000023550925,0.9976381,0.0007987852,0.00020309747,0.00023095089,0.000042095013,0.00011013968,0.000074884985],"genre_scores_gemma":[0.99123794,0.000026936894,0.005917741,0.0010854471,0.000021502732,0.00009383781,0.000025251395,0.000012877962,0.0015784816],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858665,0.00009336352,0.00035947564,0.00040677446,0.00031770286,0.00023604432],"domain_scores_gemma":[0.99911475,0.00019356822,0.00014337739,0.0004099849,0.00007690192,0.000061400424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031527726,0.00017806281,0.0002652528,0.0005442717,0.0006006101,0.0002327854,0.0004820657,0.00003270365,0.00026469765],"category_scores_gemma":[0.000007189205,0.00017613456,0.00023373967,0.0008965275,0.000036874557,0.00022809893,0.000013452198,0.00023262794,0.000017967124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000833039,0.00005354299,0.00014395092,0.0000069639345,0.00022106546,0.0000013716068,0.0003633045,0.91964537,0.0001873562,0.00020792776,0.000034334415,0.07912651],"study_design_scores_gemma":[0.000096769996,0.00023592975,0.00015239586,0.000004595259,0.00022265219,0.000006627733,0.000044652334,0.9885537,0.009947155,0.00007601038,0.00046614843,0.00019338435],"about_ca_topic_score_codex":0.00048884825,"about_ca_topic_score_gemma":0.000057860383,"teacher_disagreement_score":0.9917204,"about_ca_system_score_codex":0.000059809005,"about_ca_system_score_gemma":0.00001980887,"threshold_uncertainty_score":0.71825594},"labels":[],"label_agreement":null},{"id":"W3202097587","doi":"","title":"Learning One Representation to Optimize All Rewards","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Computer science; Representation (politics); Markov decision process; Artificial intelligence; Reinforcement learning; A priori and a posteriori; Machine learning; Markov process; Temporal difference learning; Mathematics","score_opus":0.04197470961659992,"score_gpt":0.29183757204241134,"score_spread":0.2498628624258114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202097587","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":[0.0032361443,0.00006014124,0.98540956,0.0013238696,0.00072241994,0.0002518636,4.4228787e-7,0.00049820123,0.008497358],"genre_scores_gemma":[0.9584229,0.0000096774675,0.037461348,0.0012984049,0.00012059132,0.000049925507,0.00006446659,0.0000129581495,0.0025597438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796575,0.00012772824,0.00066948915,0.00023152374,0.0006987865,0.00030671692],"domain_scores_gemma":[0.99840504,0.000056866447,0.0003905897,0.00038068957,0.00063732907,0.00012948466],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00039740404,0.00014808589,0.0002017328,0.00018164807,0.00025766113,0.001948632,0.00043996927,0.00007754767,0.0000070637793],"category_scores_gemma":[0.00043305184,0.00015545158,0.00004651492,0.0008205595,0.000013819776,0.004895332,0.00022626691,0.00025214656,0.00022115876],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003673543,0.0000056989174,0.00015286934,0.0001302303,0.000008938043,0.0000032407195,0.0035298937,0.9776489,0.0004119393,0.0009129422,0.00073232385,0.016459312],"study_design_scores_gemma":[0.00025362297,0.00006866658,0.00022049199,0.0001263446,0.0000066064044,0.000054859724,0.0006038564,0.9804281,0.0015102387,0.000010305923,0.01652518,0.00019170129],"about_ca_topic_score_codex":0.000025239708,"about_ca_topic_score_gemma":3.9400285e-7,"teacher_disagreement_score":0.9551867,"about_ca_system_score_codex":0.000105012805,"about_ca_system_score_gemma":0.00012956388,"threshold_uncertainty_score":0.99908745},"labels":[],"label_agreement":null},{"id":"W3202849004","doi":"10.1109/iccv48922.2021.01565","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/CVF International Conference on Computer Vision (ICCV)","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Embodied cognition; Computer science; Human–computer interaction; Task (project management); Perception; Oracle; Object (grammar); Models of communication; Embodied agent; Artificial intelligence; Communication; Psychology; Engineering; Software engineering","score_opus":0.03512853083241999,"score_gpt":0.3267310249632774,"score_spread":0.29160249413085737,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202849004","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":[0.024349729,0.0000641262,0.9591321,0.0026365505,0.0025179854,0.00032187905,0.000014534206,0.00006253317,0.010900609],"genre_scores_gemma":[0.9672541,0.00033404943,0.03108022,0.00049929216,0.000069727124,0.00002520081,0.00011889313,0.00001599676,0.0006025115],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969225,0.00044218122,0.0008730565,0.00062471716,0.000878495,0.00025905453],"domain_scores_gemma":[0.9970069,0.00019893583,0.00048255117,0.00087936956,0.0013348971,0.000097331504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003733276,0.00026956835,0.00035741378,0.00036388842,0.000087245324,0.000310243,0.0015119129,0.00011679957,0.00055595476],"category_scores_gemma":[0.00008689613,0.0002857187,0.00012736219,0.00062048924,0.000061627376,0.0005404475,0.0006361433,0.00032738596,0.00013408402],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001285409,0.00050950324,0.0006261831,0.000036589827,0.00018539035,0.000113952905,0.0033863732,0.8618722,0.002875675,0.07981934,0.002774676,0.047671583],"study_design_scores_gemma":[0.00071360596,0.00028656566,0.0010494184,0.00042225464,0.000006174487,0.000012268602,0.00008945279,0.989597,0.0053934813,0.0010913097,0.0010865944,0.00025186088],"about_ca_topic_score_codex":0.000025900732,"about_ca_topic_score_gemma":0.00005104586,"teacher_disagreement_score":0.94290435,"about_ca_system_score_codex":0.00025168998,"about_ca_system_score_gemma":0.00024192351,"threshold_uncertainty_score":0.99995947},"labels":[],"label_agreement":null},{"id":"W3202938653","doi":"10.1109/lra.2022.3224667","title":"Deep Reinforcement Learning for Decentralized Multi-Robot Exploration With Macro Actions","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Computer science; Robot; Robustness (evolution); Scalability; Artificial intelligence; Benchmark (surveying); Action selection; Macro; Computation; Machine learning; Distributed computing","score_opus":0.03577697130002772,"score_gpt":0.26641158264475134,"score_spread":0.23063461134472363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202938653","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":[0.0014885179,0.000013722965,0.9924181,0.0047376663,0.00047067585,0.00056147954,3.68764e-7,0.00028743563,0.000022006194],"genre_scores_gemma":[0.7050973,0.000025600695,0.29304078,0.0011759979,0.000042206928,0.00023563065,0.00005988253,0.000027333857,0.0002952317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853027,0.0000930653,0.00032513603,0.00032302397,0.0003983619,0.00033012015],"domain_scores_gemma":[0.99919766,0.00010887201,0.0002838777,0.0002554156,0.00007300006,0.000081197795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000259682,0.00017725988,0.00016255451,0.00016963496,0.0009911851,0.0002962599,0.0002846015,0.000029648972,0.000014214636],"category_scores_gemma":[0.000027540562,0.00017869785,0.000052732354,0.00030462898,0.000037216436,0.0007348805,0.00010171265,0.00021814855,0.000005468016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012398139,0.000019148176,0.00014987802,0.000022341288,0.000034402085,0.0000026090481,0.0009966803,0.99158317,0.0027533239,0.002978636,0.0002120618,0.0012353237],"study_design_scores_gemma":[0.0011922945,0.00023394744,0.00027678927,0.000012694718,0.00002460875,0.000014198287,0.00014888558,0.9957434,0.000338297,0.000023528177,0.0017540478,0.0002373348],"about_ca_topic_score_codex":0.000008203789,"about_ca_topic_score_gemma":0.0000029123562,"teacher_disagreement_score":0.7036088,"about_ca_system_score_codex":0.00015584375,"about_ca_system_score_gemma":0.000039035447,"threshold_uncertainty_score":0.7623495},"labels":[],"label_agreement":null},{"id":"W3203207428","doi":"10.1007/s00521-021-06259-1","title":"Policy invariant explicit shaping: an efficient alternative to reward shaping","year":2021,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Advice (programming); Computer science; Invariant (physics); Function (biology); Process (computing); Temporal difference learning; Artificial intelligence; Mathematics","score_opus":0.06130619872746178,"score_gpt":0.3291911299996931,"score_spread":0.2678849312722313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3203207428","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":[0.0480654,0.00003524016,0.9464669,0.0035473416,0.00008175688,0.0002646926,0.0000011399264,0.00023625339,0.0013012555],"genre_scores_gemma":[0.9523637,0.0000068007616,0.04493324,0.0022167834,0.0003280728,0.000029141913,0.000008008827,0.0000133244475,0.00010087615],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846673,0.00007794838,0.0002776095,0.0005966807,0.00024586995,0.00033514912],"domain_scores_gemma":[0.99877095,0.00013906759,0.00010742498,0.00059735513,0.00015675019,0.0002284713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001978673,0.00015445429,0.00015841241,0.0001337711,0.000470981,0.0004058393,0.0006086224,0.00003822299,0.0000022952381],"category_scores_gemma":[0.00008907418,0.00016197065,0.000039064813,0.00079125975,0.000026356476,0.00012408225,0.0007072924,0.00019731738,0.000029718156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.119499e-7,0.00002898829,0.00012679845,0.000010022528,0.000007345182,0.000004889331,0.001129854,0.814015,0.001646338,0.16603434,0.000032410517,0.01696314],"study_design_scores_gemma":[0.00014064007,0.000054538592,0.0015273652,0.000031071533,0.0000042680595,0.000039703475,0.00009803676,0.9945835,0.0011396481,0.0005813637,0.0016084253,0.00019145918],"about_ca_topic_score_codex":0.000040563587,"about_ca_topic_score_gemma":0.0000028070979,"teacher_disagreement_score":0.90429837,"about_ca_system_score_codex":0.000041293384,"about_ca_system_score_gemma":0.00008192102,"threshold_uncertainty_score":0.6604971},"labels":[],"label_agreement":null},{"id":"W3204293975","doi":"10.1007/s13235-023-00490-2","title":"Robustness and Sample Complexity of Model-Based MARL for General-Sum Markov Games","year":2023,"lang":"en","type":"article","venue":"Dynamic Games and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Ministère de la Défense Nationale","keywords":"Markov chain; Mathematics; Markov kernel; Markov perfect equilibrium; Markov process; Markov model; Discrete mathematics; Applied mathematics; Mathematical optimization; Combinatorics; Mathematical economics; Variable-order Markov model; Nash equilibrium; Statistics","score_opus":0.03328730004061116,"score_gpt":0.28858203258423304,"score_spread":0.2552947325436219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204293975","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":[0.013002407,0.000039251245,0.9852847,0.00094971526,0.000020663601,0.00044504186,0.000060759074,0.00011085745,0.00008659951],"genre_scores_gemma":[0.4628824,0.00009039913,0.5356756,0.0001077352,0.000017413415,0.00034920976,0.000119283446,0.000014461986,0.0007435199],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999242,0.000013228197,0.0001907409,0.0002727817,0.00009978306,0.00018143529],"domain_scores_gemma":[0.99918914,0.0002142952,0.00009729708,0.0003737983,0.000068485395,0.00005701121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014413767,0.00010003279,0.00014818364,0.00008655929,0.0001376838,0.000063089705,0.00027948036,0.000040328498,0.0000021104668],"category_scores_gemma":[0.000022512617,0.0000985618,0.000037075068,0.00026652313,0.0001612985,0.0000761188,0.00014385002,0.00005141014,8.620482e-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":[0.0000021754472,0.000012932834,0.00037077878,0.000087794026,0.0000088497745,5.9368425e-8,0.000054175933,0.9163953,0.00018392746,0.06573028,0.00017180266,0.016981903],"study_design_scores_gemma":[0.00022755649,0.000022880264,0.0030518998,0.000009925704,0.000008203209,6.777364e-7,0.000023197785,0.98709863,0.000025842874,0.008479628,0.0009460167,0.00010550909],"about_ca_topic_score_codex":0.000016205806,"about_ca_topic_score_gemma":0.000007849955,"teacher_disagreement_score":0.44988,"about_ca_system_score_codex":0.0000135336,"about_ca_system_score_gemma":0.000034722936,"threshold_uncertainty_score":0.40192336},"labels":[],"label_agreement":null},{"id":"W3204811657","doi":"","title":"LOCO: Adaptive exploration in reinforcement learning via local estimation of contraction coefficients","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Contraction (grammar); Computer science; Reinforcement; Artificial intelligence; Control theory (sociology); Mathematics; Mathematical optimization; Engineering; Structural engineering","score_opus":0.053273948608731185,"score_gpt":0.33253110950232107,"score_spread":0.2792571608935899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204811657","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":[0.00653691,0.0000071216978,0.9782869,0.00090507517,0.00045225138,0.0002120989,6.589449e-7,0.00009987496,0.013499058],"genre_scores_gemma":[0.99195963,0.000040248688,0.0058501093,0.000053514705,0.000028957333,0.00004986242,0.00015881931,0.000012365324,0.0018464846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99755704,0.0002883665,0.00063681434,0.00045354795,0.0008396455,0.00022458777],"domain_scores_gemma":[0.9980517,0.00031790257,0.00048275324,0.0002908312,0.00079331885,0.00006348991],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035669256,0.00016868705,0.00020080527,0.00038096184,0.0001554432,0.0001841462,0.00040584942,0.000086676984,0.0002022287],"category_scores_gemma":[0.0006276535,0.00019615827,0.00006454011,0.0005529226,0.0000805369,0.0011201423,0.00016170192,0.0005508849,0.00009713359],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034153836,0.00007615142,0.0009881787,0.0000062947706,0.00003230035,0.000015532009,0.0015798168,0.91308177,0.0015540491,0.05724219,0.000015996078,0.025373563],"study_design_scores_gemma":[0.0006808459,0.00022452795,0.00237476,0.00013083237,0.0000073186375,0.0000098113405,0.0014987296,0.9890459,0.0045945486,0.001087324,0.00018163126,0.00016372732],"about_ca_topic_score_codex":0.00014521668,"about_ca_topic_score_gemma":0.000024083085,"teacher_disagreement_score":0.98542273,"about_ca_system_score_codex":0.00024157342,"about_ca_system_score_gemma":0.00020028272,"threshold_uncertainty_score":0.79991025},"labels":[],"label_agreement":null},{"id":"W3205279237","doi":"10.1109/icra48506.2021.9560793","title":"Continual Model-Based Reinforcement Learning with Hypernetworks","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Machine learning; Dynamics (music); Control (management); Robot; Plan (archaeology); State (computer science); Engineering","score_opus":0.01245078320415947,"score_gpt":0.22087272369292985,"score_spread":0.20842194048877039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205279237","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":[0.0009312479,0.00002470088,0.9460952,0.00042685837,0.00009113607,0.0000912578,3.409354e-8,0.0003286611,0.05201085],"genre_scores_gemma":[0.78420174,0.000004719999,0.18711245,0.0010040901,0.000031599244,0.000009224893,0.0000097298425,0.00001421973,0.027612243],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984462,0.000055759072,0.00024231795,0.0003782443,0.00047953185,0.00039790093],"domain_scores_gemma":[0.9989162,0.0000892989,0.00010303938,0.00055426266,0.00022384117,0.00011331952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002077978,0.00017047056,0.00017554278,0.000052992982,0.00015668439,0.00027167547,0.00046884883,0.00006292381,0.00011287126],"category_scores_gemma":[0.000048740625,0.00014219244,0.00005511145,0.000355228,0.000039804203,0.0003066557,0.00022133722,0.00030551557,0.00006726746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060530247,0.000010122754,0.00083398726,0.000006755699,0.000017663237,0.000033575267,0.000112025686,0.9725203,0.00006160229,0.024786802,0.0003857276,0.0012253645],"study_design_scores_gemma":[0.0005975203,0.00014448799,0.000051596613,0.000030889787,0.000008221526,0.00001116685,0.000035523473,0.9934202,0.0017273459,0.000033236644,0.0037152732,0.00022457707],"about_ca_topic_score_codex":0.0000045533807,"about_ca_topic_score_gemma":0.0000037427967,"teacher_disagreement_score":0.7832705,"about_ca_system_score_codex":0.00005295557,"about_ca_system_score_gemma":0.00027142625,"threshold_uncertainty_score":0.57984394},"labels":[],"label_agreement":null},{"id":"W3205427743","doi":"","title":"MASAI: Multi-agent Summative Assessment Improvement for Unsupervised Environment Design","year":2021,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Summative assessment; Computer science; Formative assessment; Psychology; Mathematics education","score_opus":0.09432305776176142,"score_gpt":0.3331575425502579,"score_spread":0.2388344847884965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205427743","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":[0.00062690355,0.000023999448,0.9919725,0.0031061415,0.00057409547,0.0004634531,0.000008102868,0.00012578981,0.0030990054],"genre_scores_gemma":[0.60860926,0.00010741399,0.3835815,0.00056001614,0.00007065202,0.00016533966,0.00014323402,0.000025571977,0.006737045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976009,0.00022993979,0.0004335707,0.00064451946,0.00073998905,0.00035108614],"domain_scores_gemma":[0.9986582,0.00028860086,0.00026159192,0.00039603288,0.00028222243,0.00011338887],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005755951,0.00027340272,0.00022551153,0.00013359262,0.00025683787,0.0004320809,0.0009005707,0.0000682838,0.00060289697],"category_scores_gemma":[0.00020533269,0.00026959917,0.00012768262,0.00009802659,0.00003520135,0.00029340884,0.00043384166,0.0004726638,0.000116148374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025129697,0.00016498154,0.0011546403,0.00001655596,0.00015707112,0.000028197042,0.00046093424,0.877563,0.0113835465,0.08721632,0.000075718504,0.02175393],"study_design_scores_gemma":[0.001303363,0.00045406868,0.0011462115,0.000055560773,0.000011406272,0.000004409866,0.00013430841,0.9841159,0.004897569,0.0006184634,0.006973761,0.00028496736],"about_ca_topic_score_codex":0.000016249518,"about_ca_topic_score_gemma":0.0000024662759,"teacher_disagreement_score":0.608391,"about_ca_system_score_codex":0.0003657406,"about_ca_system_score_gemma":0.00016961152,"threshold_uncertainty_score":0.9999756},"labels":[],"label_agreement":null},{"id":"W3206540493","doi":"10.1109/icra48506.2021.9561333","title":"Shaping Rewards for Reinforcement Learning with Imperfect Demonstrations using Generative Models","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Vector Institute; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Generative grammar; Artificial intelligence; Machine learning; Generative model; Adversarial system; Function (biology); Action (physics); State space; Convergence (economics); Bellman equation; Range (aeronautics); Imperfect; Imitation; Mathematical optimization; Engineering; Mathematics","score_opus":0.07543834377601084,"score_gpt":0.2929367701417165,"score_spread":0.21749842636570565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206540493","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":[0.0021274253,0.000043774337,0.9884417,0.00028374567,0.00011100575,0.0003059186,2.8338658e-7,0.00019152428,0.00849461],"genre_scores_gemma":[0.47074252,0.000010286961,0.52678794,0.00025203332,0.00004905038,0.0000261194,0.000011460206,0.0000146069215,0.0021060049],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984435,0.00007160091,0.00031248602,0.00042973322,0.00034897178,0.00039369575],"domain_scores_gemma":[0.9988406,0.00013284577,0.00013809963,0.00039535618,0.0004006288,0.000092511655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000291809,0.00018717516,0.00019289582,0.00008703612,0.000568294,0.00041265995,0.00030644002,0.000059553244,0.00002851841],"category_scores_gemma":[0.000083342005,0.00016409274,0.00008145755,0.00039607778,0.000037356625,0.000954569,0.00018887843,0.000190383,0.000004638233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038949547,0.0000063138145,0.00007680817,0.0000130623075,0.00004767883,0.000006132126,0.00056742574,0.9075794,0.0030429934,0.08811917,0.00004211959,0.0004949893],"study_design_scores_gemma":[0.0004135545,0.00020157,0.000007349805,0.00004729118,0.00002148566,0.00003816832,0.00022119621,0.9863222,0.011748559,0.0004317866,0.00030363508,0.0002432002],"about_ca_topic_score_codex":0.000018050127,"about_ca_topic_score_gemma":0.000009936532,"teacher_disagreement_score":0.46861508,"about_ca_system_score_codex":0.00013041178,"about_ca_system_score_gemma":0.00047363684,"threshold_uncertainty_score":0.66915077},"labels":[],"label_agreement":null},{"id":"W3206746211","doi":"10.1109/icra48506.2021.9561017","title":"Distilling a Hierarchical Policy for Planning and Control via Representation and Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Reinforcement learning; Computer science; Hierarchy; Task (project management); Set (abstract data type); Artificial intelligence; Representation (politics); Control (management); Latent variable; Imitation; Machine learning; Sequence (biology); State space; Human–computer interaction; Engineering; Mathematics","score_opus":0.02105963226643383,"score_gpt":0.2996378555369776,"score_spread":0.27857822327054377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206746211","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":[0.0028161483,0.0000911785,0.99399775,0.0014781174,0.000067845256,0.00018852539,1.7013303e-7,0.00009724073,0.0012630089],"genre_scores_gemma":[0.9384687,0.000019142439,0.05933425,0.0004628458,0.00008468239,0.000018997665,0.000008800356,0.000008347676,0.0015942317],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989325,0.000056963134,0.00023694216,0.00033474938,0.0001849514,0.00025391323],"domain_scores_gemma":[0.99911064,0.00042903004,0.00008488623,0.00019222958,0.000079870035,0.00010334865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023118606,0.00010744727,0.00015186724,0.00008909976,0.00024669565,0.00028447693,0.000120576326,0.000044295695,0.000004839034],"category_scores_gemma":[0.00049588794,0.0001028699,0.000031814303,0.00017523543,0.00004148649,0.00027977987,0.00018810462,0.00014725848,0.0000015282393],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017414022,0.000004831519,0.006083015,0.000037053742,0.000032687618,0.000013051619,0.0011556823,0.9227993,0.0016936996,0.057086237,0.000026582962,0.011050479],"study_design_scores_gemma":[0.00086375285,0.00011047044,0.001978134,0.000025788166,0.000009179085,0.000038742484,0.00008230972,0.9938407,0.000806858,0.0011001644,0.0010186398,0.00012525536],"about_ca_topic_score_codex":0.000024000014,"about_ca_topic_score_gemma":7.4219946e-7,"teacher_disagreement_score":0.93565255,"about_ca_system_score_codex":0.000026726475,"about_ca_system_score_gemma":0.00005438857,"threshold_uncertainty_score":0.41949126},"labels":[],"label_agreement":null},{"id":"W3206893708","doi":"","title":"An Independent Learning Algorithm for a Class of Symmetric Stochastic Games","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Class (philosophy); Property (philosophy); Reinforcement learning; Mathematical economics; Computer science; Action (physics); Symmetry (geometry); Zero (linguistics); Mathematics; Mathematical optimization; Artificial intelligence; Discrete mathematics","score_opus":0.0524186279386688,"score_gpt":0.2089538804048337,"score_spread":0.1565352524661649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206893708","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":[0.025141925,0.00006406372,0.9732469,0.000013632433,0.0006067643,0.00042428361,0.0000063838893,0.00018577113,0.00031027704],"genre_scores_gemma":[0.9626042,0.000045441597,0.03610846,0.000024385454,0.000060762304,0.0000025355396,0.000051857325,0.00002855935,0.00107376],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976476,0.00021056808,0.000341136,0.0011362216,0.0002301202,0.00043435828],"domain_scores_gemma":[0.9971844,0.00032339556,0.00061103894,0.0012045673,0.0004911161,0.000185461],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045574261,0.00033601627,0.00051051285,0.0006773606,0.00014896749,0.00021798864,0.0020727674,0.00034675733,0.000015959125],"category_scores_gemma":[0.00017074315,0.0004192097,0.000296537,0.0010278414,0.000088969144,0.00045605662,0.0016745005,0.0008555966,0.000007904497],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007323588,0.00006936245,0.00032200737,0.00009742443,0.0001221752,0.00005564355,0.0003021828,0.974132,0.000026270904,0.01965677,0.000010242476,0.005198606],"study_design_scores_gemma":[0.00055564626,0.00027856394,0.0003982249,0.00012680919,0.00009956584,0.000004544764,0.00033204787,0.9966382,0.00010349441,0.0010003595,0.00006308649,0.0003995011],"about_ca_topic_score_codex":0.00007055447,"about_ca_topic_score_gemma":0.0000055937826,"teacher_disagreement_score":0.93746233,"about_ca_system_score_codex":0.00024596023,"about_ca_system_score_gemma":0.00040187716,"threshold_uncertainty_score":0.99982595},"labels":[],"label_agreement":null},{"id":"W3208016380","doi":"10.3389/frai.2022.805823","title":"Investigation of independent reinforcement learning algorithms in multi-agent environments","year":2022,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"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; Compute Canada","keywords":"Computer science; Reinforcement learning; Algorithm; Artificial intelligence; Machine learning","score_opus":0.05814036785717878,"score_gpt":0.2710809898253303,"score_spread":0.21294062196815153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208016380","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":[0.015219941,0.000087073844,0.9826191,0.00010654317,0.0014276255,0.0003880935,5.245372e-7,0.00003181724,0.00011924727],"genre_scores_gemma":[0.92341584,0.000050863036,0.07595057,0.00007871775,0.000013223866,0.0000800772,0.000010049042,0.000013121634,0.00038751945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971186,0.00030049504,0.0009219071,0.00046163716,0.00079338066,0.00040396265],"domain_scores_gemma":[0.99909794,0.00005290069,0.00034953761,0.000404354,0.000019358291,0.000075921096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011342324,0.00017816821,0.0002542113,0.0005654987,0.00015344635,0.000047842088,0.0010221793,0.000059209488,0.000056670066],"category_scores_gemma":[0.00010298225,0.00021756637,0.00006006048,0.00086764095,0.00010877107,0.00032846612,0.0007349355,0.00063517096,0.000018330253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014174405,0.00004279019,0.028927773,0.000009215537,0.000008963679,0.000017059336,0.003919426,0.94616705,0.0007783294,0.0021215952,0.00003602739,0.01795758],"study_design_scores_gemma":[0.000097848686,0.00018661987,0.0026891755,0.000023269575,0.0000028460074,0.0000014848375,0.0016533156,0.9783112,0.014796639,0.001567679,0.0004641453,0.00020576933],"about_ca_topic_score_codex":0.00017965237,"about_ca_topic_score_gemma":0.000013712464,"teacher_disagreement_score":0.9081959,"about_ca_system_score_codex":0.00061500847,"about_ca_system_score_gemma":0.0000808294,"threshold_uncertainty_score":0.8872099},"labels":[],"label_agreement":null},{"id":"W3208994216","doi":"10.48550/arxiv.2110.14096","title":"Towards Robust Bisimulation Metric Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Embedding; Computer science; Robustness (evolution); Artificial intelligence; Representation (politics); Theoretical computer science","score_opus":0.09633591901691252,"score_gpt":0.19975337179240849,"score_spread":0.10341745277549597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208994216","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":[0.040064726,0.00008208097,0.9525794,0.00006009148,0.00085517496,0.00018583858,5.9735453e-7,0.00045304195,0.005719096],"genre_scores_gemma":[0.9818867,0.00017998507,0.0136792725,0.00006060403,0.000077544544,4.556529e-7,0.000041731255,0.000024729152,0.0040490096],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976774,0.00027599648,0.00026995354,0.0011401151,0.00022625037,0.00041031858],"domain_scores_gemma":[0.99776113,0.00015259087,0.00039782978,0.0011891354,0.00034001452,0.00015932144],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003895854,0.00033827458,0.00036820988,0.00064689916,0.00023646568,0.00048200125,0.00176538,0.0003611321,0.000079167585],"category_scores_gemma":[0.00026542507,0.0004240672,0.00026268495,0.0019191896,0.00005473252,0.00063002255,0.0032817065,0.0011950261,0.00009245821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037753125,0.000020603831,0.0032060368,0.00005268929,0.00007514169,0.00019404401,0.00020309023,0.98017955,0.0000058946143,0.01509755,0.000034558852,0.00092704577],"study_design_scores_gemma":[0.00027955702,0.000046902573,0.0022862859,0.00007912477,0.00005850445,0.0000031691213,0.00009061003,0.9955764,0.000055065328,0.0005674161,0.00052413845,0.0004328216],"about_ca_topic_score_codex":0.00014009804,"about_ca_topic_score_gemma":0.0000061474825,"teacher_disagreement_score":0.94182193,"about_ca_system_score_codex":0.00037531907,"about_ca_system_score_gemma":0.00033233024,"threshold_uncertainty_score":0.9998211},"labels":[],"label_agreement":null},{"id":"W3209211538","doi":"10.48550/arxiv.2110.15572","title":"Understanding the Effect of Stochasticity in Policy Optimization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Mathematical optimization; Oracle; Convergence (economics); Initialization; Stochastic optimization; Rate of convergence; Computer science; Optimization problem; Mathematics; Key (lock); Economics","score_opus":0.10616217370546102,"score_gpt":0.20939231183322496,"score_spread":0.10323013812776394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209211538","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":[0.015054901,0.000010422424,0.9832236,0.00007037642,0.0002151963,0.00026881232,7.856854e-7,0.00005109903,0.001104774],"genre_scores_gemma":[0.9982853,0.000033423672,0.0014973655,0.000020552216,0.000024034709,4.6158436e-7,0.0000061913647,0.000008683353,0.00012398194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987158,0.00031558698,0.00018407484,0.00045363247,0.00011161753,0.00021928482],"domain_scores_gemma":[0.9984905,0.00037576223,0.00026697697,0.0007647932,0.000056451554,0.00004552189],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040837892,0.00018093342,0.0002631614,0.0003098541,0.00008568673,0.000099658966,0.0011786871,0.0001564427,0.00000911425],"category_scores_gemma":[0.00020608568,0.00016696977,0.00011590659,0.0009907706,0.000099340126,0.00021320602,0.0015589653,0.00047390032,0.0000021490853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010380666,0.000006952774,0.0025718254,0.00006548376,0.000029656148,0.000031002593,0.0003108622,0.9748871,0.000005499436,0.022063943,0.000004158967,0.000013138841],"study_design_scores_gemma":[0.00032693287,0.000074325755,0.00032104782,0.00013582416,0.000024758107,0.0000011637552,0.000093376126,0.9985731,0.00008508687,0.00022453854,8.1319394e-7,0.00013902171],"about_ca_topic_score_codex":0.00017786409,"about_ca_topic_score_gemma":0.000014541538,"teacher_disagreement_score":0.9832304,"about_ca_system_score_codex":0.00055598986,"about_ca_system_score_gemma":0.00021140749,"threshold_uncertainty_score":0.68088293},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W3209247505","doi":"10.1109/ccece53047.2021.9569056","title":"Reinforcement Learning Algorithms: An Overview and Classification","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":102,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Machine learning; Perspective (graphical); Field (mathematics); Robotics; Learning classifier system; Robot learning; Drone; Algorithm; Robot; Mobile robot","score_opus":0.0971463287431973,"score_gpt":0.32732024824265415,"score_spread":0.23017391949945687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209247505","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":[0.00070325343,0.0009402948,0.9881933,0.0004676047,0.0005433936,0.00030072202,1.4796493e-7,0.00041831704,0.008432983],"genre_scores_gemma":[0.41789678,0.009124116,0.55803704,0.0011147042,0.00029213744,0.00012648782,0.00039645354,0.00007096139,0.0129413325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974543,0.00020820955,0.00051349966,0.0009173767,0.0005766639,0.000329957],"domain_scores_gemma":[0.99789435,0.00006663359,0.0003595493,0.0012877089,0.00021616717,0.00017557996],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00058621814,0.0003230063,0.00034348186,0.00014675307,0.0001819735,0.0013567961,0.0009852876,0.00026603247,0.00009931416],"category_scores_gemma":[0.000091348644,0.000326245,0.00008636913,0.00020071183,0.000046286346,0.00067231845,0.002764982,0.00090201426,0.000031423628],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010195124,0.000017321205,0.00027971982,0.00020365238,0.00004868585,0.000010238677,0.0010882734,0.9079855,0.00007344946,0.051025886,0.00008990965,0.039176337],"study_design_scores_gemma":[0.00014103958,0.00009540773,0.0019994127,0.00016475632,0.000018436707,0.000009767877,0.00018222706,0.9920535,0.000096227355,0.00027145704,0.004588539,0.00037923307],"about_ca_topic_score_codex":0.000064281776,"about_ca_topic_score_gemma":0.0000042912898,"teacher_disagreement_score":0.43015626,"about_ca_system_score_codex":0.00012442657,"about_ca_system_score_gemma":0.00021702645,"threshold_uncertainty_score":0.99991894},"labels":[],"label_agreement":null},{"id":"W3209275463","doi":"10.1007/978-3-030-87136-9_4","title":"Dynamic VNF Resource Scaling and Migration: A Machine Learning Approach","year":2021,"lang":"en","type":"book-chapter","venue":"Wireless networks","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Computer science; Scaling; Resource (disambiguation); Distributed computing; Computer network","score_opus":0.0113441275927419,"score_gpt":0.2061103806195461,"score_spread":0.1947662530268042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209275463","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000031264306,0.004865258,0.89291245,0.00016686162,0.00024131418,0.00021456702,9.617913e-7,0.000290953,0.10127637],"genre_scores_gemma":[0.059231065,0.003963906,0.056567583,0.00058520096,0.00069686834,0.000031262058,0.000808664,0.0002717051,0.87784374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747336,0.000094051415,0.00052008225,0.00092791434,0.00052403496,0.0004605847],"domain_scores_gemma":[0.9983292,0.00018012754,0.00043699812,0.00079246965,0.00009866111,0.00016254092],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039482652,0.00050901296,0.0005757624,0.00015854572,0.00037604326,0.0005842406,0.00076214876,0.0005573238,0.000029970994],"category_scores_gemma":[0.000019857722,0.00053711573,0.00015338275,0.00013624417,0.00012084994,0.00018755239,0.0008523429,0.0017565471,0.000012927797],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046752302,0.0000053767076,0.000043223336,0.000063572974,0.00007125116,0.00004490121,0.00022589366,0.922647,0.0000016603744,0.0506903,0.00020096211,0.026001204],"study_design_scores_gemma":[0.00021038081,0.0000412948,0.000013214024,0.00036814625,0.000037129892,0.00007515722,0.000013404637,0.92475283,5.80558e-7,0.000108661734,0.07388253,0.00049668737],"about_ca_topic_score_codex":0.000010931252,"about_ca_topic_score_gemma":0.000013088406,"teacher_disagreement_score":0.8363449,"about_ca_system_score_codex":0.000102429854,"about_ca_system_score_gemma":0.00006538216,"threshold_uncertainty_score":0.99970806},"labels":[],"label_agreement":null},{"id":"W3210129106","doi":"10.48550/arxiv.2111.00876","title":"On the Expressivity of Markov Reward","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Set (abstract data type); Markov chain; Computer science; Task (project management); Expressivity; Reinforcement learning; Function (biology); Frame (networking); Construct (python library); Markov decision process; Markov process; Artificial intelligence; Machine learning; Cognitive psychology; Psychology; Mathematics; Programming language; Statistics","score_opus":0.06913435806116296,"score_gpt":0.18231306356787266,"score_spread":0.1131787055067097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210129106","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":[0.16359714,0.00001608597,0.82631224,0.00016961519,0.00045897008,0.00017275411,0.0000020455363,0.00008533999,0.009185782],"genre_scores_gemma":[0.99545616,0.00006959015,0.0017089795,0.00013853352,0.000024858315,5.6393395e-7,0.000005010143,0.000011213603,0.0025850951],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983861,0.00029542987,0.00019223832,0.00070322305,0.0001736775,0.0002493194],"domain_scores_gemma":[0.9967259,0.00046680207,0.00038406943,0.0021765528,0.00017255587,0.0000741138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036584545,0.00022949418,0.00028136212,0.00011992855,0.00012252835,0.00011992825,0.0025766965,0.00019177787,0.000085184736],"category_scores_gemma":[0.00019547684,0.00020510232,0.00023147279,0.00042398938,0.00013455584,0.00018150994,0.0032012232,0.00071653235,0.000029830173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008858336,0.000029940607,0.0005579105,0.00004397186,0.00005674881,0.00009171901,0.00019745278,0.8780669,0.000038139257,0.120291494,0.0005183404,0.00009853725],"study_design_scores_gemma":[0.00023370139,0.00007149538,0.0014515442,0.0003184985,0.000043664615,0.0000019457918,0.00011644273,0.98965734,0.0010572828,0.0064348597,0.00026030792,0.00035291613],"about_ca_topic_score_codex":0.00004856085,"about_ca_topic_score_gemma":0.0000038120422,"teacher_disagreement_score":0.831859,"about_ca_system_score_codex":0.000106896776,"about_ca_system_score_gemma":0.0001887609,"threshold_uncertainty_score":0.836383},"labels":[],"label_agreement":null},{"id":"W3210485068","doi":"10.1613/jair.1.13445","title":"Multi-Agent Advisor Q-Learning","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Government of Canada; Vector Institute; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Artificial intelligence; Action (physics); Heuristic; Sample complexity; Software deployment; Convergence (economics); Point (geometry); Operations research; Machine learning; Q-learning; Software engineering; Mathematics","score_opus":0.22346943620517123,"score_gpt":0.42782496434760386,"score_spread":0.20435552814243263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210485068","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":[0.0075390553,0.00019689451,0.9890347,0.0016980711,0.00087258755,0.0001564394,3.2451493e-7,0.000034202392,0.00046768694],"genre_scores_gemma":[0.94678664,0.00010719935,0.05139849,0.00006796445,0.00022872318,0.000011007739,5.640703e-7,0.00001834361,0.0013810524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99460304,0.0011299654,0.0008810347,0.00026122443,0.0024849516,0.0006397969],"domain_scores_gemma":[0.99746174,0.00065018144,0.00039519588,0.00039338178,0.00087737653,0.00022212193],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.008302711,0.00012171199,0.0002266124,0.00084399444,0.0010295742,0.00036335527,0.0024975038,0.000041746425,0.00047214126],"category_scores_gemma":[0.0014291055,0.00011504271,0.00016631388,0.0015809656,0.00013505958,0.00048779917,0.0013037536,0.0025129449,0.00020423015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004193715,0.00015513608,0.00018774015,0.000008887703,0.000026902999,0.00017599495,0.002229844,0.91258603,0.005488501,0.011089793,0.00057398743,0.06743524],"study_design_scores_gemma":[0.0000574792,0.0015615609,0.00009875592,0.000023083207,0.00000422585,0.00014799868,0.0039592474,0.95448047,0.007545207,0.0021306695,0.02982908,0.00016220409],"about_ca_topic_score_codex":0.00002254862,"about_ca_topic_score_gemma":0.0000018746015,"teacher_disagreement_score":0.9392476,"about_ca_system_score_codex":0.00038629,"about_ca_system_score_gemma":0.0004528772,"threshold_uncertainty_score":0.9997883},"labels":[],"label_agreement":null},{"id":"W3211684788","doi":"","title":"Average-Reward Learning and Planning with Options","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Markov decision process; Computer science; Abstraction; Convergence (economics); Sample complexity; Artificial intelligence; Machine learning; Mathematical proof; Markov chain; Sample (material); Domain (mathematical analysis); Markov process; Mathematics; Statistics","score_opus":0.01646724830475379,"score_gpt":0.2526428685441239,"score_spread":0.23617562023937008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211684788","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":[0.0074714217,0.00036277086,0.9867648,0.0002099795,0.00026882163,0.00010962712,2.8750583e-7,0.0003311759,0.004481129],"genre_scores_gemma":[0.9908171,0.0000097591255,0.0080772005,0.00016295274,0.000050455797,0.0000147764595,0.000017187023,0.0000069449334,0.00084359053],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988878,0.000063052365,0.00033621452,0.00014876276,0.0003473436,0.00021687125],"domain_scores_gemma":[0.9991324,0.000045661633,0.0002688273,0.00015042644,0.00032869194,0.000074014846],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00020055886,0.00012667417,0.00013871057,0.0001141407,0.00042047104,0.0017286509,0.0001738616,0.000051845476,0.0000020821924],"category_scores_gemma":[0.0000877347,0.00010905102,0.00001659048,0.0004021172,0.000028713395,0.0040354743,0.000107887034,0.00025028153,0.000020996746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002020981,0.0000021863532,0.0019932913,0.00018232057,0.0000065757476,0.000008865442,0.0025598542,0.988095,0.000041946863,0.001624611,0.000077698525,0.005405614],"study_design_scores_gemma":[0.00024914616,0.00005062263,0.0004164628,0.00022013966,0.000004219972,0.00028960887,0.000925723,0.98691064,0.00011299525,0.0000065275317,0.010656362,0.00015756529],"about_ca_topic_score_codex":0.0000049593386,"about_ca_topic_score_gemma":1.5861531e-7,"teacher_disagreement_score":0.9833457,"about_ca_system_score_codex":0.000034239736,"about_ca_system_score_gemma":0.00010017514,"threshold_uncertainty_score":0.99930763},"labels":[],"label_agreement":null},{"id":"W3211741236","doi":"","title":"Learning in two-player zero-sum partially observable Markov games with perfect recall","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","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":"Observable; Zero (linguistics); Computer science; Markov chain; Recall; Zero-sum game; Markov process; Mathematics; Mathematical economics; Game theory; Statistics; Machine learning; Cognitive psychology; Psychology; Physics","score_opus":0.018763851378186695,"score_gpt":0.2540259796019725,"score_spread":0.23526212822378578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211741236","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":[0.061686255,0.0002322497,0.92562246,0.0005857725,0.00068889826,0.00039584682,5.8088045e-7,0.00058120897,0.010206738],"genre_scores_gemma":[0.98836803,0.000009526449,0.00906817,0.00038155293,0.000051293977,0.00004609138,0.000027813523,0.000015074527,0.0020324308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976702,0.00020054678,0.00074301544,0.0002731318,0.0006421358,0.00047101916],"domain_scores_gemma":[0.99856144,0.000092255825,0.0004784477,0.00035766838,0.00041436107,0.00009582588],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006205395,0.00023051816,0.00029138112,0.00017590338,0.00026351772,0.001839757,0.00046058756,0.00007566524,0.000007220187],"category_scores_gemma":[0.00017213455,0.00019892579,0.00004178643,0.0008888634,0.00003320075,0.005905949,0.0001497234,0.00046671228,0.00006866969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013026364,0.00000962177,0.012281147,0.00032593735,0.000008075778,0.000019590114,0.0021168268,0.9708441,0.00015758188,0.0004777647,0.00021136056,0.013534957],"study_design_scores_gemma":[0.0006628475,0.00011502727,0.0014997617,0.0004046723,0.0000060000484,0.00013192337,0.00042081508,0.9867987,0.0004495157,0.0000067624323,0.009234232,0.00026971527],"about_ca_topic_score_codex":0.00006695371,"about_ca_topic_score_gemma":0.0000147580095,"teacher_disagreement_score":0.9266818,"about_ca_system_score_codex":0.000121697216,"about_ca_system_score_gemma":0.0003370045,"threshold_uncertainty_score":0.9991964},"labels":[],"label_agreement":null},{"id":"W3211776917","doi":"","title":"Learning Tree Interpretation from Object Representation for Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Interpretation (philosophy); Representation (politics); Tree (set theory); Object (grammar); Machine learning; Programming language; Mathematics","score_opus":0.021558708445137575,"score_gpt":0.2752711759624968,"score_spread":0.2537124675173592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211776917","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":[0.002678855,0.000117914635,0.9903236,0.00019828703,0.0009509869,0.0004528187,5.00864e-7,0.0005036673,0.0047733746],"genre_scores_gemma":[0.9891053,0.00001384428,0.008637907,0.00022716878,0.00014223422,0.00013159639,0.0004823991,0.000017113522,0.0012424287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750185,0.00018710353,0.0009978046,0.00032250411,0.0006337585,0.0003569815],"domain_scores_gemma":[0.99759746,0.00026295538,0.0009380265,0.00032021833,0.00079411885,0.0000872453],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042214512,0.0002288821,0.0002775989,0.00020575323,0.0005597151,0.0020592075,0.00041441806,0.00011997239,0.000010901425],"category_scores_gemma":[0.00082068186,0.00023606274,0.0001072625,0.00057236,0.000024543035,0.006271557,0.00015476882,0.00035326727,0.00007577864],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017488152,0.000004292278,0.0004019147,0.00016544334,0.000020124186,0.0000014557233,0.0068840706,0.9243797,0.0004421686,0.00061719905,0.00011468634,0.06695144],"study_design_scores_gemma":[0.00063793873,0.00014771434,0.00024852218,0.00017768965,0.000018660518,0.00001812388,0.0024584262,0.98959863,0.0019422704,0.000047446018,0.004450831,0.00025371832],"about_ca_topic_score_codex":0.000050753366,"about_ca_topic_score_gemma":0.0000031361367,"teacher_disagreement_score":0.9864265,"about_ca_system_score_codex":0.00017241517,"about_ca_system_score_gemma":0.00014387272,"threshold_uncertainty_score":0.99897677},"labels":[],"label_agreement":null},{"id":"W3212744543","doi":"10.48550/arxiv.2111.08172","title":"Off-Policy Actor-Critic with Emphatic Weightings","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Counterexample; Variety (cybernetics); Computer science; Variance (accounting); Work (physics); Gradient method; Mathematical optimization; Mathematics; Mathematical economics; Applied mathematics; Economics; Artificial intelligence; Discrete mathematics","score_opus":0.04648557504175391,"score_gpt":0.186150771689604,"score_spread":0.1396651966478501,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212744543","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":[0.1242654,0.000059432423,0.8680521,0.00024843056,0.00037104537,0.00024061748,0.0000016326379,0.0003555465,0.006405751],"genre_scores_gemma":[0.9865977,0.00017612909,0.0072671208,0.00029198706,0.00012820779,0.0000011046469,0.000020600079,0.000035610832,0.005481552],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99749726,0.00017139425,0.00025986938,0.0012477534,0.00023507894,0.0005886525],"domain_scores_gemma":[0.9970456,0.00017487041,0.000335453,0.0018832478,0.00031236812,0.00024847937],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019275547,0.00044701746,0.00045703372,0.0004211158,0.00021265476,0.000508975,0.0024429434,0.00027435127,0.00005703872],"category_scores_gemma":[0.000119975426,0.00047961017,0.00019537198,0.0011409272,0.00017025866,0.0006722703,0.0026900014,0.0008019894,0.00009782645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008874797,0.000042531952,0.0022762762,0.00015904837,0.00013321883,0.00077197014,0.0005651497,0.92186314,0.000017585933,0.07373411,0.00008720925,0.00034090612],"study_design_scores_gemma":[0.0006178068,0.0001264907,0.0013492397,0.00045082063,0.00011236184,0.000027381098,0.00020007885,0.9931117,0.00017136599,0.0020197139,0.0010029889,0.00081001857],"about_ca_topic_score_codex":0.00017678182,"about_ca_topic_score_gemma":0.000021381726,"teacher_disagreement_score":0.8623323,"about_ca_system_score_codex":0.0004371788,"about_ca_system_score_gemma":0.00097102806,"threshold_uncertainty_score":0.9997656},"labels":[],"label_agreement":null},{"id":"W3213430327","doi":"","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"HEC Montréal; Université de Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Task (project management); Encoder; Artificial intelligence; Representation (politics); Key (lock); Code (set theory); Machine learning; Feature learning; External Data Representation","score_opus":0.15126924877798947,"score_gpt":0.2391395437057067,"score_spread":0.08787029492771722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213430327","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":[0.0042620795,0.000016910866,0.98706114,0.00014005312,0.00027823003,0.00020659073,0.0000017159666,0.00020860358,0.007824678],"genre_scores_gemma":[0.9667357,0.000022392273,0.022226797,0.00010417205,0.000042337782,0.0000011883888,0.00009943209,0.000012358316,0.010755595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99842304,0.00008913387,0.00021063212,0.0007845548,0.00012824805,0.00036437577],"domain_scores_gemma":[0.9978207,0.00029105542,0.00016241736,0.0013821032,0.0002276823,0.00011603833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037665226,0.00014003179,0.0001486245,0.00010973397,0.00040047758,0.0001605239,0.0012375759,0.000059337417,0.000049979823],"category_scores_gemma":[0.0004279142,0.00017183776,0.00008129219,0.0007529719,0.00005120546,0.00054624653,0.0010356986,0.0002018565,0.000051455434],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005366356,0.000016510101,0.0006604356,0.000013040311,0.00003682429,0.000049594844,0.00029409767,0.859218,0.00008015295,0.13893208,0.0002774709,0.00041643783],"study_design_scores_gemma":[0.0005467739,0.000059715607,0.00014886625,0.000020892709,0.00003055027,0.000006391334,0.0003457834,0.9926105,0.00027653296,0.00028269514,0.0054761413,0.00019511607],"about_ca_topic_score_codex":0.000013011543,"about_ca_topic_score_gemma":0.0000032847968,"teacher_disagreement_score":0.96483433,"about_ca_system_score_codex":0.00009541949,"about_ca_system_score_gemma":0.00018032902,"threshold_uncertainty_score":0.7007341},"labels":[],"label_agreement":null},{"id":"W3213853783","doi":"","title":"On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Convexity; Truncation (statistics); Variance (accounting); Convergence (economics); Mathematics; Term (time); Variance reduction; Reinforcement learning; Applied mathematics; Mathematical optimization; Function (biology); Distribution (mathematics); Computer science; Combinatorics; Statistics; Mathematical analysis; Physics; Economics; Artificial intelligence","score_opus":0.05728126830244275,"score_gpt":0.21214144427449538,"score_spread":0.15486017597205265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213853783","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":[0.10152836,0.0000101260475,0.89618766,0.00038142444,0.00013295593,0.00007586159,0.000001593423,0.00003280737,0.0016492272],"genre_scores_gemma":[0.98826665,0.000046705394,0.010707706,0.00022344875,0.000013174342,2.0640289e-7,6.2864586e-7,0.0000043745754,0.0007370909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990231,0.00017382148,0.00012083868,0.00037680133,0.00009224433,0.00021324093],"domain_scores_gemma":[0.9982222,0.0008631718,0.00011434509,0.00062019995,0.00010693211,0.00007316351],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002677781,0.000104672574,0.00012880292,0.00009190254,0.00015324302,0.000034723747,0.00063213083,0.00003769444,0.000037852227],"category_scores_gemma":[0.00049077946,0.00009158714,0.00005576337,0.0010745106,0.00011093195,0.00014640918,0.0003256863,0.00012341364,0.000013981524],"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":[0.0000033879571,0.00001805782,0.00028482848,0.0000057828343,0.000012331103,0.000014495063,0.00022536062,0.3619614,0.0005540926,0.6367816,0.000028476401,0.00011023223],"study_design_scores_gemma":[0.00028289398,0.00011059134,0.0012564603,0.000023568213,0.000014764119,0.0000068109034,0.000117213014,0.96715105,0.006996054,0.023578992,0.00031837382,0.00014321167],"about_ca_topic_score_codex":0.000110341665,"about_ca_topic_score_gemma":0.0000028696622,"teacher_disagreement_score":0.8867383,"about_ca_system_score_codex":0.000051327745,"about_ca_system_score_gemma":0.00015479725,"threshold_uncertainty_score":0.37348154},"labels":[],"label_agreement":null},{"id":"W3214099510","doi":"","title":"Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Guelph","funders":"","keywords":"Reinforcement learning; Construct (python library); Brick; Computer science; Object (grammar); Action (physics); Combinatorial explosion; Artificial intelligence; Space (punctuation); Theoretical computer science; Mathematics; Engineering; Programming language; Civil engineering","score_opus":0.020863170148706995,"score_gpt":0.15937401891041583,"score_spread":0.13851084876170883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214099510","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":[0.031150514,0.00001859105,0.95780283,0.00006487149,0.000554364,0.00010845109,1.7268948e-7,0.00023534374,0.01006484],"genre_scores_gemma":[0.9918407,0.000051187886,0.0031333715,0.00008327935,0.00004662426,3.9814253e-7,0.000015918828,0.000013976196,0.0048145065],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985104,0.00012714187,0.00018299046,0.0005937681,0.00019609141,0.0003895712],"domain_scores_gemma":[0.9987508,0.00009153453,0.00020260304,0.0005453263,0.00025453226,0.0001552065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014652516,0.0002002713,0.00019801108,0.00010548307,0.00033705903,0.00017263692,0.0005623675,0.00009326302,0.00008680256],"category_scores_gemma":[0.000057950074,0.00022492072,0.00007458006,0.0010468235,0.0001210738,0.00071943435,0.0003439761,0.00034656917,0.000103204366],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018589344,0.00001917097,0.0048090233,0.000009170848,0.000047152695,0.0001751299,0.0001107627,0.80316275,0.00011036499,0.1911162,0.00014952048,0.00027216712],"study_design_scores_gemma":[0.0016369406,0.00027934098,0.000248599,0.000030074087,0.000041984014,0.00005580225,0.0003041198,0.9889662,0.001343954,0.0007871611,0.005921342,0.00038442938],"about_ca_topic_score_codex":0.000031946372,"about_ca_topic_score_gemma":0.0000037136945,"teacher_disagreement_score":0.9606902,"about_ca_system_score_codex":0.00019962068,"about_ca_system_score_gemma":0.00016506431,"threshold_uncertainty_score":0.9172001},"labels":[],"label_agreement":null},{"id":"W3214290601","doi":"","title":"Risk-Aware Transfer in Reinforcement Learning using Successor Features","year":2021,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Successor cardinal; Reinforcement learning; Computer science; Generalization; Variance (accounting); Task (project management); Representation (politics); Artificial intelligence; Function (biology); Domain (mathematical analysis); Machine learning; Bellman equation; Robot; Transfer of learning; Risk aversion (psychology); Expected utility hypothesis; Mathematical optimization; Mathematics; Engineering; Economics","score_opus":0.048609391666622925,"score_gpt":0.19407695932822996,"score_spread":0.14546756766160704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214290601","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":[0.22417164,0.000026434946,0.77374804,0.00003618108,0.00014518286,0.00008784579,3.5646812e-7,0.00010639966,0.0016778939],"genre_scores_gemma":[0.9946644,0.0001188109,0.0012552714,0.000078552635,0.000024660969,2.4609068e-7,0.00000594919,0.000013481492,0.0038386725],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841577,0.00021901212,0.00020685351,0.0005864634,0.00014265245,0.00042925795],"domain_scores_gemma":[0.9990379,0.000111883426,0.00008785587,0.0005252749,0.0001254962,0.00011158013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002495768,0.00019298175,0.00020720542,0.0002127165,0.00024649946,0.00013583718,0.0006869267,0.0001113259,0.00007403954],"category_scores_gemma":[0.00007621519,0.00022905502,0.00009462912,0.0012307772,0.000049659488,0.00073726143,0.00029850935,0.00053405925,0.000036431036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011350796,0.000017403632,0.0220902,0.00001549212,0.000025626545,0.00042886846,0.00036440158,0.95421773,0.00021354923,0.022459079,0.00001372901,0.0001425741],"study_design_scores_gemma":[0.00075735635,0.00005888426,0.004198643,0.00005047646,0.000024673778,0.000011980609,0.00023558982,0.9924342,0.0013127126,0.00018793397,0.00044567362,0.00028185532],"about_ca_topic_score_codex":0.0001942598,"about_ca_topic_score_gemma":0.00007483006,"teacher_disagreement_score":0.7724928,"about_ca_system_score_codex":0.00021678224,"about_ca_system_score_gemma":0.00014918041,"threshold_uncertainty_score":0.93405926},"labels":[],"label_agreement":null},{"id":"W3214824629","doi":"10.1109/icra46639.2022.9812407","title":"Learning Interactive Driving Policies via Data-driven Simulation","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Computer science; Bottleneck; Domain (mathematical analysis); Policy learning; Enhanced Data Rates for GSM Evolution; Transfer of learning; State (computer science); Machine learning; Artificial intelligence","score_opus":0.04795188783829782,"score_gpt":0.31789167568736826,"score_spread":0.26993978784907047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214824629","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":[0.005155783,0.0000060799275,0.9849523,0.0035593403,0.0009709363,0.00017848032,0.000010954996,0.00024973127,0.004916419],"genre_scores_gemma":[0.9881276,0.000021525755,0.009752605,0.00035429653,0.00007757291,0.000009806168,0.00027983583,0.000014939633,0.0013618572],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979505,0.00018135329,0.00036706796,0.00048096178,0.00080552883,0.0002146204],"domain_scores_gemma":[0.998646,0.00025989965,0.00037771757,0.0004425147,0.00020701646,0.00006681997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037288337,0.00017878746,0.00016282825,0.00031974676,0.00055452465,0.00052486046,0.0012774174,0.000038107835,0.00042389735],"category_scores_gemma":[0.00018868994,0.00019852376,0.00003913346,0.00024742584,0.000041299125,0.00092411984,0.0017460448,0.00050015526,0.000037116835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005608898,0.000030715248,0.00078960834,0.0000040230507,0.00003947691,0.0000040374994,0.0007631341,0.91621643,0.00034122635,0.07472607,0.00012526754,0.0069544073],"study_design_scores_gemma":[0.00025211638,0.00017741762,0.0028123383,0.000024491394,0.000008486597,0.000010942372,0.00035032484,0.9932656,0.00003119388,0.0010146956,0.0018448246,0.00020756],"about_ca_topic_score_codex":0.000021715876,"about_ca_topic_score_gemma":0.000003538121,"teacher_disagreement_score":0.9829718,"about_ca_system_score_codex":0.0001850366,"about_ca_system_score_gemma":0.00008256352,"threshold_uncertainty_score":0.8095564},"labels":[],"label_agreement":null},{"id":"W3215048956","doi":"10.1109/icra46639.2022.9812276","title":"VISTA 2.0: An Open, Data-driven Simulator for Multimodal Sensing and Policy Learning for Autonomous Vehicles","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toyota Motor Corporation (Canada); University of Toronto","funders":"National Science Foundation","keywords":"Computer science; Robustness (evolution); Software deployment; Key (lock); Testbed; Artificial intelligence; Viewpoints; World Wide Web; Software engineering","score_opus":0.07474863535135583,"score_gpt":0.34999590304230355,"score_spread":0.2752472676909477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215048956","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":[0.007259767,0.000007904517,0.98560095,0.005551902,0.00039016755,0.00064530666,0.00008469561,0.00014615561,0.00031316228],"genre_scores_gemma":[0.89680403,0.000011803394,0.10107082,0.0004998888,0.00010856639,0.000035848523,0.0005896536,0.000021959842,0.00085739413],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836826,0.00009824071,0.00034225226,0.00058726146,0.00037025256,0.00023374718],"domain_scores_gemma":[0.9987136,0.00027028166,0.00029244527,0.00039376525,0.00023355837,0.0000963176],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00054895534,0.00017311785,0.00019583428,0.00022204142,0.00076679763,0.0011586222,0.0013363864,0.000043881493,0.000025727248],"category_scores_gemma":[0.00025948725,0.00019350497,0.000027941454,0.00012449069,0.000046432655,0.0007765133,0.0018087223,0.00021279631,0.0000018549084],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022228072,0.00003080102,0.00009511224,0.000012922441,0.000030338117,0.0000012262853,0.00030108576,0.7814997,0.0005185157,0.19596615,0.00012611564,0.021395843],"study_design_scores_gemma":[0.00089895906,0.0004640365,0.00066903385,0.000018273096,0.000011568164,0.000009650303,0.0002018316,0.9909117,0.000035613153,0.0024401254,0.004117268,0.0002219476],"about_ca_topic_score_codex":0.00006087433,"about_ca_topic_score_gemma":0.0000075422417,"teacher_disagreement_score":0.8895443,"about_ca_system_score_codex":0.0001295331,"about_ca_system_score_gemma":0.00023961713,"threshold_uncertainty_score":0.9998783},"labels":[],"label_agreement":null},{"id":"W359568995","doi":"","title":"A convergent O ( n ) algorithm for off-policy temporal-difference learning with linear function approximation","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":120,"is_retracted":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":"Temporal difference learning; Markov decision process; Algorithm; Stochastic approximation; Function (biology); Reinforcement learning; Stochastic gradient descent; Markov process; Mathematics; Quadratic equation; Approximation algorithm; Norm (philosophy); Computer science; Function approximation; Mathematical optimization; Applied mathematics; Artificial intelligence; Statistics; Artificial neural network","score_opus":0.02640782854945645,"score_gpt":0.2470170740798348,"score_spread":0.22060924553037836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W359568995","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":[0.0018317318,0.000015944897,0.995727,0.00025531728,0.0001451855,0.00041449378,3.8866708e-7,0.00039275188,0.0012171962],"genre_scores_gemma":[0.18584812,0.00004416417,0.79293776,0.00033074652,0.00021208066,0.000085706706,0.00003974153,0.000023660767,0.020478023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986966,0.000044151027,0.00025291851,0.00034550842,0.0003602682,0.000300558],"domain_scores_gemma":[0.9991305,0.000077890385,0.00017786914,0.00031326673,0.00020924756,0.00009122711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018146646,0.00016804504,0.0001626731,0.0001541893,0.0003228672,0.00006627512,0.00032624725,0.000065312124,0.000019126988],"category_scores_gemma":[0.000069599235,0.00013356237,0.000051510506,0.0004188903,0.000053089392,0.00039237255,0.00008964076,0.00016644938,0.000052951167],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048147533,0.00009628459,0.006016062,0.00006157948,0.00008575082,0.000008028179,0.0014794413,0.6766451,0.00033225925,0.01790076,0.0007215899,0.29660502],"study_design_scores_gemma":[0.00065072323,0.0006401619,0.001450273,0.000013611994,0.0000063022717,0.00002383586,0.000032842127,0.988685,0.0005460291,0.00008043269,0.0076791784,0.0001915766],"about_ca_topic_score_codex":0.000047989255,"about_ca_topic_score_gemma":0.0000014354783,"teacher_disagreement_score":0.31203997,"about_ca_system_score_codex":0.000070550814,"about_ca_system_score_gemma":0.0001779047,"threshold_uncertainty_score":0.54465157},"labels":[],"label_agreement":null},{"id":"W36013382","doi":"10.3390/life12081203","title":"A decision-theoretic approach to task assistance for persons with dementia","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Rehabilitation Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Dementia; Task (project management); Personalization; Computer science; Independence (probability theory); Markov decision process; Process (computing); Cognition; Markov process; Artificial intelligence; Human–computer interaction; Cognitive psychology; Risk analysis (engineering); Machine learning; Psychology; Disease; Markov model; Markov chain; Medicine; Engineering; Neuroscience; Mathematics","score_opus":0.013658746007665902,"score_gpt":0.24319007784262545,"score_spread":0.22953133183495955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36013382","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":[0.00037388215,0.000022556405,0.9611648,0.0010604287,0.00006772053,0.00041750676,7.1431083e-7,0.00015187908,0.036740527],"genre_scores_gemma":[0.34406966,8.743858e-7,0.6525288,0.00070259906,0.000032146298,0.000054431206,0.000001279916,0.000009688673,0.0026004822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986867,0.000016759837,0.00018246827,0.000410979,0.00035020098,0.0003528978],"domain_scores_gemma":[0.9989962,0.00014043514,0.00005741918,0.00058550236,0.00008373149,0.00013668629],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002712736,0.00014090637,0.0001300711,0.0000912545,0.00015540593,0.00022122571,0.0008561195,0.00003473452,0.000025890164],"category_scores_gemma":[0.00005751012,0.000105239254,0.000049695453,0.00032929922,0.000033799246,0.00028540287,0.0001384277,0.00007384959,0.00006731624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027725142,0.0000555437,0.00030874397,0.000013562555,0.000043112606,6.841507e-7,0.0006014275,0.7079242,0.000049534297,0.26566863,0.015163856,0.01014302],"study_design_scores_gemma":[0.0005084597,0.00021609594,0.000391867,0.000021790342,0.000018744006,0.000008380868,0.000050657927,0.92814624,0.000162678,0.0003511583,0.06988348,0.00024045445],"about_ca_topic_score_codex":0.000001349846,"about_ca_topic_score_gemma":0.0000045465395,"teacher_disagreement_score":0.34369576,"about_ca_system_score_codex":0.00005211467,"about_ca_system_score_gemma":0.000049625938,"threshold_uncertainty_score":0.4291532},"labels":[],"label_agreement":null},{"id":"W409933044","doi":"10.1609/aiide.v8i1.12515","title":"Statechart-Based AI in Practice","year":2012,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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":"Modular design; USable; Reuse; Computer science; Tree (set theory); Artificial intelligence; Software engineering; Point (geometry); Scale (ratio); Human–computer interaction; Programming language; Engineering; World Wide Web","score_opus":0.039331803373794744,"score_gpt":0.30429367141374575,"score_spread":0.26496186803995103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W409933044","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":[0.26818684,0.00006391231,0.62496334,0.02007833,0.001508377,0.0018466888,0.000013157538,0.00017204646,0.08316731],"genre_scores_gemma":[0.9978657,0.000016916509,0.00077545614,0.0011271402,0.000025187277,0.000027609152,0.0000010594031,0.000009762129,0.00015116805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983294,0.000019607365,0.00048781742,0.0003141386,0.00044963238,0.00039942889],"domain_scores_gemma":[0.9988283,0.00020160417,0.00035274544,0.00019401925,0.00031881774,0.00010454309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035343794,0.0002172652,0.00020229732,0.00016483119,0.00007524815,0.0004856078,0.0007527302,0.000052030835,0.000017112476],"category_scores_gemma":[0.00057299325,0.00016382406,0.00007535019,0.00030194773,0.0001417987,0.0030110143,0.0003709065,0.00035413983,0.000049717633],"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":[0.00046228757,0.001253652,0.0057948637,0.00006689915,0.00007663242,0.0000018873504,0.007845038,0.0037322224,0.0071855527,0.86598605,0.00015934953,0.10743556],"study_design_scores_gemma":[0.00029161168,0.0018316784,0.0023323512,0.0012644026,0.000039287333,0.00002209762,0.010817196,0.47928116,0.48317784,0.015073502,0.0049427804,0.00092609675],"about_ca_topic_score_codex":0.000016258773,"about_ca_topic_score_gemma":8.510268e-7,"teacher_disagreement_score":0.8509126,"about_ca_system_score_codex":0.00012432227,"about_ca_system_score_gemma":0.00004324323,"threshold_uncertainty_score":0.6680552},"labels":[],"label_agreement":null},{"id":"W41346994","doi":"","title":"Bootstrapping the Learning Process for the Semi-automated Design of a Challenging Game AI","year":2004,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; Bootstrapping (finance); Artificial intelligence; Process (computing); Key (lock); Game design; Representation (politics); Decomposition; Control (management); Machine learning; Human–computer interaction; Programming language","score_opus":0.03322517527403423,"score_gpt":0.2744859141496011,"score_spread":0.24126073887556687,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W41346994","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":[0.0006945257,0.0008994591,0.9860305,0.008928919,0.0002107045,0.0012341541,0.0000028416168,0.00068319263,0.001315655],"genre_scores_gemma":[0.99500716,0.0003773282,0.0032451083,0.00011123109,0.000021707485,0.00021146487,0.00003241849,0.000042778414,0.00095083506],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99495363,0.0026412082,0.00066478516,0.000660708,0.00061238545,0.0004672606],"domain_scores_gemma":[0.9908023,0.003933421,0.0009931844,0.0022209943,0.001970473,0.000079643134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006362273,0.00034480813,0.00036124367,0.00015836641,0.00070683134,0.0006491718,0.0038976846,0.00022276517,0.000008767521],"category_scores_gemma":[0.0020214347,0.00025992666,0.000223163,0.00052702654,0.00026236873,0.00021825182,0.0014506058,0.0010845523,0.0000062152153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003842567,0.000048004073,0.00005017648,0.00021671469,0.00008716922,6.9055113e-7,0.011126066,0.9700755,0.00023175668,0.01737237,0.000029345149,0.000758348],"study_design_scores_gemma":[0.00031521858,0.0000010808681,0.0001957435,0.0017419388,0.00004137192,0.000006586629,0.00021820483,0.9889496,0.0057995813,0.0016818087,0.0007891479,0.00025973833],"about_ca_topic_score_codex":0.00014378442,"about_ca_topic_score_gemma":0.000017369252,"teacher_disagreement_score":0.9943126,"about_ca_system_score_codex":0.00012323586,"about_ca_system_score_gemma":0.00059545704,"threshold_uncertainty_score":0.9999853},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"simulation_or_modeling","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4200140111","doi":"10.1109/iros51168.2021.9636140","title":"Memory-based Deep Reinforcement Learning for POMDPs","year":2021,"lang":"en","type":"article","venue":"2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":77,"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":"Compute Canada","keywords":"Reinforcement learning; Markov decision process; Computer science; Observable; Artificial intelligence; Partially observable Markov decision process; Noise (video); Robotics; Component (thermodynamics); Sensitivity (control systems); Feature (linguistics); Deep learning; Markov process; Markov chain; Machine learning; Robot; Markov model","score_opus":0.06087323939367912,"score_gpt":0.30000014092519434,"score_spread":0.23912690153151522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200140111","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":[0.0004599668,0.00015489136,0.98089457,0.0012634736,0.0038975875,0.0005399879,0.0000033048952,0.00013045369,0.012655756],"genre_scores_gemma":[0.9750868,0.0003226251,0.0068206266,0.000640633,0.00043251397,0.00019954225,0.00014152403,0.00003751478,0.016318185],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99668247,0.00016684842,0.0008429089,0.0008342643,0.00097508734,0.00049843424],"domain_scores_gemma":[0.9973763,0.00038939036,0.0004287966,0.00058523065,0.0009940602,0.00022620955],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006089497,0.00038455057,0.00042678235,0.00025737722,0.00032219978,0.0011836938,0.0009288816,0.0001613365,0.0003615584],"category_scores_gemma":[0.00029970714,0.00036831244,0.00019284626,0.0002311891,0.00006208236,0.00033711572,0.00022049889,0.00039731612,0.00015645457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023490431,0.000056432873,0.00017866866,0.00007794801,0.00012415189,0.000030101299,0.0004081693,0.8524416,0.0009895745,0.14184795,0.0004786097,0.003343312],"study_design_scores_gemma":[0.0006008809,0.0003026774,0.00003606673,0.00031791133,0.000021255099,0.000025718886,0.00041221495,0.9767465,0.0051074107,0.00020104482,0.015825955,0.00040236086],"about_ca_topic_score_codex":0.000048932157,"about_ca_topic_score_gemma":0.000009288976,"teacher_disagreement_score":0.97462684,"about_ca_system_score_codex":0.00024571552,"about_ca_system_score_gemma":0.00029825344,"threshold_uncertainty_score":0.99987686},"labels":[],"label_agreement":null},{"id":"W4200372371","doi":"10.1002/cpe.6743","title":"Scalable grid‐based approximation algorithms for partially observable Markov decision processes","year":2021,"lang":"en","type":"article","venue":"Concurrency and Computation Practice and Experience","topic":"Reinforcement Learning in Robotics","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":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Computer science; Markov decision process; Scalability; Observable; Mathematical optimization; Implementation; Grid; Markov process; Process (computing); Focus (optics); Algorithm; Markov chain; Markov model; Machine learning; Mathematics","score_opus":0.04756454524991755,"score_gpt":0.3385360643285482,"score_spread":0.29097151907863067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200372371","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":[0.0054582534,0.0010551214,0.9915822,0.0008321505,0.0004602975,0.00023536551,0.0000018769776,0.00007701764,0.0002976732],"genre_scores_gemma":[0.41121665,0.00037087285,0.58718264,0.0008865413,0.00007063757,0.0001275946,0.000041197687,0.000009041389,0.00009482712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986756,0.00007455219,0.0003043898,0.00045778957,0.00027340947,0.00021424888],"domain_scores_gemma":[0.9975835,0.0012630391,0.00021332684,0.00018107636,0.00066727074,0.000091793394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032504907,0.00013574515,0.00014746278,0.000044996676,0.00037815186,0.00060245773,0.00017980993,0.000056550947,0.000006658689],"category_scores_gemma":[0.0016789072,0.00013581193,0.000021414045,0.00041018196,0.00006368129,0.0023594422,0.00011202411,0.00009448268,0.0000038052494],"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":[0.00013526845,0.00027856816,0.0012044423,0.0007223407,0.00003778428,0.000030191502,0.011956088,0.22956462,0.0005983859,0.01707579,0.001282313,0.7371142],"study_design_scores_gemma":[0.00063439587,0.00014839495,0.00022416761,0.000087281085,0.00001526248,0.000031660027,0.0007981002,0.98070127,0.0021002686,0.0009266083,0.014136112,0.00019645109],"about_ca_topic_score_codex":0.000005264318,"about_ca_topic_score_gemma":0.000001136805,"teacher_disagreement_score":0.75113666,"about_ca_system_score_codex":0.00001571822,"about_ca_system_score_gemma":0.0002794247,"threshold_uncertainty_score":0.5809514},"labels":[],"label_agreement":null},{"id":"W4200400844","doi":"10.32920/17313137","title":"Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Artificial intelligence; Obstacle; Train; Obstacle avoidance; Perception; Trajectory; Action (physics); Object (grammar); Robot; Mobile robot","score_opus":0.0186631170123467,"score_gpt":0.2561486766434662,"score_spread":0.2374855596311195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200400844","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":[0.0036901224,0.00021984575,0.9659929,0.00025457435,0.0010535015,0.00043486396,1.1793596e-7,0.00042387718,0.02793017],"genre_scores_gemma":[0.72178257,0.00017181378,0.27279577,0.0001663753,0.00008190915,0.000030787804,0.000035747482,0.000036831567,0.0048981705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962412,0.00018178132,0.0011991597,0.0009925119,0.00074144313,0.000643863],"domain_scores_gemma":[0.9964114,0.00024338768,0.00105069,0.0017918047,0.000382912,0.000119802346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058389717,0.000516004,0.00076248473,0.00016812241,0.00019763985,0.000597883,0.0022425214,0.0003996736,0.00021230285],"category_scores_gemma":[0.00031435635,0.0005261801,0.00036252162,0.00032334198,0.00009743361,0.00058380945,0.0068422225,0.0014090117,0.000029367526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023951138,0.000021177717,0.00051632104,0.00021918034,0.00014396425,0.000011979168,0.0026306633,0.9832607,0.0012996612,0.007019046,0.000039014143,0.004835933],"study_design_scores_gemma":[0.00028585954,0.00014054512,0.00037166668,0.00028876972,0.000035111567,0.000006564452,0.00029779636,0.9890514,0.007382421,0.00022796601,0.0013712591,0.0005406238],"about_ca_topic_score_codex":0.00031190776,"about_ca_topic_score_gemma":0.000016428785,"teacher_disagreement_score":0.71809244,"about_ca_system_score_codex":0.00026917644,"about_ca_system_score_gemma":0.00054377684,"threshold_uncertainty_score":0.99971896},"labels":[],"label_agreement":null},{"id":"W4200507047","doi":"10.32920/17313137.v1","title":"Safe Driving Of Autonomous Vehicles Through Improved Deep Reinforcement Learning","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Artificial intelligence; Obstacle; Train; Obstacle avoidance; Perception; Trajectory; Action (physics); Object (grammar); Robot; Mobile robot","score_opus":0.0186631170123467,"score_gpt":0.2561486766434662,"score_spread":0.2374855596311195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200507047","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":[0.0036901224,0.00021984575,0.9659929,0.00025457435,0.0010535015,0.00043486396,1.1793596e-7,0.00042387718,0.02793017],"genre_scores_gemma":[0.72178257,0.00017181378,0.27279577,0.0001663753,0.00008190915,0.000030787804,0.000035747482,0.000036831567,0.0048981705],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962412,0.00018178132,0.0011991597,0.0009925119,0.00074144313,0.000643863],"domain_scores_gemma":[0.9964114,0.00024338768,0.00105069,0.0017918047,0.000382912,0.000119802346],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058389717,0.000516004,0.00076248473,0.00016812241,0.00019763985,0.000597883,0.0022425214,0.0003996736,0.00021230285],"category_scores_gemma":[0.00031435635,0.0005261801,0.00036252162,0.00032334198,0.00009743361,0.00058380945,0.0068422225,0.0014090117,0.000029367526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023951138,0.000021177717,0.00051632104,0.00021918034,0.00014396425,0.000011979168,0.0026306633,0.9832607,0.0012996612,0.007019046,0.000039014143,0.004835933],"study_design_scores_gemma":[0.00028585954,0.00014054512,0.00037166668,0.00028876972,0.000035111567,0.000006564452,0.00029779636,0.9890514,0.007382421,0.00022796601,0.0013712591,0.0005406238],"about_ca_topic_score_codex":0.00031190776,"about_ca_topic_score_gemma":0.000016428785,"teacher_disagreement_score":0.71809244,"about_ca_system_score_codex":0.00026917644,"about_ca_system_score_gemma":0.00054377684,"threshold_uncertainty_score":0.99971896},"labels":[],"label_agreement":null},{"id":"W4200555244","doi":"10.11606/t.55.2021.tde-21122021-111842","title":"Synthesizing interpretable strategies for real-time planning in zero-sum games","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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":"Division of Mathematical Sciences; Centro de Ciências Matemáticas Aplicadas à Indústria; Universidade Federal de Viçosa; Fundação de Amparo à Pesquisa do Estado de São Paulo; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Compute Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Computer science; Scripting language; Action (physics); Artificial intelligence; Set (abstract data type); Abstraction; Zero (linguistics); Machine learning; Programming language","score_opus":0.018196227617453244,"score_gpt":0.2910867091637649,"score_spread":0.2728904815463116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200555244","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":[0.0037106548,0.00019074851,0.8610263,0.000034514003,0.0007264782,0.00036344148,0.0000014070773,0.00026355556,0.13368294],"genre_scores_gemma":[0.31200436,0.00022882203,0.39791042,0.00022152858,0.0002169327,0.00038751416,0.0012992615,0.00020062378,0.28753054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980457,0.00006222813,0.0005242599,0.00059425563,0.00030797097,0.00046557465],"domain_scores_gemma":[0.9985001,0.0004963458,0.00027639835,0.00053927914,0.00013396192,0.000053908687],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034860123,0.00031811098,0.00047354316,0.0002939418,0.000093913004,0.0009287599,0.0009396122,0.00025621895,0.00006639372],"category_scores_gemma":[0.00017086818,0.0003240448,0.00013018816,0.00029445626,0.000013277619,0.0007730975,0.00011371786,0.0003054372,0.000029615185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057310725,0.00004484781,0.00020600775,0.0010068746,0.00015370168,0.00007231565,0.014162763,0.8971233,0.0075943395,0.06896999,0.0044532893,0.006155276],"study_design_scores_gemma":[0.00028792507,0.00012367843,0.00034718707,0.002306365,0.000031004074,0.000004857222,0.0067942184,0.982015,0.0038192233,0.0020467106,0.0014779066,0.0007458946],"about_ca_topic_score_codex":0.00010386888,"about_ca_topic_score_gemma":0.000034407698,"teacher_disagreement_score":0.46311584,"about_ca_system_score_codex":0.000099124765,"about_ca_system_score_gemma":0.0004430418,"threshold_uncertainty_score":0.99992114},"labels":[],"label_agreement":null},{"id":"W4206522553","doi":"10.22215/etd/2021-14679","title":"Evolution of Multiobjective Neuromodulated Neurocontrollers for Multi-Robot Systems","year":2021,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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; Queen's University","funders":"","keywords":"Neuroevolution; Artificial intelligence; Artificial neural network; Computer science; Inheritance (genetic algorithm); Genetic algorithm; Machine learning; Biology","score_opus":0.02769569525311363,"score_gpt":0.28359359275935947,"score_spread":0.25589789750624586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206522553","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":[0.0011761109,0.00028126093,0.99105465,0.00001309151,0.0038971999,0.001598239,0.0000052434984,0.00019812769,0.0017760436],"genre_scores_gemma":[0.8781891,0.000032442982,0.07250127,0.000034427943,0.00012691299,0.0003103271,0.00056024,0.00009276412,0.048152555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976562,0.00014841455,0.00073006446,0.00068330014,0.00044103948,0.0003409807],"domain_scores_gemma":[0.997213,0.00022404385,0.00076655456,0.0006811062,0.0010404199,0.00007483977],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020991583,0.0003411566,0.0006108788,0.00032070858,0.000119626086,0.0001626762,0.00076330896,0.00030748497,0.0000041683297],"category_scores_gemma":[0.00037295136,0.0003433363,0.00028295425,0.0004634926,0.000019303045,0.000290614,0.00006780996,0.00028064588,0.000008144199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003873387,0.00006115572,0.000046153902,0.00040364117,0.00012422289,0.0000048012616,0.00051004445,0.984848,0.0070589604,0.00628494,0.00017155438,0.00044779776],"study_design_scores_gemma":[0.0014249121,0.00018691557,0.0029867073,0.0001601021,0.000056484667,0.0000035221165,0.0004679421,0.99241126,0.0018860806,0.00001065966,0.000112530055,0.00029291355],"about_ca_topic_score_codex":0.0002274408,"about_ca_topic_score_gemma":0.000060612434,"teacher_disagreement_score":0.9185534,"about_ca_system_score_codex":0.00017340656,"about_ca_system_score_gemma":0.00034937492,"threshold_uncertainty_score":0.9999019},"labels":[],"label_agreement":null},{"id":"W4206914807","doi":"10.1109/ssci50451.2021.9660081","title":"Investigation of Maximization Bias in Sarsa Variants","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","topic":"Reinforcement Learning in Robotics","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":"Maximization; Reinforcement learning; Computer science; Randomness; Artificial intelligence; Q-learning; Expectation–maximization algorithm; Variance (accounting); Machine learning; Statistics; Mathematical optimization; Mathematics; Maximum likelihood; Economics","score_opus":0.05639518078776527,"score_gpt":0.2753421580849772,"score_spread":0.2189469772972119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206914807","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":[0.012041168,0.000030767224,0.9829642,0.0021323022,0.0010304388,0.00018670796,0.000004739159,0.000049840044,0.0015598261],"genre_scores_gemma":[0.8295961,0.00012267056,0.16859198,0.00056251267,0.00008557805,0.000017317385,0.00010697784,0.000022282178,0.00089458795],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997302,0.00026744587,0.0007961372,0.0005696949,0.00077098474,0.0002937331],"domain_scores_gemma":[0.9979909,0.00045173342,0.00034870848,0.00048192887,0.0006290608,0.000097671895],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004619833,0.00022925327,0.00028612334,0.00032494578,0.00011315029,0.00020434581,0.000628616,0.00011483038,0.00010606873],"category_scores_gemma":[0.00022611534,0.00025808281,0.000082859,0.0016035364,0.00013638061,0.0009345615,0.00016679197,0.00024152313,0.00012122449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015474492,0.00004122922,0.0015255911,0.000036951245,0.000016644877,0.000029779105,0.000979288,0.9224274,0.0024312336,0.07105975,0.00009743626,0.0013392069],"study_design_scores_gemma":[0.00014482519,0.00022195283,0.002724304,0.00016989517,0.000006672034,0.00002996502,0.000117232616,0.9136293,0.064081326,0.018472176,0.00012994916,0.00027243388],"about_ca_topic_score_codex":0.00002927607,"about_ca_topic_score_gemma":0.000015310796,"teacher_disagreement_score":0.81755495,"about_ca_system_score_codex":0.00013828308,"about_ca_system_score_gemma":0.0004874345,"threshold_uncertainty_score":0.9999871},"labels":[],"label_agreement":null},{"id":"W4210257517","doi":"10.1109/cdc45484.2021.9682777","title":"Convergence and Near Optimality of Q-Learning with Finite Memory for Partially Observed Models","year":2021,"lang":"en","type":"article","venue":"2021 60th IEEE Conference on Decision and Control (CDC)","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Markov decision process; Convergence (economics); Computer science; Quantization (signal processing); Q-learning; Mathematical optimization; Limit (mathematics); State space; Optimal control; Markov process; Mathematics; Algorithm; Artificial intelligence","score_opus":0.06092869236888402,"score_gpt":0.2648753527444318,"score_spread":0.2039466603755478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210257517","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":[0.054183446,0.00017105244,0.94400567,0.0004459162,0.00017986256,0.0003131023,0.0000058699047,0.000037317197,0.0006577703],"genre_scores_gemma":[0.95995015,0.00026275197,0.038701918,0.00031616385,0.000024747611,0.00003069022,0.000004475181,0.000013930948,0.0006951657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978358,0.00017891383,0.0004888673,0.0006610516,0.00049115863,0.00034418816],"domain_scores_gemma":[0.997158,0.0011026214,0.00027763663,0.0005697267,0.00069359754,0.00019844434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006117236,0.00024802235,0.0005066342,0.00006174688,0.00023517998,0.00039590074,0.00040876755,0.00011236635,0.00007803965],"category_scores_gemma":[0.0004490551,0.00021058515,0.00007802839,0.00023332464,0.00016152978,0.00042344196,0.00014216983,0.00025335513,0.000007547641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000426236,0.00005089507,0.0010196607,0.00005090361,0.00007191636,0.0000321195,0.00043922348,0.93718535,0.001461527,0.022901176,0.000062214094,0.03629878],"study_design_scores_gemma":[0.0028234592,0.00060744525,0.0010592408,0.0001802995,0.00003362876,0.000007743752,0.00012259197,0.99171853,0.0011828544,0.0016130175,0.0003993941,0.00025177954],"about_ca_topic_score_codex":0.000013284701,"about_ca_topic_score_gemma":0.000015412465,"teacher_disagreement_score":0.9057667,"about_ca_system_score_codex":0.000016470496,"about_ca_system_score_gemma":0.00037256753,"threshold_uncertainty_score":0.8587413},"labels":[],"label_agreement":null},{"id":"W4210266050","doi":"10.1109/cinti53070.2021.9668479","title":"Deep Reinforcement Learning with DQN vs. PPO in VizDoom","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Convergence (economics); Reinforcement; Quality (philosophy); Track (disk drive); Object (grammar); Machine learning; Human–computer interaction; Engineering","score_opus":0.010729311580889345,"score_gpt":0.2251434012773191,"score_spread":0.21441408969642975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210266050","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":[0.0015363569,0.000032212127,0.93610215,0.0007064392,0.00011998679,0.00010388798,7.4024897e-9,0.00017911331,0.06121984],"genre_scores_gemma":[0.8957915,0.0000337193,0.083398886,0.0009336182,0.000030274397,0.000013014291,0.0000068543186,0.000016038335,0.019776128],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982871,0.00007924813,0.0003099949,0.00040428713,0.00048449743,0.0004349133],"domain_scores_gemma":[0.99904126,0.000092158734,0.00009644184,0.0005601531,0.00011374021,0.00009624647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025895517,0.0001667678,0.0001909958,0.00011826717,0.00010564241,0.00025114507,0.00053339096,0.000057336933,0.0002933374],"category_scores_gemma":[0.00008965797,0.00014344508,0.00004034431,0.0007083161,0.000030244535,0.00047819855,0.0004033702,0.000346095,0.00018926203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000062918166,0.000012375498,0.007102697,0.000011587194,0.000012729625,0.00011473743,0.00053685484,0.9662264,0.000077114375,0.024173284,0.00009300607,0.0016329394],"study_design_scores_gemma":[0.00061542843,0.00020682174,0.002166497,0.00004379592,0.0000036934512,0.000029706385,0.00016604358,0.987105,0.0015598531,0.00005795791,0.007807495,0.00023771233],"about_ca_topic_score_codex":0.000039504437,"about_ca_topic_score_gemma":0.000051539315,"teacher_disagreement_score":0.8942551,"about_ca_system_score_codex":0.000101999845,"about_ca_system_score_gemma":0.00014555994,"threshold_uncertainty_score":0.58495206},"labels":[],"label_agreement":null},{"id":"W4210732917","doi":"10.1016/bs.hna.2021.12.016","title":"Machine learning and control theory","year":2022,"lang":"en","type":"book-chapter","venue":"Handbook of numerical analysis","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Chinese University of Hong Kong; Saint Mary’s University; National Science Foundation","keywords":"Computer science; Artificial intelligence; Machine learning; Online machine learning; Algorithmic learning theory; Reinforcement learning; Computational learning theory; Control (management); Stochastic gradient descent; Probably approximately correct learning; Field (mathematics); Active learning (machine learning); Artificial neural network; Mathematics","score_opus":0.009157608706874624,"score_gpt":0.21918081536263434,"score_spread":0.21002320665575971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210732917","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.7913387e-7,0.0046333857,0.8963783,0.00009218919,0.000046736473,0.00009639161,0.000007254764,0.000080683116,0.098664686],"genre_scores_gemma":[0.0585654,0.0053051026,0.027601143,0.0006756119,0.00011733016,0.000026585329,0.00015060206,0.000110181856,0.90744805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979336,0.00014433771,0.00051771867,0.00052722555,0.00064432004,0.0002328015],"domain_scores_gemma":[0.99818337,0.0005256181,0.0005913981,0.00049554545,0.00007950972,0.00012458484],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045354973,0.00031005824,0.00093888876,0.0005216478,0.000190887,0.00006653291,0.00063360436,0.0001221501,0.0030495527],"category_scores_gemma":[0.00007624731,0.00028275864,0.00050998974,0.0002552017,0.0001337886,0.00010977199,0.00052393094,0.000661825,0.000028845901],"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":[0.000060982657,0.000034340464,0.0020929778,0.00007902146,0.00847127,0.00006741024,0.00037124028,0.43721917,0.00004834439,0.5180634,0.00010724377,0.03338457],"study_design_scores_gemma":[0.000519766,0.00036675425,0.000047215202,0.000056268058,0.0027282396,0.000008493557,0.000005157456,0.791121,0.000012315033,0.0065249186,0.19808571,0.0005241477],"about_ca_topic_score_codex":0.000023709352,"about_ca_topic_score_gemma":7.882499e-7,"teacher_disagreement_score":0.86877716,"about_ca_system_score_codex":0.000053213265,"about_ca_system_score_gemma":0.000040002524,"threshold_uncertainty_score":0.99996245},"labels":[],"label_agreement":null},{"id":"W4212802944","doi":"10.3390/s22041393","title":"Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation","year":2022,"lang":"en","type":"article","venue":"Sensors","topic":"Reinforcement Learning in Robotics","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":"University of Toronto; Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Reinforcement learning; Overfitting; Computer science; Kalman filter; Artificial intelligence; Temporal difference learning; Representation (politics); Inefficiency; Machine learning; Artificial neural network","score_opus":0.036404439744145194,"score_gpt":0.27237387310785766,"score_spread":0.23596943336371246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212802944","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":[0.20400554,0.0000344258,0.79428065,0.00026737107,0.00031572956,0.00032764606,5.470212e-7,0.00019844237,0.00056962704],"genre_scores_gemma":[0.9762602,0.00001465518,0.016508931,0.0001235503,0.000027560814,0.000037086418,0.000016075866,0.00001554294,0.0069963974],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979381,0.00027911575,0.00033070866,0.0004952876,0.0006121393,0.0003446324],"domain_scores_gemma":[0.99903935,0.00010967774,0.00026244286,0.00041678155,0.0000616863,0.00011008787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032751157,0.00018370675,0.00018316404,0.00015596783,0.00064262,0.00012863734,0.0004888688,0.000033043285,0.00005687297],"category_scores_gemma":[0.00007292825,0.00019141253,0.000054212356,0.00035769132,0.00006162627,0.00021781154,0.00089046825,0.00041733822,0.000022998627],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001582588,0.000017480243,0.011780511,0.000007409337,0.000022857297,0.000026418635,0.0026271448,0.9815009,0.0007866247,0.00092822337,0.000038654296,0.002247903],"study_design_scores_gemma":[0.0005020246,0.0003280204,0.014628848,0.000007882978,0.000008568915,0.000021243322,0.0006501584,0.98206353,0.00047169573,0.000043639902,0.0010457106,0.00022869374],"about_ca_topic_score_codex":0.00025266947,"about_ca_topic_score_gemma":0.0000062143913,"teacher_disagreement_score":0.7777718,"about_ca_system_score_codex":0.00014085567,"about_ca_system_score_gemma":0.00003376918,"threshold_uncertainty_score":0.78055763},"labels":[],"label_agreement":null},{"id":"W4221161302","doi":"10.48550/arxiv.2201.01666","title":"Sample Efficient Deep Reinforcement Learning via Uncertainty Estimation","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Weighting; Computer science; Heteroscedasticity; Variance (accounting); Sample (material); Noise (video); Bayesian probability; Probabilistic logic; Process (computing); Artificial intelligence; Machine learning; Mathematical optimization; Mathematics","score_opus":0.04515281141028903,"score_gpt":0.20083283265483545,"score_spread":0.1556800212445464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221161302","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":[0.008406102,0.000021776828,0.98685175,0.00006161174,0.000950768,0.0005213412,0.0000015986221,0.00056633673,0.0026187112],"genre_scores_gemma":[0.9868923,0.000042779677,0.010673755,0.00009195345,0.00004256145,0.0000051674724,0.00017275228,0.00002988421,0.0020488822],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970753,0.0003025169,0.00041565596,0.0012292168,0.0003805862,0.0005967085],"domain_scores_gemma":[0.99714524,0.00034980392,0.00065334846,0.0014855827,0.00016848429,0.00019753775],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062001916,0.0004392822,0.0003834816,0.0004231344,0.0006787614,0.00023748938,0.0023917116,0.0002118332,0.00042749918],"category_scores_gemma":[0.00021880922,0.0005503385,0.00026587766,0.0008378148,0.000093188384,0.0002532934,0.0051627806,0.0014177666,0.0001297986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001729469,0.000030518473,0.00049959065,0.00006382036,0.00006928829,0.00006082804,0.0005304369,0.9268074,0.0000043346954,0.071088865,0.000033804055,0.0007938391],"study_design_scores_gemma":[0.00040928533,0.00014711477,0.00015363998,0.000042137694,0.000059112557,0.000002963352,0.00011560433,0.99497813,0.000014574732,0.0023263877,0.0011956069,0.00055542396],"about_ca_topic_score_codex":0.00043476713,"about_ca_topic_score_gemma":0.000005261106,"teacher_disagreement_score":0.9784862,"about_ca_system_score_codex":0.0012044671,"about_ca_system_score_gemma":0.00023785954,"threshold_uncertainty_score":0.9996948},"labels":[],"label_agreement":null},{"id":"W4224220194","doi":"10.1016/j.neunet.2022.03.037","title":"Deep learning, reinforcement learning, and world models","year":2022,"lang":"en","type":"review","venue":"Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":493,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Session (web analytics); Human intelligence; Deep learning; Cognitive science; Reinforcement; Psychology","score_opus":0.04696882901226523,"score_gpt":0.2927112085831605,"score_spread":0.2457423795708953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224220194","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.6838467e-8,0.5497999,0.44269603,0.000014360888,0.0006205231,0.00043855395,7.871848e-8,0.00033899196,0.0060915155],"genre_scores_gemma":[0.0000861663,0.9745811,0.0012266609,0.00015475518,0.0003219173,0.00017725994,0.00011216794,0.000112439615,0.023227535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99517775,0.0007663104,0.0010521293,0.0011428697,0.00084075704,0.0010201774],"domain_scores_gemma":[0.9971245,0.0006886589,0.0010304758,0.0008201958,0.000045328492,0.00029084264],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00065443193,0.000849761,0.0015385428,0.00047869765,0.0008028433,0.00063431606,0.0018252541,0.0002887159,0.0004274015],"category_scores_gemma":[0.0000839915,0.0007896046,0.00048542765,0.0012551282,0.00009776878,0.0005656304,0.0027014718,0.0042230175,0.000034381083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010827216,0.0000036846018,0.000003175718,0.0004128048,0.000043224536,0.000023990186,0.000041993426,0.5494549,9.859455e-10,0.001698198,0.0002604373,0.44805646],"study_design_scores_gemma":[0.0000856254,0.00013175137,1.4269399e-7,0.00033270312,0.00008425572,0.000038540267,0.0000032438522,0.5022877,3.2507463e-9,0.000017328457,0.49663875,0.00037996616],"about_ca_topic_score_codex":0.000012704428,"about_ca_topic_score_gemma":0.000003855707,"teacher_disagreement_score":0.4963783,"about_ca_system_score_codex":0.00024400016,"about_ca_system_score_gemma":0.000078035046,"threshold_uncertainty_score":0.9994555},"labels":[],"label_agreement":null},{"id":"W4224240386","doi":"10.1186/s40708-022-00156-6","title":"Hierarchical intrinsically motivated agent planning behavior with dreaming in grid environments","year":2022,"lang":"en","type":"article","venue":"Brain Informatics","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"Russian Foundation for Basic Research","keywords":"Grid; Psychology; Computer science; Cognitive psychology; Geography","score_opus":0.014002934279106349,"score_gpt":0.23164296966890013,"score_spread":0.2176400353897938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224240386","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":[0.24431989,0.000005745917,0.75283664,0.0003110096,0.00040755674,0.0004427423,0.0000026866094,0.00012421109,0.0015495338],"genre_scores_gemma":[0.89428586,0.00000350953,0.10225061,0.002318373,0.000068693684,0.00012573722,0.0000812125,0.000032723827,0.00083329657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783653,0.00009801915,0.00061467604,0.00016909627,0.0008310866,0.0004505972],"domain_scores_gemma":[0.99893856,0.00020459184,0.00024406385,0.0004889431,0.000010993758,0.000112850474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051916915,0.00018676277,0.0001980019,0.00028131052,0.00026826366,0.00014097115,0.00097205065,0.00004388118,0.00003558376],"category_scores_gemma":[0.00008713869,0.00017791447,0.00003641123,0.0005292076,0.000063103165,0.0005591667,0.0010961121,0.0006825843,0.000028302447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013366239,0.00007566259,0.011987475,0.000015716809,0.000013417026,0.00009495046,0.008441891,0.97354805,0.000052441672,0.0016870268,0.0006422262,0.0034278012],"study_design_scores_gemma":[0.0015947206,0.00067206495,0.038855128,0.000059437472,0.000010314138,0.0001355863,0.0011360378,0.9245669,0.00014523893,0.000041572093,0.03228841,0.0004945508],"about_ca_topic_score_codex":0.000006222148,"about_ca_topic_score_gemma":4.2804976e-7,"teacher_disagreement_score":0.650586,"about_ca_system_score_codex":0.00026981987,"about_ca_system_score_gemma":0.00008138566,"threshold_uncertainty_score":0.7255141},"labels":[],"label_agreement":null},{"id":"W4225836256","doi":"10.1109/tiv.2022.3167616","title":"Deep Reinforcement Learning With NMPC Assistance Nash Switching for Urban Autonomous Driving","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Intelligent Vehicles","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Toyota Motor Corporation","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.016984844672470276,"score_gpt":0.2404053362757641,"score_spread":0.22342049160329383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225836256","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":[0.004438317,0.000042059055,0.99282885,0.00030920206,0.00077006896,0.0006359608,9.64374e-7,0.00049498235,0.00047962338],"genre_scores_gemma":[0.97194356,0.000023811264,0.023934454,0.00026962374,0.000046977795,0.00043988123,0.000004498104,0.00005226393,0.0032849514],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973224,0.00013560808,0.0005401929,0.00064057583,0.00075211236,0.00060910266],"domain_scores_gemma":[0.9984466,0.00039684138,0.00028711703,0.00061128987,0.0001136756,0.00014450685],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0005436868,0.0003238748,0.00027468379,0.00031828776,0.0018508672,0.00030272722,0.0009999396,0.00005787628,0.00012307816],"category_scores_gemma":[0.0000137003935,0.00032835043,0.00019146097,0.0005030116,0.000047125475,0.00044348912,0.000023405599,0.0008512852,0.00002651322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007841087,0.00007715464,0.00016228274,0.000026177497,0.00009716175,0.000007515108,0.0020188522,0.9757032,0.00053751137,0.0021015343,0.00005851214,0.019131681],"study_design_scores_gemma":[0.00042099616,0.0012148444,0.000045400353,0.000054692948,0.00003603141,0.000021251473,0.00058662676,0.9750465,0.0126304785,0.00007019414,0.009448082,0.00042489383],"about_ca_topic_score_codex":0.000024368925,"about_ca_topic_score_gemma":0.000021000804,"teacher_disagreement_score":0.96889436,"about_ca_system_score_codex":0.00057094655,"about_ca_system_score_gemma":0.00013295878,"threshold_uncertainty_score":0.99991685},"labels":[],"label_agreement":null},{"id":"W4225848424","doi":"10.1609/aaai.v36i7.20764","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","year":2022,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Reinforcement learning; Observable; Computer science; Latent variable; Block (permutation group theory); Artificial intelligence; Artificial neural network; Markov process; Machine learning; Markov decision process; Variable (mathematics); Algorithm; Mathematics","score_opus":0.14809175079995085,"score_gpt":0.3238548945512752,"score_spread":0.17576314375132435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4225848424","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":[0.00864207,0.000029264227,0.9765597,0.00184015,0.001410495,0.0018552575,0.0000044693747,0.00037022607,0.009288367],"genre_scores_gemma":[0.97274595,0.00012068622,0.01777588,0.00018921342,0.00016400656,0.00049168896,0.000017807313,0.00006889545,0.008425872],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946226,0.00007624093,0.0015159237,0.0013157859,0.0015324879,0.00093696034],"domain_scores_gemma":[0.9955468,0.0002193057,0.0020379417,0.0007615866,0.0012582486,0.00017610643],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.001777161,0.00068041595,0.00076766853,0.0002861875,0.0010437749,0.00096084067,0.0056238435,0.0003253492,0.00019411868],"category_scores_gemma":[0.0013503117,0.0006282656,0.00054999435,0.0005592981,0.00025761066,0.0004607374,0.0059209117,0.002682238,0.00003408584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000883356,0.00005054368,0.00007877832,0.0002209438,0.00005779117,4.818026e-7,0.00155921,0.7264161,0.0033993481,0.26513457,0.00013390776,0.0028599675],"study_design_scores_gemma":[0.00006434446,0.00048921595,0.000005176941,0.0003643083,0.000068387504,0.0000016531596,0.00038520523,0.90610117,0.047710743,0.04339894,0.0008292898,0.00058155984],"about_ca_topic_score_codex":0.00006285763,"about_ca_topic_score_gemma":0.0000041042736,"teacher_disagreement_score":0.9641039,"about_ca_system_score_codex":0.0003366556,"about_ca_system_score_gemma":0.00077488227,"threshold_uncertainty_score":0.9997562},"labels":[],"label_agreement":null},{"id":"W4230186541","doi":"10.22215/etd/2007-06291","title":"Æip: a generalized framework for the study of interactive learning","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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; Canadian Heritage","funders":"","keywords":"Computer science; Mathematics education; Humanities; Mathematics; Art","score_opus":0.02939189543155943,"score_gpt":0.365568793608507,"score_spread":0.3361768981769476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230186541","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":[0.010306619,0.000060944527,0.98306143,0.00003127332,0.0013651728,0.0012138835,2.1574908e-7,0.00009900723,0.0038614233],"genre_scores_gemma":[0.706521,0.00003944231,0.23766813,0.000162677,0.00023879879,0.00023477424,0.00007066983,0.00006757516,0.05499696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983404,0.000090402296,0.0004819073,0.0003580394,0.00047843083,0.0002508025],"domain_scores_gemma":[0.9965305,0.0018563338,0.0006496522,0.0005860475,0.00034373894,0.00003374283],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005490647,0.00022854572,0.00032272283,0.00018188987,0.00020752731,0.0001508479,0.0012598523,0.00018859375,0.000045877918],"category_scores_gemma":[0.0006246979,0.00015830202,0.00014201862,0.0003499254,0.000014329723,0.00015450273,0.00011229017,0.0007103943,0.000010289346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027717737,0.0002399247,0.0004244874,0.00012504142,0.00070040824,0.000003954875,0.05058188,0.83775747,0.0000802454,0.07959967,0.0004915356,0.029718222],"study_design_scores_gemma":[0.0014917119,0.0022324522,0.002873382,0.00029218433,0.00022057322,0.0000017618894,0.037883967,0.9454003,0.0014524915,0.002000207,0.0055003716,0.00065058406],"about_ca_topic_score_codex":0.000113197944,"about_ca_topic_score_gemma":0.000060613853,"teacher_disagreement_score":0.74539334,"about_ca_system_score_codex":0.000044324803,"about_ca_system_score_gemma":0.00007120101,"threshold_uncertainty_score":0.6455369},"labels":[],"label_agreement":null},{"id":"W4231805100","doi":"10.22215/etd/2012-09679","title":"Multi-agent reinforcement learning in games","year":2012,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Reinforcement learning; Humanities; Computer science; Artificial intelligence; Art","score_opus":0.026466873854124048,"score_gpt":0.2866958448495736,"score_spread":0.26022897099544956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231805100","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":[0.0018528149,0.0003142065,0.93126136,0.000052252133,0.0019106016,0.0004561072,6.908802e-8,0.0003879264,0.063764654],"genre_scores_gemma":[0.5490905,0.00015964081,0.042062063,0.0001378365,0.00010305243,0.000078405355,0.000277079,0.000051590738,0.40803984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975899,0.0000824648,0.000629868,0.000466868,0.0006052317,0.000625681],"domain_scores_gemma":[0.99874514,0.00007028436,0.00036941905,0.0005971395,0.0000898631,0.00012814163],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00045502448,0.00036452987,0.00034544413,0.00042896,0.00010083513,0.00019751202,0.0010356823,0.00027834796,0.0003110707],"category_scores_gemma":[0.00011521579,0.00035188373,0.00011889332,0.00036842242,0.000012618048,0.00051042764,0.00018922037,0.0007976286,0.0006838508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000069135117,0.00003809359,0.0023270946,0.00012432942,0.000032986776,0.000010271927,0.003758338,0.97995025,0.00029959995,0.0038829213,0.0003976264,0.0091716],"study_design_scores_gemma":[0.0006562017,0.000108827866,0.03039918,0.00024260335,0.00001869873,0.0000027412254,0.00059281243,0.94398874,0.00088422105,0.0000128338725,0.022336913,0.0007562464],"about_ca_topic_score_codex":0.00013169963,"about_ca_topic_score_gemma":0.00010489573,"teacher_disagreement_score":0.8891993,"about_ca_system_score_codex":0.00021484077,"about_ca_system_score_gemma":0.00013898389,"threshold_uncertainty_score":0.9998933},"labels":[],"label_agreement":null},{"id":"W4233539997","doi":"10.1109/ijcnn.2006.1716136","title":"A Reinforcement Learning Framework for Medical Image Segmentation","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Thresholding; Artificial intelligence; Segmentation; Image segmentation; Structuring element; Computer vision; Machine learning; Image (mathematics); Image processing; Mathematical morphology","score_opus":0.03411624730538505,"score_gpt":0.2948383576014699,"score_spread":0.2607221102960849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233539997","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":[0.005449948,0.0000101434825,0.9668142,0.012492955,0.0015891439,0.00058256096,0.0000010520447,0.00028328755,0.012776714],"genre_scores_gemma":[0.9558555,0.000038566817,0.037058115,0.0020592138,0.0018154324,0.0001729822,0.000029777788,0.000029857118,0.0029405942],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996981,0.000033083477,0.0006460291,0.0004708091,0.0013187397,0.0005503016],"domain_scores_gemma":[0.9983706,0.00029460128,0.0004949169,0.00019986641,0.0005372813,0.00010275269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008024382,0.00028992392,0.00022497709,0.00011067683,0.00039004293,0.000756777,0.0014662269,0.0001344424,0.00015448543],"category_scores_gemma":[0.00029430527,0.00022277652,0.00014392742,0.00027754277,0.00012090253,0.0006074935,0.00021823765,0.000667858,0.000086045235],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044799675,0.000021429647,0.00019390577,0.000012634937,0.00002883292,0.0000033810115,0.00013638099,0.5141384,0.0006096106,0.47172147,0.010906313,0.0021828255],"study_design_scores_gemma":[0.0004693365,0.00026662793,0.0002969017,0.00018899435,0.000011300983,0.000023491568,0.000044162887,0.9701421,0.0012333079,0.024806803,0.0022578316,0.0002590908],"about_ca_topic_score_codex":0.000028430995,"about_ca_topic_score_gemma":0.0000022540269,"teacher_disagreement_score":0.95040554,"about_ca_system_score_codex":0.00014079353,"about_ca_system_score_gemma":0.00007655358,"threshold_uncertainty_score":0.90845627},"labels":[],"label_agreement":null},{"id":"W4238326899","doi":"10.1109/hri.2013.6483585","title":"Integrating a robot in a tabletop reservoir engineering application","year":2013,"lang":"en","type":"article","venue":"2013 8th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Computer science; Visualization; Human–computer interaction; Simple (philosophy); Robot; Data visualization; Artificial intelligence","score_opus":0.11787837137254176,"score_gpt":0.3673373850222076,"score_spread":0.24945901364966583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238326899","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":[0.026914801,0.000011896,0.94947547,0.006454815,0.002538683,0.0008991477,0.0000030017723,0.0004201616,0.013282007],"genre_scores_gemma":[0.97779,0.000023753508,0.017734377,0.00057932426,0.00031725765,0.0005325565,0.00006720005,0.000042883756,0.0029126417],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966083,0.000117215204,0.0010039464,0.00085765746,0.00084515597,0.0005677266],"domain_scores_gemma":[0.99691147,0.0003282844,0.00056813384,0.0011195741,0.00089922885,0.00017332128],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004437694,0.0004520349,0.0003644307,0.00084248174,0.00018049825,0.0010921028,0.002719391,0.00019385638,0.0010620756],"category_scores_gemma":[0.00051627995,0.00045859112,0.00012330021,0.0005321745,0.000047328205,0.0026026994,0.00047435449,0.001086772,0.0016799241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024630155,0.00025720452,0.0007020741,0.00003832733,0.00008476003,0.000011508544,0.001229553,0.84966934,0.038768597,0.0965487,0.006958998,0.0057063354],"study_design_scores_gemma":[0.00054628873,0.00017218923,0.0021395616,0.00036926058,0.0000053536983,0.00002110632,0.00028233856,0.98885906,0.0023644306,0.0012177867,0.0035424249,0.0004801937],"about_ca_topic_score_codex":0.0014377822,"about_ca_topic_score_gemma":0.00029179972,"teacher_disagreement_score":0.9508752,"about_ca_system_score_codex":0.0006346307,"about_ca_system_score_gemma":0.000103656355,"threshold_uncertainty_score":0.99994487},"labels":[],"label_agreement":null},{"id":"W4240203305","doi":"10.22215/etd/2014-10293","title":"Multiple Model Reinforcement Learning for Environments with Poissonian Time Delays","year":2014,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Mobile robot; Robot; Reinforcement; Q-learning; Artificial intelligence; Grid; Simulation; Mathematics; Engineering","score_opus":0.01021222507287907,"score_gpt":0.22475181885179654,"score_spread":0.21453959377891746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4240203305","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":[0.00062030234,0.000011315193,0.97506416,0.000047364374,0.00016568365,0.0008969409,6.57946e-7,0.00023130083,0.022962302],"genre_scores_gemma":[0.27121383,0.000020261083,0.1911267,0.0002479045,0.00008114961,0.0002587006,0.0013798858,0.00012752209,0.53554404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973291,0.00004008797,0.00051652425,0.00075049,0.00074429787,0.0006194594],"domain_scores_gemma":[0.9982661,0.00015637062,0.0005484198,0.0007828857,0.000081622966,0.00016462394],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003160429,0.0005052012,0.00043828384,0.00020000248,0.0003450473,0.0002576632,0.0011279156,0.00029178767,0.000056004075],"category_scores_gemma":[0.000087679226,0.00044272386,0.00014685144,0.0001266372,0.00002397464,0.00037798498,0.000121158715,0.00043360423,0.0003500898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005744031,0.000014082297,0.00007356589,0.000070938026,0.0000799604,0.0000011306704,0.00055054965,0.99467033,0.00032201357,0.0019142563,0.0005080788,0.0017376234],"study_design_scores_gemma":[0.0009135022,0.0005116458,0.00007019616,0.00009979404,0.000050266448,0.0000016038424,0.000031015075,0.9885686,0.00086252164,0.000055261262,0.008246062,0.0005895252],"about_ca_topic_score_codex":0.000023438724,"about_ca_topic_score_gemma":0.00001800775,"teacher_disagreement_score":0.7839374,"about_ca_system_score_codex":0.00018807933,"about_ca_system_score_gemma":0.00012756928,"threshold_uncertainty_score":0.9998025},"labels":[],"label_agreement":null},{"id":"W4243101510","doi":"10.1002/9781118445112.stat08000","title":"Reinforcement Learning","year":2017,"lang":"en","type":"other","venue":"Wiley StatsRef: Statistics Reference Online","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; A priori and a posteriori; Sequence (biology); Artificial intelligence; Quality (philosophy); Reinforcement; Machine learning; Psychology","score_opus":0.04106047788657132,"score_gpt":0.31309103557408263,"score_spread":0.27203055768751133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243101510","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":[1.8139939e-7,0.00038401122,0.7244181,0.00006407052,0.00081716815,0.0003662418,0.00040571002,0.0007050133,0.27283952],"genre_scores_gemma":[0.00017987625,0.004122622,0.31690392,0.00013159109,0.00029609574,0.000023948336,0.0027059857,0.00037593098,0.67526007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995591,0.00016058845,0.0007326906,0.0011254309,0.0013542742,0.0010360598],"domain_scores_gemma":[0.9947877,0.00019804643,0.0017761455,0.002593876,0.0002710316,0.0003732364],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031818968,0.000869224,0.00089079066,0.0005439047,0.00042419884,0.0006670341,0.003467757,0.00050712907,0.0014477175],"category_scores_gemma":[0.00062714715,0.000850586,0.00009707216,0.00020658605,0.00027515893,0.00027600356,0.0012138312,0.0015327116,0.0009891036],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009794948,0.00007089866,0.00006739977,0.00027779405,0.00021067381,0.00017298634,0.0001302759,0.051839843,0.000009880401,0.081488036,0.8169449,0.048777528],"study_design_scores_gemma":[0.0005045365,0.00032261037,0.000028476346,0.0008596986,0.000050676546,0.000008992144,0.000012420683,0.1584417,0.0000044327144,0.0006409884,0.8382706,0.0008548518],"about_ca_topic_score_codex":0.00044641152,"about_ca_topic_score_gemma":0.0002432949,"teacher_disagreement_score":0.40751418,"about_ca_system_score_codex":0.00021074527,"about_ca_system_score_gemma":0.0005520557,"threshold_uncertainty_score":0.99978876},"labels":[],"label_agreement":null},{"id":"W4244090038","doi":"10.1007/978-1-4471-7452-3_17","title":"Reinforcement Learning","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Error-driven learning; Formalism (music); Artificial intelligence; Psychology; Social psychology","score_opus":0.01983590515921726,"score_gpt":0.22694637773350715,"score_spread":0.20711047257428988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244090038","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":[4.2321577e-8,0.0000324068,0.488828,0.00008702543,0.00039216896,0.00015413285,4.90835e-8,0.00026406825,0.5102421],"genre_scores_gemma":[0.00096693827,0.000118702614,0.00915066,0.00048011285,0.00010707717,0.0000024081785,0.00002111838,0.000050862356,0.9891021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978575,0.000012616595,0.0004588819,0.000558874,0.00074230495,0.0003698413],"domain_scores_gemma":[0.9981821,0.00009990587,0.00036325052,0.0011353887,0.00011542896,0.00010390936],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00023012992,0.00039678643,0.00036895173,0.0002195161,0.00010623449,0.00025002318,0.0013708525,0.00030191106,0.0019437063],"category_scores_gemma":[0.000026864273,0.00037386845,0.00019185072,0.000036992937,0.00003617885,0.0002950315,0.0009089526,0.0008265647,0.011127645],"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":[7.1078637e-7,5.8321206e-7,0.0000035812172,0.00001815172,0.000030893283,0.0000062922486,0.000033010212,0.4221015,0.0000020533341,0.57308847,0.0028907734,0.0018240062],"study_design_scores_gemma":[0.00014056425,0.00016141469,0.0000020571363,0.00008599095,0.000011470387,0.0000067542237,0.0000016603293,0.2895986,0.000015383304,0.0012013342,0.70836574,0.00040899415],"about_ca_topic_score_codex":0.0000041127487,"about_ca_topic_score_gemma":4.4979254e-7,"teacher_disagreement_score":0.705475,"about_ca_system_score_codex":0.00014290934,"about_ca_system_score_gemma":0.0001898704,"threshold_uncertainty_score":0.9998713},"labels":[],"label_agreement":null},{"id":"W4246058920","doi":"10.1109/.2005.1507451","title":"Attention shifts during action sequence recognition for social robots","year":2005,"lang":"en","type":"article","venue":"ICAR '05. Proceedings., 12th International Conference on Advanced Robotics, 2005.","topic":"Reinforcement Learning in Robotics","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":"Imperial College of Toronto","funders":"Engineering and Physical Sciences Research Council; Royal Society","keywords":"Action (physics); Sequence (biology); Robot; Computer science; Artificial intelligence; Human–computer interaction; Cognitive science; Psychology; Physics; Biology; Genetics","score_opus":0.10749375011927112,"score_gpt":0.34372097079146,"score_spread":0.2362272206721889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246058920","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":[0.01850374,0.000014921514,0.9580199,0.0123962555,0.0027998309,0.0010844562,0.000031558564,0.000566365,0.0065829833],"genre_scores_gemma":[0.8090148,0.00018301983,0.18509662,0.0004972811,0.0012669091,0.00017734685,0.00013915794,0.000061075094,0.003563812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652976,0.000023316372,0.0007465468,0.00096535153,0.000988218,0.00074683485],"domain_scores_gemma":[0.997547,0.000055545064,0.00072382885,0.0002378318,0.0012466449,0.00018915987],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003752636,0.0004471925,0.00034802686,0.00039133825,0.00053852284,0.00061933673,0.001225112,0.00023440486,0.00014665505],"category_scores_gemma":[0.00030065287,0.000495294,0.00020375532,0.00025665775,0.00011295538,0.0027157383,0.00022612716,0.0005217727,0.0002553124],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000422694,0.00032487823,0.00035250883,0.00020620348,0.00021286293,0.000009899953,0.000815563,0.59115255,0.054763243,0.2687243,0.001742012,0.08127328],"study_design_scores_gemma":[0.002710101,0.00040269282,0.0039095073,0.00046919403,0.000049267037,0.00004201263,0.0002609507,0.9689759,0.012597721,0.005021111,0.0044679116,0.0010936378],"about_ca_topic_score_codex":0.0000044277936,"about_ca_topic_score_gemma":0.000013028229,"teacher_disagreement_score":0.790511,"about_ca_system_score_codex":0.0006822649,"about_ca_system_score_gemma":0.00011737532,"threshold_uncertainty_score":0.9997499},"labels":[],"label_agreement":null},{"id":"W4247188402","doi":"10.36227/techrxiv.14842245","title":"Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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; Software deployment; Robot; Computer science; Robotics; Artificial intelligence; State space; Simulation; Human–computer interaction; Software engineering; Mathematics","score_opus":0.03484376922820494,"score_gpt":0.2772683896775365,"score_spread":0.24242462044933155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247188402","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":[0.0060164304,0.00010297406,0.98829705,0.00007638217,0.00077153667,0.00054842414,1.808378e-7,0.0003897933,0.0037972499],"genre_scores_gemma":[0.5777539,0.00015084395,0.42108092,0.00007120272,0.000045900528,0.000016495023,0.00003499717,0.0000328252,0.00081291783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629724,0.00025050336,0.0011740939,0.0007853335,0.0010501754,0.00044263966],"domain_scores_gemma":[0.9969306,0.00010592391,0.0010041002,0.0013229739,0.00051601493,0.00012036519],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073951186,0.0004013757,0.00055663177,0.0002751164,0.00014463766,0.0004048747,0.0011877897,0.00027270394,0.00017602554],"category_scores_gemma":[0.00017233583,0.00041973,0.00022416178,0.00044608233,0.000037975406,0.00037556453,0.004120194,0.00072668074,0.000009394073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031536008,0.00003304826,0.0011902374,0.00032958106,0.00009919225,0.0000065161503,0.0015509345,0.992224,0.00095370086,0.002917774,0.000014098289,0.0006777567],"study_design_scores_gemma":[0.00025739463,0.000102439764,0.00017895036,0.00034393588,0.000054326723,0.0000055416576,0.00013340691,0.9921904,0.0058539924,0.00004265769,0.00043605806,0.00040088093],"about_ca_topic_score_codex":0.00018043754,"about_ca_topic_score_gemma":0.0000065167783,"teacher_disagreement_score":0.57173747,"about_ca_system_score_codex":0.0004810134,"about_ca_system_score_gemma":0.0006954513,"threshold_uncertainty_score":0.9998255},"labels":[],"label_agreement":null},{"id":"W4250455569","doi":"10.1109/ijcnn.2006.1716795","title":"Extend Single-agent Reinforcement Learning Approach to a Multi-robot Cooperative Task in an Unknown Dynamic Environment","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Robot; Markov decision process; Robustness (evolution); Robot learning; Artificial intelligence; Q-learning; Obstacle; Mobile robot; Markov process; Machine learning; Mathematics","score_opus":0.052808010837956824,"score_gpt":0.26725047299880855,"score_spread":0.21444246216085172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250455569","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":[0.067667834,0.000019686711,0.9159742,0.002201477,0.00074060523,0.0011018761,0.0000015936059,0.00021534521,0.012077357],"genre_scores_gemma":[0.9810828,0.000021954529,0.013600375,0.0007853197,0.00025805205,0.00014972907,0.000033589116,0.000032892076,0.004035269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99666405,0.00008569179,0.0007584609,0.0008330412,0.00094199117,0.0007167914],"domain_scores_gemma":[0.9988455,0.00005687819,0.00037880847,0.0003196872,0.0002503576,0.00014873884],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005769551,0.00044344392,0.00032439447,0.00023291873,0.0002863924,0.00074229547,0.0015815032,0.00009628271,0.000028377763],"category_scores_gemma":[0.000042386102,0.00035561388,0.00009152617,0.00039810373,0.00012006726,0.00070896605,0.0004049499,0.000708204,0.00011136324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004735575,0.00018848953,0.00027097235,0.000006588221,0.0000189907,0.0000060970806,0.00073517265,0.96673936,0.0053500235,0.024646673,0.00033655262,0.0016537299],"study_design_scores_gemma":[0.0005874382,0.00057527435,0.0023105403,0.000110238885,0.000007925537,0.000019597792,0.00008739922,0.99426544,0.0004431905,0.0002070225,0.00097357837,0.00041237785],"about_ca_topic_score_codex":0.000066733104,"about_ca_topic_score_gemma":0.000018231536,"teacher_disagreement_score":0.91341496,"about_ca_system_score_codex":0.000523723,"about_ca_system_score_gemma":0.000044570632,"threshold_uncertainty_score":0.9998896},"labels":[],"label_agreement":null},{"id":"W4251839393","doi":"10.1007/978-1-4899-7502-7_77-1","title":"Dynamic Programming","year":2014,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Machine Learning and Data Mining","topic":"Reinforcement Learning in Robotics","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 Ottawa; University of British Columbia","funders":"","keywords":"Computer science; Programming language","score_opus":0.016937534042023732,"score_gpt":0.26894804897153735,"score_spread":0.2520105149295136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251839393","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00002491494,0.0019080088,0.6241929,0.0001316242,0.0003777646,0.00018846817,0.000016562672,0.00027833504,0.3728814],"genre_scores_gemma":[0.0030240896,0.004194586,0.36680382,0.0000665756,0.0001948195,0.0000054213738,0.0011971288,0.00013233279,0.62438124],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973085,0.0000757546,0.00067524274,0.0009997135,0.00054899656,0.00039181544],"domain_scores_gemma":[0.9969123,0.0005153886,0.0008362178,0.0015166999,0.000072545605,0.0001468571],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010532122,0.00046666432,0.0006352253,0.00029054296,0.00021751653,0.0001713431,0.0019801431,0.00027118326,0.00005723744],"category_scores_gemma":[0.00056364026,0.00046361634,0.00007438974,0.000072578325,0.00013736793,0.00033718752,0.0028398125,0.0010522478,0.000040657942],"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":[0.000009809129,0.000009366071,0.0017995841,0.0003694218,0.00014490752,0.000037910315,0.0007884637,0.007022249,0.000002888729,0.022483097,0.00086990016,0.9664624],"study_design_scores_gemma":[0.0001866578,0.00016564486,0.000035854722,0.00029746737,0.000050322495,0.00002331077,0.000010717515,0.3704379,2.1911829e-7,0.000101539124,0.6283363,0.00035408736],"about_ca_topic_score_codex":0.00002311321,"about_ca_topic_score_gemma":0.000009960883,"teacher_disagreement_score":0.9661083,"about_ca_system_score_codex":0.000025438967,"about_ca_system_score_gemma":0.00009238122,"threshold_uncertainty_score":0.99978155},"labels":[],"label_agreement":null},{"id":"W4254092108","doi":"10.1145/860685.860689","title":"Coordination in multiagent reinforcement learning","year":2003,"lang":"en","type":"article","venue":"Proceedings of the second international joint conference on Autonomous agents and multiagent systems - AAMAS '03","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Multi-agent system; Artificial intelligence","score_opus":0.03543263955971353,"score_gpt":0.256654267176619,"score_spread":0.22122162761690545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254092108","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":[0.7604927,0.00014853071,0.058501277,0.0027617214,0.0055907345,0.00336982,0.000010015915,0.00026796496,0.16885723],"genre_scores_gemma":[0.9809346,0.000041984425,0.0007818726,0.00020710178,0.000035104084,0.000072157825,0.000004868547,0.000019498668,0.017902799],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99734575,0.000060796607,0.0009319422,0.0005649609,0.0007182695,0.0003783123],"domain_scores_gemma":[0.99828196,0.000051789524,0.000873567,0.00022951045,0.0004439361,0.0001192564],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087492994,0.0003193471,0.00036006595,0.00034982892,0.0001842537,0.00042339513,0.00087987084,0.000116418436,0.00023838019],"category_scores_gemma":[0.00030823727,0.000259047,0.00012084865,0.00021252823,0.00007845903,0.00061789504,0.00034991102,0.0004015766,0.000045854504],"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":[0.000035122146,0.00029222167,0.02252729,0.00042077355,0.00027615955,0.0000073712713,0.0053996956,0.28325048,0.01474181,0.6693706,0.0016803544,0.0019981554],"study_design_scores_gemma":[0.0014872139,0.0002007755,0.01033033,0.0004604127,0.000012260952,0.000022131564,0.000724872,0.94980454,0.007104612,0.00018784036,0.029290471,0.00037452203],"about_ca_topic_score_codex":0.000092283706,"about_ca_topic_score_gemma":0.000006397745,"teacher_disagreement_score":0.6691827,"about_ca_system_score_codex":0.00034063758,"about_ca_system_score_gemma":0.00009385569,"threshold_uncertainty_score":0.9999862},"labels":[],"label_agreement":null},{"id":"W4255384105","doi":"10.31234/osf.io/ptz2r","title":"Inferring Actions, Intentions, and Causal Relations in a Neural Network","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research","funders":"Wellcome Trust; Canadian Institute for Advanced Research","keywords":"Generative grammar; Inference; Action (physics); Computer science; Representation (politics); Artificial intelligence; Process (computing); Generative model; Causal inference; Artificial neural network; Control (management); Machine learning; Cognitive science; Theoretical computer science; Psychology; Mathematics; Econometrics","score_opus":0.04283485095793588,"score_gpt":0.2884694462248224,"score_spread":0.24563459526688652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255384105","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":[0.016007992,0.00027233886,0.9746681,0.0010533951,0.001219189,0.00021183076,2.8986005e-7,0.00020285982,0.006363994],"genre_scores_gemma":[0.9001636,0.00011628772,0.09776214,0.00016544403,0.00008913615,0.00003621383,0.000022041255,0.000012110159,0.0016330677],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984608,0.00012017741,0.00040819304,0.00047225665,0.00025978126,0.00027878824],"domain_scores_gemma":[0.9989404,0.0001369307,0.00014182269,0.00062130054,0.00008784658,0.0000717123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030033384,0.0001818742,0.00021603452,0.00019543046,0.00014058578,0.0006474181,0.00042922742,0.00018387468,0.000048532063],"category_scores_gemma":[0.00015788554,0.00019789259,0.00006562891,0.0003717885,0.000033538443,0.00043046847,0.002558979,0.001035561,0.000008705016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7110055e-7,0.000008589033,0.0272522,0.000018233817,0.00001755717,0.000012509498,0.00022526503,0.95948696,0.000005254603,0.011790482,0.00028774768,0.00089475844],"study_design_scores_gemma":[0.00010965633,0.000011743014,0.04669917,0.00016308899,0.00000954578,0.000017257735,0.00007209409,0.95181096,0.0000032649116,0.0005213078,0.00038274936,0.00019916026],"about_ca_topic_score_codex":0.00017655526,"about_ca_topic_score_gemma":0.0002706759,"teacher_disagreement_score":0.8841556,"about_ca_system_score_codex":0.000115695664,"about_ca_system_score_gemma":0.00018385591,"threshold_uncertainty_score":0.8069826},"labels":[],"label_agreement":null},{"id":"W4256006693","doi":"10.1109/wsc.2015.7408303","title":"Imitation challenges: From uniform random variables to complex systems","year":2015,"lang":"en","type":"article","venue":"2015 Winter Simulation Conference (WSC)","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Imitation; Computer science; Random variable; Theoretical computer science; Mathematics; Statistics; Psychology","score_opus":0.1790954619224176,"score_gpt":0.3286150655444003,"score_spread":0.1495196036219827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256006693","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":[0.0013401761,0.00008039731,0.98496073,0.001553283,0.001347709,0.00053842756,0.000008086582,0.00029285505,0.009878319],"genre_scores_gemma":[0.9811294,0.000009741792,0.017411895,0.00026041095,0.00021373614,0.000026900147,0.000073286355,0.000019015895,0.0008556269],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769795,0.00020885651,0.00055663596,0.00051662116,0.0006727436,0.00034721385],"domain_scores_gemma":[0.9972704,0.00046475834,0.00025983716,0.00079552585,0.00089812145,0.00031133078],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006538998,0.0002588387,0.00034686262,0.00020500286,0.00009190736,0.00059453177,0.0009575283,0.00012398497,0.0000708516],"category_scores_gemma":[0.00038136117,0.00024550428,0.000057151086,0.00024253606,0.000035386995,0.0010850218,0.00028992552,0.00015895038,0.0006351487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045418292,0.000018582667,0.0001397416,0.000012020405,0.000032800515,0.0000021975557,0.004695338,0.96886146,0.000056500405,0.022630246,0.001402332,0.002103384],"study_design_scores_gemma":[0.0015617242,0.00016139343,0.0010792037,0.000100907106,0.000012939491,0.0000013947198,0.00061705004,0.97467744,0.000024510735,0.0015151128,0.019954184,0.0002941238],"about_ca_topic_score_codex":0.00018458393,"about_ca_topic_score_gemma":0.000026622178,"teacher_disagreement_score":0.9797892,"about_ca_system_score_codex":0.00016951644,"about_ca_system_score_gemma":0.00017258205,"threshold_uncertainty_score":0.9999997},"labels":[],"label_agreement":null},{"id":"W4280563754","doi":"10.18196/jrc.v3i2.13082","title":"Consensus of Multi-agent Reinforcement Learning Systems: The Effect of Immediate Rewards","year":2022,"lang":"en","type":"article","venue":"Journal of Robotics and Control (JRC)","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"","keywords":"Reinforcement learning; Cumulative prospect theory; Computer science; Function (biology); Artificial intelligence; Mathematics; Statistics","score_opus":0.010502809948478941,"score_gpt":0.23320032861499804,"score_spread":0.2226975186665191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280563754","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":[0.020345846,0.0022352808,0.9747054,0.0008191925,0.0012761327,0.00043939578,0.0000017917223,0.000013808925,0.00016312317],"genre_scores_gemma":[0.99793375,0.00012468595,0.0014991042,0.000059617385,0.000063752814,0.0000062236113,6.0114996e-7,0.000012159597,0.0003001297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99695957,0.00064602646,0.0010808922,0.00014314082,0.00090529665,0.00026509064],"domain_scores_gemma":[0.99651706,0.00087653723,0.0018993884,0.00033181655,0.0002744227,0.00010076567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029968584,0.00017757886,0.00061224727,0.00017255176,0.0002401689,0.00007200014,0.0007224144,0.000042903892,0.000007042472],"category_scores_gemma":[0.00035435086,0.00011894946,0.00020480572,0.00022149674,0.000103067585,0.000084644525,0.00031624272,0.000580873,8.5263395e-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":[0.000121844365,0.000018389603,0.0033390098,0.000091483766,0.00022973857,0.000027985468,0.0004666042,0.99252033,0.0010346003,0.0013291425,0.00011115122,0.0007097212],"study_design_scores_gemma":[0.0036949124,0.0033238349,0.0006993586,0.00008637977,0.00015664633,0.0001540275,0.00028499012,0.99003685,0.0002751517,0.000009186078,0.0011574149,0.00012127219],"about_ca_topic_score_codex":0.00002806152,"about_ca_topic_score_gemma":3.594947e-7,"teacher_disagreement_score":0.9775879,"about_ca_system_score_codex":0.000081443366,"about_ca_system_score_gemma":0.00012243386,"threshold_uncertainty_score":0.48506182},"labels":[],"label_agreement":null},{"id":"W4283160467","doi":"10.1002/cjce.24508","title":"A survey and comparative evaluation of actor‐critic methods in process control","year":2022,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Process (computing); Optimal control; Artificial neural network; Control engineering; Process control; Control (management); Artificial intelligence; Machine learning; Mathematical optimization; Engineering; Mathematics","score_opus":0.0722343985281289,"score_gpt":0.3391115488946168,"score_spread":0.2668771503664879,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283160467","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":[0.6657621,0.00061112415,0.33293098,0.00029530795,0.0001854639,0.00014621472,0.000002334458,0.000004221896,0.00006220013],"genre_scores_gemma":[0.99706286,2.2550941e-7,0.002896517,0.00002369654,0.000008989037,0.0000033841093,3.6473037e-7,0.0000027743397,0.00000115712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905705,0.00023645337,0.0002369867,0.00005325618,0.0002897984,0.00012644313],"domain_scores_gemma":[0.99910647,0.00042591448,0.00010728213,0.0000873677,0.0001732395,0.00009970826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033037113,0.000052644387,0.0001554729,0.00012238018,0.000034354023,0.000027553417,0.00038019635,0.000014750381,0.0000093139],"category_scores_gemma":[0.00065969187,0.00004503988,0.000019556433,0.000260423,0.000027753666,0.00009719244,0.000022277874,0.00030400784,5.6732535e-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":[0.0000025393304,0.0000017655768,0.00072097674,0.0000071339737,0.0000135470145,0.0000017087891,0.001108382,0.9940177,0.0035014385,0.00030492854,0.0000051525885,0.00031469463],"study_design_scores_gemma":[0.00036319759,0.000029432316,0.003169186,0.000016404623,0.000009297667,0.00002609611,0.00003030949,0.99263257,0.0035682332,0.00009077345,0.000017041873,0.000047463345],"about_ca_topic_score_codex":0.0003638491,"about_ca_topic_score_gemma":0.000080999016,"teacher_disagreement_score":0.33130077,"about_ca_system_score_codex":0.0002012505,"about_ca_system_score_gemma":0.0005013688,"threshold_uncertainty_score":0.1836673},"labels":[],"label_agreement":null},{"id":"W4283797949","doi":"10.1609/aaai.v36i9.21233","title":"Stochastic Goal Recognition Design Problems with Suboptimal Agents","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"National Science Foundation","keywords":"Ambiguity; Computer science; Generalization; Observability; Action (physics); Benchmark (surveying); Artificial intelligence; Range (aeronautics); Mathematical optimization; Observer (physics); Machine learning; Mathematics; Engineering","score_opus":0.12589060475098662,"score_gpt":0.27620741389932374,"score_spread":0.15031680914833712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283797949","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":[0.024353497,0.0000055362734,0.9703914,0.0010225201,0.00033623356,0.0008476899,0.0000033084211,0.00012983165,0.0029099674],"genre_scores_gemma":[0.9849914,0.000003883459,0.014306175,0.00016710955,0.000029552892,0.00013666265,0.0000014267938,0.000018121045,0.00034566803],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976083,0.00004716043,0.00047025707,0.0005024269,0.00096631236,0.0004055316],"domain_scores_gemma":[0.9985246,0.00010684138,0.0005240828,0.00028962662,0.0004727837,0.000082070655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074203504,0.00023142027,0.00021286863,0.00015961581,0.0005079584,0.0002598929,0.0021489381,0.000036682333,0.00018459259],"category_scores_gemma":[0.00019286078,0.00017977788,0.00007399151,0.0008563429,0.00019420542,0.00042678564,0.00066165667,0.0005045254,0.00007924158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019022479,0.00023507807,0.000058949452,0.000036717025,0.00003357282,0.000001716385,0.0023102625,0.85259116,0.0054175043,0.12122287,0.00019809967,0.017703878],"study_design_scores_gemma":[0.0000731677,0.0013379044,0.000049870545,0.00013564054,0.000021146649,0.000025732734,0.0005309642,0.9339495,0.036495812,0.027029034,0.000044855387,0.00030640338],"about_ca_topic_score_codex":0.000018377741,"about_ca_topic_score_gemma":0.000001032391,"teacher_disagreement_score":0.9606379,"about_ca_system_score_codex":0.000111037196,"about_ca_system_score_gemma":0.00015406634,"threshold_uncertainty_score":0.73311293},"labels":[],"label_agreement":null},{"id":"W4283801867","doi":"10.1609/aaai.v36i7.20764","title":"Blockwise Sequential Model Learning for Partially Observable Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Observable; Reinforcement learning; Computer science; Latent variable; Block (permutation group theory); Artificial intelligence; Artificial neural network; Markov process; Variable (mathematics); Machine learning; Markov chain; Algorithm; Mathematics","score_opus":0.0468047699607824,"score_gpt":0.2675118803325101,"score_spread":0.22070711037172772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283801867","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":[0.0015711011,0.000022761938,0.98732114,0.0005898941,0.00042782878,0.0005419915,3.7305293e-7,0.0006819971,0.008842939],"genre_scores_gemma":[0.82027227,0.000009616918,0.08326696,0.0005985442,0.00008038855,0.0003367442,0.000043152144,0.000041054776,0.09535127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707526,0.00016011328,0.00053932273,0.0005933674,0.000850083,0.0007818771],"domain_scores_gemma":[0.99874014,0.00015193218,0.00028361016,0.0005353689,0.00013655452,0.00015239738],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010967457,0.00025537054,0.0002599261,0.00015413598,0.0016251466,0.0003213598,0.0013146063,0.000054567437,0.0003500913],"category_scores_gemma":[0.00016467812,0.00027969482,0.0001900241,0.00039874358,0.000032045158,0.0005682815,0.0015570503,0.0006790732,0.000043612636],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002451242,0.000019702304,0.00026086214,0.000018292947,0.000034629138,0.0000048250718,0.00065974204,0.9569856,0.0009270739,0.0388077,0.0014055561,0.00085148873],"study_design_scores_gemma":[0.00074556447,0.0005553709,0.000007790494,0.000005560281,0.000017478415,0.000008034292,0.00013881177,0.94011474,0.0007476675,0.0004044443,0.05691121,0.00034330625],"about_ca_topic_score_codex":0.000033821158,"about_ca_topic_score_gemma":0.000002249793,"teacher_disagreement_score":0.90405416,"about_ca_system_score_codex":0.00025059347,"about_ca_system_score_gemma":0.0002798032,"threshold_uncertainty_score":0.99996555},"labels":[],"label_agreement":null},{"id":"W4283815468","doi":"10.1609/aaai.v36i6.20639","title":"A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research; McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Bootstrapping (finance); Computer science; Reinforcement learning; Successor cardinal; Value (mathematics); Artificial intelligence; Bellman equation; Machine learning; Function (biology); Generality; Feature (linguistics); Mathematics; Econometrics; Mathematical optimization","score_opus":0.05540860206408431,"score_gpt":0.2917252413087566,"score_spread":0.23631663924467228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283815468","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":[0.079512015,0.00009163772,0.9028898,0.0074054855,0.0015036291,0.0017001155,0.000020149884,0.00036758522,0.0065095937],"genre_scores_gemma":[0.97890514,0.000019548046,0.019020908,0.00025896388,0.000057123303,0.00015057191,0.0000035384592,0.000022208616,0.0015620011],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997723,0.00005865489,0.00047747578,0.00058319484,0.0007113742,0.00044629522],"domain_scores_gemma":[0.9985419,0.00018640277,0.0005180336,0.00027206773,0.00037587574,0.00010570555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00091464305,0.0002521251,0.00029058516,0.00018305785,0.0011795952,0.00034416156,0.0017106008,0.000076727476,0.00004595267],"category_scores_gemma":[0.00052521843,0.00021988867,0.00014735281,0.00067759614,0.0002247543,0.0002635276,0.000870619,0.0006968147,0.0000056748627],"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":[0.000052522704,0.00006404671,0.00020047497,0.00003135133,0.00002364291,2.3506037e-7,0.0015525757,0.30441713,0.004970009,0.6866579,0.0004505952,0.0015795212],"study_design_scores_gemma":[0.000105436855,0.00091944647,0.00008183095,0.00006581956,0.000025185385,0.00001100626,0.0008084377,0.94016784,0.024490545,0.030462848,0.0026231618,0.00023841453],"about_ca_topic_score_codex":0.00001879438,"about_ca_topic_score_gemma":4.2420493e-7,"teacher_disagreement_score":0.89939314,"about_ca_system_score_codex":0.00008237784,"about_ca_system_score_gemma":0.00013005268,"threshold_uncertainty_score":0.9072612},"labels":[],"label_agreement":null},{"id":"W4285061979","doi":"","title":"Graph augmented Deep Reinforcement Learning in the GameRLand3D environment","year":2021,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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":"Ubisoft (Canada)","funders":"","keywords":"Reinforcement learning; Graph; Computer science; Artificial intelligence; Reinforcement; Theoretical computer science; Psychology; Social psychology","score_opus":0.012907675169355612,"score_gpt":0.2150617302733661,"score_spread":0.20215405510401047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285061979","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":[0.0065968544,0.00072705146,0.96363634,0.006691156,0.00022721679,0.0005961142,7.517017e-7,0.00020565737,0.02131887],"genre_scores_gemma":[0.93838537,0.001605831,0.053570922,0.0003758547,0.000020960028,0.0001781484,0.0003910396,0.000040313498,0.0054315906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98937845,0.007060946,0.0008372315,0.0010244085,0.0011076612,0.00059132196],"domain_scores_gemma":[0.9939266,0.0013012271,0.00071692344,0.00341887,0.00049861113,0.00013780032],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0070243524,0.00045037022,0.0004209247,0.00029480917,0.00042498813,0.0012761799,0.0037362874,0.0002632267,0.000142846],"category_scores_gemma":[0.00082219025,0.0004155066,0.000270553,0.00060920237,0.00018674106,0.00027809505,0.0036065276,0.0016373919,0.000054135093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004115813,0.00023248796,0.0020695324,0.00010223825,0.00008334438,0.000033248707,0.026416032,0.9275152,0.00023824828,0.029510299,0.00016302132,0.013632245],"study_design_scores_gemma":[0.0006580378,0.0000016410189,0.00392042,0.00110277,0.00003460668,0.000016514758,0.00061932043,0.98091966,0.002439354,0.0006426828,0.009049707,0.00059529435],"about_ca_topic_score_codex":0.0005371497,"about_ca_topic_score_gemma":0.00023339395,"teacher_disagreement_score":0.9317885,"about_ca_system_score_codex":0.00024745768,"about_ca_system_score_gemma":0.0002374916,"threshold_uncertainty_score":0.99982965},"labels":[],"label_agreement":null},{"id":"W4285102525","doi":"10.1109/icra46639.2022.9811652","title":"Exploiting Abstract Symmetries in Reinforcement Learning for Complex Environments","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Robotics and Automation (ICRA)","topic":"Reinforcement Learning in Robotics","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 British Columbia, Okanagan Campus; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Heuristics; Abstraction; Exploit; Sample (material); Artificial intelligence; Sample complexity; State space; Inefficiency; Space (punctuation); Field (mathematics); State (computer science); Algorithm; Mathematics","score_opus":0.062108136455817274,"score_gpt":0.29000277259952806,"score_spread":0.22789463614371078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285102525","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":[0.0035718852,0.000010273622,0.9862233,0.0033192877,0.0005125958,0.0003694795,0.000004720918,0.000091715294,0.0058967704],"genre_scores_gemma":[0.9870206,0.000043397347,0.01029495,0.0004672955,0.000032922046,0.00011217346,0.00016228335,0.000012758797,0.0018536204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982243,0.00005677925,0.00044619248,0.00034820498,0.000682295,0.00024218188],"domain_scores_gemma":[0.9992145,0.00016956229,0.00031459733,0.00018091324,0.00006828429,0.00005215112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005030281,0.00015901783,0.00016026435,0.0003376458,0.00038555823,0.00028242308,0.0005697622,0.000032468153,0.0003631887],"category_scores_gemma":[0.00014266516,0.00018365736,0.000042497082,0.00017735873,0.0000325257,0.00034627726,0.00044745466,0.00030775234,0.000014192993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008866876,0.000028299846,0.0004564863,0.0000090810745,0.000017008579,0.0000028525271,0.00028218707,0.8038387,0.00094799633,0.19109611,0.00013052646,0.0031819162],"study_design_scores_gemma":[0.0005991872,0.00023578703,0.0055216365,0.000024924393,0.000003467357,0.0000041684784,0.00044145552,0.9881295,0.000116090494,0.0012438961,0.0034901206,0.00018974447],"about_ca_topic_score_codex":0.000011234436,"about_ca_topic_score_gemma":0.0000013238074,"teacher_disagreement_score":0.9834487,"about_ca_system_score_codex":0.00023601337,"about_ca_system_score_gemma":0.000051988703,"threshold_uncertainty_score":0.748933},"labels":[],"label_agreement":null},{"id":"W4285199588","doi":"10.1007/978-3-031-79167-3_1","title":"Background and Definitions","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science","score_opus":0.09273344441866999,"score_gpt":0.25646224030904613,"score_spread":0.16372879589037614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285199588","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.492324e-7,0.000063585925,0.36298078,0.00021834526,0.0001634775,0.000056537257,0.0000014433723,0.000108650245,0.6364069],"genre_scores_gemma":[0.00019293194,0.00044060632,0.033662535,0.0006467994,0.00003886684,0.00000600076,0.000022446153,0.000021164657,0.9649686],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99912006,0.000008079573,0.00016734151,0.0002953096,0.0002755616,0.00013367798],"domain_scores_gemma":[0.9992413,0.00010426446,0.00008848176,0.0004815011,0.000025682031,0.000058749727],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00008789757,0.00015577604,0.00013959821,0.0001115,0.00018124148,0.00016603294,0.00046957898,0.00007757278,0.0038410493],"category_scores_gemma":[0.000005157823,0.00015965028,0.00005076162,0.000024102701,0.000046811656,0.00018619244,0.00079629355,0.00032626206,0.00030563714],"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":[2.0476122e-7,0.0000011175969,0.0000014564557,0.0000065325194,0.0000127434305,0.000010858495,0.000025144596,0.0019198305,2.8078915e-7,0.9938909,0.0032692745,0.0008616642],"study_design_scores_gemma":[0.000079458034,0.0000723947,0.000010735939,0.000012296239,0.000012047373,0.000037187365,0.000004552089,0.010177525,4.2381208e-7,0.048231523,0.94111705,0.00024480742],"about_ca_topic_score_codex":0.000005513847,"about_ca_topic_score_gemma":0.0000016340721,"teacher_disagreement_score":0.94565934,"about_ca_system_score_codex":0.000047885504,"about_ca_system_score_gemma":0.000051749736,"threshold_uncertainty_score":0.9970696},"labels":[],"label_agreement":null},{"id":"W4285255083","doi":"10.1007/978-3-031-79167-3_2","title":"Reinforcement Learning Theory","year":2022,"lang":"en","type":"book-chapter","venue":"Synthesis lectures on artificial intelligence and machine learning","topic":"Reinforcement Learning in Robotics","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 Alberta; Canadian Institute for Advanced Research","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Plan (archaeology); Context (archaeology); Cognitive science; Artificial intelligence; Psychology; Social psychology; History","score_opus":0.04072940189197726,"score_gpt":0.2609339799200801,"score_spread":0.22020457802810284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285255083","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000051342267,0.0004871864,0.62111557,0.0004927206,0.00038549554,0.00031432544,0.0000014104138,0.00042628762,0.37677187],"genre_scores_gemma":[0.4125758,0.004721509,0.0031884767,0.0017863638,0.0006417387,0.0001477763,0.00009831593,0.00036529,0.5764747],"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","domain_scores_codex":[0.99586546,0.00040990883,0.000872353,0.0011399644,0.0010373528,0.0006749509],"domain_scores_gemma":[0.9962017,0.002061094,0.00070034154,0.0007480432,0.00008757147,0.00020127483],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014856984,0.00079339667,0.0006986815,0.00066426233,0.001419708,0.00048440724,0.0012255663,0.0003317415,0.0057749324],"category_scores_gemma":[0.0013112616,0.00076104654,0.0003066263,0.00015723,0.00019572605,0.00025715327,0.00092943927,0.0034257295,0.00056272],"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":[0.00004011289,0.000006761147,0.0000027082865,0.000022935088,0.000070719776,0.000025977732,0.0003789987,0.44320533,0.00001855186,0.39147916,0.000031444855,0.16471732],"study_design_scores_gemma":[0.000039558116,0.0010996555,0.0000031152958,0.00028225788,0.00012339563,0.0000374629,0.00010413577,0.3952208,0.0021355392,0.07133807,0.5282778,0.0013382375],"about_ca_topic_score_codex":0.000044900724,"about_ca_topic_score_gemma":0.000009729972,"teacher_disagreement_score":0.6179271,"about_ca_system_score_codex":0.00019757164,"about_ca_system_score_gemma":0.000111386464,"threshold_uncertainty_score":0.9998803},"labels":[],"label_agreement":null},{"id":"W4285600734","doi":"10.24963/ijcai.2022/478","title":"CCLF: A Contrastive-Curiosity-Driven Learning Framework for Sample-Efficient Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"Nanyang Technological University; National Research Foundation Singapore; National Research Foundation","keywords":"Computer science; Reinforcement learning; Curiosity; Artificial intelligence; Encoder; Exploit; Sample (material); Machine learning; Code (set theory); Encoding (memory); Representation (politics)","score_opus":0.06430454282604245,"score_gpt":0.29373130230923883,"score_spread":0.22942675948319638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285600734","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":[0.008247299,0.000008993653,0.97940165,0.0062986608,0.0016079972,0.00091969006,0.000009448588,0.0001949413,0.0033113337],"genre_scores_gemma":[0.97630024,0.000024101902,0.022325302,0.00038080462,0.00014667677,0.00023523114,0.000009193174,0.00003064173,0.000547786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959245,0.000063216896,0.0010496606,0.0007488555,0.0016286838,0.00058513193],"domain_scores_gemma":[0.99623996,0.0008829917,0.0012942046,0.0003014569,0.0011540003,0.00012738498],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0012518751,0.00037159008,0.00040265374,0.00034375172,0.0014191092,0.00048028215,0.0031239039,0.000098638164,0.00032423984],"category_scores_gemma":[0.0038223201,0.00033511524,0.00032992358,0.00060868467,0.00023148328,0.0003124301,0.0017881575,0.001414028,0.0000368409],"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":[0.00008984858,0.00007589168,0.00028601644,0.000021537076,0.000046221132,4.4136118e-7,0.0017023822,0.49395838,0.0008564221,0.5012636,0.000032299202,0.0016669213],"study_design_scores_gemma":[0.000111583715,0.00073078024,0.00013155253,0.00027044574,0.000021287853,0.000008293553,0.0016750226,0.93361866,0.015372938,0.045462817,0.0022453764,0.00035124822],"about_ca_topic_score_codex":0.000048633163,"about_ca_topic_score_gemma":0.0000019798913,"teacher_disagreement_score":0.968053,"about_ca_system_score_codex":0.0004472782,"about_ca_system_score_gemma":0.00016318554,"threshold_uncertainty_score":0.9999101},"labels":[],"label_agreement":null},{"id":"W4285604500","doi":"10.24963/ijcai.2022/440","title":"Multi-policy Grounding and Ensemble Policy Learning for Transfer Learning with Dynamics Mismatch","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"York University; University of Toronto","funders":"","keywords":"Computer science; Task (project management); Quality (philosophy); Imitation; Feature (linguistics); Policy learning; Artificial intelligence; Transfer of learning; Ensemble learning; Machine learning; Algorithm; Engineering","score_opus":0.055653521465682323,"score_gpt":0.28927776346081047,"score_spread":0.23362424199512816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285604500","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":[0.051292576,0.000007896906,0.9309913,0.013086185,0.0003810738,0.0006020953,0.00000548679,0.0001485206,0.0034848636],"genre_scores_gemma":[0.9864537,0.00004285971,0.011439752,0.00021833966,0.0001262527,0.000106459265,0.0000052773867,0.000032689783,0.0015746626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99743134,0.000040892857,0.0006186008,0.0005849238,0.0008768204,0.00044743464],"domain_scores_gemma":[0.9984489,0.00021675284,0.00041897278,0.00017857504,0.0006368375,0.00009993421],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00084775646,0.000297853,0.0003013169,0.0004983012,0.0010497103,0.00048490995,0.0016475341,0.00006740851,0.000027047416],"category_scores_gemma":[0.0008066078,0.00025038753,0.00013319415,0.0007033254,0.00021755892,0.00048941054,0.00071470166,0.000847212,0.000007447737],"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":[0.000113680886,0.0000744414,0.00071289844,0.000054042437,0.00005245817,7.8346557e-7,0.0033186143,0.23830922,0.0040938915,0.74490744,0.000008712052,0.008353806],"study_design_scores_gemma":[0.00015897055,0.00062808197,0.00029019633,0.00017616605,0.00001499808,0.00003937485,0.0028118084,0.96819305,0.01287531,0.013903801,0.0005953997,0.0003128481],"about_ca_topic_score_codex":0.00019270723,"about_ca_topic_score_gemma":0.000028474604,"teacher_disagreement_score":0.9351611,"about_ca_system_score_codex":0.00045203118,"about_ca_system_score_gemma":0.00022592291,"threshold_uncertainty_score":0.9999948},"labels":[],"label_agreement":null},{"id":"W4286910437","doi":"10.48550/arxiv.2110.02355","title":"Robustness and sample complexity of model-based MARL for general-sum Markov games","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de la Défense Nationale","keywords":"Markov chain; Mathematics; Markov kernel; Markov process; Markov perfect equilibrium; Discrete mathematics; Markov model; Applied mathematics; Combinatorics; Mathematical optimization; Variable-order Markov model; Nash equilibrium; Statistics","score_opus":0.12315007179665002,"score_gpt":0.21884184029032583,"score_spread":0.0956917684936758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286910437","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":[0.10739985,0.00003483954,0.8915175,0.00009211755,0.00024345808,0.00036344343,0.000036454298,0.00009399506,0.0002183234],"genre_scores_gemma":[0.6982971,0.00004643606,0.30088693,0.0000614678,0.000023076182,0.0000016937337,0.000058395228,0.000016738222,0.0006081713],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981956,0.00011397582,0.00027642483,0.00094354147,0.00012531367,0.00034517437],"domain_scores_gemma":[0.9976226,0.0003164615,0.00037527108,0.0011946523,0.00035540285,0.0001356119],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00027224465,0.00030844414,0.0004876041,0.00020793668,0.00013589367,0.00014487805,0.001286118,0.00023717502,0.000017557739],"category_scores_gemma":[0.00010923719,0.00037734743,0.00022429237,0.00031013833,0.0002830808,0.00023953767,0.001753168,0.00032328966,5.193042e-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":[0.000026561203,0.000038499016,0.0013698513,0.0003527713,0.00006359435,0.0000138401465,0.00007560095,0.9633426,0.000028013626,0.03440688,0.00008960454,0.00019218418],"study_design_scores_gemma":[0.0006108685,0.00004979336,0.0005436922,0.00010243686,0.00005744677,9.099177e-7,0.00003363084,0.9924962,0.00023585717,0.0054650092,0.000037364523,0.00036682078],"about_ca_topic_score_codex":0.000136748,"about_ca_topic_score_gemma":0.000030806077,"teacher_disagreement_score":0.59089726,"about_ca_system_score_codex":0.000121406214,"about_ca_system_score_gemma":0.00035798116,"threshold_uncertainty_score":0.99986786},"labels":[],"label_agreement":null},{"id":"W4287251902","doi":"10.48550/arxiv.2103.15793","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement\\n Learning","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Action (physics); Computer science; Artificial intelligence; Space (punctuation); Task (project management); Machine learning; Engineering; Physics","score_opus":0.0890968772339231,"score_gpt":0.21438475174161317,"score_spread":0.12528787450769008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287251902","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":[0.12259276,0.000075347874,0.87021184,0.00014468779,0.002578402,0.0015250765,0.0000018119345,0.00055760605,0.002312436],"genre_scores_gemma":[0.9366442,0.0011078494,0.003966744,0.00007886093,0.000271308,0.000011129686,0.00017367356,0.000120246266,0.05762597],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9921796,0.0008715851,0.0010644094,0.003415758,0.0006106955,0.0018579825],"domain_scores_gemma":[0.993365,0.0007523189,0.002050384,0.0019452181,0.0012399529,0.0006471661],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0015875539,0.0012765613,0.0011923212,0.00080656493,0.0020010748,0.0013524991,0.0024962295,0.00094035227,0.00031779977],"category_scores_gemma":[0.00064644177,0.0016976062,0.0012023599,0.0019596152,0.00029882987,0.0009341436,0.0045528268,0.003610651,0.00030676316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017747894,0.00014145578,0.002090252,0.00053254707,0.0005214415,0.00026178503,0.0017890735,0.9826034,0.00021919905,0.009843749,0.00006643976,0.0017531903],"study_design_scores_gemma":[0.002346488,0.0007933825,0.0002998148,0.0007675873,0.0004904427,0.000019459261,0.0018296913,0.9843642,0.0010108824,0.00006912642,0.0064027817,0.0016061318],"about_ca_topic_score_codex":0.00020629197,"about_ca_topic_score_gemma":0.000019041354,"teacher_disagreement_score":0.86624515,"about_ca_system_score_codex":0.0017004464,"about_ca_system_score_gemma":0.000898058,"threshold_uncertainty_score":0.9999986},"labels":[],"label_agreement":null},{"id":"W4287333197","doi":"10.48550/arxiv.2102.02639","title":"Improving Reinforcement Learning with Human Assistance: An Argument for\\n Human Subject Studies with HIPPO Gym","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Northern Alberta Institute of Technology","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Human–computer interaction; Subject (documents); World Wide Web","score_opus":0.09487229354682383,"score_gpt":0.2386730474669452,"score_spread":0.14380075392012137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287333197","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":[0.32223746,0.00012057509,0.6741806,0.000033042506,0.00038824126,0.0015526325,0.0000019821834,0.00032908728,0.0011563211],"genre_scores_gemma":[0.9756898,0.000260792,0.008826072,0.000099990124,0.0002251694,0.00003127893,0.00017947963,0.00016287841,0.014524521],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990953,0.00067874446,0.0011968988,0.004330982,0.0008670476,0.0019733051],"domain_scores_gemma":[0.99086386,0.0003456899,0.0026701281,0.003410275,0.0020546778,0.0006553647],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.0016668258,0.0017469149,0.0017773529,0.0007230197,0.003759756,0.0015830233,0.0033068133,0.00052981026,0.000098411016],"category_scores_gemma":[0.000121156736,0.001779191,0.0004986386,0.0015537255,0.0009161659,0.0022409393,0.0033875555,0.0024162624,0.000014373459],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003206404,0.00019955571,0.010466948,0.0011270159,0.0017019052,0.0007115409,0.0046177036,0.94959027,0.00059128087,0.030245792,0.000013879249,0.00041350187],"study_design_scores_gemma":[0.0053363577,0.008024834,0.001690273,0.0024103606,0.0014009277,0.000031073927,0.012884929,0.96307063,0.0012072171,0.0004247963,0.00037571153,0.0031428742],"about_ca_topic_score_codex":0.00043358182,"about_ca_topic_score_gemma":0.0006813187,"teacher_disagreement_score":0.66535455,"about_ca_system_score_codex":0.002435691,"about_ca_system_score_gemma":0.0010683468,"threshold_uncertainty_score":0.9998852},"labels":[],"label_agreement":null},{"id":"W4287647350","doi":"10.48550/arxiv.2010.01062","title":"Exploration in Approximate Hyper-State Space for Meta Reinforcement\\n Learning","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; European Commission; Nvidia; Compute Canada; Microsoft Research","keywords":"Reinforcement learning; Task (project management); Meta learning (computer science); Computer science; State space; Artificial intelligence; Space (punctuation); Machine learning; State (computer science); Mathematics; Engineering; Algorithm","score_opus":0.17159142916653772,"score_gpt":0.2178853611837374,"score_spread":0.046293932017199696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287647350","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":[0.0024398027,0.00003386961,0.99348605,0.0005261427,0.00035185769,0.00093330693,0.0000023444923,0.00037964928,0.001846961],"genre_scores_gemma":[0.9795994,0.00024111033,0.013802103,0.00012531117,0.00004771273,0.000022905333,0.00007177138,0.0000402463,0.0060493997],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975158,0.00018266575,0.00039886034,0.0012119063,0.00017215466,0.0005186408],"domain_scores_gemma":[0.9980658,0.00017464548,0.00054527994,0.00089067494,0.00016379115,0.000159759],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00048968766,0.00043655385,0.0005922994,0.0003704771,0.00017402346,0.00027214843,0.001639546,0.00021046745,0.0000189476],"category_scores_gemma":[0.00016976758,0.0005109712,0.0003324202,0.00072986534,0.000059805745,0.001029591,0.0020097794,0.00088687893,0.000064203276],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038365117,0.0000143899215,0.00024589885,0.00016591765,0.0002139325,0.000044978842,0.00076032296,0.94463754,0.000032592114,0.053601578,0.00011670325,0.00012778265],"study_design_scores_gemma":[0.0006698093,0.00013385953,0.000025186291,0.000053902622,0.0001947273,8.0081486e-7,0.00009896048,0.98416036,0.00022852117,0.011364122,0.0025790704,0.0004906536],"about_ca_topic_score_codex":0.00007724124,"about_ca_topic_score_gemma":0.000013768019,"teacher_disagreement_score":0.97968394,"about_ca_system_score_codex":0.00026570112,"about_ca_system_score_gemma":0.0001749638,"threshold_uncertainty_score":0.99973416},"labels":[],"label_agreement":null},{"id":"W4288047783","doi":"10.1109/icuas54217.2022.9836052","title":"Soft Actor-Critic with Inhibitory Networks for Retraining UAV Controllers Faster","year":2022,"lang":"en","type":"article","venue":"2022 International Conference on Unmanned Aircraft Systems (ICUAS)","topic":"Reinforcement Learning in Robotics","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":"Lockheed Martin (Canada)","funders":"","keywords":"Computer science; Retraining; Distributed computing; Control engineering; Engineering; Business","score_opus":0.030338078660022628,"score_gpt":0.25649256579083246,"score_spread":0.22615448713080982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288047783","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":[0.0016105488,0.000080330494,0.9755118,0.0028228564,0.005953085,0.0011808311,0.000050124065,0.00034597827,0.012444442],"genre_scores_gemma":[0.9868697,0.000007990459,0.00095363427,0.0009751965,0.0004828911,0.0007246283,0.0001267739,0.000051751787,0.009807437],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960177,0.00029311195,0.00070971786,0.0008600665,0.0014687673,0.00065064384],"domain_scores_gemma":[0.99770546,0.00046958204,0.00047419453,0.00066689117,0.0005100227,0.00017384224],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009661343,0.00040147104,0.00046267413,0.00040300813,0.0006142262,0.0006391537,0.0020055026,0.0001074015,0.0003367191],"category_scores_gemma":[0.00013235385,0.00038585332,0.0001495475,0.0003421378,0.00009325768,0.00057541026,0.00049303554,0.0007530651,0.000039163693],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025618388,0.000071824434,0.00041095304,0.0000418433,0.0002451813,0.000048898986,0.0007262789,0.8630658,0.0004026806,0.12651469,0.0074642403,0.0007514481],"study_design_scores_gemma":[0.0020029633,0.0011000081,0.000098049924,0.00017818842,0.000019125113,0.00005504614,0.001277586,0.9765835,0.000026587577,0.00015796564,0.018024357,0.00047665727],"about_ca_topic_score_codex":0.000023276561,"about_ca_topic_score_gemma":0.0000068866493,"teacher_disagreement_score":0.9852592,"about_ca_system_score_codex":0.0005217356,"about_ca_system_score_gemma":0.00028746872,"threshold_uncertainty_score":0.99985933},"labels":[],"label_agreement":null},{"id":"W4289829023","doi":"10.1109/med54222.2022.9837194","title":"Time-delayed Data Transmission in Heterogeneous Multi-agent Deep Reinforcement Learning System","year":2022,"lang":"en","type":"article","venue":"2022 30th Mediterranean Conference on Control and Automation (MED)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Reinforcement; Transmission (telecommunications); Artificial intelligence; Data transmission; Computer network; Telecommunications; Engineering","score_opus":0.03798392676037204,"score_gpt":0.26433006271469006,"score_spread":0.22634613595431802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289829023","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":[0.0027633223,0.000215807,0.99306506,0.0014778913,0.0005903,0.0008666811,0.000011077877,0.0004730325,0.00053680444],"genre_scores_gemma":[0.9962303,0.000050505663,0.0018078819,0.0004164685,0.00006566775,0.00014114701,0.00032111397,0.000025440135,0.0009414588],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960756,0.0006755859,0.0008017832,0.0008222908,0.0011190911,0.0005056913],"domain_scores_gemma":[0.99822766,0.00021380401,0.0004038381,0.0008650815,0.00007906045,0.00021058184],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001366568,0.0003332893,0.0004402297,0.0003516326,0.00057851267,0.00025564933,0.0014318567,0.00008459315,0.00044309485],"category_scores_gemma":[0.00006992005,0.00032282964,0.00006364247,0.00035092453,0.00006437739,0.0005072669,0.0005620095,0.0006408913,0.00007064196],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007591296,0.00005355109,0.000030528536,0.00006467469,0.000049749116,0.00008119876,0.00232594,0.9479647,0.0008159896,0.00063469505,0.00018399843,0.04771901],"study_design_scores_gemma":[0.0029910114,0.0005740041,0.00016782373,0.000099591765,0.000026294087,0.000047804802,0.00038696412,0.990801,0.000033849476,0.000009412262,0.0045264508,0.00033582948],"about_ca_topic_score_codex":0.000031279258,"about_ca_topic_score_gemma":0.0000066306234,"teacher_disagreement_score":0.993467,"about_ca_system_score_codex":0.00023830392,"about_ca_system_score_gemma":0.00014895914,"threshold_uncertainty_score":0.9999224},"labels":[],"label_agreement":null},{"id":"W4291821302","doi":"10.32470/ccn.2022.1229-0","title":"Continual Reinforcement Learning with Multi-Timescale Successor Features","year":2022,"lang":"en","type":"article","venue":"2022 Conference on Cognitive Computational Neuroscience","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Successor cardinal; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Engineering; Structural engineering; Mathematics","score_opus":0.0353669370020116,"score_gpt":0.2839279176125578,"score_spread":0.2485609806105462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291821302","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":[0.008372466,0.0000149923135,0.98468894,0.0008527588,0.00046995483,0.0005150656,0.000011561294,0.00025864152,0.0048155943],"genre_scores_gemma":[0.98625106,0.0000071393856,0.004809146,0.002640358,0.000024212952,0.0001500184,0.00005188357,0.000020088133,0.006046088],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958309,0.00038810726,0.0003467231,0.000995059,0.0018823597,0.0005568629],"domain_scores_gemma":[0.998201,0.00049930264,0.00035914927,0.0002689478,0.00049559784,0.00017599917],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0004727086,0.00031410973,0.00024895213,0.00030887694,0.001560275,0.00050088635,0.001391929,0.000030589305,0.00023551116],"category_scores_gemma":[0.00032409476,0.0003015963,0.00007079392,0.0011309704,0.0003162814,0.00061334507,0.0010029285,0.00092615094,0.000049753962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006603684,0.00009633431,0.0008794645,0.0000066801904,0.0000086041655,0.00007264468,0.000500937,0.96410096,0.00034887737,0.031366143,0.0001559901,0.0023973554],"study_design_scores_gemma":[0.0012426419,0.0017639898,0.012734469,0.00004020872,0.000009023957,0.00008289801,0.0003583936,0.98205,0.00025591758,0.00022548158,0.0008181431,0.00041883186],"about_ca_topic_score_codex":0.0000124495555,"about_ca_topic_score_gemma":0.0000019157449,"teacher_disagreement_score":0.9798798,"about_ca_system_score_codex":0.00010819723,"about_ca_system_score_gemma":0.00046391977,"threshold_uncertainty_score":0.9999436},"labels":[],"label_agreement":null},{"id":"W4293155040","doi":"","title":"Dynamic Programming in Distributional Reinforcement Learning","year":2020,"lang":"en","type":"report","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Dynamic programming; Artificial intelligence; Psychology; Algorithm; Social psychology","score_opus":0.01766060272860948,"score_gpt":0.252790648297136,"score_spread":0.2351300455685265,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293155040","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":[0.00018205374,0.00036103063,0.9095304,0.004612946,0.00031764008,0.0004949332,0.000005170303,0.00042927777,0.08406655],"genre_scores_gemma":[0.81322694,0.0015180976,0.13508351,0.00009284415,0.000047014633,0.00016846678,0.0024046607,0.0001015441,0.047356896],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929319,0.00256984,0.0010531441,0.0010481784,0.0017162451,0.0006806925],"domain_scores_gemma":[0.99381804,0.0010221854,0.0009883047,0.0016118357,0.0023098206,0.0002498026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.006901232,0.00046636874,0.00053906237,0.00031815915,0.0003888571,0.0007725556,0.002394274,0.00033295655,0.00008297304],"category_scores_gemma":[0.004938642,0.0005275152,0.0002475942,0.001117257,0.0001619701,0.00039036182,0.0016965324,0.0015020677,0.00010689039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029624556,0.000827661,0.021352362,0.0016602838,0.00049555243,0.00020898455,0.016925836,0.41479334,0.0006161073,0.24896833,0.00638615,0.28773576],"study_design_scores_gemma":[0.00048400444,0.0000018025572,0.0025249796,0.0017543308,0.000024277271,0.000032219607,0.00004572445,0.7514139,0.00050246215,0.00018635679,0.24238932,0.0006406295],"about_ca_topic_score_codex":0.000525552,"about_ca_topic_score_gemma":0.00031513948,"teacher_disagreement_score":0.8130449,"about_ca_system_score_codex":0.000963141,"about_ca_system_score_gemma":0.0014696982,"threshold_uncertainty_score":0.99971765},"labels":[],"label_agreement":null},{"id":"W4293370597","doi":"10.1109/lra.2022.3196132","title":"Safe-Control-Gym: A Unified Benchmark Suite for Safe Learning-Based Control and Reinforcement Learning in Robotics","year":2022,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dynamic Systems Analysis (Canada); Vector Institute; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Suite; Benchmark (surveying); Machine learning","score_opus":0.009230860443678211,"score_gpt":0.22130848297750758,"score_spread":0.21207762253382936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293370597","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":[0.006357235,0.000059659164,0.9805166,0.0113608,0.00046868427,0.0009226509,0.0000026679706,0.00020757006,0.00010410149],"genre_scores_gemma":[0.9711221,0.000015913529,0.024365302,0.0038949717,0.00006247828,0.00011565884,0.0000467332,0.00003474267,0.0003420866],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971209,0.00035532887,0.0007372752,0.0005660666,0.0005966036,0.0006238142],"domain_scores_gemma":[0.99814206,0.00078672497,0.000499915,0.00033738127,0.000089223875,0.0001446706],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012693545,0.0003365871,0.00044657534,0.00044672488,0.00079884665,0.00037808117,0.00044006683,0.000086750006,0.000014673877],"category_scores_gemma":[0.00018286853,0.00037684862,0.00009875868,0.00043899115,0.000089863985,0.00039786275,0.000115323186,0.0006451203,0.000004103025],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049495942,0.000024409856,0.0031993156,0.00007543294,0.00004018018,0.000012237522,0.00039852908,0.9892525,0.0014961001,0.004204102,0.00028439375,0.00096327404],"study_design_scores_gemma":[0.004472965,0.00047512102,0.0027374423,0.000041545696,0.000043595206,0.000009637048,0.00005664865,0.98931646,0.000042510226,0.00007070688,0.0023164677,0.000416904],"about_ca_topic_score_codex":0.000025745263,"about_ca_topic_score_gemma":0.0000043453892,"teacher_disagreement_score":0.9647649,"about_ca_system_score_codex":0.00022912427,"about_ca_system_score_gemma":0.000110097855,"threshold_uncertainty_score":0.99986833},"labels":[],"label_agreement":null},{"id":"W4293863172","doi":"10.1109/siu55565.2022.9864806","title":"Autonomous Driving Systems for Decision-Making Under Uncertainty Using Deep Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Reinforcement Learning in Robotics","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":"Stantec (Canada)","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Markov decision process; Computer science; Artificial intelligence; Action (physics); Process (computing); Observable; Control (management); Markov process; State (computer science); Autonomous agent; Markov chain; Machine learning; Markov model; Mathematics","score_opus":0.04014414957858934,"score_gpt":0.30787330434500143,"score_spread":0.26772915476641207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863172","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":[0.00041287037,0.0019066937,0.9946258,0.000423363,0.00006138229,0.001061835,0.0000029810406,0.00029620196,0.0012088435],"genre_scores_gemma":[0.9201249,0.00015811443,0.07715924,0.00014484553,0.000035024525,0.0019546454,0.00005779444,0.000031058516,0.00033436573],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99746746,0.0001903823,0.00073287357,0.0006167292,0.0005237685,0.00046880374],"domain_scores_gemma":[0.99630743,0.0009793433,0.00066440617,0.0014787823,0.00044812457,0.00012192547],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010381412,0.00027783986,0.00030959418,0.0003051674,0.0055230036,0.0009815549,0.002644013,0.0000741308,0.00004476012],"category_scores_gemma":[0.000069371934,0.00031515607,0.00008074404,0.00094930956,0.00019123302,0.00052234886,0.0021554944,0.000700154,0.0000050080153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053184785,0.00003820801,0.00009321538,0.000039882016,0.000023265746,2.2489297e-7,0.00073146087,0.8440272,0.0001470946,0.06744343,0.000021173757,0.087429516],"study_design_scores_gemma":[0.00023072844,0.00009389446,0.00003388359,0.00012696031,0.00004260358,0.000027311298,0.0028696798,0.97778064,0.000004523553,0.0030596917,0.015369523,0.00036056238],"about_ca_topic_score_codex":0.0000477275,"about_ca_topic_score_gemma":0.0000074380637,"teacher_disagreement_score":0.91971207,"about_ca_system_score_codex":0.00040888393,"about_ca_system_score_gemma":0.00060330366,"threshold_uncertainty_score":0.99993},"labels":[],"label_agreement":null},{"id":"W4293863350","doi":"10.1109/siu55565.2022.9864802","title":"Context Detection and Identification In Multi-Agent Reinforcement Learning With Non-Stationary Environment","year":2022,"lang":"en","type":"article","venue":"2022 30th Signal Processing and Communications Applications Conference (SIU)","topic":"Reinforcement Learning in Robotics","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":"Stantec (Canada)","funders":"","keywords":"Reinforcement learning; Identification (biology); Context (archaeology); Computer science; Artificial intelligence; Machine learning; Geography","score_opus":0.03048400050106643,"score_gpt":0.2569068097743107,"score_spread":0.22642280927324426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293863350","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":[0.002433132,0.0007042895,0.9946866,0.00081032695,0.000010499041,0.00075706234,0.0000022018496,0.00009196537,0.0005039439],"genre_scores_gemma":[0.98168653,0.00051348493,0.014408539,0.00010794784,0.0000059050394,0.002420731,0.00008426453,0.000015702039,0.00075690873],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827343,0.00015793288,0.00047693378,0.00048285135,0.00037881368,0.00023003232],"domain_scores_gemma":[0.9984781,0.00011829618,0.0003905073,0.00081533723,0.00011372316,0.00008404811],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00058261846,0.00018550662,0.00016718937,0.0002602357,0.0018275611,0.00030669163,0.0008929551,0.000041318995,0.000032309483],"category_scores_gemma":[0.000008990343,0.00020253085,0.000020404159,0.0005709344,0.00021288404,0.00048612544,0.0008932892,0.00057736353,0.000009711226],"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":[0.00002329378,0.00022845017,0.0022707542,0.0000750825,0.000029198023,0.0000013206459,0.0055631814,0.44308996,0.0041642142,0.012487125,0.000010174652,0.5320572],"study_design_scores_gemma":[0.00054192205,0.00014624481,0.0041368227,0.000028551418,0.000018450322,0.000017245015,0.0033585215,0.9830806,0.00017313405,0.00027125303,0.007976592,0.00025064553],"about_ca_topic_score_codex":0.00006653631,"about_ca_topic_score_gemma":0.000026066216,"teacher_disagreement_score":0.980278,"about_ca_system_score_codex":0.00018866271,"about_ca_system_score_gemma":0.00015477651,"threshold_uncertainty_score":0.9994719},"labels":[],"label_agreement":null},{"id":"W4294912101","doi":"10.36227/techrxiv.14842245.v2","title":"Safe Deployment of a Reinforcement Learning Robot Using Self Stabilization","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","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; Software deployment; Robot; Robotics; Computer science; State space; Artificial intelligence; Simulation; Human–computer interaction; Software engineering; Mathematics","score_opus":0.037504982322837374,"score_gpt":0.286013155198828,"score_spread":0.24850817287599059,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294912101","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":[0.0023313747,0.00006212622,0.9874425,0.00008516848,0.0009072704,0.00077235926,5.1636556e-7,0.00050392165,0.007894778],"genre_scores_gemma":[0.578265,0.00015695089,0.4184684,0.00012000218,0.000061010058,0.00006633573,0.0000590601,0.000058968948,0.0027442577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99599814,0.00030788657,0.0011657325,0.00076081813,0.0013165954,0.00045082538],"domain_scores_gemma":[0.99704933,0.00012110384,0.0011706147,0.0013183625,0.00023355964,0.000107026484],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001045085,0.00039077824,0.0004952146,0.00038306258,0.0002659507,0.00020687169,0.0016893424,0.00017123565,0.0007181141],"category_scores_gemma":[0.00012274756,0.00041860316,0.00020822696,0.0004813871,0.00003609479,0.00027976726,0.00679748,0.0009616518,0.000011284052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006085351,0.000033517783,0.0015460665,0.00023606613,0.00008165665,0.0000038180774,0.0013497456,0.98756826,0.00027234224,0.008348975,0.00003826245,0.000515234],"study_design_scores_gemma":[0.0002720501,0.0001993341,0.00014564474,0.00009342626,0.000047443347,0.000003451373,0.00010648497,0.9940839,0.00093017175,0.00013385293,0.003578896,0.00040534264],"about_ca_topic_score_codex":0.00019909747,"about_ca_topic_score_gemma":0.0000025772445,"teacher_disagreement_score":0.57593364,"about_ca_system_score_codex":0.00080657465,"about_ca_system_score_gemma":0.0005492633,"threshold_uncertainty_score":0.99982655},"labels":[],"label_agreement":null},{"id":"W4295308610","doi":"10.1109/access.2022.3206035","title":"On Meeting a Maximum Delay Constraint Using Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"Telefonaktiebolaget LM Ericsson","keywords":"Reinforcement learning; Computer science; Constraint (computer-aided design); Reinforcement; Mathematical optimization; Artificial intelligence; Mathematics; Engineering","score_opus":0.04462453885572762,"score_gpt":0.30320423508470057,"score_spread":0.2585796962289729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295308610","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":[0.05583293,0.000015515863,0.93008065,0.00012556915,0.0011342017,0.00024291784,3.8200798e-7,0.00026352072,0.012304287],"genre_scores_gemma":[0.99248314,0.000002563786,0.0058601513,0.0011519563,0.00006774222,0.00003231662,0.0000032364594,0.000022987913,0.0003759024],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975454,0.00019976865,0.00041419565,0.00045627684,0.0008658175,0.0005185067],"domain_scores_gemma":[0.9987558,0.00021032392,0.00033620815,0.00053631543,0.00006886627,0.00009249783],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00076912803,0.00020606557,0.00019569583,0.00023865768,0.00097478175,0.0005181695,0.0018741903,0.000038104197,0.0001809258],"category_scores_gemma":[0.00010695748,0.00022254666,0.000088290195,0.0005777285,0.000049672577,0.0005971101,0.001166331,0.0006555068,0.00003398574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009313634,0.000014361721,0.00047435358,0.000010285593,0.000023232838,0.00005963385,0.00042386583,0.9906636,0.00053539715,0.005656942,0.00019618351,0.0019328463],"study_design_scores_gemma":[0.00038255577,0.000221544,0.000027480704,0.000033531407,0.000008867919,0.000051971434,0.00009117066,0.9937512,0.0012550139,0.00052410853,0.003367606,0.00028490435],"about_ca_topic_score_codex":0.00008800697,"about_ca_topic_score_gemma":8.335467e-7,"teacher_disagreement_score":0.9366502,"about_ca_system_score_codex":0.0003343554,"about_ca_system_score_gemma":0.00013694432,"threshold_uncertainty_score":0.907519},"labels":[],"label_agreement":null},{"id":"W4295683034","doi":"10.1016/j.neunet.2025.108521","title":"Multi-step first: A lightweight deep reinforcement learning strategy for robust continuous control with partial observability","year":2025,"lang":"en","type":"preprint","venue":"Neural Networks","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"Social Sciences and Humanities Research Council of Canada; Australian Research Council; Alliance de recherche numérique du Canada","keywords":"Observability; Robot; Computer science; State space; Robustness (evolution); Control theory (sociology); Reinforcement learning; Control (management); Control engineering; Artificial intelligence; Engineering; Mathematics","score_opus":0.03587578380555461,"score_gpt":0.2609447892771726,"score_spread":0.22506900547161796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295683034","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":[0.0004921224,0.00035448594,0.99231625,0.00063053455,0.0019251783,0.0032584341,0.0000043754135,0.00065910944,0.00035951473],"genre_scores_gemma":[0.9000752,0.00007405749,0.094412886,0.0006375952,0.0006735087,0.000916925,0.00017504144,0.00006695401,0.0029678654],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948481,0.00032559858,0.0012070886,0.0016400478,0.0006592483,0.0013199673],"domain_scores_gemma":[0.9955852,0.0008813626,0.0010070443,0.0017073168,0.0005316913,0.00028737215],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007328078,0.0009199518,0.0011706161,0.00014091545,0.0006220332,0.0009403568,0.002302142,0.00072035665,0.000027150762],"category_scores_gemma":[0.00020271726,0.00079654995,0.00044380172,0.00035693398,0.00015540134,0.00037532544,0.0014325661,0.0023397047,0.000005393163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023281584,0.000054944416,0.00418643,0.00027905664,0.00022712525,0.000024685352,0.00019107683,0.98929125,9.1695074e-7,0.0006298789,0.0003573725,0.0045244545],"study_design_scores_gemma":[0.002976884,0.0008143194,0.00063696306,0.00031726528,0.00016847136,0.000006431632,0.00002287929,0.99104035,0.000010193249,0.000016790136,0.0031797201,0.0008097091],"about_ca_topic_score_codex":0.00012809112,"about_ca_topic_score_gemma":0.0001619552,"teacher_disagreement_score":0.89958304,"about_ca_system_score_codex":0.0002689924,"about_ca_system_score_gemma":0.00024574963,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W4296182512","doi":"10.31234/osf.io/z8yrv","title":"Action chunking as conditional policy compression","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Office of Naval Research; National Science Foundation","keywords":"Chunking (psychology); Action (physics); Compression (physics); Computer science; Econometrics; Natural language processing; Artificial intelligence; Economics","score_opus":0.055071456781607964,"score_gpt":0.3614701003934595,"score_spread":0.30639864361185154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296182512","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":[0.0005790429,0.000015860678,0.9118388,0.0017299915,0.0014263293,0.00021774638,0.0000029499327,0.00048281281,0.08370646],"genre_scores_gemma":[0.8842698,0.00007955931,0.08190945,0.002766287,0.0008721317,0.00012771397,0.0006081457,0.000041367657,0.0293256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979367,0.00012676296,0.00030084327,0.0005350529,0.0008327972,0.0002678249],"domain_scores_gemma":[0.99859774,0.0001063768,0.00030695117,0.0008339304,0.00007118459,0.00008379379],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023281157,0.00021552753,0.00019494261,0.00033678018,0.0003417966,0.00037102445,0.0015346877,0.00014663879,0.0017864446],"category_scores_gemma":[0.00007780298,0.00022151992,0.0001220217,0.00023645353,0.00003290221,0.00027515407,0.0053006955,0.0009855522,0.00019948723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019723648,0.000013411742,0.00009471386,0.00002816828,0.00002025622,0.000006134413,0.00013563866,0.81933916,0.0001244639,0.17641474,0.002651761,0.0011695973],"study_design_scores_gemma":[0.00023757732,0.000060548384,0.0019524577,0.00006208791,0.00000867974,0.000027876407,0.000045751654,0.90817094,0.00050785154,0.029498016,0.058991663,0.0004365267],"about_ca_topic_score_codex":0.00026134623,"about_ca_topic_score_gemma":0.0000010665846,"teacher_disagreement_score":0.8836907,"about_ca_system_score_codex":0.0003851485,"about_ca_system_score_gemma":0.0004982696,"threshold_uncertainty_score":0.9991261},"labels":[],"label_agreement":null},{"id":"W4296474750","doi":"10.1109/cog51982.2022.9893546","title":"Mitigating Cowardice for Reinforcement Learning Agents in Combat Scenarios","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Cowardice; Reinforcement learning; Computer science; Reinforcement; Computer security; Artificial intelligence; Engineering; Geography","score_opus":0.037629556357336454,"score_gpt":0.28277255263449574,"score_spread":0.2451429962771593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4296474750","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":[0.0059100557,0.000016276921,0.982662,0.00059640757,0.0004000473,0.0005776958,3.0194633e-7,0.00020932037,0.009627848],"genre_scores_gemma":[0.95851004,0.0000034333266,0.031828847,0.0011468999,0.000025514819,0.00019284381,0.000020648307,0.000017233293,0.008254519],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803305,0.00012849511,0.00042758224,0.00036375818,0.0005673162,0.00047978392],"domain_scores_gemma":[0.99910283,0.00022878076,0.00018221096,0.00036072935,0.000050128812,0.00007532366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009414246,0.00014810576,0.00018400763,0.0001813447,0.0005592041,0.00014152072,0.0009479527,0.000029049555,0.00019166045],"category_scores_gemma":[0.00017185848,0.00016380892,0.0000808798,0.00047115338,0.000021105567,0.0003100283,0.0010345869,0.00041020222,0.00002458661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005786607,0.000014871976,0.0032584714,0.000018651494,0.000011315758,0.0000069369275,0.0010279428,0.9791692,0.00008964579,0.013727489,0.0011097565,0.0015599506],"study_design_scores_gemma":[0.00087249704,0.00028696522,0.00052108424,0.000014848029,0.00000331276,0.000006166139,0.0004176935,0.97356004,0.00015126218,0.000119266144,0.023845887,0.0002009753],"about_ca_topic_score_codex":0.0000724142,"about_ca_topic_score_gemma":0.0000031341237,"teacher_disagreement_score":0.9526,"about_ca_system_score_codex":0.00027212274,"about_ca_system_score_gemma":0.00008415439,"threshold_uncertainty_score":0.66799337},"labels":[],"label_agreement":null},{"id":"W4297822508","doi":"10.48550/arxiv.2103.02142","title":"Learning to Fly -- a Gym Environment with PyBullet Physics for\\n Reinforcement Learning of Multi-agent Quadcopter Control","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; Institute for Christian Studies; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Software portability; Artificial intelligence; Human–computer interaction; Physics engine; Machine learning; Operating system","score_opus":0.05253152417695468,"score_gpt":0.18862842276405678,"score_spread":0.1360968985871021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297822508","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":[0.049551085,0.000059044793,0.9465839,0.00011765195,0.00049459597,0.0025590456,0.000005904732,0.00015714196,0.00047162644],"genre_scores_gemma":[0.9626438,0.0003349516,0.023690091,0.00021930068,0.00013530087,0.000026232681,0.000075644144,0.00012350082,0.012751164],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99293315,0.00068267726,0.001230454,0.0029128627,0.0007208926,0.001519943],"domain_scores_gemma":[0.9937513,0.0005940889,0.0020414866,0.0021895682,0.00072708575,0.0006965106],"candidate_categories":["metaepi_narrow"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.001094421,0.0013054152,0.0016300458,0.00042731455,0.00082080706,0.00042804057,0.002465639,0.00050535647,0.00024991774],"category_scores_gemma":[0.00022233419,0.0015162181,0.00083834,0.00088300946,0.0003789869,0.0006267671,0.0031461206,0.0020550825,0.00018329783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005316378,0.00027003128,0.007318414,0.0004925147,0.0011052842,0.00018761875,0.005734474,0.9788123,0.00033939938,0.0037571776,0.000021655656,0.0014295004],"study_design_scores_gemma":[0.005500058,0.003023725,0.00064247224,0.00089179777,0.0006575925,0.000007002764,0.0022248493,0.9808536,0.00075246225,0.00002443494,0.0038778642,0.0015441069],"about_ca_topic_score_codex":0.00019716806,"about_ca_topic_score_gemma":0.000009518834,"teacher_disagreement_score":0.9228938,"about_ca_system_score_codex":0.0011892896,"about_ca_system_score_gemma":0.00066854176,"threshold_uncertainty_score":0.9999697},"labels":[],"label_agreement":null},{"id":"W4297848563","doi":"10.48550/arxiv.2001.06627","title":"Multi-agent Motion Planning for Dense and Dynamic Environments via Deep\\n Reinforcement Learning","year":2020,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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; Toronto Metropolitan University","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Motion planning; Mathematical optimization; Artificial intelligence; Collision; Path (computing); Simple (philosophy); Algorithm; Mathematics; Robot","score_opus":0.0764126386328068,"score_gpt":0.2122913612488068,"score_spread":0.13587872261599998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297848563","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":[0.020620642,0.00012064589,0.97611904,0.00013839443,0.0008911431,0.0017829767,0.0000029135151,0.00019771195,0.00012653413],"genre_scores_gemma":[0.9759098,0.0007163786,0.01759277,0.00019574813,0.00007378008,0.000008302699,0.00012980192,0.00008597682,0.0052874377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946588,0.00035507887,0.00084269774,0.002685486,0.0003523841,0.0011055429],"domain_scores_gemma":[0.99644077,0.0003039076,0.0012924246,0.0011676335,0.00015302215,0.0006422664],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063303387,0.0009939821,0.00081007206,0.00042143784,0.0010731047,0.00040871373,0.0016750258,0.000578368,0.00005018304],"category_scores_gemma":[0.00023438985,0.0013270072,0.00040965513,0.00048800567,0.00030803794,0.00080904056,0.003932336,0.0015263833,0.00017511229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015656326,0.00006929905,0.003228704,0.00034326513,0.00036390606,0.00021147353,0.0024655473,0.9895827,0.0008129154,0.0010996906,0.000010347153,0.0016555629],"study_design_scores_gemma":[0.0025995744,0.00061073044,0.0029719784,0.0002854501,0.00038818404,0.00001336665,0.00049836474,0.98990285,0.000112603135,0.00032017234,0.0011255649,0.0011711378],"about_ca_topic_score_codex":0.00003839175,"about_ca_topic_score_gemma":0.000004004645,"teacher_disagreement_score":0.95852625,"about_ca_system_score_codex":0.0010933139,"about_ca_system_score_gemma":0.00012242267,"threshold_uncertainty_score":0.99891794},"labels":[],"label_agreement":null},{"id":"W4298364546","doi":"","title":"A robot to study the development of artwork appreciation through social interactions","year":2013,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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":"NeuroDevNet","funders":"","keywords":"Robot; Human–computer interaction; Computer science; Artificial intelligence","score_opus":0.027332943354547532,"score_gpt":0.2639089202192305,"score_spread":0.23657597686468299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4298364546","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":[0.057190366,0.000011381431,0.9225257,0.006861799,0.00013568059,0.0005659499,3.5979113e-7,0.00010000892,0.0126087265],"genre_scores_gemma":[0.77783257,0.000001859076,0.21983834,0.00009147683,0.000011646521,0.00009809731,0.0000068306686,0.000008942007,0.002110219],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968797,0.0017151805,0.00046670806,0.00030254282,0.00041275783,0.00022309984],"domain_scores_gemma":[0.9967969,0.0007886921,0.0003081348,0.0009381246,0.0011110983,0.00005704269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022379092,0.00013211824,0.00014834247,0.00007691871,0.00063205644,0.00031976154,0.0013457757,0.000036763657,0.00007631515],"category_scores_gemma":[0.000492892,0.00011211539,0.000060696184,0.00069414894,0.000053125023,0.00042058877,0.00069677905,0.00018984656,0.00014160875],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007758952,0.00157593,0.006699909,0.00002804753,0.00026984102,7.0516313e-7,0.5570228,0.023868008,0.0057458393,0.15033622,0.0029822567,0.25146267],"study_design_scores_gemma":[0.0020863225,0.000008120979,0.38171622,0.0006497661,0.000083122024,0.000009632338,0.008298941,0.45186958,0.102040894,0.0056763776,0.04620123,0.0013597677],"about_ca_topic_score_codex":0.00018132199,"about_ca_topic_score_gemma":0.00033763688,"teacher_disagreement_score":0.7206422,"about_ca_system_score_codex":0.00007689162,"about_ca_system_score_gemma":0.00010111955,"threshold_uncertainty_score":0.4861331},"labels":[],"label_agreement":null},{"id":"W4300126582","doi":"10.48550/arxiv.2005.06223","title":"DREAM Architecture: a Developmental Approach to Open-Ended Learning in\\n Robotics","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Animal Health Institute","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Robot; Flexibility (engineering); Task (project management); Adaptation (eye); Robotics; Cognitive architecture; Architecture; Robot learning; Restructuring; Behavior-based robotics; Scale (ratio); Human–computer interaction; Cognition; Engineering; Mobile robot; Psychology; Mathematics","score_opus":0.09995570773760962,"score_gpt":0.20679875872831407,"score_spread":0.10684305099070446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300126582","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":[0.004154614,0.0000074950226,0.9613786,0.00036450438,0.00030010732,0.00087022304,0.0000016653693,0.00034366993,0.032579154],"genre_scores_gemma":[0.8134565,0.00001833552,0.18374245,0.0003683032,0.000042464242,0.0000034725788,0.00003393551,0.000035294634,0.0022992617],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996748,0.00026428438,0.00038740304,0.0017387075,0.00022517728,0.00063648476],"domain_scores_gemma":[0.99824667,0.00011224509,0.0002908377,0.00087428273,0.000094744406,0.00038121064],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00036064035,0.00050430733,0.0005746433,0.00048587602,0.00020834587,0.0005912705,0.0058939126,0.00030964185,0.000008598301],"category_scores_gemma":[0.00017335506,0.00062237,0.00014285871,0.0015264977,0.00007149539,0.0003663939,0.014325249,0.0019887914,0.00017413283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028508159,0.00006920225,0.0015492531,0.00006882879,0.00006488238,0.00017341106,0.0014899311,0.93675953,0.000030627645,0.059217658,0.00015019964,0.00039794674],"study_design_scores_gemma":[0.0006758102,0.00009808532,0.0014140097,0.00011436312,0.000025362306,0.000011687569,0.0002112863,0.9913438,0.00003651702,0.0040990068,0.0011935481,0.00077655184],"about_ca_topic_score_codex":0.000113761685,"about_ca_topic_score_gemma":0.000019672347,"teacher_disagreement_score":0.80930185,"about_ca_system_score_codex":0.00061349466,"about_ca_system_score_gemma":0.0006583902,"threshold_uncertainty_score":0.99962276},"labels":[],"label_agreement":null},{"id":"W4300362000","doi":"10.48550/arxiv.1712.02441","title":"A Novel Model for Arbitration between Planning and Habitual Control\\n Systems","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Action selection; Reinforcement learning; Internal model; Task (project management); Control (management); Action (physics); Artificial intelligence; Kinematics; A priori and a posteriori; Machine learning; Human–computer interaction; Engineering","score_opus":0.15153388522042371,"score_gpt":0.22919272519554015,"score_spread":0.07765883997511644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300362000","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":[0.01113234,0.000045036315,0.9867875,0.000052129402,0.00037489727,0.0006474779,0.00003056821,0.0001562928,0.000773735],"genre_scores_gemma":[0.9897744,0.000009379835,0.008588139,0.000036325262,0.00012779699,0.0000030740132,0.000026154428,0.000017269414,0.0014174606],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985144,0.000041381965,0.00022500004,0.0007961997,0.00010406244,0.00031894128],"domain_scores_gemma":[0.9980156,0.00021284007,0.00052733533,0.0009454853,0.00016812905,0.00013061202],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041361203,0.00027118804,0.00039457052,0.00017174902,0.00037415285,0.00052530755,0.0013048295,0.0003053455,2.5936163e-7],"category_scores_gemma":[0.00008317624,0.00031965197,0.00011176266,0.00006127021,0.00009190467,0.00051309424,0.00079392863,0.0004211775,0.000003841885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013968233,0.000007736996,0.0027362893,0.00010619542,0.00008928406,0.000008247614,0.00024982975,0.9290528,0.000022967342,0.0676383,0.000045788664,0.000028557066],"study_design_scores_gemma":[0.0010355023,0.000057237874,0.00071363297,0.00016739655,0.00010387681,0.0000020076698,0.000020309339,0.9951081,0.0000053162457,0.0023923013,0.00006197126,0.00033234654],"about_ca_topic_score_codex":0.000057326808,"about_ca_topic_score_gemma":0.000002865647,"teacher_disagreement_score":0.97864205,"about_ca_system_score_codex":0.00011656081,"about_ca_system_score_gemma":0.00019743964,"threshold_uncertainty_score":0.99992555},"labels":[],"label_agreement":null},{"id":"W4301808900","doi":"10.48550/arxiv.2011.04118","title":"Joint Estimation of Expertise and Reward Preferences From Human Demonstrations","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Inference; Leverage (statistics); Robot; Computer science; Set (abstract data type); Artificial intelligence; Function (biology); Human–robot interaction; Machine learning; Human–computer interaction; Space (punctuation)","score_opus":0.14989913086949452,"score_gpt":0.21265690373065238,"score_spread":0.06275777286115786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301808900","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":[0.23081666,0.000020989813,0.7677718,0.000094498595,0.00012304878,0.00014704315,0.000005515902,0.00010092658,0.0009195272],"genre_scores_gemma":[0.9801653,0.000056752484,0.01958294,0.000022872526,0.000021679201,6.618292e-7,0.000032046883,0.000006612516,0.00011110921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988484,0.00008788906,0.00025267017,0.00058494735,0.000096983844,0.00012913308],"domain_scores_gemma":[0.99883276,0.000060133516,0.0003513427,0.00057703257,0.00007711314,0.000101597216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007958702,0.0001752847,0.0002509505,0.00011658962,0.00011584994,0.00010375542,0.0007033638,0.0001480741,0.000016913284],"category_scores_gemma":[0.000056788314,0.00020340476,0.000073497,0.0001961223,0.00011984391,0.00031667354,0.0010908158,0.0002981948,0.000010960605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031605352,0.000013804885,0.0017215357,0.00004003431,0.00004540665,0.000013687863,0.0008007613,0.9538656,0.00026217598,0.042737316,0.000045224817,0.0004512886],"study_design_scores_gemma":[0.00017059052,0.00006270996,0.005697495,0.000112907976,0.00004459648,3.4195227e-7,0.00006535621,0.96453935,0.0005316202,0.028576113,0.000009884115,0.00018904121],"about_ca_topic_score_codex":0.0003166578,"about_ca_topic_score_gemma":0.000019947187,"teacher_disagreement_score":0.74934864,"about_ca_system_score_codex":0.000058668687,"about_ca_system_score_gemma":0.00010524533,"threshold_uncertainty_score":0.82946056},"labels":[],"label_agreement":null},{"id":"W4302917494","doi":"10.48550/arxiv.1806.06161","title":"BaRC: Backward Reachability Curriculum for Robotic Reinforcement\\n Learning","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Toyota Research Institute","keywords":"Reinforcement learning; Computer science; Leverage (statistics); Bottleneck; Reachability; Prior probability; Flexibility (engineering); Artificial intelligence; Optimal control; Curriculum; Mathematical optimization; Machine learning; Bayesian probability; Theoretical computer science; Mathematics","score_opus":0.06339507954544266,"score_gpt":0.21067285721099221,"score_spread":0.14727777766554956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302917494","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":[0.009523658,0.000023459945,0.9812831,0.000113540336,0.0015809655,0.0010998675,0.0000015712538,0.0006622817,0.00571151],"genre_scores_gemma":[0.97133696,0.00008242089,0.015979419,0.000095712145,0.00025807007,0.000007884392,0.00007965478,0.000049950675,0.0121099325],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960981,0.00027919823,0.0005507282,0.0018930766,0.0002618302,0.0009170566],"domain_scores_gemma":[0.9957428,0.0002989427,0.00072723284,0.0022862465,0.0006274197,0.00031735282],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009659015,0.000623202,0.00065518083,0.00036130194,0.0005116225,0.0003363629,0.0033429533,0.000513152,0.00009444075],"category_scores_gemma":[0.00047873854,0.00072823215,0.0005281841,0.00065575744,0.0002810368,0.00065397413,0.004076254,0.0011830422,0.00029893755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020049898,0.000041216827,0.004128111,0.00023357253,0.00011960844,0.000023161054,0.00020313343,0.9495648,0.000006594971,0.044585213,0.0008955518,0.00017899428],"study_design_scores_gemma":[0.00065806165,0.00035927046,0.00030141763,0.00016584389,0.00011766316,0.0000031895227,0.00007141081,0.9875356,0.000046235582,0.0058856215,0.004092628,0.0007630402],"about_ca_topic_score_codex":0.00015473805,"about_ca_topic_score_gemma":0.00000966798,"teacher_disagreement_score":0.9653037,"about_ca_system_score_codex":0.00061131624,"about_ca_system_score_gemma":0.0003360177,"threshold_uncertainty_score":0.9995169},"labels":[],"label_agreement":null},{"id":"W4306167947","doi":"10.1109/tpami.2022.3213503","title":"Robust Losses for Learning Value Functions","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; University of Alberta","funders":"","keywords":"Reinforcement learning; Mean squared error; Outlier; Clipping (morphology); Computer science; Bellman equation; Variance (accounting); Mathematical optimization; Robust statistics; Function (biology); Robust control; Sensitivity (control systems); Robust regression; Robustness (evolution); Mathematics; Artificial intelligence; Statistics; Control system","score_opus":0.03400760162769441,"score_gpt":0.26375318575433804,"score_spread":0.22974558412664364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306167947","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":[0.0004171278,0.00005018211,0.9982578,0.00044225887,0.00037131942,0.0001771637,0.000023710241,0.00014377607,0.00011663146],"genre_scores_gemma":[0.9916115,0.000068547044,0.0049805418,0.00035532395,0.000018904477,0.000120130826,0.000015287607,0.000014599037,0.0028151812],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841356,0.00013182034,0.00033987695,0.0005032068,0.00034484442,0.0002666619],"domain_scores_gemma":[0.99900025,0.00030100968,0.00013410604,0.0004051386,0.000067414694,0.00009205852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037534145,0.00018572061,0.00024450966,0.00055922713,0.001141587,0.00017304775,0.0004939105,0.000031932075,0.0003372944],"category_scores_gemma":[0.0000107102605,0.00018642918,0.00028974464,0.0012298289,0.000043069336,0.0001933336,0.000016643735,0.00046343275,0.000017378896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000071091818,0.000057778372,0.00037914273,0.00000853697,0.00029917233,0.0000020371265,0.00021445066,0.8566494,0.000036895464,0.00018542627,0.000018249035,0.1421418],"study_design_scores_gemma":[0.0000872094,0.00035178103,0.0001320134,0.0000043156706,0.00033484618,0.000010094115,0.00017002935,0.9938461,0.003283393,0.00006659817,0.001500598,0.00021300618],"about_ca_topic_score_codex":0.00035721235,"about_ca_topic_score_gemma":0.00009100027,"teacher_disagreement_score":0.9932773,"about_ca_system_score_codex":0.000067311455,"about_ca_system_score_gemma":0.000028128356,"threshold_uncertainty_score":0.878028},"labels":[],"label_agreement":null},{"id":"W4306680367","doi":"10.1609/aiide.v18i1.21966","title":"World Models with an Entity-Based Representation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Reinforcement learning; Representation (politics); Architecture; Artificial intelligence; Ideal (ethics); Machine learning","score_opus":0.0656754816214134,"score_gpt":0.2890941038071535,"score_spread":0.2234186221857401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4306680367","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":[0.2312372,0.000005709522,0.7375543,0.0023875283,0.00033893113,0.00084405445,0.000014221638,0.00009804945,0.027519973],"genre_scores_gemma":[0.9980221,0.000002557951,0.0009841387,0.00033936265,0.000014319157,0.00007049349,0.000004838089,0.000010835681,0.0005513617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982764,0.000023882107,0.00035633365,0.00045825052,0.0006541661,0.00023097944],"domain_scores_gemma":[0.99897337,0.00007348561,0.0003658351,0.00024824467,0.00026221614,0.00007686994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001766739,0.00018784287,0.00017596825,0.00019705156,0.00027320997,0.0006455728,0.000988681,0.000016594258,0.000055742297],"category_scores_gemma":[0.000047306992,0.00014178676,0.0000714981,0.00041784957,0.00014101257,0.001884163,0.0005238302,0.000293091,0.000005725081],"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":[0.0006712483,0.00059582357,0.0012062059,0.000026784692,0.000061108876,0.0000021493267,0.0041170726,0.21005233,0.0018826104,0.7442463,0.000055177046,0.03708316],"study_design_scores_gemma":[0.00008047005,0.0015474819,0.000082275816,0.00010345829,0.000010795808,0.0000052009264,0.003517235,0.9130795,0.05537007,0.025821155,0.00016625407,0.00021611933],"about_ca_topic_score_codex":0.000022618959,"about_ca_topic_score_gemma":0.0000048877596,"teacher_disagreement_score":0.7667849,"about_ca_system_score_codex":0.0001209634,"about_ca_system_score_gemma":0.00005355019,"threshold_uncertainty_score":0.6225273},"labels":[],"label_agreement":null},{"id":"W4307490062","doi":"10.1613/jair.1.13854","title":"Low-Rank Representation of Reinforcement Learning Policies","year":2022,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal; Canadian Institute for Advanced Research; McGill University","funders":"Canadian Institute for Advanced Research","keywords":"Reproducing kernel Hilbert space; Reinforcement learning; Representation (politics); Computer science; Embedding; Rank (graph theory); Stability (learning theory); Kernel (algebra); Convergence (economics); Space (punctuation); Hilbert space; Hilbert curve; Mathematical optimization; Artificial intelligence; Theoretical computer science; Machine learning; Mathematics; Algorithm; Discrete mathematics; Economics; Pure mathematics","score_opus":0.15821192415856822,"score_gpt":0.4211595401058433,"score_spread":0.26294761594727506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4307490062","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":[0.041676976,0.00007808381,0.9548143,0.0011230313,0.00046684186,0.00018793554,2.6104482e-7,0.00001875455,0.0016338057],"genre_scores_gemma":[0.995194,0.00013093057,0.0038572138,0.000029693181,0.00014531569,0.0000073325427,0.0000010773911,0.000010948899,0.00062346837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945222,0.0008052091,0.001207599,0.0002023563,0.0027861602,0.00047647406],"domain_scores_gemma":[0.99679255,0.000771342,0.00072106486,0.0004157782,0.0011722029,0.00012707309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00537001,0.000107457876,0.00027702667,0.001012713,0.00056879903,0.00017705343,0.0017109187,0.000038649538,0.00029149832],"category_scores_gemma":[0.0014429269,0.0001038176,0.00016923904,0.0020779974,0.00019363489,0.0005507454,0.00092520955,0.0013207644,0.00002958772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000075342505,0.00006900338,0.00023569251,0.0000195496,0.000030715084,0.000027142285,0.0038418176,0.92116916,0.011930412,0.035364304,0.00024159512,0.026995242],"study_design_scores_gemma":[0.00007576452,0.0025146042,0.00012040994,0.00006638232,0.000007987888,0.0000732461,0.008277825,0.7822275,0.19722131,0.0073095784,0.0019446373,0.00016073533],"about_ca_topic_score_codex":0.00010306546,"about_ca_topic_score_gemma":0.0000019070632,"teacher_disagreement_score":0.953517,"about_ca_system_score_codex":0.00026783234,"about_ca_system_score_gemma":0.00038944292,"threshold_uncertainty_score":0.5738138},"labels":[],"label_agreement":null},{"id":"W4308364487","doi":"10.1109/tnnls.2022.3217189","title":"Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Quantile; Reinforcement learning; Quantile regression; CVAR; Computer science; Quantile function; Monotonic function; Function (biology); Bellman equation; Q-learning; Mathematical optimization; Offline learning; Artificial intelligence; Expected shortfall; Machine learning; Econometrics; Online learning; Mathematics; Cumulative distribution function; Risk management; Statistics; Economics; Probability density function","score_opus":0.02027412986570837,"score_gpt":0.2429601647000125,"score_spread":0.22268603483430413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308364487","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":[0.005306731,0.00044084346,0.9895608,0.00014780661,0.002988646,0.0009429316,0.0000014328627,0.00047738853,0.00013343246],"genre_scores_gemma":[0.99175465,0.00007924741,0.0012701062,0.00017188817,0.00029190074,0.00046986373,0.000011945744,0.000057553345,0.0058928314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967082,0.0006818013,0.0006758041,0.0006716871,0.00045693238,0.0008055364],"domain_scores_gemma":[0.9980834,0.0007984457,0.00040250915,0.00044312133,0.00008393309,0.000188569],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001287982,0.00036041753,0.00042893642,0.00018799596,0.0035841216,0.00042954503,0.0004672117,0.00010658458,0.00003011114],"category_scores_gemma":[0.000016595208,0.00037301806,0.00020144471,0.0006450524,0.000049743598,0.00031679074,0.000029712539,0.001881494,0.0000052646187],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000068293506,0.000025658865,0.00006863742,0.000039642393,0.000070750466,0.00007583574,0.0003244463,0.9926523,0.000010224171,0.0006282402,0.00044576576,0.0055902232],"study_design_scores_gemma":[0.00077513204,0.0015005071,0.000008194828,0.000046531797,0.000041431435,0.0006360969,0.00034813888,0.97773135,0.0000059458403,0.000003482736,0.018514054,0.00038913963],"about_ca_topic_score_codex":0.00012317751,"about_ca_topic_score_gemma":0.0000064812434,"teacher_disagreement_score":0.98829067,"about_ca_system_score_codex":0.00013392798,"about_ca_system_score_gemma":0.000036607198,"threshold_uncertainty_score":0.99987215},"labels":[],"label_agreement":null},{"id":"W4309997788","doi":"10.23919/wmnc56391.2022.9954301","title":"Multi-Agent Actor-Critic for Cooperative Resource Allocation in Vehicular Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Reinforcement learning; Resource allocation; Quality of service; Scarcity; Distributed computing; Resource (disambiguation); Resource management (computing); Computer network; Artificial intelligence","score_opus":0.02763291788261548,"score_gpt":0.2692623007355205,"score_spread":0.241629382852905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309997788","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":[0.0019074003,0.000054255725,0.99611866,0.000797379,0.00021357292,0.00049049564,4.587688e-7,0.00009156157,0.0003262393],"genre_scores_gemma":[0.9395124,0.000003843263,0.056177184,0.0012773857,0.000032864024,0.00022575447,0.000025809057,0.0000121581415,0.002732613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988482,0.00014414858,0.00022379044,0.00028886794,0.0002330474,0.00026195633],"domain_scores_gemma":[0.9993465,0.00016246953,0.000052761643,0.0003341732,0.00005895807,0.000045138415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004830508,0.00009836009,0.00010912652,0.00008566975,0.00023893549,0.000096543146,0.0005916,0.000029269324,0.000040558574],"category_scores_gemma":[0.000082960636,0.000100081634,0.00004005491,0.0003532641,0.000018083454,0.00017750695,0.00035484362,0.00020589466,0.0000067384635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042862653,0.000033601013,0.00020631785,0.000004376396,0.0000066070315,0.0000033818794,0.00058807596,0.98858654,0.00015657682,0.008945858,0.00086285453,0.0006015049],"study_design_scores_gemma":[0.00050725485,0.00013619698,0.0005349599,0.000005238896,0.0000025061772,0.0000022640302,0.00022575242,0.9790437,0.000117810865,0.000012335921,0.019285958,0.0001259993],"about_ca_topic_score_codex":0.000019641055,"about_ca_topic_score_gemma":0.000007706392,"teacher_disagreement_score":0.93994147,"about_ca_system_score_codex":0.00018610976,"about_ca_system_score_gemma":0.000049493497,"threshold_uncertainty_score":0.40812105},"labels":[],"label_agreement":null},{"id":"W4310608701","doi":"10.1002/9781119808602.index","title":"Index","year":2022,"lang":"en","type":"paratext","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Index (typography); Library science; Computer science; World Wide Web","score_opus":0.017327383746605786,"score_gpt":0.2601855583018081,"score_spread":0.24285817455520234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310608701","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.3537655e-7,0.00006656833,0.51243,0.00013467882,0.0028895698,0.00006423241,7.199619e-7,0.00007388425,0.48434022],"genre_scores_gemma":[0.00041454428,0.00007633945,0.008416607,0.0009684629,0.00014283249,0.000023116587,0.00005022804,0.000018796032,0.9898891],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985109,0.000058677953,0.00021890229,0.0003902404,0.000546246,0.00027505765],"domain_scores_gemma":[0.9987452,0.00006266724,0.00014664604,0.0009541857,0.000032008356,0.00005927275],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00014133863,0.00018562307,0.0001985926,0.00017317873,0.00013862096,0.00023407712,0.0023520808,0.000118404394,0.06827024],"category_scores_gemma":[0.000014080869,0.00017808795,0.00008475173,0.00033446375,0.000017778017,0.00015804869,0.0016174857,0.0006325669,0.03864199],"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":[2.4497353e-7,0.0000028664822,0.0000032009293,0.000008672791,0.000011027699,0.0000034286588,0.000025310119,0.37819746,4.1119017e-7,0.0046337177,0.61622566,0.0008879805],"study_design_scores_gemma":[0.00005945807,0.00003834999,0.000006794203,0.0000045797387,0.0000015685578,0.0000045353368,0.000003830947,0.17092316,0.0000059532877,0.000023594375,0.8287399,0.00018829782],"about_ca_topic_score_codex":0.00002942579,"about_ca_topic_score_gemma":3.5340935e-7,"teacher_disagreement_score":0.50554883,"about_ca_system_score_codex":0.00010970793,"about_ca_system_score_gemma":0.00019794147,"threshold_uncertainty_score":0.9621065},"labels":[],"label_agreement":null},{"id":"W4310903337","doi":"10.18280/jesa.550514","title":"Simulation of Reinforcement Learning Algorithm for Motion Control of an Autonomous Humanoid","year":2022,"lang":"en","type":"article","venue":"Journal Européen des Systèmes Automatisés","topic":"Reinforcement Learning in Robotics","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; Markov decision process; Q-learning; Computer science; Humanoid robot; Artificial intelligence; Task (project management); Robot; Robotics; Autonomy; Controller (irrigation); Action (physics); Process (computing); Action selection; Markov chain; Machine learning; Human–computer interaction; Markov process; Engineering; Mathematics","score_opus":0.02035538598490284,"score_gpt":0.26879168026521866,"score_spread":0.24843629428031583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310903337","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":[0.009537329,0.00009003547,0.98912233,0.000026074818,0.000405074,0.00044874087,0.0000046679365,0.00013425553,0.00023146956],"genre_scores_gemma":[0.9090432,0.0000050729564,0.090296954,0.000031878168,0.000073112744,0.000020452419,0.000011687822,0.000026456502,0.00049117336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997073,0.00050318346,0.0010850923,0.0002297796,0.0007876555,0.00032132096],"domain_scores_gemma":[0.99714726,0.00033766037,0.0016383356,0.0003513008,0.00042334045,0.00010211178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016003305,0.0001814933,0.00039104788,0.00034958863,0.0006608465,0.00013713275,0.00079533004,0.000041930827,0.000071096685],"category_scores_gemma":[0.00025197357,0.00018515921,0.00018322743,0.00033097644,0.00006001078,0.00077842275,0.00020684644,0.00033380563,0.0000027164365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010835197,0.000038715418,0.00009273177,0.000055528046,0.00005396579,0.000005468429,0.000861203,0.7641288,0.0005176154,0.0010662148,0.000012779267,0.23315613],"study_design_scores_gemma":[0.0012441889,0.0019637886,0.004802906,0.000046442237,0.000039118782,0.000077185774,0.00012467988,0.9901827,0.00032414641,0.00054618076,0.0004819755,0.00016667448],"about_ca_topic_score_codex":0.000010667749,"about_ca_topic_score_gemma":2.0938482e-7,"teacher_disagreement_score":0.8995059,"about_ca_system_score_codex":0.0003027999,"about_ca_system_score_gemma":0.00015909382,"threshold_uncertainty_score":0.75505733},"labels":[],"label_agreement":null},{"id":"W4311681064","doi":"10.22215/etd/2022-15178","title":"Learning Transition Dynamics via Rewarded Exploration: A Study using Unity's MLAgents","year":2022,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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","funders":"","keywords":"Computer science; Popularity; Artificial intelligence; Hyperparameter; Transition (genetics); Action (physics); Dynamics (music); Variable (mathematics); Focus (optics); Artificial neural network; State (computer science); Game engine; Machine learning; Work (physics); Human–computer interaction; Engineering; Psychology; Social psychology","score_opus":0.03340026244345544,"score_gpt":0.30001871666234387,"score_spread":0.2666184542188884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311681064","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":[0.044359397,0.00001321826,0.9480271,0.000052699284,0.0015489595,0.00086202234,9.0485577e-7,0.00047656937,0.004659156],"genre_scores_gemma":[0.95340014,0.000020999385,0.01737851,0.0001031733,0.0001145677,0.000116900956,0.0025326966,0.00010247392,0.026230566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99672467,0.00050841615,0.0006169527,0.00066985155,0.0011315639,0.0003485308],"domain_scores_gemma":[0.99850863,0.00006502742,0.00047195563,0.00064257777,0.00022455207,0.000087260814],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058679405,0.0003808365,0.00036644834,0.00045719446,0.0008638314,0.00042327377,0.00097100553,0.00016881204,0.00036012966],"category_scores_gemma":[0.000052387644,0.000441126,0.00013065012,0.00094338116,0.000011927066,0.0010379703,0.0001546351,0.0009977759,0.00003652348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022453843,0.00011698175,0.00007903142,0.000056137163,0.00008018126,0.000035127032,0.022944087,0.97226423,0.000059145623,0.0005210748,0.000023887793,0.0037976755],"study_design_scores_gemma":[0.00042425917,0.00061610213,0.0001610464,0.000033976303,0.00007977247,0.000006196283,0.021631204,0.976219,0.000036967598,0.00014913332,0.00018761618,0.0004547232],"about_ca_topic_score_codex":0.00024370366,"about_ca_topic_score_gemma":0.00021340037,"teacher_disagreement_score":0.93064857,"about_ca_system_score_codex":0.0005471492,"about_ca_system_score_gemma":0.00021082425,"threshold_uncertainty_score":0.9998041},"labels":[],"label_agreement":null},{"id":"W4312372616","doi":"10.1109/aeeca55500.2022.9918998","title":"Exploration Methods in Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Advances in Electrical Engineering and Computer Applications (AEECA)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Strengths and weaknesses; Error-driven learning; Focus (optics); Artificial intelligence; Human–computer interaction; Engineering; Psychology","score_opus":0.026318313508834495,"score_gpt":0.326034692121068,"score_spread":0.2997163786122335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312372616","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":[0.00021758584,0.00014128904,0.9967522,0.00040246913,0.0003629881,0.00027044804,5.4155043e-7,0.00012281482,0.0017296799],"genre_scores_gemma":[0.8304901,0.0009208639,0.16601841,0.00027337298,0.00013391877,0.0015593763,0.000037033424,0.000023105362,0.00054381555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836063,0.00010634899,0.00039673425,0.00045138958,0.00042180083,0.0002630975],"domain_scores_gemma":[0.9993202,0.00021657268,0.00011661393,0.0002368246,0.00005315332,0.000056601686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004389834,0.00016532469,0.00017228827,0.00056787685,0.00012388827,0.00011443974,0.000751718,0.000035238474,0.000030732554],"category_scores_gemma":[0.000028721353,0.00019409854,0.000030009063,0.0008879555,0.000016742673,0.0004885536,0.00025665408,0.00071915955,0.0000066697835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005981377,0.000030217794,0.000067138484,0.0000042057486,0.0000048336524,0.0000024587932,0.00010621199,0.7328575,0.00029914122,0.19559056,0.000010779099,0.071020916],"study_design_scores_gemma":[0.0003092221,0.00020750683,0.00012262164,0.0000140794355,0.0000013169811,0.000008343967,0.000019045985,0.97259724,0.00015079205,0.0016496745,0.024728127,0.00019200952],"about_ca_topic_score_codex":0.0000065012573,"about_ca_topic_score_gemma":0.0000011859169,"teacher_disagreement_score":0.8307338,"about_ca_system_score_codex":0.00031130988,"about_ca_system_score_gemma":0.000041481613,"threshold_uncertainty_score":0.7915109},"labels":[],"label_agreement":null},{"id":"W4312374764","doi":"10.1007/978-3-031-18192-4_2","title":"Investigating Effects of Centralized Learning Decentralized Execution on Team Coordination in the Level Based Foraging Environment as a Sequential Social Dilemma","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Foraging; Computer science; Dilemma; Social dilemma; Reinforcement learning; Artificial intelligence; Convergence (economics); Social learning; Action (physics); State (computer science); Machine learning; Knowledge management; Ecology; Algorithm; Psychology; Social psychology","score_opus":0.024871536777855238,"score_gpt":0.2559807411380916,"score_spread":0.23110920436023635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312374764","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":[0.002852557,0.000034873003,0.99391395,0.0009231337,0.0006751594,0.0009308573,0.0000016181424,0.00007288799,0.00059497077],"genre_scores_gemma":[0.9359128,0.000014136506,0.062769964,0.0010183365,0.00011277181,0.000042797834,0.000031365533,0.00003459845,0.000063220505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519396,0.00043544083,0.00069817074,0.0009898941,0.0019956494,0.000686894],"domain_scores_gemma":[0.9972334,0.0012642486,0.000751157,0.0006044458,0.00006819926,0.000078560086],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018654705,0.00046662346,0.00049183756,0.0007838093,0.00058410066,0.00034736178,0.0022306072,0.00019890303,0.00003222039],"category_scores_gemma":[0.00045290682,0.00042088603,0.00016618535,0.0006968233,0.00048742938,0.00043713994,0.0007329606,0.0014275133,0.000006618651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011371197,0.000035269844,0.00017519174,0.00008111962,0.000009368593,0.000027169928,0.0033736743,0.944313,0.0006559712,0.01908218,0.000007904492,0.032227773],"study_design_scores_gemma":[0.0012604287,0.0004306799,0.00044876852,0.0004286785,0.00001801411,0.000011133334,0.0000023147022,0.98511153,0.0027113582,0.007826874,0.001283126,0.00046707763],"about_ca_topic_score_codex":0.00011713123,"about_ca_topic_score_gemma":0.0000071384857,"teacher_disagreement_score":0.9330602,"about_ca_system_score_codex":0.0009363362,"about_ca_system_score_gemma":0.00042865696,"threshold_uncertainty_score":0.9998243},"labels":[],"label_agreement":null},{"id":"W4312683699","doi":"10.1109/case49997.2022.9926520","title":"Pareto Frontier Approximation Network (PA-Net) to Solve Bi-objective TSP","year":2022,"lang":"en","type":"article","venue":"2022 IEEE 18th International Conference on Automation Science and Engineering (CASE)","topic":"Reinforcement Learning in Robotics","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":"Toronto Metropolitan University","funders":"","keywords":"Pareto principle; Mathematical optimization; Computer science; Multi-objective optimization; Reinforcement learning; Set (abstract data type); Metric (unit); Scheduling (production processes); Optimization problem; Job shop scheduling; Mathematics; Artificial intelligence; Schedule; Engineering","score_opus":0.025091202479126374,"score_gpt":0.26447059761505104,"score_spread":0.23937939513592466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312683699","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":[0.051726654,0.000007831824,0.9412382,0.00091711065,0.0025831196,0.00032282047,0.000008181634,0.000299115,0.00289695],"genre_scores_gemma":[0.963381,0.000005796861,0.035565678,0.0004886935,0.00012383387,0.000130577,0.000009693085,0.000012983082,0.00028174545],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99731916,0.00003768181,0.00035648886,0.0005855869,0.0013087963,0.00039226288],"domain_scores_gemma":[0.9988437,0.000086985725,0.00016866626,0.00036689214,0.00036679726,0.00016692157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013321618,0.00019873577,0.00016238561,0.0005889704,0.0007006319,0.00067883654,0.0009199725,0.00003637493,0.00013704876],"category_scores_gemma":[0.00021136644,0.00021508777,0.00003920259,0.0012646719,0.000064475134,0.001067161,0.00046865534,0.00031571017,0.000040576208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055303444,0.000014670702,0.000054483353,0.000006071661,0.000014436253,0.0001465576,0.001209633,0.90351844,0.00096299197,0.08886111,0.0011784374,0.0040276316],"study_design_scores_gemma":[0.00017702254,0.00016144561,0.0004839847,0.000023956252,0.0000042446795,0.0008716445,0.0003873576,0.9950809,0.0002669933,0.00035282123,0.0019401276,0.00024950234],"about_ca_topic_score_codex":0.000029591049,"about_ca_topic_score_gemma":0.0000037843274,"teacher_disagreement_score":0.91165435,"about_ca_system_score_codex":0.00048483635,"about_ca_system_score_gemma":0.00019726255,"threshold_uncertainty_score":0.87710243},"labels":[],"label_agreement":null},{"id":"W4312995559","doi":"10.1109/tnsm.2022.3210827","title":"FLoadNet: Load Balancing in Fog Networks With Cooperative Multiagent Using Actor–Critic Method","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Network and Service Management","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Distributed computing; Load balancing (electrical power); Cloud computing; Edge computing; Edge device; Context (archaeology); Enhanced Data Rates for GSM Evolution; Workload; Server; Shared resource; Computer network; Artificial intelligence","score_opus":0.01611502068863893,"score_gpt":0.24853917710541473,"score_spread":0.2324241564167758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312995559","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":[0.0020937538,0.00007875724,0.99534523,0.0004151442,0.0006946694,0.0005968301,0.0000012420447,0.000107216205,0.00066717574],"genre_scores_gemma":[0.8772879,0.0001361685,0.11911666,0.002943091,0.00006175107,0.00015835503,0.00000301716,0.000032548567,0.0002604952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978231,0.000300217,0.00031521975,0.0005442762,0.00049722294,0.0005199445],"domain_scores_gemma":[0.99916315,0.00013469078,0.00008693846,0.00045507864,0.00006230483,0.00009782056],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061316264,0.0002568033,0.0002489097,0.0001531028,0.00072953996,0.0001711774,0.00046765784,0.000040255396,0.00005191974],"category_scores_gemma":[6.1238967e-7,0.0002542831,0.000042197174,0.0012687506,0.00001845248,0.00025068872,0.000047283716,0.00049899094,0.0000036215374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050637263,0.00006810198,0.00004949464,0.00004220543,0.00009522126,0.000060189723,0.0010029649,0.98781776,0.000007665615,0.0003312514,0.000033839802,0.010440651],"study_design_scores_gemma":[0.0009327535,0.00021143915,0.00022997067,0.000085643325,0.00005406337,0.00001763395,0.0005543383,0.9961434,0.000018636292,0.000014699285,0.0014451101,0.0002923109],"about_ca_topic_score_codex":0.00019305479,"about_ca_topic_score_gemma":0.0002660656,"teacher_disagreement_score":0.8762286,"about_ca_system_score_codex":0.00035978205,"about_ca_system_score_gemma":0.00005082438,"threshold_uncertainty_score":0.99999094},"labels":[],"label_agreement":null},{"id":"W4313061161","doi":"10.1007/978-3-031-19679-9_63","title":"Reinforcement Learning for Exploring Pedagogical Strategies in Virtual Reality Training","year":2022,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","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":"National Research Council Canada","funders":"","keywords":"TUTOR; Reinforcement learning; Computer science; Virtual reality; Reinforcement; Human–computer interaction; Training (meteorology); Multimedia; Artificial intelligence; Psychology","score_opus":0.3056666438607475,"score_gpt":0.3725653755714306,"score_spread":0.06689873171068311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313061161","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":[0.00003759839,0.00004971129,0.8763994,0.00048238563,0.0002703469,0.0004935682,0.0000015241333,0.00009883327,0.12216661],"genre_scores_gemma":[0.79577297,0.006289433,0.18947321,0.0011100938,0.00013546427,0.0008656256,0.0003903971,0.00004739622,0.0059153866],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974515,0.00006485577,0.0010489289,0.0003630795,0.00067934976,0.0003923113],"domain_scores_gemma":[0.99732447,0.00052362034,0.00046868675,0.0013840065,0.00020602289,0.000093195275],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0026219455,0.00025685603,0.00032814054,0.0011541363,0.0008124138,0.00088211073,0.003214277,0.000093997594,0.000020306568],"category_scores_gemma":[0.00013436057,0.00028374692,0.000063154854,0.00047929186,0.0004678682,0.0112615945,0.0032459476,0.0009493324,0.000008067975],"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":[0.0000023069092,0.0000028613194,0.0000070886204,0.000012701226,0.0000019865033,2.2908911e-7,0.0077508916,0.4714378,4.6617347e-7,0.48526406,0.000008429138,0.03551115],"study_design_scores_gemma":[0.00033155162,0.00018282392,0.0001453863,0.00010577515,0.0000025346603,0.0000065709746,0.0008118945,0.8412448,9.235936e-7,0.0026076606,0.15428632,0.00027370692],"about_ca_topic_score_codex":0.000020232785,"about_ca_topic_score_gemma":0.000008991491,"teacher_disagreement_score":0.7957354,"about_ca_system_score_codex":0.00039160153,"about_ca_system_score_gemma":0.0005951292,"threshold_uncertainty_score":0.9999615},"labels":[],"label_agreement":null},{"id":"W4313483332","doi":"10.48550/arxiv.2301.00051","title":"Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 Rehabilitation Institute; University of Alberta","funders":"","keywords":"Leverage (statistics); Computer science; Artificial intelligence; Machine learning; Reinforcement learning; Task (project management); Adversarial system; Imitation; Engineering","score_opus":0.09622267453762151,"score_gpt":0.2116297504875747,"score_spread":0.1154070759499532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313483332","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":[0.078047864,0.000011213072,0.91927105,0.0000681922,0.0007009891,0.00075669936,0.000008561516,0.0005467762,0.00058867165],"genre_scores_gemma":[0.9784813,0.000030566094,0.01838433,0.00005049799,0.00019823434,0.000016356335,0.00089864346,0.000058016634,0.0018820364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704313,0.00039585656,0.000381983,0.001401658,0.00028353927,0.00049380626],"domain_scores_gemma":[0.9972983,0.0005533829,0.00091669866,0.00082160515,0.00027622684,0.0001337604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005692893,0.00042957417,0.00040524302,0.00035198274,0.00090365374,0.00035240542,0.001389172,0.00026587184,0.00006903733],"category_scores_gemma":[0.0003534827,0.0005233329,0.00020478453,0.0005246932,0.00006711616,0.0013703577,0.001969068,0.0014603499,0.000020579786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012420304,0.000020582835,0.002578744,0.00005359841,0.00012126382,0.00005422302,0.0018198079,0.98810196,0.00012456533,0.0059903157,0.000120472454,0.00089023734],"study_design_scores_gemma":[0.0013644625,0.00047561948,0.00029221643,0.000048577444,0.00013651402,0.0000012564468,0.0014290087,0.9908108,0.0000937732,0.0028827165,0.0018641512,0.00060090655],"about_ca_topic_score_codex":0.0005841276,"about_ca_topic_score_gemma":0.00003510986,"teacher_disagreement_score":0.9008867,"about_ca_system_score_codex":0.00058895943,"about_ca_system_score_gemma":0.00046609284,"threshold_uncertainty_score":0.9997218},"labels":[],"label_agreement":null},{"id":"W4315588467","doi":"10.48550/arxiv.2301.02952","title":"Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research; Agencia Nacional de Investigación y Desarrollo; Microsoft Research","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Abstraction; Action (physics); Representation (politics); Function (biology); Markov process; State (computer science); Temporal difference learning; Markov decision process; Machine learning; Theoretical computer science; Algorithm; Mathematics","score_opus":0.08623908006050819,"score_gpt":0.24314598183921113,"score_spread":0.15690690177870292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315588467","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":[0.04229413,0.0000070719225,0.9534913,0.000056657685,0.00071337685,0.0010249577,0.0000035346404,0.00047213622,0.001936886],"genre_scores_gemma":[0.9670489,0.00012468199,0.0054965336,0.000017187203,0.00007489214,0.00002326791,0.00012302889,0.000056455392,0.027035082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729216,0.00016293113,0.0005710211,0.0011498791,0.00024550495,0.00057849387],"domain_scores_gemma":[0.99674124,0.000472171,0.0009225452,0.0012745452,0.0004105968,0.00017891699],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005925968,0.00039599612,0.00053054147,0.00064777624,0.00041147394,0.00015803616,0.0019614103,0.00032282333,0.000025650801],"category_scores_gemma":[0.0003830305,0.0005072811,0.00043119185,0.0008590049,0.00012809262,0.0003842206,0.002585221,0.001079476,0.0000769646],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017512119,0.000028671773,0.012805835,0.00018799401,0.00012338224,0.000047169124,0.000836084,0.9701473,0.00010649673,0.015222669,0.00013620408,0.00034069346],"study_design_scores_gemma":[0.00060743955,0.00027239186,0.004244685,0.00019108273,0.00017866046,0.0000016534701,0.00041032583,0.99239635,0.00021534711,0.0006222909,0.00039253006,0.00046725036],"about_ca_topic_score_codex":0.00026833653,"about_ca_topic_score_gemma":0.000009432861,"teacher_disagreement_score":0.9479947,"about_ca_system_score_codex":0.00024160909,"about_ca_system_score_gemma":0.0002739921,"threshold_uncertainty_score":0.99973786},"labels":[],"label_agreement":null},{"id":"W4315798474","doi":"10.1007/978-3-031-19907-3_31","title":"Maze Learning Using a Hyperdimensional Predictive Processing Cognitive Architecture","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Computer science; Cognitive architecture; Architecture; Cognition; Artificial intelligence; Cognitive science; Human–computer interaction; Psychology; Neuroscience","score_opus":0.026256872872513812,"score_gpt":0.2637810035091903,"score_spread":0.2375241306366765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4315798474","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":[0.00015209094,0.00018856305,0.9950333,0.00019916115,0.0012826675,0.00053791126,0.000004110303,0.00059494557,0.0020072348],"genre_scores_gemma":[0.32587352,0.000041450432,0.6683499,0.0013226562,0.0011964941,0.000022157488,0.000033548346,0.00022400862,0.0029362151],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99425447,0.00008780281,0.00065557414,0.0019904298,0.0019496451,0.0010620926],"domain_scores_gemma":[0.99690974,0.0010238286,0.0005741284,0.0007104738,0.0005467548,0.00023508811],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010515162,0.0007643799,0.00067754416,0.0014243127,0.0006021349,0.0008049942,0.0023457913,0.00044912152,0.000014318099],"category_scores_gemma":[0.00046960913,0.0007268938,0.00017727756,0.0012598062,0.00096656114,0.0007237333,0.0025503887,0.0024994554,0.0000803679],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011046183,0.000007873231,0.000059354894,0.000048625898,0.000020528141,0.00014797093,0.0015004901,0.83243847,0.00010411238,0.0008200366,0.0000016509606,0.16483985],"study_design_scores_gemma":[0.0003238394,0.00026810245,0.00010363403,0.00186048,0.000026818447,0.00017178744,0.0000013496481,0.9775553,0.00023538778,0.018521188,0.00017456817,0.00075758225],"about_ca_topic_score_codex":0.000011959019,"about_ca_topic_score_gemma":0.0000065655604,"teacher_disagreement_score":0.32668337,"about_ca_system_score_codex":0.00044947804,"about_ca_system_score_gemma":0.0012785667,"threshold_uncertainty_score":0.9998018},"labels":[],"label_agreement":null},{"id":"W4316464918","doi":"10.3390/robotics12010012","title":"Simulated and Real Robotic Reach, Grasp, and Pick-and-Place Using Combined Reinforcement Learning and Traditional Controls","year":2023,"lang":"en","type":"article","venue":"Robotics","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"Korea Electrotechnology Research Institute","keywords":"Reinforcement learning; GRASP; Task (project management); Artificial intelligence; Robotics; Computer science; Robot; Control (management); Plan (archaeology); Margin (machine learning); Human–computer interaction; Machine learning; Engineering; Software engineering; Systems engineering","score_opus":0.03761961539231777,"score_gpt":0.26665880430827926,"score_spread":0.22903918891596148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4316464918","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":[0.16427547,0.00020431315,0.8323089,0.0012935995,0.0003341601,0.000625165,0.0000013003242,0.00051721215,0.00043992014],"genre_scores_gemma":[0.981108,0.0006102253,0.017123736,0.00012398118,0.000060960487,0.0000034909738,0.000032421598,0.00003154746,0.0009056194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979825,0.00013000019,0.00045127407,0.00051134086,0.00042870236,0.0004961534],"domain_scores_gemma":[0.99854493,0.00066219736,0.00020656099,0.00025369736,0.00008541066,0.00024717295],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000541715,0.00029286763,0.00039765687,0.00021950102,0.0004875838,0.00040175652,0.000190327,0.000143113,0.000004522433],"category_scores_gemma":[0.00019176751,0.00030076914,0.00003345045,0.00037511162,0.00020791641,0.00042518525,0.00041517062,0.00037052072,0.0000063644975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001890077,0.000009481034,0.005964671,0.000060676786,0.000056133293,0.00002642704,0.00047471814,0.9690546,0.00034902227,0.023458041,0.000045188957,0.00048215734],"study_design_scores_gemma":[0.001572768,0.00036812265,0.007359562,0.00008782505,0.00006315106,0.000059151553,0.00009193832,0.98927784,0.000021832177,0.00068989926,0.000086565386,0.00032136124],"about_ca_topic_score_codex":0.0000565636,"about_ca_topic_score_gemma":0.0000038386497,"teacher_disagreement_score":0.81683254,"about_ca_system_score_codex":0.00006557628,"about_ca_system_score_gemma":0.000062237355,"threshold_uncertainty_score":0.99994445},"labels":[],"label_agreement":null},{"id":"W4318620677","doi":"10.48550/arxiv.2301.11490","title":"Neural Episodic Control with State Abstraction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"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":"JST-Mirai Program; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Abstraction; Computer science; Leverage (statistics); Episodic memory; Reinforcement learning; Artificial intelligence; Sample (material); State (computer science); Inefficiency; Control (management); Machine learning; Scalability; Programming language; Psychology; Database","score_opus":0.07064646825082561,"score_gpt":0.18665949019521444,"score_spread":0.11601302194438882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318620677","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":[0.073590435,0.0000056052795,0.92359823,0.0001338593,0.0008125949,0.00030736858,0.000004620424,0.0006741811,0.0008731251],"genre_scores_gemma":[0.99234915,0.00003648604,0.00106447,0.00009548456,0.00005283294,7.738053e-7,0.000013453522,0.000029002098,0.006358364],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981953,0.00008921212,0.00021744674,0.00087326154,0.00017770671,0.00044708006],"domain_scores_gemma":[0.9980365,0.00019650915,0.00039600578,0.0010458818,0.0001675726,0.00015750318],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032841833,0.00029916997,0.00027946042,0.00033901536,0.00015046351,0.0002032294,0.0013447403,0.00017642345,0.000011931007],"category_scores_gemma":[0.000028768492,0.00031458237,0.0001221545,0.00053146365,0.00010329536,0.0004493061,0.00074503454,0.0008760485,0.00032569762],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043228425,0.000013564499,0.0042911097,0.000039171213,0.00008807249,0.0005706627,0.00008375565,0.98902476,0.000008603662,0.0054583102,0.000103621,0.00027515093],"study_design_scores_gemma":[0.00065740687,0.00011017868,0.009960201,0.00005364519,0.000048644084,0.0000060522966,0.00002622329,0.9867234,0.000027057311,0.0018450067,0.00018627348,0.00035591694],"about_ca_topic_score_codex":0.0002010811,"about_ca_topic_score_gemma":0.000048559476,"teacher_disagreement_score":0.92253375,"about_ca_system_score_codex":0.00020653155,"about_ca_system_score_gemma":0.0001413639,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W4318829810","doi":"10.2139/ssrn.4229967","title":"Combining Information-Seeking Exploration and Reward Maximization: Unified Inference on Continuous State and Action Spaces Under Partial Observability","year":2022,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Observability; Inference; Action (physics); Maximization; State (computer science); Utility maximization; Mathematical economics; Complete information; Computer science; Artificial intelligence; Psychology; Microeconomics; Social psychology; Economics; Mathematics; Algorithm; Applied mathematics","score_opus":0.031766764619397814,"score_gpt":0.2606905869329649,"score_spread":0.22892382231356706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318829810","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":[0.17348507,0.00005148082,0.82448465,0.0014783541,0.0002336324,0.0001237638,4.1606586e-7,0.00004602924,0.00009659218],"genre_scores_gemma":[0.9983729,0.0005763783,0.0006763356,0.00018869304,0.000027363374,0.0000101192,0.000006987074,0.0000059379563,0.00013526587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982416,0.00022133274,0.00032316198,0.00016774859,0.00040317138,0.00064297154],"domain_scores_gemma":[0.99919754,0.00012410934,0.00035000473,0.000171195,0.00009864578,0.000058511716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012872404,0.000121009776,0.00012870468,0.00012753508,0.0007648512,0.0005298403,0.00023454113,0.000028775527,0.000007652469],"category_scores_gemma":[0.000111321824,0.00012368112,0.000021694837,0.00024558973,0.00003771135,0.0022217585,0.00018903754,0.0010519327,0.0000027557917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049878083,0.000014219775,0.0038821993,0.0000073807073,0.000030070127,7.423325e-7,0.0021384421,0.8225785,0.000040262086,0.15197438,0.000008596374,0.019275323],"study_design_scores_gemma":[0.0014668342,0.0015572784,0.004887689,0.000025364772,0.00001891385,0.00015078239,0.0070029106,0.8456278,0.000087832486,0.13739428,0.0014331372,0.0003472283],"about_ca_topic_score_codex":0.000026924014,"about_ca_topic_score_gemma":0.000028300119,"teacher_disagreement_score":0.8248879,"about_ca_system_score_codex":0.00046036087,"about_ca_system_score_gemma":0.00054140174,"threshold_uncertainty_score":0.5882695},"labels":[],"label_agreement":null},{"id":"W4319441257","doi":"10.1016/j.neucom.2023.01.076","title":"Uncertainty-aware transfer across tasks using hybrid model-based successor feature reinforcement learning☆","year":2023,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","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":"Defence Research and Development Canada; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Successor cardinal; Generalization; Artificial intelligence; Feature (linguistics); Machine learning; Sample (material); Knowledge transfer; Kalman filter; Stability (learning theory); Mathematics","score_opus":0.033756259061986336,"score_gpt":0.29683880846576377,"score_spread":0.26308254940377745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319441257","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":[0.11021328,0.000009225647,0.8865426,0.00055988954,0.00052591413,0.00040748253,0.0000025343377,0.0014938515,0.00024517725],"genre_scores_gemma":[0.9886619,0.00000471349,0.009270641,0.00093767676,0.0001650946,0.000013516789,0.000050926006,0.000072304174,0.0008232685],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960269,0.0001784071,0.00057125575,0.0009462894,0.0009456531,0.0013315133],"domain_scores_gemma":[0.99828357,0.0002961095,0.00019358839,0.00079953356,0.00020640963,0.00022080769],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074136886,0.00046528096,0.00040181467,0.00025785327,0.001096285,0.000649188,0.0015517625,0.00013319032,0.0000083344485],"category_scores_gemma":[0.00011705428,0.00048115576,0.0002290504,0.0013448779,0.00008160585,0.00047436956,0.00065246783,0.0010234776,0.000083964274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011458718,0.000011024667,0.00050137716,0.00007965499,0.00001699433,0.00008836229,0.0006815255,0.9934852,0.0013697307,0.0002375489,0.00034660357,0.0031704844],"study_design_scores_gemma":[0.00079504674,0.00012900775,0.0001313059,0.0001122552,0.000013109785,0.00002057668,0.000047476286,0.9942748,0.0018712282,0.000027296319,0.0020957976,0.00048212963],"about_ca_topic_score_codex":0.00003539693,"about_ca_topic_score_gemma":0.0000019278943,"teacher_disagreement_score":0.8784486,"about_ca_system_score_codex":0.00015780829,"about_ca_system_score_gemma":0.00020411849,"threshold_uncertainty_score":0.999764},"labels":[],"label_agreement":null},{"id":"W4319985622","doi":"10.1002/cjce.24878","title":"Multi‐agent reinforcement learning for process control: Exploring the intersection between fields of reinforcement learning, control theory, and game theory","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal of Chemical Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta","keywords":"Reinforcement learning; Marl; Controller (irrigation); Computer science; Process (computing); Function (biology); Control (management); Intersection (aeronautics); Reinforcement; Control system; Control theory (sociology); Control engineering; Artificial intelligence; Engineering","score_opus":0.02187824374282683,"score_gpt":0.2356329742072273,"score_spread":0.2137547304644005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319985622","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":[0.094167374,0.00007030266,0.9047008,0.00040996293,0.00029106054,0.00028656967,3.9692918e-7,0.00004116602,0.00003237476],"genre_scores_gemma":[0.9992668,0.000008043477,0.00028734683,0.00007339719,0.00016817612,0.000032226788,0.000001863702,0.000022015489,0.00014013935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843156,0.00010659449,0.0005782439,0.00014268565,0.00030698086,0.0004339054],"domain_scores_gemma":[0.9977845,0.0012305947,0.00035687137,0.0002089221,0.00019374327,0.00022535205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027363026,0.00018244689,0.00029658235,0.0001800112,0.00019048211,0.00012786213,0.00070686126,0.0000701323,0.0000070483043],"category_scores_gemma":[0.001545684,0.00012629648,0.00013662245,0.0002598064,0.00009169948,0.00025699844,0.000057774978,0.00071103807,0.0000016742093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037040292,0.0000011483455,0.00026715404,0.000060117058,0.00015185053,0.000003269505,0.0033116539,0.98867065,0.0013101115,0.004415771,0.000014378931,0.0017568537],"study_design_scores_gemma":[0.0011912553,0.00024477567,0.00029971724,0.00018857546,0.00007726764,0.000017742992,0.0002920929,0.98987585,0.0068055345,0.00031327116,0.00053300406,0.00016089606],"about_ca_topic_score_codex":0.00007331636,"about_ca_topic_score_gemma":0.0000070059614,"teacher_disagreement_score":0.9050994,"about_ca_system_score_codex":0.00015777993,"about_ca_system_score_gemma":0.00016620975,"threshold_uncertainty_score":0.5150221},"labels":[],"label_agreement":null},{"id":"W4319996478","doi":"10.1109/tg.2023.3237943","title":"Predictive Dead Reckoning for Online Peer-to-Peer Games","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Games","topic":"Reinforcement Learning in Robotics","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":"Ubisoft (Canada); University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dead reckoning; Peer-to-peer; Computer science; Internet privacy; World Wide Web; Telecommunications; Global Positioning System","score_opus":0.03682903211344726,"score_gpt":0.3037323543981614,"score_spread":0.26690332228471414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319996478","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":[0.004369576,0.00000740673,0.9859241,0.006075117,0.0016256017,0.00050278514,0.000057656944,0.0009818176,0.0004559037],"genre_scores_gemma":[0.78158426,0.000028797453,0.15311755,0.0009457071,0.0001988598,0.00030400112,0.000030763502,0.00006690828,0.06372318],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979292,0.000048779057,0.00031254496,0.0005071848,0.00070961623,0.00049266516],"domain_scores_gemma":[0.9983328,0.00047180196,0.00007995777,0.0005761212,0.00038243257,0.00015689082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004189962,0.00022045194,0.00021934987,0.00044669418,0.00027652996,0.00017880643,0.0006831777,0.000102696984,0.000024110854],"category_scores_gemma":[0.00011210894,0.0002192461,0.00016322795,0.0009582366,0.000045468394,0.00036324505,0.000008131711,0.0003034323,0.0002735238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029028495,0.00004901474,0.000014886864,0.000017520792,0.00005128458,0.00000398159,0.0015646847,0.9497359,0.00030582736,0.00024370418,0.006101703,0.041882485],"study_design_scores_gemma":[0.00059652363,0.00073620933,0.000686494,0.000084901585,0.00003761272,0.0000065098848,0.00031680273,0.93538356,0.008820175,0.00023850804,0.052753557,0.0003391682],"about_ca_topic_score_codex":0.000015352338,"about_ca_topic_score_gemma":0.000014813638,"teacher_disagreement_score":0.8328066,"about_ca_system_score_codex":0.00010028558,"about_ca_system_score_gemma":0.00008967578,"threshold_uncertainty_score":0.89405966},"labels":[],"label_agreement":null},{"id":"W4320204347","doi":"10.48550/arxiv.2206.05860","title":"IGN : Implicit Generative Networks","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Science North","funders":"","keywords":"Discriminator; Reinforcement learning; Quantile regression; Computer science; Generator (circuit theory); Quantile; Baseline (sea); Bellman equation; Artificial intelligence; State (computer science); Function (biology); Generative grammar; Action (physics); Mathematical optimization; Machine learning; Econometrics; Algorithm; Mathematics; Power (physics)","score_opus":0.06671544719590597,"score_gpt":0.19403896368444742,"score_spread":0.12732351648854145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320204347","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":[0.0046997843,0.000056077024,0.9817442,0.00009782088,0.0013092965,0.00032996666,0.000004631263,0.00038725015,0.01137097],"genre_scores_gemma":[0.9846776,0.00017458663,0.005091136,0.00034852794,0.00015346952,0.0000028841612,0.00004481755,0.0000295296,0.009477407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976237,0.0002649862,0.00024090392,0.0012183933,0.00014786288,0.0005041428],"domain_scores_gemma":[0.99747753,0.0001324397,0.00036268117,0.0017418541,0.000115788476,0.00016973022],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030078003,0.00036918613,0.0003489095,0.00023960137,0.00039575438,0.00022351519,0.0032355143,0.00024073118,0.0002741279],"category_scores_gemma":[0.000026011876,0.000458955,0.00024236634,0.0007225406,0.00008104456,0.00030771026,0.00688204,0.0013242177,0.00007044527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061027795,0.000017162092,0.00078999356,0.000011610778,0.00007802133,0.00018408638,0.0001537807,0.83522815,0.000003930457,0.1624066,0.0009738806,0.0001466907],"study_design_scores_gemma":[0.00023572937,0.00007666301,0.00036683725,0.000017797342,0.00003898174,0.0000036001215,0.000054774642,0.9914877,0.000011749708,0.0045577665,0.0026744478,0.00047396263],"about_ca_topic_score_codex":0.00008227465,"about_ca_topic_score_gemma":0.000006579219,"teacher_disagreement_score":0.97997785,"about_ca_system_score_codex":0.00045860442,"about_ca_system_score_gemma":0.00022620104,"threshold_uncertainty_score":0.9997862},"labels":[],"label_agreement":null},{"id":"W4320342078","doi":"10.48550/arxiv.2302.00237","title":"Bridging Physics-Informed Neural Networks with Reinforcement Learning: Hamilton-Jacobi-Bellman Proximal Policy Optimization (HJBPPO)","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo","keywords":"Hamilton–Jacobi–Bellman equation; Reinforcement learning; Bellman equation; Artificial neural network; Bridging (networking); Computer science; Mathematical optimization; Optimal control; Mathematics; Artificial intelligence","score_opus":0.05811504637595478,"score_gpt":0.20704281154236612,"score_spread":0.14892776516641135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320342078","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":[0.0034362895,0.000008505294,0.9910418,0.00020401114,0.00056431635,0.00091303873,0.0000014662645,0.001383069,0.0024475455],"genre_scores_gemma":[0.98152775,0.00022172646,0.006579584,0.00019327723,0.0004618394,0.000007745874,0.00021772037,0.000102486665,0.010687892],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963378,0.00017359972,0.00052394124,0.0014440606,0.0004073876,0.0011132577],"domain_scores_gemma":[0.99664986,0.00015378138,0.0009553347,0.0015727575,0.00035002708,0.0003182435],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003422039,0.00074763125,0.0005858816,0.0005948488,0.0006004813,0.0006009864,0.0023678709,0.00037697743,0.000015779264],"category_scores_gemma":[0.00008701281,0.0008217042,0.00027061926,0.0019197933,0.00021185142,0.001112109,0.0027163262,0.0018560443,0.00006663294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005605044,0.000024109595,0.0023606063,0.00012618647,0.00017274756,0.00015717372,0.00059559377,0.98205423,0.0000011520582,0.013931258,0.00015073386,0.00037012814],"study_design_scores_gemma":[0.0009276087,0.00029330666,0.00024306013,0.00022857494,0.000088258545,0.000007713939,0.000069525886,0.99693793,0.00002111355,0.0001393101,0.00015921182,0.0008843797],"about_ca_topic_score_codex":0.00029820765,"about_ca_topic_score_gemma":0.000015801577,"teacher_disagreement_score":0.9844622,"about_ca_system_score_codex":0.00085559,"about_ca_system_score_gemma":0.00073437137,"threshold_uncertainty_score":0.9994234},"labels":[],"label_agreement":null},{"id":"W4321472417","doi":"10.48550/arxiv.2302.09465","title":"Stochastic Generative Flow Networks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Samsung; Genentech; Canadian Institute for Advanced Research","keywords":"Computer science; Probabilistic logic; Inference; Variety (cybernetics); Stochastic modelling; Limit (mathematics); Generative grammar; Sample (material); Flow (mathematics); Stochastic dynamics; Mathematical optimization; Artificial intelligence; Mathematics; Statistical physics","score_opus":0.10064847479664266,"score_gpt":0.19619547860151418,"score_spread":0.09554700380487152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321472417","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":[0.00099639,0.00002597465,0.9947692,0.000114904935,0.0022063595,0.00031585537,0.000004174545,0.00077694206,0.000790186],"genre_scores_gemma":[0.9767625,0.000079214675,0.01059933,0.00013579769,0.00025728872,0.0000019142242,0.000044294706,0.000042421834,0.012077287],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977921,0.00015483597,0.00023347484,0.0011706513,0.00013430737,0.00051459234],"domain_scores_gemma":[0.99767137,0.00020738343,0.00028021607,0.0014861196,0.00016928287,0.00018560805],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00026822148,0.00037539846,0.0003490123,0.00027901726,0.00022411927,0.00024896185,0.0023868687,0.00034594798,0.00002601045],"category_scores_gemma":[0.000072165596,0.00044695844,0.00021015914,0.00074909,0.00010601718,0.00028366304,0.0037567175,0.0009833194,0.00044417227],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005499157,0.000011426427,0.00010751607,0.00001714202,0.00009420828,0.00019487564,0.00015556776,0.95847774,0.0000011166911,0.039746225,0.0010371016,0.00015158465],"study_design_scores_gemma":[0.0002312744,0.000046241345,0.00017831159,0.000077643956,0.000045526074,0.0000019554586,0.000022669079,0.99300766,0.000003817523,0.005859418,0.00008224419,0.00044323475],"about_ca_topic_score_codex":0.00004432938,"about_ca_topic_score_gemma":0.000014720838,"teacher_disagreement_score":0.9841699,"about_ca_system_score_codex":0.0002580833,"about_ca_system_score_gemma":0.00019343974,"threshold_uncertainty_score":0.99979824},"labels":[],"label_agreement":null},{"id":"W4323020953","doi":"10.1109/access.2023.3249572","title":"Bridging the Reality Gap Between Virtual and Physical Environments Through Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Virtual reality; Bridging (networking); Metaverse; Artificial intelligence; Human–computer interaction; Physics engine; Task (project management); Simulation; Engineering","score_opus":0.08104295423193325,"score_gpt":0.3377379428838238,"score_spread":0.25669498865189055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323020953","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":[0.12781706,0.0000058637333,0.8689557,0.0012389066,0.00025224028,0.0001975302,6.2422106e-7,0.0002284404,0.001303657],"genre_scores_gemma":[0.9976567,0.00005500643,0.00014771725,0.00030217567,0.00033428543,0.000018840386,0.000010797451,0.000016118238,0.0014583616],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99813575,0.00013811767,0.00026339342,0.00041623748,0.000608142,0.00043836396],"domain_scores_gemma":[0.9988442,0.00030808008,0.00017183764,0.0005884627,0.000014467987,0.00007296546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005170781,0.00018264222,0.00019542481,0.000054042823,0.00049013627,0.00051410234,0.001326732,0.00004814098,0.000005173289],"category_scores_gemma":[0.00007129266,0.00014209673,0.000056524943,0.0004458069,0.00012653774,0.0011485532,0.0010774966,0.0003773452,0.00014574944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024339279,0.000005702182,0.0055546537,0.000010715596,0.000038295784,0.000007102559,0.0021160762,0.9790944,0.00027368788,0.002695138,0.0010826236,0.009119193],"study_design_scores_gemma":[0.00033611731,0.000121995516,0.024996104,0.000030969724,0.000022324573,0.000002552359,0.00007971036,0.9635002,0.0028911575,0.00088599545,0.006856146,0.0002767326],"about_ca_topic_score_codex":0.000078577876,"about_ca_topic_score_gemma":5.9442203e-7,"teacher_disagreement_score":0.8698396,"about_ca_system_score_codex":0.000054865803,"about_ca_system_score_gemma":0.000021644375,"threshold_uncertainty_score":0.57945365},"labels":[],"label_agreement":null},{"id":"W4327810476","doi":"10.48550/arxiv.2303.09032","title":"Conditionally Optimistic Exploration for Cooperative Deep Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Institut de Valorisation des Données; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Monte Carlo tree search; Intuition; Tree (set theory); Artificial intelligence; Software deployment; Machine learning; Mathematical optimization; Mathematics; Cognitive science","score_opus":0.04615468709767459,"score_gpt":0.28443516501314803,"score_spread":0.23828047791547344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327810476","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":[0.00018763728,0.00020062433,0.98943543,0.0029474671,0.0009758741,0.0034709373,0.00003356456,0.0025640295,0.00018441748],"genre_scores_gemma":[0.22654484,0.00045733954,0.75146204,0.0013214458,0.00031542452,0.0072059473,0.001723953,0.00020472707,0.010764251],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99492854,0.00029484447,0.0013879936,0.0013314496,0.0009390386,0.0011181358],"domain_scores_gemma":[0.9955222,0.0005473277,0.0011402491,0.0015902278,0.0008140961,0.0003859007],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015321114,0.0008273529,0.00075266376,0.000792005,0.0007745167,0.0012592257,0.0020937554,0.00069028593,0.000026021225],"category_scores_gemma":[0.0014586136,0.00092009094,0.0004134456,0.00054575485,0.00011690859,0.0008170648,0.0023408479,0.0015352383,0.00011970166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032914402,0.00007040471,0.00020457622,0.0001788057,0.00017563997,0.000033695287,0.00095083535,0.961639,0.000316073,0.033849023,0.0015698781,0.0009791636],"study_design_scores_gemma":[0.0008384182,0.00036090857,0.0006724816,0.00025158442,0.00007035753,0.0000130877415,0.00013824273,0.9918099,0.0012835818,0.0020234776,0.0016313894,0.00090656796],"about_ca_topic_score_codex":0.0007925,"about_ca_topic_score_gemma":0.00031569903,"teacher_disagreement_score":0.23797338,"about_ca_system_score_codex":0.0014522014,"about_ca_system_score_gemma":0.00084886554,"threshold_uncertainty_score":0.99977756},"labels":[],"label_agreement":null},{"id":"W4352994281","doi":"10.1007/978-3-031-25549-6_3","title":"Efficient Deep Reinforcement Learning via Policy-Extended Successor Feature Approximator","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Successor cardinal; Reinforcement learning; Computer science; Artificial intelligence; Generalization; Generalizability theory; Representation (politics); Decoupling (probability); Feature learning; Machine learning; Task (project management); Policy learning; Feature (linguistics); Mathematics","score_opus":0.013348182838903204,"score_gpt":0.25064532749151375,"score_spread":0.23729714465261054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4352994281","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":[0.000013287178,0.00013694588,0.9880436,0.0015559063,0.0024322702,0.0008844127,9.017525e-7,0.00092587963,0.0060067917],"genre_scores_gemma":[0.36324877,0.00016581791,0.5993195,0.00377364,0.0027888035,0.00011088895,0.00007816938,0.00044621178,0.030068196],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920106,0.000087734385,0.0009655756,0.0023908324,0.0028117918,0.0017334833],"domain_scores_gemma":[0.99533087,0.00068400294,0.00083132216,0.0022767654,0.00045143263,0.00042561605],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00162027,0.0010901091,0.00093892193,0.0023495196,0.00077892246,0.0012110254,0.0057797236,0.0006739221,0.000028237844],"category_scores_gemma":[0.000499665,0.0010215571,0.00031140854,0.0021929848,0.00079792115,0.00040791903,0.003896101,0.0025788338,0.0003945629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007393078,0.000014042945,0.000021718406,0.0000819732,0.000027061715,0.00010345385,0.0008159119,0.90009314,0.00005866151,0.02206216,0.000019762023,0.076694734],"study_design_scores_gemma":[0.0004198753,0.00029745468,0.000069666865,0.00041053558,0.000015118531,0.00007088158,5.830062e-7,0.9862104,0.00032459953,0.009909145,0.00121244,0.0010593124],"about_ca_topic_score_codex":0.000047061996,"about_ca_topic_score_gemma":0.00002325286,"teacher_disagreement_score":0.38872412,"about_ca_system_score_codex":0.0010655695,"about_ca_system_score_gemma":0.000986351,"threshold_uncertainty_score":0.99982584},"labels":[],"label_agreement":null},{"id":"W4353091694","doi":"10.1038/s41467-023-37180-x","title":"Catalyzing next-generation Artificial Intelligence through NeuroAI","year":2023,"lang":"en","type":"review","venue":"Nature Communications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":283,"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; Mila - Quebec Artificial Intelligence Institute; Ontario Brain Institute; Montreal Neurological Institute and Hospital","funders":"National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Eye Institute; National Institute of Mental Health; Natural Sciences and Engineering Research Council of Canada; Intelligence Advanced Research Projects Activity; Defense Advanced Research Projects Agency; Office of Naval Research; Cold Spring Harbor Laboratory; Multidisciplinary University Research Initiative; James S. McDonnell Foundation; Canadian Institute for Advanced Research; National Science Foundation; Semiconductor Research Corporation; National Institutes of Health; Lourie Foundation; Howard Hughes Medical Institute","keywords":"Computer science; Artificial intelligence; Data science","score_opus":0.3747334748993592,"score_gpt":0.4284879568866756,"score_spread":0.053754481987316416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4353091694","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.5297532e-8,0.6795169,0.31718647,0.00068821496,0.000934313,0.00045120632,0.000005800267,0.00041828732,0.00079878693],"genre_scores_gemma":[0.00004266411,0.9429298,0.05543158,0.000187854,0.00026696228,0.00013930841,0.0006494219,0.00006073066,0.0002916915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99720573,0.00049677,0.00094621535,0.0005722158,0.00042509998,0.00035398285],"domain_scores_gemma":[0.99218655,0.0010347543,0.00061310094,0.005900882,0.0001940795,0.000070616115],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005107338,0.0003976944,0.0007144585,0.00028371834,0.00067876617,0.0007687197,0.008350063,0.00072435325,0.0000052253395],"category_scores_gemma":[0.0007427941,0.00037819467,0.0003350507,0.0021362545,0.00012726299,0.00077664875,0.0027929626,0.0031099454,0.0009061987],"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":[1.1732692e-7,0.000024875691,1.0896713e-7,0.00053587725,0.000062538325,0.000003023236,0.00022502399,0.0036688386,0.0000011067324,0.33643445,0.0018991241,0.6571449],"study_design_scores_gemma":[0.0000072134876,0.000015151085,1.4010972e-7,0.0010377391,0.00010695642,0.000013101693,0.000009514318,0.10743571,0.000002375512,0.000542495,0.89051497,0.00031463703],"about_ca_topic_score_codex":0.0000147058745,"about_ca_topic_score_gemma":0.0000684054,"teacher_disagreement_score":0.88861585,"about_ca_system_score_codex":0.0001723035,"about_ca_system_score_gemma":0.00039579705,"threshold_uncertainty_score":0.99987173},"labels":[],"label_agreement":null},{"id":"W4360764167","doi":"10.1109/icmla55696.2022.00101","title":"Hyperparameter Tuning in Offline Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Lakehead University","funders":"","keywords":"Hyperparameter; Reinforcement learning; Benchmark (surveying); Metric (unit); Computer science; Machine learning; Performance metric; Artificial intelligence; Scheme (mathematics); Hyperparameter optimization; Friedman test; Statistical hypothesis testing; Statistics; Mathematics; Engineering","score_opus":0.01903993677232508,"score_gpt":0.2398741299863006,"score_spread":0.22083419321397552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360764167","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":[0.00811636,0.000018637313,0.9550312,0.00045923772,0.00025642864,0.00014481191,3.8394397e-8,0.00021414558,0.0357591],"genre_scores_gemma":[0.9559676,0.0000045444585,0.027802266,0.0008169026,0.000017639704,0.000038689534,0.00000564493,0.000011005208,0.0153357275],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833465,0.00013543804,0.00034018196,0.00030255457,0.0005177269,0.00036945904],"domain_scores_gemma":[0.9993019,0.000113527174,0.000101611375,0.0004034098,0.000023881623,0.000055687768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006829737,0.000121554775,0.00014477053,0.00025798127,0.000256682,0.000100213496,0.00085545366,0.000021454858,0.0006237041],"category_scores_gemma":[0.000082834194,0.000126289,0.000048879563,0.00062979874,0.000016543308,0.00032013663,0.0012653345,0.0005477693,0.00007367597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000035004286,0.00001121041,0.003366865,0.0000030736653,0.0000051524175,0.000018244578,0.00053368026,0.97975236,0.00020515965,0.014044675,0.00020575227,0.0018503065],"study_design_scores_gemma":[0.00035820648,0.00020567521,0.00049114623,0.000004562109,0.0000013976456,0.0000133686335,0.00015151403,0.96837556,0.00010544886,0.0000707122,0.030058347,0.00016406138],"about_ca_topic_score_codex":0.00005641,"about_ca_topic_score_gemma":0.0000017950522,"teacher_disagreement_score":0.94785124,"about_ca_system_score_codex":0.00017926296,"about_ca_system_score_gemma":0.00005306304,"threshold_uncertainty_score":0.68291223},"labels":[],"label_agreement":null},{"id":"W4360764815","doi":"10.1109/icmla55696.2022.00044","title":"Benchmarking Offline Reinforcement Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Lakehead University","funders":"","keywords":"Benchmarking; Reinforcement learning; Computer science; Hyperparameter; Machine learning; Artificial intelligence; Offline learning; Performance improvement; Online learning; Engineering","score_opus":0.013732024615425604,"score_gpt":0.22941801827976827,"score_spread":0.21568599366434266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360764815","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":[0.0005493773,0.000016714659,0.9260619,0.00042116613,0.00047995694,0.00011237076,4.3496215e-8,0.00034385076,0.072014585],"genre_scores_gemma":[0.934501,0.000006291603,0.03840866,0.00090065267,0.00007152223,0.000032472115,0.000011826335,0.000011079875,0.026056515],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983526,0.0000962123,0.00027406804,0.00028919472,0.0006523338,0.0003355777],"domain_scores_gemma":[0.99926615,0.00007686581,0.00012826158,0.00042577457,0.000035785262,0.00006718489],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059333246,0.00011539431,0.00011183007,0.0001366981,0.000673566,0.00012357325,0.00095134764,0.000016525666,0.0017124506],"category_scores_gemma":[0.00003844792,0.00011926358,0.000060557388,0.00045786527,0.000015301748,0.00027684687,0.0016212235,0.0004096977,0.00007946304],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001760805,0.0000067591336,0.0006692787,0.000002959626,0.000009324734,0.000008557305,0.00028941568,0.9428643,0.00009206019,0.050844785,0.0012562308,0.003954538],"study_design_scores_gemma":[0.00018552499,0.00025602715,0.00016768728,0.000002192011,0.000002196032,0.00001364318,0.00006636833,0.8755998,0.000105835104,0.00006890354,0.123387165,0.00014463259],"about_ca_topic_score_codex":0.000021769545,"about_ca_topic_score_gemma":3.9372281e-7,"teacher_disagreement_score":0.9339516,"about_ca_system_score_codex":0.00013843608,"about_ca_system_score_gemma":0.000056374814,"threshold_uncertainty_score":0.9992001},"labels":[],"label_agreement":null},{"id":"W4360764838","doi":"10.1109/icmla55696.2022.00097","title":"IGN : Implicit Generative Networks","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Science North","funders":"","keywords":"Discriminator; Reinforcement learning; Computer science; Quantile regression; Generator (circuit theory); Baseline (sea); Quantile; Artificial intelligence; Bellman equation; State (computer science); Generative grammar; Action (physics); Machine learning; Mathematical optimization; Algorithm; Econometrics; Mathematics; Power (physics)","score_opus":0.013866665707804763,"score_gpt":0.23323073197724947,"score_spread":0.2193640662694447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360764838","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":[0.00021294896,0.000023026047,0.9663562,0.0006372082,0.00039261865,0.00008550274,1.5526967e-7,0.00018461555,0.03210768],"genre_scores_gemma":[0.8904119,0.0000046331734,0.087918155,0.0040969653,0.0001073447,0.000051511284,0.0000053537347,0.000010865868,0.017393254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991459,0.000071098904,0.0001225901,0.00020433286,0.00024067325,0.00021536404],"domain_scores_gemma":[0.99945956,0.000048065827,0.00004762807,0.00037799703,0.00002240377,0.000044336015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001934121,0.00007085217,0.00007075515,0.00004307013,0.00033380266,0.000097308344,0.0007765502,0.000013257696,0.00046025502],"category_scores_gemma":[0.000007582782,0.00006725382,0.000034097244,0.00030972736,0.000011193078,0.00014777483,0.000880727,0.00018513824,0.00003674317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.205118e-7,0.000004442516,0.00012756193,2.7552383e-7,0.0000055837186,0.0000038284306,0.00013314914,0.84966016,0.000042850264,0.1404601,0.007962226,0.0015993004],"study_design_scores_gemma":[0.000087567685,0.0000925885,0.00019443843,3.3656804e-7,0.0000011131674,0.000009488079,0.00003492279,0.9788647,0.0000733868,0.000346794,0.020201068,0.00009353833],"about_ca_topic_score_codex":0.000012607424,"about_ca_topic_score_gemma":6.749774e-7,"teacher_disagreement_score":0.89019895,"about_ca_system_score_codex":0.000060222883,"about_ca_system_score_gemma":0.000031216583,"threshold_uncertainty_score":0.50394696},"labels":[],"label_agreement":null},{"id":"W4360771686","doi":"10.1109/icmla55696.2022.00008","title":"Keynotes","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Microsoft (Canada)","funders":"","keywords":"Computer science","score_opus":0.010275642458580992,"score_gpt":0.20805035321039803,"score_spread":0.19777471075181705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360771686","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":[0.00039221163,0.0000074048326,0.9301216,0.00087906985,0.00022294252,0.000027849286,4.893066e-8,0.0001828954,0.06816597],"genre_scores_gemma":[0.9161437,6.999484e-7,0.06302974,0.0013459551,0.000014233938,0.000010031406,7.383155e-7,0.0000030540425,0.019451851],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99952495,0.000023127166,0.000057844263,0.00009628169,0.00019954008,0.00009824256],"domain_scores_gemma":[0.9996721,0.000032154152,0.000018662648,0.00024959454,0.000007922311,0.000019548503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011283648,0.00002910652,0.000029130104,0.000033041233,0.00015979703,0.000044795357,0.00059633056,0.000003939906,0.0006288378],"category_scores_gemma":[0.00001188816,0.00002794562,0.000016802565,0.00017292991,0.000005549029,0.00010327387,0.0006278115,0.00007670972,0.00010515942],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.6323326e-7,0.00000479352,0.00043932756,5.5948004e-7,0.0000022115723,0.0000035909343,0.00013468797,0.7292359,0.00006663119,0.2623942,0.005146352,0.0025714894],"study_design_scores_gemma":[0.00007209868,0.00006629588,0.00040559765,2.2391461e-7,4.7613418e-7,0.000008658392,0.000027563767,0.85800034,0.00023338698,0.00081354135,0.14030467,0.000067165645],"about_ca_topic_score_codex":0.0000058089017,"about_ca_topic_score_gemma":9.34091e-8,"teacher_disagreement_score":0.91575146,"about_ca_system_score_codex":0.00002148452,"about_ca_system_score_gemma":0.000017110757,"threshold_uncertainty_score":0.6885333},"labels":[],"label_agreement":null},{"id":"W4361273506","doi":"10.3390/systems11040180","title":"It’s All about Reward: Contrasting Joint Rewards and Individual Reward in Centralized Learning Decentralized Execution Algorithms","year":2023,"lang":"en","type":"article","venue":"Systems","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Mitacs","keywords":"Reinforcement learning; Variance (accounting); Computer science; Joint (building); Function (biology); Foraging; Machine learning; Artificial intelligence; Value (mathematics); Engineering","score_opus":0.06219908550440429,"score_gpt":0.2892080950814729,"score_spread":0.2270090095770686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361273506","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":[0.12730494,0.002141781,0.852792,0.0032492955,0.006165422,0.0027969691,0.000014526388,0.002937103,0.0025979495],"genre_scores_gemma":[0.9918698,0.0007447284,0.005475141,0.00021058925,0.00011832334,0.00008041253,0.000073771625,0.000050116396,0.0013770921],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955892,0.0006445806,0.0010059898,0.00072693295,0.00093758333,0.0010956877],"domain_scores_gemma":[0.99846363,0.00026484884,0.00043325694,0.0004781206,0.00011525791,0.0002448713],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029467612,0.00033464405,0.0005869637,0.0004312926,0.00022723911,0.00070870447,0.0006332737,0.00021365071,0.0000060297157],"category_scores_gemma":[0.00065035454,0.00033611458,0.00009496938,0.0009738241,0.00007527207,0.0005539913,0.0004393699,0.0005560879,0.00008969922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067328634,0.00007312545,0.029267166,0.00078766036,0.00038131277,0.0005543931,0.042049628,0.89448345,0.0038260422,0.0056068394,0.011026016,0.011877041],"study_design_scores_gemma":[0.0029622829,0.00017306919,0.019325735,0.0008502858,0.000033304932,0.000088825116,0.0013946878,0.94253856,0.00019829965,0.00009468614,0.03171716,0.00062309747],"about_ca_topic_score_codex":0.00030471708,"about_ca_topic_score_gemma":0.000010331914,"teacher_disagreement_score":0.8645649,"about_ca_system_score_codex":0.000221723,"about_ca_system_score_gemma":0.000117062475,"threshold_uncertainty_score":0.9999091},"labels":[],"label_agreement":null},{"id":"W4364304082","doi":"10.1109/raai56146.2022.10092979","title":"Addressing Different Goal Selection Strategies In Hindsight Experience Replay With Actor-Critic Methods For Robotic Hand Manipulation","year":2022,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Hindsight bias; Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Selection (genetic algorithm); Robot; Block (permutation group theory); Binary number; Machine learning; Human–computer interaction; Engineering; Mathematics","score_opus":0.07996687853250528,"score_gpt":0.373707120529135,"score_spread":0.29374024199662974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364304082","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":[0.04893246,0.000023824507,0.9498071,0.0001036352,0.0002891981,0.00038422595,1.02655896e-7,0.00011669331,0.00034273454],"genre_scores_gemma":[0.7872183,7.9412325e-7,0.21208687,0.00005122741,0.00002087928,0.00016278414,0.000005955964,0.000011718597,0.00044151657],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837905,0.00024299914,0.0002942633,0.00043465968,0.0003207083,0.00032830331],"domain_scores_gemma":[0.9992156,0.0002654097,0.0001257942,0.0002879926,0.000056998215,0.000048178288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000354343,0.00016410895,0.00018899486,0.00018952045,0.0005097333,0.0005719823,0.00042567673,0.000035023622,0.0000627222],"category_scores_gemma":[0.00005041639,0.00013800168,0.000036038804,0.00043018642,0.000042578726,0.0009109335,0.00018024565,0.00022574622,6.766468e-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":[0.000025958963,0.000030179111,0.002204168,0.000023421568,0.000007669717,0.0000022378356,0.0028253836,0.97133756,0.005864744,0.015919337,0.000014389593,0.0017449498],"study_design_scores_gemma":[0.00045799278,0.00039125164,0.0078678345,0.000023998906,0.000006960072,0.000022843165,0.0010146227,0.98413646,0.0051667304,0.00057973666,0.000125464,0.00020611826],"about_ca_topic_score_codex":0.000048104765,"about_ca_topic_score_gemma":0.000034550874,"teacher_disagreement_score":0.7382858,"about_ca_system_score_codex":0.00025905078,"about_ca_system_score_gemma":0.00008912792,"threshold_uncertainty_score":0.5627545},"labels":[],"label_agreement":null},{"id":"W4367016230","doi":"10.1109/tse.2023.3269804","title":"A Search-Based Testing Approach for Deep Reinforcement Learning Agents","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cisco Systems (Canada); École de Technologie Supérieure; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Machine learning; Software testing; Software engineering; Programming language; Software","score_opus":0.04544628432889011,"score_gpt":0.25729172732987793,"score_spread":0.21184544300098782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367016230","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":[0.0006383811,0.00000454791,0.99573284,0.000021951795,0.00046346424,0.00045737118,0.0000010239257,0.0026209138,0.000059490463],"genre_scores_gemma":[0.5927373,0.0000024442102,0.40645197,0.00004813849,0.00003526558,0.0001880706,0.000011498064,0.000047875074,0.00047743018],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981533,0.00002727279,0.00031084352,0.00042309138,0.00046717547,0.0006182844],"domain_scores_gemma":[0.99866116,0.00060632935,0.000059637172,0.00041978504,0.00011157522,0.0001414871],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041313615,0.00024589663,0.0001909584,0.0004949536,0.00037661835,0.00016689989,0.0005319753,0.00008985886,0.000008817609],"category_scores_gemma":[0.00016708871,0.00027594468,0.0001393434,0.001272861,0.000018576846,0.00028122857,0.000008164444,0.00044293734,0.00006013378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000053053222,0.000016045393,0.00006023975,0.00013081527,0.000033676853,0.000004336891,0.0002360686,0.99352336,0.00018093796,0.000051373234,0.000025788651,0.005732055],"study_design_scores_gemma":[0.0004786784,0.00019253552,0.00009300671,0.00006190662,0.000012921474,0.0000031336235,0.000023047585,0.9951137,0.003417718,0.0000014754692,0.00032459715,0.00027733404],"about_ca_topic_score_codex":0.000006494386,"about_ca_topic_score_gemma":1.3126994e-7,"teacher_disagreement_score":0.59209895,"about_ca_system_score_codex":0.00015520862,"about_ca_system_score_gemma":0.00006328034,"threshold_uncertainty_score":0.99996924},"labels":[],"label_agreement":null},{"id":"W4367060663","doi":"10.48550/arxiv.2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Successor cardinal; Representation (politics); Value (mathematics); Artificial intelligence; Function (biology); Carry (investment); Feature learning; Object (grammar); Machine learning; Mathematics","score_opus":0.09279756993421001,"score_gpt":0.21577094032397215,"score_spread":0.12297337038976214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367060663","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":[0.018873751,0.000015557222,0.976674,0.00009498331,0.0006021333,0.00095611066,8.4311284e-7,0.0011944311,0.0015881511],"genre_scores_gemma":[0.98399365,0.00011726045,0.007996733,0.00005368576,0.00016055992,0.000009318731,0.000057971127,0.00006105393,0.007549769],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703866,0.00035402397,0.0003157329,0.0014677075,0.00025816908,0.00056568714],"domain_scores_gemma":[0.99740833,0.00024935385,0.00054749247,0.0014104256,0.00020955433,0.0001748332],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005516869,0.0004036499,0.00038320597,0.00036325186,0.00037538083,0.0003711994,0.0018333113,0.0003304079,0.000011770369],"category_scores_gemma":[0.00012367476,0.00044289397,0.0001701601,0.0012423348,0.00013064119,0.00059453445,0.0026140176,0.001537825,0.00013746246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030247249,0.00001583441,0.015041518,0.00007245222,0.00010862092,0.00035674524,0.0002758131,0.9673922,0.000003724359,0.016321452,0.00011141547,0.00026999437],"study_design_scores_gemma":[0.00041024864,0.00009699726,0.0023235902,0.00033276706,0.00006619595,0.0000060195803,0.0001447699,0.9942784,0.00002883427,0.0016074923,0.0002014003,0.00050331943],"about_ca_topic_score_codex":0.00024042692,"about_ca_topic_score_gemma":0.00000980268,"teacher_disagreement_score":0.9686773,"about_ca_system_score_codex":0.00026120705,"about_ca_system_score_gemma":0.00022453444,"threshold_uncertainty_score":0.9998023},"labels":[],"label_agreement":null},{"id":"W4367189765","doi":"10.48550/arxiv.2304.13223","title":"Reinforcement Learning with Partial Parametric Model Knowledge","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 British Columbia; Honeywell (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Ignorance; Bridge (graph theory); Parametric statistics; Control (management); Complete information; Linear-quadratic regulator; Mathematical optimization; Artificial intelligence; Mathematics; Mathematical economics; Law","score_opus":0.1275187607125167,"score_gpt":0.21539233160582583,"score_spread":0.08787357089330913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367189765","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":[0.011344991,0.000020583888,0.9783932,0.000053069598,0.00041239007,0.00041437245,9.770239e-7,0.0010544463,0.008305999],"genre_scores_gemma":[0.96041787,0.00015048849,0.0050646486,0.000032305838,0.000059398557,0.0000040128302,0.00002877761,0.000052425643,0.03419009],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99714035,0.0001570074,0.0003480338,0.0013802674,0.0002556148,0.00071872683],"domain_scores_gemma":[0.99728215,0.0002092699,0.00046911347,0.0015396981,0.0002394977,0.00026026505],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004584053,0.00049722445,0.00045787168,0.00074367394,0.00032321425,0.00029262956,0.0023535863,0.0003304075,0.000017013786],"category_scores_gemma":[0.000108471795,0.0005286958,0.00021032016,0.0017780996,0.00013022451,0.00044642552,0.0036886542,0.0014031387,0.000619991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023837862,0.000026348695,0.001387618,0.00008196537,0.000121090605,0.00013808563,0.00031340725,0.93150944,0.0000017940114,0.06609155,0.00020031806,0.00010454996],"study_design_scores_gemma":[0.0005473852,0.00018770072,0.00010700684,0.00014263975,0.0000872675,0.0000024961234,0.00005074046,0.99592286,0.000037698104,0.0014998387,0.00078072114,0.00063364324],"about_ca_topic_score_codex":0.000066958615,"about_ca_topic_score_gemma":0.000010187716,"teacher_disagreement_score":0.97332853,"about_ca_system_score_codex":0.00041709704,"about_ca_system_score_gemma":0.0005162961,"threshold_uncertainty_score":0.99971646},"labels":[],"label_agreement":null},{"id":"W4367319168","doi":"10.1145/3543873.3587661","title":"Investigating Action-Space Generalization in Reinforcement Learning for Recommendation Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Generalization; Reinforcement learning; Computer science; Action (physics); Space (punctuation); Artificial intelligence; Machine learning; Mathematics","score_opus":0.0737814705673724,"score_gpt":0.31667723497223127,"score_spread":0.24289576440485888,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367319168","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":[0.0023754654,0.0000032680962,0.99275625,0.0011657004,0.00063275767,0.00043898716,7.278709e-8,0.00052217284,0.0021053406],"genre_scores_gemma":[0.95308304,0.000051698156,0.032690704,0.00023552694,0.00013226795,0.00021620218,0.00019426261,0.000025668627,0.013370644],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879456,0.00008611403,0.00036357774,0.00026189248,0.00020371944,0.00029012116],"domain_scores_gemma":[0.99930006,0.00018545083,0.00018915189,0.00018653735,0.00008797369,0.000050799703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007968536,0.00010819951,0.00011514556,0.00030614287,0.0001931099,0.00025266103,0.00024128388,0.00005872648,0.0000087257995],"category_scores_gemma":[0.00029895126,0.00011265502,0.000024318808,0.00095178146,0.000010078835,0.0006511,0.00012188005,0.00012125722,0.00006331337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[5.566613e-7,0.0000017309029,0.0018099624,0.000039328195,0.000004789654,1.8324006e-7,0.00037546264,0.95833254,0.0007775763,0.03517972,0.0019849583,0.0014931858],"study_design_scores_gemma":[0.00028682157,0.00007128285,0.0004398978,0.000036384565,0.0000017246971,8.661077e-7,0.0002265215,0.9874437,0.0006581579,0.00011647384,0.010586522,0.00013165441],"about_ca_topic_score_codex":0.00010047554,"about_ca_topic_score_gemma":0.000009458177,"teacher_disagreement_score":0.96006554,"about_ca_system_score_codex":0.0001504324,"about_ca_system_score_gemma":0.000044958473,"threshold_uncertainty_score":0.45939383},"labels":[],"label_agreement":null},{"id":"W4368227480","doi":"10.1109/iccae56788.2023.10111485","title":"Proximity-Based Reward System and Reinforcement Learning for Path Planning","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université de Moncton","funders":"","keywords":"Reinforcement learning; Motion planning; Computer science; Artificial intelligence; Path (computing); Automation; Machine learning; Robotics; Field (mathematics); Task (project management); Robot; Engineering; Mathematics","score_opus":0.03200085973623594,"score_gpt":0.26905691784965347,"score_spread":0.2370560581134175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4368227480","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":[0.0020598173,0.000011897629,0.99161994,0.00031977746,0.00023056201,0.00050742016,1.5934066e-7,0.0013883949,0.0038619984],"genre_scores_gemma":[0.94175535,0.0000026410596,0.053299557,0.00018368533,0.000052651558,0.00010474615,0.00001823111,0.00002037508,0.0045627556],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985259,0.00004628623,0.00029761926,0.00036418432,0.00033323572,0.00043275687],"domain_scores_gemma":[0.9990776,0.00027014242,0.00013420053,0.0003377475,0.00007876002,0.00010153198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078480324,0.00015658209,0.00017882469,0.00019013496,0.00033425653,0.00025550628,0.00039190202,0.00006321095,0.0000028097397],"category_scores_gemma":[0.0001367545,0.00014063848,0.00005367087,0.00039215732,0.000024212974,0.00031244443,0.00023521761,0.00015045235,0.000048378788],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000070372926,0.0000018703383,0.0016095884,0.0002163988,0.0000120524755,0.000008538233,0.00034718486,0.9709044,0.00008082686,0.025274228,0.000831257,0.0007065873],"study_design_scores_gemma":[0.00051772065,0.00024839916,0.00031685273,0.00013475651,0.0000065281088,0.000003398126,0.00019167655,0.99022865,0.00036464076,0.000034095418,0.0077696196,0.00018368122],"about_ca_topic_score_codex":0.0000064345522,"about_ca_topic_score_gemma":1.06639845e-7,"teacher_disagreement_score":0.93969554,"about_ca_system_score_codex":0.00006762363,"about_ca_system_score_gemma":0.000063771906,"threshold_uncertainty_score":0.5735071},"labels":[],"label_agreement":null},{"id":"W4372259970","doi":"10.1109/icassp49357.2023.10095236","title":"MEET: A Monte Carlo Exploration-Exploitation Trade-Off for Buffer Sampling","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Infineon Technologies (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Sampling (signal processing); Convergence (economics); Task (project management); Importance sampling; Bellman equation; Selection (genetic algorithm); Monte Carlo method; Function (biology); Machine learning; State (computer science); Mathematical optimization; Artificial intelligence; Algorithm; Statistics; Mathematics; Engineering","score_opus":0.08781016052838872,"score_gpt":0.3141202326013707,"score_spread":0.22631007207298195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4372259970","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":[0.0031644406,0.000014959249,0.9908797,0.003411396,0.00047095524,0.0003657608,9.624798e-7,0.0007371546,0.00095463067],"genre_scores_gemma":[0.758444,0.000048999776,0.23420554,0.000759815,0.00019905335,0.00030111236,0.00002391283,0.000039370207,0.0059781782],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885815,0.00002455045,0.00025545427,0.00028957133,0.0002842439,0.00028802652],"domain_scores_gemma":[0.9991697,0.00028152906,0.000075288175,0.00034429584,0.00006815486,0.00006102481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032424388,0.0001167411,0.00011716241,0.00015852749,0.0001806506,0.00022233813,0.00041839803,0.000050122315,0.000008173664],"category_scores_gemma":[0.00015060825,0.00011040124,0.00007201093,0.00051452324,0.000013969861,0.0010369249,0.0000861523,0.000058628862,0.000095060364],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002980879,0.000005848539,0.00007898964,0.000014859817,0.00001400953,8.203923e-7,0.003007196,0.95121694,0.00028079175,0.03278191,0.0050765267,0.0075191315],"study_design_scores_gemma":[0.000264682,0.00008862815,0.00038632101,0.000012320837,0.0000051015986,6.6796224e-7,0.00045502133,0.98705095,0.00042657962,0.0014361435,0.009724855,0.00014871694],"about_ca_topic_score_codex":0.000010012938,"about_ca_topic_score_gemma":0.0000093733315,"teacher_disagreement_score":0.75667423,"about_ca_system_score_codex":0.000045422774,"about_ca_system_score_gemma":0.000040964092,"threshold_uncertainty_score":0.45020318},"labels":[],"label_agreement":null},{"id":"W4375798913","doi":"10.1109/lra.2023.3273421","title":"Multi-Abstractive Neural Controller: An Efficient Hierarchical Control Architecture for Interactive Driving","year":2023,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"Toyota Research Institute","keywords":"Interpretability; Controller (irrigation); Computer science; Artificial neural network; Artificial intelligence; Set (abstract data type); Machine learning; Programming language","score_opus":0.014628632478758305,"score_gpt":0.2679701900467087,"score_spread":0.2533415575679504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375798913","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":[0.069010675,0.0000034344787,0.92161196,0.0075188135,0.0007980746,0.00060327275,0.000005365678,0.00044183538,0.000006554151],"genre_scores_gemma":[0.92805547,0.0000014034716,0.07024477,0.0014488386,0.00014353426,0.00004605089,0.0000138144605,0.00002058715,0.000025526306],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839425,0.00012764843,0.00033988905,0.00043351372,0.00029039785,0.00041428042],"domain_scores_gemma":[0.998525,0.0007811995,0.00021594405,0.00025204144,0.000086088854,0.0001397151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003422221,0.00021545454,0.0002588879,0.00025948748,0.00029057328,0.0003690407,0.00036155566,0.000071827635,0.0000010103965],"category_scores_gemma":[0.00014390613,0.00019730712,0.00009598145,0.00024180925,0.00008042701,0.00042068274,0.00006243196,0.000294901,0.000012860376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017075155,0.000027810192,0.00009888705,0.0000154112,0.00004410351,0.000006956865,0.0011164809,0.9843815,0.0102124065,0.0008695204,0.00012536804,0.0030844936],"study_design_scores_gemma":[0.0017751347,0.00012828053,0.00950422,0.000027937558,0.000018541616,0.000009747995,0.000041746483,0.9879948,0.00013803813,0.00007026967,0.000071781484,0.00021952827],"about_ca_topic_score_codex":0.0000040649325,"about_ca_topic_score_gemma":0.0000017892144,"teacher_disagreement_score":0.8590448,"about_ca_system_score_codex":0.000055312477,"about_ca_system_score_gemma":0.000023112669,"threshold_uncertainty_score":0.8045951},"labels":[],"label_agreement":null},{"id":"W4376223516","doi":"10.1613/jair.1.14580","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Component (thermodynamics); Exploit; Property (philosophy); Offline learning; Key (lock); Class (philosophy); Artificial intelligence; Machine learning; Action (physics); State (computer science); Reinforcement; Online and offline; State action; Online learning; Algorithm","score_opus":0.29473503459567824,"score_gpt":0.4630904091938908,"score_spread":0.16835537459821254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376223516","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":[0.08895168,0.000060372946,0.909827,0.00045055256,0.0002783884,0.00027488184,5.42821e-7,0.000055948927,0.00010066561],"genre_scores_gemma":[0.97709894,0.00065085915,0.021256214,0.000013763521,0.00033915899,0.000011168623,0.0000035104674,0.000021876447,0.0006045336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99656534,0.0002922209,0.0009119301,0.00026427465,0.0012157178,0.00075054367],"domain_scores_gemma":[0.99638253,0.0013216896,0.00043235166,0.00027473803,0.001364103,0.00022456447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009659824,0.0001491343,0.00027532488,0.0008389419,0.00064455665,0.00059380225,0.0006919449,0.00007998419,0.000021098424],"category_scores_gemma":[0.0028116722,0.00012870737,0.00013215048,0.0012874973,0.00012565027,0.0008916739,0.00035871688,0.0008462504,0.00003262782],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010682707,0.000021962538,0.00014240839,0.000053676507,0.000050347844,0.0000294422,0.0015965975,0.86498255,0.012835989,0.0055381223,0.00017335633,0.11446875],"study_design_scores_gemma":[0.00006768596,0.0014535914,0.00016628583,0.000102644444,0.000006904472,0.000049847466,0.0012709629,0.9528758,0.027663037,0.015359727,0.00084825465,0.00013525195],"about_ca_topic_score_codex":0.000066574874,"about_ca_topic_score_gemma":0.0000055576684,"teacher_disagreement_score":0.8885708,"about_ca_system_score_codex":0.00024202636,"about_ca_system_score_gemma":0.00035388695,"threshold_uncertainty_score":0.57260484},"labels":[],"label_agreement":null},{"id":"W4376606197","doi":"10.1109/aero55745.2023.10115987","title":"Stress Propagation in Human-Robot Teams Based on Computational Logic Model","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robot; Stress (linguistics); Toll; Core (optical fiber); Influence diagram; Artificial intelligence; Human–computer interaction; Machine learning; Decision tree","score_opus":0.04069771383618445,"score_gpt":0.29980528452134625,"score_spread":0.25910757068516177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376606197","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":[0.00391872,4.2625942e-7,0.98687625,0.00079970417,0.000066974055,0.0001865266,5.7459556e-7,0.00037311905,0.00777772],"genre_scores_gemma":[0.93408304,2.7246716e-7,0.06383455,0.000510404,0.00001315242,0.000016563023,0.000046726524,0.000007167562,0.0014881087],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988126,0.000045494548,0.00021621809,0.00027279515,0.0004383055,0.00021456103],"domain_scores_gemma":[0.9994779,0.00010464857,0.0000628982,0.00026236643,0.000055181856,0.000037006743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026135557,0.000100092446,0.000090257265,0.0002727769,0.00009310347,0.000107721506,0.00042949454,0.000044214732,0.000017891727],"category_scores_gemma":[0.000036991514,0.000090004105,0.000027742095,0.00058746856,0.000022528797,0.0002098216,0.00010239707,0.00013274846,0.00016760684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013386482,0.00002513027,0.00094616634,0.000008804637,0.0000012325446,0.0000045686097,0.000076374665,0.9175837,0.00006951066,0.08059188,0.00023037044,0.00046094897],"study_design_scores_gemma":[0.00029683218,0.00007644006,0.005406719,0.00002482042,6.810032e-7,2.1662669e-7,0.000010917185,0.9895576,0.00018320308,0.0043263487,0.0000049638106,0.00011122124],"about_ca_topic_score_codex":0.000011987171,"about_ca_topic_score_gemma":0.0000044150306,"teacher_disagreement_score":0.93016434,"about_ca_system_score_codex":0.00007952253,"about_ca_system_score_gemma":0.00007426493,"threshold_uncertainty_score":0.3670261},"labels":[],"label_agreement":null},{"id":"W4376639574","doi":"10.1145/3564246.3585161","title":"Optimistic MLE: A Generic Model-Based Algorithm for Partially Observable Sequential Decision Making","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Google; National Science Foundation","keywords":"Observable; Computer science; Simple (philosophy); Class (philosophy); Reinforcement learning; Rank (graph theory); Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.07463704283305572,"score_gpt":0.31685020754951426,"score_spread":0.24221316471645854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376639574","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":[0.000252531,0.000014237436,0.9974443,0.0001183261,0.00059540477,0.00035303883,0.0000029082785,0.0007497569,0.00046952348],"genre_scores_gemma":[0.052535105,0.000006083812,0.9448649,0.000482023,0.000084725056,0.00007931211,0.000018818597,0.0000270101,0.0019020141],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980787,0.00003259417,0.0003586706,0.00048453896,0.00047663235,0.00056885974],"domain_scores_gemma":[0.9986578,0.00035026768,0.00010966319,0.0006327239,0.00015068427,0.000098855235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005240345,0.00018613628,0.0001906465,0.00016000027,0.0002550803,0.00036311464,0.00096089696,0.00009498983,0.000032231073],"category_scores_gemma":[0.00012765342,0.00017662124,0.00012022418,0.0008012557,0.000027820288,0.00031960546,0.00032242772,0.00010966962,0.0001443213],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066382695,0.000009026882,0.000008666536,0.000012713755,0.00000954233,0.000009547284,0.000033164364,0.8807009,0.00013609715,0.002172535,0.0021350377,0.11476614],"study_design_scores_gemma":[0.00052430003,0.00012215653,0.000015568132,0.00003495096,0.00001298404,0.0000026292196,0.000004711676,0.9963382,0.00033360143,0.0013985768,0.0009807415,0.00023158405],"about_ca_topic_score_codex":0.0000044583226,"about_ca_topic_score_gemma":0.0000020361947,"teacher_disagreement_score":0.11563731,"about_ca_system_score_codex":0.000083771396,"about_ca_system_score_gemma":0.0002508277,"threshold_uncertainty_score":0.7202405},"labels":[],"label_agreement":null},{"id":"W4377018773","doi":"10.32473/flairs.36.133317","title":"Evaluation of Techniques for Sim2Real Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Bridging (networking); Bridge (graph theory); Generalization; Noise (video); Domain (mathematical analysis); Human–computer interaction; Transfer of learning; Process (computing); Artificial intelligence; Mathematics","score_opus":0.2601722272290781,"score_gpt":0.42715826990483485,"score_spread":0.16698604267575673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377018773","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":[0.03162128,0.000019722973,0.9435728,0.0049760113,0.0010135456,0.0020120423,0.000005650845,0.00026680328,0.016512118],"genre_scores_gemma":[0.9914294,0.00013209102,0.007120717,0.000021305412,0.00017697908,0.00022322996,0.000006317567,0.000013629883,0.0008763621],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443245,0.000055357083,0.0007108808,0.0004081477,0.003930742,0.0004624391],"domain_scores_gemma":[0.9883778,0.0005529157,0.00042155787,0.00023972282,0.010343828,0.000064160056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011987141,0.00015316704,0.00020062871,0.00023520006,0.00033843823,0.0002606954,0.0029358594,0.00010784516,0.00004510781],"category_scores_gemma":[0.0043647294,0.00012917204,0.00026027588,0.0013126167,0.0003557846,0.0005899029,0.0011698594,0.0004708591,0.000019030567],"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":[0.000038173952,0.0000420232,0.0003727943,0.0001391192,0.00016460875,8.629897e-8,0.0044088243,0.19836816,0.087836646,0.6414411,0.0026339053,0.064554535],"study_design_scores_gemma":[0.000033546145,0.000121191384,0.00004775445,0.00011525465,0.000011819212,4.4747406e-7,0.0014416452,0.66042787,0.29397556,0.043137304,0.0006055086,0.000082131635],"about_ca_topic_score_codex":0.00005510717,"about_ca_topic_score_gemma":0.0000024311548,"teacher_disagreement_score":0.9598081,"about_ca_system_score_codex":0.00030861006,"about_ca_system_score_gemma":0.0004924182,"threshold_uncertainty_score":0.5455606},"labels":[],"label_agreement":null},{"id":"W4377971347","doi":"10.1109/tai.2023.3279057","title":"Interpreting Tangled Program Graphs Under Partially Observable Dota 2 Invoker Tasks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Graph; Context (archaeology); Machine learning; Task (project management); Theoretical computer science","score_opus":0.08019492026766367,"score_gpt":0.32383461407993724,"score_spread":0.24363969381227357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4377971347","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":[0.005704484,0.000008894842,0.9876691,0.0011573248,0.0021492431,0.0005689865,0.0000034436607,0.001873617,0.00086490024],"genre_scores_gemma":[0.98260134,0.00004459998,0.015625551,0.0005101623,0.000046971523,0.00018813708,0.000004321351,0.000040129176,0.0009388016],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703944,0.00015204045,0.00072171964,0.00070292095,0.0006191909,0.0007647194],"domain_scores_gemma":[0.99821675,0.00035969543,0.0001605773,0.000892935,0.00017298128,0.00019704315],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00059341924,0.0003170495,0.00026205747,0.00041184705,0.00051768625,0.00054744293,0.0011887116,0.0001574909,0.00015279361],"category_scores_gemma":[0.000046294568,0.00032184747,0.00022250647,0.0023820007,0.00017496513,0.0006121966,0.000020465313,0.0005811628,0.0020455495],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022459988,0.00013309177,0.0000103954,0.000013071893,0.00004129376,0.000017387416,0.0007060345,0.8544594,0.0018485807,0.015546546,0.00015089949,0.12705085],"study_design_scores_gemma":[0.000038769915,0.0003404067,0.00002976855,0.00008152886,0.000018592284,0.0000055251594,0.00028813336,0.9116938,0.07731156,0.008863362,0.0009610455,0.0003675241],"about_ca_topic_score_codex":0.00007527359,"about_ca_topic_score_gemma":0.00013312958,"teacher_disagreement_score":0.9768968,"about_ca_system_score_codex":0.00010291423,"about_ca_system_score_gemma":0.00011008238,"threshold_uncertainty_score":0.99992335},"labels":[],"label_agreement":null},{"id":"W4378192263","doi":"10.1109/syscon53073.2023.10131174","title":"A Deep Reinforcement Learning Solution for the Low Level Motion Control of a Robot Manipulator System","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Robot; Artificial intelligence; Motion (physics); Collision avoidance; Object (grammar); Motion control; Tower; Motion planning; Robot control; Variety (cybernetics); Manipulator (device); Artificial neural network; Control (management); Simulation; Collision; Control engineering; Engineering; Mobile robot","score_opus":0.04408496626621557,"score_gpt":0.25571941673726994,"score_spread":0.2116344504710544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378192263","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":[0.0001637006,0.000019233023,0.9973103,0.0004158961,0.00045521712,0.00081210164,2.6239672e-7,0.0004205451,0.00040274684],"genre_scores_gemma":[0.98765105,0.0000054623765,0.010008208,0.00006358431,0.000060169343,0.000104083054,0.0000083278055,0.000014018419,0.002085106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984328,0.0000666018,0.00044624906,0.00024736204,0.0004424548,0.00036451724],"domain_scores_gemma":[0.99872607,0.00030687597,0.00028164271,0.00045309655,0.0001838643,0.00004844832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009296911,0.00014028727,0.00019368494,0.00013421834,0.00031034224,0.00010278106,0.00060940837,0.00006558562,0.000007978604],"category_scores_gemma":[0.00016020541,0.000102418,0.00012915047,0.00042985557,0.00003164393,0.0002644844,0.00016886769,0.0001241656,0.00007758745],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010692926,0.000004258753,0.000115275754,0.00011358739,0.000045160556,6.8340177e-7,0.0002484692,0.95197237,0.00082368165,0.041801944,0.00009732117,0.00476655],"study_design_scores_gemma":[0.0007705492,0.00015383787,0.0013468699,0.00005439481,0.000023312696,0.0000034749983,0.0001863561,0.9965968,0.0005638738,0.000028657467,0.00015749635,0.00011438348],"about_ca_topic_score_codex":0.0000590612,"about_ca_topic_score_gemma":0.0000037486923,"teacher_disagreement_score":0.9874873,"about_ca_system_score_codex":0.00012200678,"about_ca_system_score_gemma":0.000038451217,"threshold_uncertainty_score":0.4176485},"labels":[],"label_agreement":null},{"id":"W4378701136","doi":"10.1016/j.sysconle.2023.105563","title":"Approximated multi-agent fitted Q iteration","year":2023,"lang":"en","type":"article","venue":"Systems & Control Letters","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"Computation; Reinforcement learning; Mathematical optimization; Computer science; Mathematics; Function (biology); Property (philosophy); Applied mathematics; Algorithm; Artificial intelligence","score_opus":0.021773525130426286,"score_gpt":0.24165134738091315,"score_spread":0.21987782225048685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378701136","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":[0.030087769,0.000029182223,0.963424,0.0024452012,0.0018550206,0.00082189747,0.0000022415659,0.0011739066,0.00016078007],"genre_scores_gemma":[0.99502057,0.000001888989,0.0019279919,0.0015736214,0.0001235491,0.00011321127,0.000028033279,0.00002222413,0.0011889271],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980423,0.00020680224,0.00042874936,0.0004045218,0.0004609917,0.00045662734],"domain_scores_gemma":[0.99889714,0.00010917326,0.00019918951,0.0006289081,0.00007497741,0.000090591755],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055116403,0.00019110386,0.00025562427,0.00023804382,0.00013031912,0.00047363705,0.00061899825,0.000068722555,0.000007910291],"category_scores_gemma":[0.000050853047,0.00017845887,0.000080917074,0.00060401345,0.00002079578,0.00039587004,0.00009099865,0.00015695469,0.0014371368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005067955,0.000008776001,0.0022379411,0.000058702273,0.000064635795,0.00004020762,0.00047506488,0.94144607,0.048506867,0.0018058656,0.0051690014,0.00018180112],"study_design_scores_gemma":[0.0013261458,0.000030596,0.0034571562,0.000048977385,0.000007439311,0.0000067785004,0.000025483478,0.99025685,0.00007532478,0.0000019017194,0.004565798,0.0001975674],"about_ca_topic_score_codex":0.000048603877,"about_ca_topic_score_gemma":7.762582e-7,"teacher_disagreement_score":0.9649328,"about_ca_system_score_codex":0.00009919868,"about_ca_system_score_gemma":0.00002082639,"threshold_uncertainty_score":0.99934036},"labels":[],"label_agreement":null},{"id":"W4378768695","doi":"10.48550/arxiv.2305.17198","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology","score_opus":0.13688357938669765,"score_gpt":0.2271378487904828,"score_spread":0.09025426940378514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378768695","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":[0.0018952402,0.0000069909584,0.99380857,0.0015540522,0.0005273857,0.0011012087,0.0000020474763,0.00069861533,0.00040591715],"genre_scores_gemma":[0.95670813,0.000024467436,0.023050016,0.00023994732,0.00005513636,0.000012757188,0.000069960064,0.000036224414,0.019803379],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975414,0.00020150293,0.00037992437,0.0010451752,0.00029743195,0.00053454866],"domain_scores_gemma":[0.9976355,0.00011529768,0.00045540984,0.0012643171,0.00035402656,0.00017548428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00088282774,0.00037540027,0.000281336,0.00043010816,0.00049766694,0.0002502834,0.0021151346,0.00023183388,0.000009043283],"category_scores_gemma":[0.00014309768,0.00036870549,0.00021118717,0.000954802,0.000060418046,0.00027469822,0.0027489257,0.00091084436,0.00039528537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001633149,0.000028186036,0.00027002158,0.00006973355,0.00005022469,0.000021428268,0.00045372272,0.98570335,0.000041170835,0.012384418,0.0007191662,0.0002422279],"study_design_scores_gemma":[0.00052718114,0.000113415466,0.00016208265,0.00014944036,0.000053354834,4.876151e-7,0.000043164968,0.99705875,0.000051364394,0.00045201482,0.0009856044,0.00040315595],"about_ca_topic_score_codex":0.00014910249,"about_ca_topic_score_gemma":0.00005225749,"teacher_disagreement_score":0.9707585,"about_ca_system_score_codex":0.0007109483,"about_ca_system_score_gemma":0.00033830106,"threshold_uncertainty_score":0.9998765},"labels":[],"label_agreement":null},{"id":"W4378771708","doi":"10.48550/arxiv.2305.18246","title":"Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"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":"Alberta Machine Intelligence Institute; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Markov chain Monte Carlo; Computer science; Monte Carlo method; Markov decision process; Posterior probability; Mathematical optimization; Scalability; Gaussian; Regret; Artificial intelligence; Algorithm; Markov process; Mathematics; Machine learning; Bayesian probability; Physics","score_opus":0.12894877218383827,"score_gpt":0.22685229743409413,"score_spread":0.09790352525025586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378771708","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":[0.043057933,0.000018755061,0.95436925,0.0003262725,0.0003662472,0.000568492,4.083645e-7,0.00037385087,0.00091878837],"genre_scores_gemma":[0.9910642,0.0002040119,0.0024695385,0.000038744107,0.000032772587,0.000005705293,0.000012071981,0.000026493546,0.0061464906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979554,0.00019736499,0.00031046534,0.0009186255,0.00019769614,0.00042043746],"domain_scores_gemma":[0.99851435,0.00017619286,0.0003442084,0.00072112976,0.00011955572,0.00012457874],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00064403564,0.0002835907,0.00029954576,0.0004193039,0.00014796863,0.00022265581,0.00051550666,0.00022084589,0.000006618061],"category_scores_gemma":[0.00018992455,0.00033318534,0.00006374568,0.00064731156,0.000063256724,0.0005312535,0.00219391,0.0009348921,0.000109439396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015166905,0.00002085247,0.001615772,0.00009332656,0.00002830598,0.00025550317,0.0007222954,0.98861,0.000016971126,0.008428883,0.000086262735,0.00010662438],"study_design_scores_gemma":[0.00037540658,0.00011040538,0.0005765515,0.00015226942,0.0000250965,0.0000032188752,0.00019411648,0.99726635,0.000031262312,0.00055637694,0.0003813023,0.0003276214],"about_ca_topic_score_codex":0.00042467547,"about_ca_topic_score_gemma":0.000058692327,"teacher_disagreement_score":0.9518997,"about_ca_system_score_codex":0.00034299633,"about_ca_system_score_gemma":0.00015560581,"threshold_uncertainty_score":0.999912},"labels":[],"label_agreement":null},{"id":"W4379881949","doi":"10.1007/s13369-023-07934-2","title":"Reinforcement Learning DDPG–PPO Agent-Based Control System for Rotary Inverted Pendulum","year":2023,"lang":"en","type":"article","venue":"Arabian Journal for Science and Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":31,"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 Windsor","funders":"","keywords":"Inverted pendulum; Control theory (sociology); PID controller; Reinforcement learning; Benchmark (surveying); Controller (irrigation); Linear-quadratic regulator; Pendulum; Computer science; Nonlinear system; Control engineering; Engineering; Artificial intelligence; Control (management); Physics; Temperature control","score_opus":0.019102979118655116,"score_gpt":0.23912099867232542,"score_spread":0.2200180195536703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379881949","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":[0.008772662,0.00003342766,0.9883223,0.0005532353,0.0015089929,0.00043046253,8.3160324e-7,0.0002989612,0.00007911285],"genre_scores_gemma":[0.98596627,0.000011330103,0.013461655,0.0001411936,0.0001269179,0.000056027893,0.000002929666,0.00001934437,0.00021435284],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790514,0.000017312985,0.0003962197,0.00032751902,0.0005917904,0.0007620005],"domain_scores_gemma":[0.9987774,0.00021396976,0.00016259552,0.00023613613,0.0003033422,0.00030659058],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025433875,0.00018352749,0.00021711095,0.0005397739,0.0009816148,0.00066038343,0.00082351005,0.000047020403,0.0000013622678],"category_scores_gemma":[0.00058319414,0.00017209818,0.00010123599,0.0009129234,0.000067646135,0.0009390915,0.000078319346,0.00024613715,0.000010814555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008173041,0.0000020094344,0.00019845912,0.00010453538,0.000016374624,0.000008771764,0.00019224458,0.99059534,0.003996832,0.0026033698,0.00023272463,0.0020411927],"study_design_scores_gemma":[0.0011172064,0.0003092505,0.00043263423,0.00015373417,0.000013882555,0.000045049386,0.0001464768,0.9924547,0.0009899378,0.00001953186,0.0041018426,0.0002157688],"about_ca_topic_score_codex":0.0000031289649,"about_ca_topic_score_gemma":2.9359347e-7,"teacher_disagreement_score":0.9771936,"about_ca_system_score_codex":0.00019749443,"about_ca_system_score_gemma":0.00022349056,"threshold_uncertainty_score":0.75498873},"labels":[],"label_agreement":null},{"id":"W4380319104","doi":"10.1007/978-3-319-08234-9_524-1","title":"Trustworthy Embodied Virtual Agents","year":2023,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Embodied cognition; Trustworthiness; Computer science; Embodied agent; Human–computer interaction; Internet privacy; Artificial intelligence","score_opus":0.0178975753135585,"score_gpt":0.2319258496028856,"score_spread":0.21402827428932708,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380319104","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007607837,0.000380701,0.5221147,0.00023037064,0.0030148057,0.00038565128,0.000015768377,0.00039292115,0.47338903],"genre_scores_gemma":[0.0035394465,0.033723373,0.026320944,0.001061021,0.0013892767,0.00002163401,0.00012160712,0.00024831516,0.9335744],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974213,0.000033837037,0.00071513763,0.00071446685,0.00073769846,0.0003775226],"domain_scores_gemma":[0.99793583,0.00030653842,0.0005291027,0.00088034035,0.0001652939,0.00018288023],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00031068266,0.0005131326,0.00070136465,0.0006065105,0.000115385235,0.0001533238,0.0011434641,0.00037097008,0.000030381076],"category_scores_gemma":[0.000019039706,0.0005040717,0.00027275464,0.00016696821,0.00023627792,0.00021599223,0.0010492876,0.00058137777,0.00007713485],"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":[0.0000041057433,0.000010114089,0.00018321007,0.0000768727,0.00017681986,0.000047350783,0.00040258048,0.0042026085,8.1867924e-8,0.9540837,0.012455198,0.028357385],"study_design_scores_gemma":[0.00063134154,0.0006860669,0.0018457756,0.00048463672,0.000096763615,0.00001657325,0.0000052338596,0.19925192,0.0000015113842,0.059343595,0.7365687,0.0010678801],"about_ca_topic_score_codex":0.000006980739,"about_ca_topic_score_gemma":0.000004074294,"teacher_disagreement_score":0.8947401,"about_ca_system_score_codex":0.000014249968,"about_ca_system_score_gemma":0.000090775015,"threshold_uncertainty_score":0.9997411},"labels":[],"label_agreement":null},{"id":"W4380684831","doi":"10.1109/tmlcn.2023.3285543","title":"Reinforcement Learning With Non-Cumulative Objective","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Machine Learning in Communications and Networking","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Markov decision process; Bottleneck; Function (biology); Mathematical optimization; Process (computing); Artificial intelligence; Bellman equation; Convergence (economics); Markov process; Mathematics; Statistics","score_opus":0.028966426693772064,"score_gpt":0.27923764646791815,"score_spread":0.25027121977414607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380684831","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":[0.002517091,0.00012037631,0.9921656,0.0006609696,0.0001516712,0.00030452418,3.0399656e-7,0.00051009125,0.00356936],"genre_scores_gemma":[0.98760396,0.0019326601,0.008692925,0.00009497306,0.00002495306,0.00009409474,0.000013036007,0.000033700617,0.0015097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810654,0.00035018008,0.00038378144,0.00040070576,0.00031448578,0.00044429704],"domain_scores_gemma":[0.9977914,0.0009765303,0.00020330958,0.00086914655,0.00007346908,0.000086151354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007618597,0.00025134013,0.00025487837,0.00053358224,0.0012076927,0.00019754835,0.0007956886,0.00008786351,0.000008254284],"category_scores_gemma":[0.00001180635,0.0002404095,0.00005816173,0.0018089187,0.00013084205,0.00037408786,0.00005779747,0.0016480932,0.0000383013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019751757,0.000022578031,0.0021960752,0.000009126217,0.000041379088,0.0000049625205,0.0024252613,0.951214,0.000032686534,0.00029099645,0.000004778526,0.04373838],"study_design_scores_gemma":[0.00065040996,0.00043080194,0.0012863289,0.00021405422,0.0000150586175,0.0000092685295,0.00024316745,0.9929357,0.00004291605,0.000053385258,0.0038462412,0.00027266654],"about_ca_topic_score_codex":0.0001893606,"about_ca_topic_score_gemma":0.00012734806,"teacher_disagreement_score":0.98508686,"about_ca_system_score_codex":0.00011616902,"about_ca_system_score_gemma":0.00005497864,"threshold_uncertainty_score":0.98036146},"labels":[],"label_agreement":null},{"id":"W4381730562","doi":"10.1109/radarconf2351548.2023.10149670","title":"Priority-based Task Scheduling in Dynamic Environments for Cognitive MFR via Transfer DRL","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Defence Research and Development Canada; University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Scheduling (production processes); Adaptability; Transfer of learning; Dynamic priority scheduling; Distributed computing; Radar; Task analysis; Real-time computing; Adaptation (eye); Task (project management); Artificial intelligence; Computer network; Engineering; Systems engineering","score_opus":0.01586660077822366,"score_gpt":0.2675579138119542,"score_spread":0.25169131303373055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381730562","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":[0.044693347,0.000005705598,0.9537247,0.000421039,0.00017431841,0.000520473,0.0000025511597,0.00018731765,0.00027058946],"genre_scores_gemma":[0.9556837,0.000007077639,0.04265647,0.0003580396,0.000012355521,0.00006636576,0.0000364511,0.000017903803,0.0011616484],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860704,0.000046865483,0.00026276827,0.00038602095,0.00028468532,0.0004126248],"domain_scores_gemma":[0.9993302,0.00030982352,0.000029221457,0.0002470702,0.00001808339,0.000065564476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038839594,0.00014816872,0.00015445628,0.00021261426,0.00009289964,0.00007535831,0.00043122802,0.00007672182,0.000017366945],"category_scores_gemma":[0.0000572924,0.00015050458,0.00007148342,0.0004560209,0.000040545783,0.0002593954,0.00008080905,0.00016129199,0.00025304535],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016450973,0.000041943433,0.0019451043,0.00003823447,0.000019240277,0.000011971292,0.0004934206,0.9843466,0.004048406,0.0013053942,0.000009581638,0.007723627],"study_design_scores_gemma":[0.0011815287,0.00011142817,0.004723863,0.00004041956,0.000006924787,4.790185e-7,0.0000449727,0.991162,0.0019263523,0.00023511998,0.0003784511,0.00018848277],"about_ca_topic_score_codex":0.000008542885,"about_ca_topic_score_gemma":0.00001032476,"teacher_disagreement_score":0.9110682,"about_ca_system_score_codex":0.000085971915,"about_ca_system_score_gemma":0.00005280449,"threshold_uncertainty_score":0.6137399},"labels":[],"label_agreement":null},{"id":"W4382050679","doi":"10.1109/icuas57906.2023.10156452","title":"Coordinated Multi-Robot Exploration using Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Regina","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Robot; Robotics; Focus (optics); Process (computing); Autonomous agent; Human–computer interaction; Machine learning","score_opus":0.10639687791579537,"score_gpt":0.31741472475726124,"score_spread":0.21101784684146585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382050679","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":[0.0012897694,0.0000044691064,0.9940922,0.00026873808,0.0003998336,0.00019940668,3.32153e-8,0.0014830638,0.0022624338],"genre_scores_gemma":[0.8848714,0.000016004973,0.09962352,0.00021359787,0.00004457291,0.000015093708,0.000019557587,0.000023170027,0.015173067],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985041,0.00007703039,0.00033584537,0.00032584314,0.00033829233,0.00041890694],"domain_scores_gemma":[0.9991916,0.00006883711,0.00014169404,0.000396057,0.00012384875,0.00007798253],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00046104778,0.00015905131,0.00014166308,0.00028263312,0.0003146638,0.0002694658,0.0005270957,0.00006554539,0.00004270369],"category_scores_gemma":[0.00015097992,0.00015466823,0.000054389908,0.0012668252,0.000025832263,0.0011925708,0.00043523783,0.0002053852,0.0008452449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014125012,0.0000049423825,0.0004238092,0.000007994509,0.000012311021,0.000008840561,0.00049756543,0.98985803,0.0030960261,0.004586158,0.00022382036,0.0012790738],"study_design_scores_gemma":[0.00036353167,0.00007106286,0.00019192277,0.00001969469,0.000004214385,0.0000029430435,0.00017395997,0.995309,0.0021867773,0.0000397763,0.00143815,0.00019898298],"about_ca_topic_score_codex":0.000048946127,"about_ca_topic_score_gemma":0.0000016623603,"teacher_disagreement_score":0.8944687,"about_ca_system_score_codex":0.000096840726,"about_ca_system_score_gemma":0.000052899595,"threshold_uncertainty_score":0.9999327},"labels":[],"label_agreement":null},{"id":"W4382197597","doi":"10.21203/rs.3.rs-3080402/v1","title":"Long short-term prediction guides human metacognitive reinforcement learning","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"Samsung; Ministry of Science and ICT, South Korea; University of Oxford; Korea Advanced Institute of Science and Technology; National Research Foundation; National Research Foundation of Korea; Somerville College, University of Oxford","keywords":"Term (time); Reinforcement learning; Metacognition; Reinforcement; Cognitive psychology; Psychology; Computer science; Artificial intelligence; Machine learning; Social psychology; Cognition; Neuroscience","score_opus":0.16443007410398042,"score_gpt":0.4243602209578892,"score_spread":0.2599301468539088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382197597","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":[0.0074220183,0.00019072414,0.9747743,0.00039554757,0.0010773167,0.0022513473,0.0000111057625,0.0017564615,0.012121184],"genre_scores_gemma":[0.97125363,0.0004921958,0.002327071,0.000022882345,0.0006364546,0.0006213648,0.0007565059,0.00012374687,0.023766158],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.990626,0.0011885773,0.0010473161,0.0016094873,0.003983843,0.0015447827],"domain_scores_gemma":[0.9949754,0.0007186027,0.00029143595,0.0019064345,0.0017269343,0.00038121705],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0055594654,0.0005557559,0.00059481,0.0015456901,0.0013055207,0.0017201827,0.0029965173,0.0005387416,0.00012503144],"category_scores_gemma":[0.0014252304,0.00057185465,0.00036099658,0.0011745052,0.00027239643,0.0006378929,0.009968016,0.004777181,0.0007082712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011086257,0.000035686156,0.016518813,0.0008322469,0.00028181003,0.00020356939,0.0016500715,0.9718572,0.00023014426,0.0034285188,0.002029157,0.0029216867],"study_design_scores_gemma":[0.000530131,0.0012315415,0.063115224,0.0033413523,0.00006940919,0.000012534313,0.00057472714,0.9245808,0.0014561825,0.0019390425,0.002144795,0.0010042461],"about_ca_topic_score_codex":0.00019948086,"about_ca_topic_score_gemma":0.00002358547,"teacher_disagreement_score":0.9724472,"about_ca_system_score_codex":0.0008608457,"about_ca_system_score_gemma":0.00050517946,"threshold_uncertainty_score":0.99999464},"labels":[],"label_agreement":null},{"id":"W4382202736","doi":"10.1609/aaai.v37i10.26371","title":"Learning to Shape Rewards Using a Game of Two Partners","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Alberta; UK Research and Innovation; Alberta Machine Intelligence Institute; Compute Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Task (project management); Function (biology); Convergence (economics); Construct (python library); Markov decision process; Artificial intelligence; State (computer science); Domain (mathematical analysis); Machine learning; Markov process; Algorithm; Mathematics; Engineering","score_opus":0.15084227496424973,"score_gpt":0.37279789706808497,"score_spread":0.22195562210383524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382202736","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":[0.80824417,0.0000047629346,0.1815467,0.0018374716,0.00056231517,0.00055910874,0.0000013602836,0.0003052412,0.0069388575],"genre_scores_gemma":[0.9928456,0.000013453428,0.0064388397,0.0001106918,0.000047078473,0.000011581549,3.35897e-7,0.000017775697,0.0005146569],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975744,0.000028694465,0.00067262055,0.00046664252,0.0007855231,0.00047210132],"domain_scores_gemma":[0.998212,0.00013490835,0.0005060469,0.0003294535,0.0006997765,0.000117835814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092235336,0.00021924649,0.00032636934,0.0003257226,0.00016138154,0.00018848504,0.0021361292,0.00006912412,0.000044886703],"category_scores_gemma":[0.0011381786,0.00018263755,0.00013120225,0.0021147658,0.00019710696,0.00033575765,0.0008671129,0.00035604538,0.00016897319],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003846505,0.00003471047,0.0011840892,0.000066856264,0.00002360191,9.798515e-7,0.005964089,0.47090822,0.11144512,0.38381892,0.00008442326,0.026430506],"study_design_scores_gemma":[0.000023880288,0.0002471151,0.00014794627,0.00027026163,0.000009345761,0.0000019791348,0.00069819577,0.79993725,0.18886964,0.009533662,0.00008797129,0.00017277422],"about_ca_topic_score_codex":0.000045073473,"about_ca_topic_score_gemma":0.0000018054404,"teacher_disagreement_score":0.37428525,"about_ca_system_score_codex":0.00005699352,"about_ca_system_score_gemma":0.00013523451,"threshold_uncertainty_score":0.7447743},"labels":[],"label_agreement":null},{"id":"W4382239700","doi":"10.1609/aaai.v37i6.25825","title":"PiCor: Multi-Task Deep Reinforcement Learning with Policy Correction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Task (project management); Computer science; Constraint (computer-aided design); Set (abstract data type); Artificial intelligence; Interference (communication); Machine learning; Channel (broadcasting); Mathematics; Engineering","score_opus":0.06260084640833517,"score_gpt":0.2989850664917558,"score_spread":0.23638422008342064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382239700","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":[0.013885499,0.000004568438,0.9710676,0.0021800718,0.00076122273,0.00055779103,2.5331147e-7,0.00052980665,0.011013205],"genre_scores_gemma":[0.9934386,0.000051784507,0.0023597085,0.00015659501,0.00008464202,0.00003710558,0.0000014470238,0.00002173315,0.003848389],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975906,0.000024575667,0.0005535978,0.0005091121,0.0007793089,0.0005427827],"domain_scores_gemma":[0.9982592,0.00011501106,0.00054402853,0.00034892705,0.0006230652,0.00010976811],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053514953,0.00027589148,0.00025418625,0.00038004483,0.00041489973,0.00035741032,0.0017288275,0.0000934659,0.000028879647],"category_scores_gemma":[0.0007938605,0.00020295392,0.00009918239,0.0020878382,0.0002273838,0.000511422,0.0005397301,0.0005300157,0.0003729894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000555641,0.00004277975,0.0008220025,0.000037760037,0.000027794133,0.0000010789593,0.002780319,0.67854685,0.011013279,0.27456403,0.00013776321,0.031970788],"study_design_scores_gemma":[0.00004972408,0.00045495125,0.00041698376,0.00018750016,0.0000096776275,0.0000057214634,0.00076413306,0.89911497,0.09645052,0.0020953622,0.00021788785,0.00023258443],"about_ca_topic_score_codex":0.000089540954,"about_ca_topic_score_gemma":0.000008455007,"teacher_disagreement_score":0.9795531,"about_ca_system_score_codex":0.00012295935,"about_ca_system_score_gemma":0.00016331846,"threshold_uncertainty_score":0.82762206},"labels":[],"label_agreement":null},{"id":"W4382318178","doi":"10.1609/aaai.v37i8.26146","title":"Hypernetworks for Zero-Shot Transfer in Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Computer science; Transfer of learning; Context (archaeology); Artificial intelligence; Task (project management); Set (abstract data type); Machine learning; Bellman equation; Mathematical optimization; Mathematics","score_opus":0.1140650363566056,"score_gpt":0.30957506420392306,"score_spread":0.19551002784731747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318178","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":[0.043517977,0.000008755408,0.9415976,0.002451647,0.00060202397,0.0010096818,7.477175e-7,0.0002609395,0.010550657],"genre_scores_gemma":[0.9966988,0.00006158241,0.0012903663,0.00014276634,0.0000485935,0.00009196417,0.0000017781205,0.000019113653,0.0016450594],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976925,0.000018296512,0.00070041977,0.00047573357,0.00053967914,0.0005733526],"domain_scores_gemma":[0.9988997,0.00021737887,0.00018760428,0.0002608654,0.00036109818,0.00007337801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000988232,0.00023457769,0.00029230374,0.0002618379,0.00020099519,0.00022597788,0.0018474094,0.000116327654,0.000029254208],"category_scores_gemma":[0.0004834271,0.00019225704,0.0001248316,0.0012918437,0.00013955023,0.00036603725,0.00030229712,0.0004483723,0.000099333185],"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":[0.00004446092,0.00002177543,0.00030232497,0.00004777159,0.000010045122,3.8967167e-7,0.0014018049,0.43167633,0.0067016566,0.54965985,0.00013646511,0.009997107],"study_design_scores_gemma":[0.00006138445,0.00033423444,0.0001296653,0.00023254665,0.0000070413657,0.0000010350476,0.00030189473,0.89585304,0.08019302,0.022260899,0.00040490105,0.00022032316],"about_ca_topic_score_codex":0.000016603639,"about_ca_topic_score_gemma":0.000004238305,"teacher_disagreement_score":0.9531808,"about_ca_system_score_codex":0.000067359375,"about_ca_system_score_gemma":0.00008063376,"threshold_uncertainty_score":0.78400147},"labels":[],"label_agreement":null},{"id":"W4382334265","doi":"10.48550/arxiv.2306.14808","title":"Maximum State Entropy Exploration using Predecessor and Successor Representations","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Canada Excellence Research Chairs, Government of Canada; Canadian Institute for Advanced Research","keywords":"Successor cardinal; Computer science; Entropy (arrow of time); Exploratory research; Artificial intelligence; Machine learning; Mathematics; Sociology","score_opus":0.17693395941218948,"score_gpt":0.24389825658468828,"score_spread":0.0669642971724988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382334265","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":[0.1042276,0.000014188637,0.89383805,0.00019904872,0.000651974,0.00038055817,0.000009648213,0.00041164405,0.00026728405],"genre_scores_gemma":[0.9863017,0.00036795138,0.009187092,0.000032600048,0.00005502038,0.0000022329637,0.000042674452,0.000032184962,0.0039785025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979982,0.00017038824,0.0002809903,0.0010353621,0.0001636783,0.0003513789],"domain_scores_gemma":[0.99806166,0.0001481572,0.00040900297,0.0010498732,0.00018698772,0.00014430685],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025182104,0.000271675,0.00025921533,0.00037871365,0.00027812071,0.0004686811,0.0010708133,0.00015598345,0.00001041647],"category_scores_gemma":[0.00008703509,0.0003343899,0.00009418481,0.0006540166,0.00010768703,0.0012663803,0.00242306,0.00042649146,0.00006216811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010439142,0.0000139777485,0.003835663,0.000062269406,0.00006426004,0.000105577274,0.0004820387,0.97699815,0.00006818855,0.018183025,0.0000879368,0.00008846324],"study_design_scores_gemma":[0.00031711019,0.000029679179,0.0011579798,0.000076689714,0.000052314626,0.0000023450043,0.00010953631,0.9613213,0.00015262573,0.03636658,0.00009855518,0.0003152861],"about_ca_topic_score_codex":0.00027121181,"about_ca_topic_score_gemma":0.000024541423,"teacher_disagreement_score":0.88465095,"about_ca_system_score_codex":0.00017675405,"about_ca_system_score_gemma":0.00015597591,"threshold_uncertainty_score":0.99991083},"labels":[],"label_agreement":null},{"id":"W4382653405","doi":"10.1002/9781119873747.ch2","title":"Markov Decision Process and Reinforcement Learning","year":2023,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","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 Manitoba","funders":"","keywords":"Markov decision process; Reinforcement learning; Computer science; Q-learning; Markov process; Key (lock); Partially observable Markov decision process; Process (computing); Mathematical optimization; Markov chain; Bellman equation; Extension (predicate logic); Machine learning; Artificial intelligence; Markov model; Mathematics","score_opus":0.011509651708220893,"score_gpt":0.2672792631151527,"score_spread":0.25576961140693183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382653405","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.741936e-7,0.000051812942,0.5733636,0.00004099468,0.0002866828,0.0001570503,7.0790094e-8,0.0015062958,0.4245926],"genre_scores_gemma":[0.00081222976,0.0004445069,0.024316313,0.000099136,0.00009724141,0.000018231989,0.000003992483,0.00043857913,0.9737698],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983117,0.000025991027,0.0002613187,0.0005050903,0.0005666335,0.00032929506],"domain_scores_gemma":[0.9989974,0.00014044248,0.00021796295,0.0005048533,0.000035669607,0.000103680926],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026545138,0.00026686248,0.00025195346,0.00035942232,0.00008859329,0.00024089227,0.00070665934,0.0002039987,0.00055900123],"category_scores_gemma":[0.00016505261,0.0002308759,0.000043043412,0.00034494774,0.000036500584,0.00015747499,0.0005623726,0.00032283066,0.00062868354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058193655,0.000008207612,0.0005659068,0.00022658998,0.000099835626,0.000042359137,0.00033724605,0.47061715,0.0000019690062,0.01037468,0.41914713,0.09857309],"study_design_scores_gemma":[0.0002966597,0.00011531044,0.00006437883,0.0004539158,0.000010633588,0.0000068605227,0.00002901035,0.52593416,0.000008707192,0.000121475234,0.47253153,0.00042734813],"about_ca_topic_score_codex":0.00005018463,"about_ca_topic_score_gemma":0.000020418656,"teacher_disagreement_score":0.54917717,"about_ca_system_score_codex":0.000037231002,"about_ca_system_score_gemma":0.000049475293,"threshold_uncertainty_score":0.9414846},"labels":[],"label_agreement":null},{"id":"W4383097435","doi":"10.1109/icra48891.2023.10160684","title":"Real-Time Reinforcement Learning for Vision-Based Robotics Utilizing Local and Remote Computers","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Computation; Workstation; Robotics; Robot; Artificial intelligence; Mobile robot; Resource (disambiguation); Distributed computing; Real-time computing; Operating system; Computer network","score_opus":0.02114241953396678,"score_gpt":0.27674038051919714,"score_spread":0.25559796098523035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383097435","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":[0.00032383148,0.0000060683947,0.99347675,0.0010486337,0.00028923253,0.00041167933,1.6608179e-7,0.001158742,0.0032849207],"genre_scores_gemma":[0.28335986,0.00008087941,0.7060875,0.0005869736,0.00007339006,0.000010657745,0.000059959115,0.000058909776,0.009681848],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997891,0.000069380425,0.0004443788,0.0005296555,0.00045171138,0.00061383983],"domain_scores_gemma":[0.99814314,0.0008769422,0.0001629445,0.0005092982,0.00012517592,0.00018253126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007672889,0.0002454196,0.0002737458,0.00027957157,0.00039697648,0.00032997952,0.00059270125,0.00010128011,0.000012893042],"category_scores_gemma":[0.00013176176,0.00023667245,0.000097002456,0.0006033276,0.00009946329,0.000316853,0.00048177294,0.00019877937,0.00016005014],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010001272,0.000004147508,0.000041152674,0.000050362898,0.000017529452,0.000007660114,0.00013348035,0.97150874,0.00028748674,0.0068395073,0.001976612,0.019123344],"study_design_scores_gemma":[0.0007039627,0.0004248713,0.00016794,0.000092021,0.000010448002,0.000003290426,0.000056277,0.9947498,0.00029615808,0.00015944066,0.003049599,0.00028619161],"about_ca_topic_score_codex":0.00004263101,"about_ca_topic_score_gemma":7.7122206e-7,"teacher_disagreement_score":0.2873892,"about_ca_system_score_codex":0.00009120967,"about_ca_system_score_gemma":0.00010868709,"threshold_uncertainty_score":0.9651222},"labels":[],"label_agreement":null},{"id":"W4383097456","doi":"10.1109/icra48891.2023.10160572","title":"On Legible and Predictable Robot Navigation in Multi-Agent Environments","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Legibility; Predictability; Computer science; Robot; Generalization; Artificial intelligence; Human–computer interaction; Computer vision; Mathematics","score_opus":0.033752734947392074,"score_gpt":0.2678673256716823,"score_spread":0.23411459072429025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383097456","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":[0.042377207,0.0000067929623,0.9553973,0.00025237963,0.00016260578,0.00016029377,2.0606392e-7,0.00014181885,0.0015013702],"genre_scores_gemma":[0.9665858,0.000034898465,0.020033818,0.00015702263,0.000008715093,0.000015926114,0.000010200127,0.000008002804,0.013145625],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991718,0.00002709724,0.00013919841,0.00023343912,0.0002242808,0.00020416774],"domain_scores_gemma":[0.9996197,0.000052512183,0.00003343433,0.00024356706,0.000003889286,0.000046848923],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021375081,0.00007602136,0.00006877724,0.00011018665,0.000054786968,0.000073888914,0.00021601094,0.00003558572,0.000014417893],"category_scores_gemma":[0.000024250347,0.00007032945,0.000011559711,0.00027417048,0.000017325123,0.00027671846,0.00020260032,0.00009202386,0.00036966335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011427265,0.000017984374,0.0053033433,0.000005812494,0.000002978582,0.000008127925,0.00027547937,0.98852223,0.0006584746,0.0039185965,0.0003368896,0.0009489203],"study_design_scores_gemma":[0.00037387118,0.00006830673,0.032023545,0.000022820766,8.389852e-7,9.874789e-7,0.000019659206,0.9655449,0.0008488843,0.00015665531,0.0008618551,0.000077716],"about_ca_topic_score_codex":0.000027118336,"about_ca_topic_score_gemma":0.0000018666065,"teacher_disagreement_score":0.93536353,"about_ca_system_score_codex":0.00004789849,"about_ca_system_score_gemma":0.000008758432,"threshold_uncertainty_score":0.4751398},"labels":[],"label_agreement":null},{"id":"W4383112356","doi":"10.1109/lra.2023.3292004","title":"SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding","year":2023,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristic; Path (computing); Observable; Computer science; Mathematical optimization; Artificial intelligence; Mathematics; Physics","score_opus":0.0428821579873367,"score_gpt":0.2687953178799828,"score_spread":0.2259131598926461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383112356","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":[0.031739555,0.0000064173114,0.9619867,0.004795012,0.0005736906,0.00040340563,0.0000038355597,0.0004876241,0.000003739416],"genre_scores_gemma":[0.7800946,0.0000055417863,0.21821764,0.00127649,0.00007913647,0.00005726359,0.000057426623,0.000030820796,0.00018106302],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850965,0.000051764222,0.0003155372,0.00036578538,0.00034229574,0.00041498308],"domain_scores_gemma":[0.9990896,0.0002389,0.00017919898,0.00030459862,0.00009178499,0.00009591697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033941946,0.00019256858,0.00018681343,0.00016085742,0.00033131312,0.00039220566,0.0002695439,0.000058386293,0.0000018021244],"category_scores_gemma":[0.00007239057,0.00018001032,0.00006170283,0.0003493013,0.00004785861,0.00038706162,0.0000447926,0.000107807486,0.000030991712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042699708,0.000018717503,0.0016662767,0.00013074797,0.000022295117,0.000011082712,0.00013991185,0.9902044,0.0054433476,0.0008630463,0.0009151591,0.00058073126],"study_design_scores_gemma":[0.0008383132,0.000110782865,0.009727848,0.00011678848,0.00002932468,0.0000026305754,0.000016210257,0.98824996,0.0003812626,0.000023545159,0.00026747293,0.00023585632],"about_ca_topic_score_codex":0.0000052029723,"about_ca_topic_score_gemma":0.0000025964493,"teacher_disagreement_score":0.7483551,"about_ca_system_score_codex":0.00006704871,"about_ca_system_score_gemma":0.000052929678,"threshold_uncertainty_score":0.73406076},"labels":[],"label_agreement":null},{"id":"W4383424630","doi":"10.1007/978-3-031-36183-8_9","title":"Unified Emulation-Simulation Training Environment for Autonomous Cyber Agents","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Carleton University; Queen's University; Defence Research and Development Canada","funders":"","keywords":"Emulation; Computer science; Reinforcement learning; Fidelity; Process (computing); Artificial intelligence; Human–computer interaction; Intelligent agent; Simulation; Distributed computing; Operating system","score_opus":0.06123982952119357,"score_gpt":0.2813513022896291,"score_spread":0.22011147276843557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383424630","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":[0.00002347313,0.000021572649,0.99534774,0.00032890282,0.0018475996,0.0008421596,0.000004113221,0.00031052367,0.0012739351],"genre_scores_gemma":[0.265666,0.00002151859,0.72656053,0.00095073454,0.00064423145,0.00004300274,0.00005799258,0.000116807736,0.0059391554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962017,0.000027687345,0.0006723839,0.0013576616,0.0010342622,0.0007062859],"domain_scores_gemma":[0.99707514,0.0010676918,0.00043119604,0.0011597498,0.00012024219,0.00014598026],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009240151,0.00048720697,0.0004487447,0.00075502845,0.00037049572,0.0005096957,0.0020828664,0.00031979338,0.000023721412],"category_scores_gemma":[0.00014623054,0.00050297886,0.00015677896,0.00036743298,0.00027884977,0.0005374891,0.00083298696,0.0004967985,0.00012420412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002653021,0.000004832982,0.000013585043,0.000016919323,0.00001115025,0.000009274331,0.001042693,0.8168644,0.000009327033,0.008878052,0.0000064738356,0.17314069],"study_design_scores_gemma":[0.00030925404,0.00012791963,0.0003031998,0.00014093795,0.000010402117,0.0000040079353,2.6064683e-7,0.96572787,0.00004217436,0.028982315,0.0038446211,0.0005070569],"about_ca_topic_score_codex":0.0000057877746,"about_ca_topic_score_gemma":0.000006014735,"teacher_disagreement_score":0.26878718,"about_ca_system_score_codex":0.0005060687,"about_ca_system_score_gemma":0.00034546686,"threshold_uncertainty_score":0.9997422},"labels":[],"label_agreement":null},{"id":"W4383560595","doi":"10.54254/2755-2721/5/20230668","title":"Applications of deep reinforcement learning — Alphago","year":2023,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Deep learning; Field (mathematics); Computer science; Engineering","score_opus":0.006777116084209396,"score_gpt":0.21245335243257704,"score_spread":0.20567623634836765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4383560595","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":[0.00079406844,0.000023111708,0.997235,0.0000478247,0.000034555564,0.00012907237,9.276226e-8,0.00028339992,0.0014529005],"genre_scores_gemma":[0.9595425,0.000010428422,0.040226378,0.000025873278,0.000024515934,0.00005004013,0.000021197759,0.000008461972,0.00009058635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927,0.000003781963,0.00019727145,0.00015791405,0.0002210268,0.00015001115],"domain_scores_gemma":[0.99959433,0.00014602048,0.00006277598,0.00011230994,0.000038071015,0.000046518944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012270117,0.00008564454,0.000098144636,0.00015813315,0.00007491288,0.000037804093,0.00019428426,0.000026606673,0.000004055488],"category_scores_gemma":[0.000010430315,0.00009479976,0.000021735228,0.0004914384,0.00001530027,0.00008349,0.00015300252,0.00009630742,0.000033777964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.695921e-7,0.0000017475589,0.000026958396,0.000023781593,0.000011101266,3.508039e-7,0.00016471925,0.7701821,0.00019129817,0.22195168,0.000007543855,0.0074383137],"study_design_scores_gemma":[0.00014741602,0.000016008866,0.001027192,0.0000061405913,0.0000028955174,0.0000020591287,0.00002643555,0.9958897,0.0001157947,0.0011433722,0.0015300231,0.000092940674],"about_ca_topic_score_codex":0.0000011965618,"about_ca_topic_score_gemma":2.9298057e-8,"teacher_disagreement_score":0.95874846,"about_ca_system_score_codex":0.000013079551,"about_ca_system_score_gemma":0.00001381262,"threshold_uncertainty_score":0.3865822},"labels":[],"label_agreement":null},{"id":"W4384574988","doi":"10.23952/jano.5.2023.2.01","title":"Multi-step actor-critic framework for reinforcement learning in continuous control","year":2023,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Reinforcement Learning in Robotics","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; Temporal difference learning; Computer science; Sequence (biology); State (computer science); Control (management); Artificial intelligence; Reinforcement; Optimal control; Action (physics); Machine learning; Mathematical optimization; Mathematics; Algorithm; Engineering","score_opus":0.015598831028528763,"score_gpt":0.2672656284476811,"score_spread":0.2516667974191523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384574988","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":[0.0003090465,0.000029546687,0.9986778,0.0003875884,0.00018706059,0.00024268501,1.5797993e-7,0.000052426047,0.00011367105],"genre_scores_gemma":[0.6061676,0.00006510926,0.39347225,0.00017075457,0.00005512069,0.00000947877,0.0000022356844,0.0000097398715,0.000047715854],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988026,0.000030768428,0.000506311,0.00015170146,0.0002654127,0.0002432321],"domain_scores_gemma":[0.99892753,0.0004312873,0.0003287215,0.000108738575,0.000114337745,0.00008940976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051293656,0.00011320011,0.00030175532,0.00020324708,0.00008997731,0.00012153174,0.00022770467,0.00008596822,0.0000059934773],"category_scores_gemma":[0.0003259993,0.000100778074,0.00006865932,0.0003780361,0.000022930539,0.00022525188,0.0000535895,0.00029346146,0.0000037546904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006385638,0.000016666987,0.00020047928,0.000018099689,0.000024296474,0.000004404697,0.00030857697,0.98821306,0.00007662349,0.005237695,0.00003643178,0.005799809],"study_design_scores_gemma":[0.0016111622,0.00028412134,0.00032619678,0.00004563882,0.000015003787,0.000004105963,0.00010564444,0.9965022,0.000037379676,0.0002782046,0.00067951315,0.00011083471],"about_ca_topic_score_codex":0.0000012971777,"about_ca_topic_score_gemma":2.9608458e-8,"teacher_disagreement_score":0.60585856,"about_ca_system_score_codex":0.00004715164,"about_ca_system_score_gemma":0.00003779406,"threshold_uncertainty_score":0.41096106},"labels":[],"label_agreement":null},{"id":"W4385190059","doi":"10.1145/3583133.3590596","title":"Neuroevolution for Autonomous Cyber Defense","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Neuroevolution; Computer science; Reinforcement learning; Observability; Artificial intelligence; Task (project management); Domain (mathematical analysis); Adversary; Python (programming language); Artificial neural network; Evolutionary algorithm; Machine learning; Computer security; Systems engineering; Engineering","score_opus":0.029155177021413986,"score_gpt":0.2647024273516445,"score_spread":0.23554725033023052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385190059","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":[0.0011092201,0.000002002813,0.9828348,0.0010469222,0.0004804082,0.00016207676,2.8965565e-7,0.0008864985,0.0134777855],"genre_scores_gemma":[0.6820165,0.000012315397,0.19102047,0.0015591573,0.00016387514,0.000086966786,0.000018966522,0.00003149454,0.12509023],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992991,0.000014969362,0.000120576085,0.0002016772,0.00012511715,0.00023852896],"domain_scores_gemma":[0.9994149,0.00012734484,0.000034415567,0.00033708214,0.000043903518,0.000042340132],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00018337258,0.00006327443,0.00005990885,0.00008728552,0.00009864729,0.000087851884,0.00036505496,0.000027414606,0.000020679277],"category_scores_gemma":[0.000098747136,0.000058972597,0.00004713774,0.0003335344,0.000012644228,0.00020649868,0.00015106608,0.0000466997,0.0014112915],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018900054,0.0000054140064,0.00033757542,0.00000890844,0.000006773963,0.000004562813,0.00015419621,0.6868691,0.00020739218,0.2610123,0.046665728,0.004726175],"study_design_scores_gemma":[0.00013208082,0.000039999784,0.0016815077,0.00000168696,0.0000018475856,0.000003771137,0.0000051652605,0.94650817,0.00014297359,0.001054007,0.050353184,0.00007560724],"about_ca_topic_score_codex":0.0000057650664,"about_ca_topic_score_gemma":0.0000010633076,"teacher_disagreement_score":0.7918143,"about_ca_system_score_codex":0.000026663703,"about_ca_system_score_gemma":0.000032493503,"threshold_uncertainty_score":0.9993662},"labels":[],"label_agreement":null},{"id":"W4385299175","doi":"10.1109/tai.2023.3299252","title":"Facilitating Sim-to-Real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Robot; Artificial intelligence; Heuristic; Robotics; Generalizability theory; Task (project management); Simulation; Engineering","score_opus":0.06739551366683552,"score_gpt":0.3288240012675382,"score_spread":0.2614284876007027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385299175","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":[0.024019325,7.319545e-7,0.9743639,0.00011865047,0.00030459955,0.000776987,0.00000416726,0.00025991705,0.00015170804],"genre_scores_gemma":[0.9905654,0.000010710254,0.0087820105,0.000021027028,0.000025001602,0.00007840394,0.000015974312,0.000019035673,0.00048240143],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977521,0.00009984797,0.0008481247,0.00044163922,0.00045101464,0.00040728404],"domain_scores_gemma":[0.9978688,0.0013265893,0.00021034184,0.00031411485,0.00018810062,0.000092105176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006861479,0.00019985529,0.00025145742,0.00054082443,0.00023881369,0.000080486,0.00037257015,0.00009852189,0.000028541033],"category_scores_gemma":[0.00018130724,0.00023264668,0.00008487779,0.0013472781,0.000046011126,0.00035310522,0.000010035819,0.00024141706,0.00021284934],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069767564,0.000037507372,0.000008099282,0.000026495789,0.000010765812,6.940852e-7,0.0018668106,0.91431034,0.018742371,0.0007778151,0.0000065686363,0.064142786],"study_design_scores_gemma":[0.00006593091,0.0005304572,0.000073124684,0.0000619537,0.00000819666,2.0687375e-7,0.00023683258,0.9576486,0.04080189,0.00036178555,0.000014494168,0.00019653174],"about_ca_topic_score_codex":0.00029414482,"about_ca_topic_score_gemma":0.0000474696,"teacher_disagreement_score":0.9665461,"about_ca_system_score_codex":0.00018464429,"about_ca_system_score_gemma":0.000050638275,"threshold_uncertainty_score":0.9487056},"labels":[],"label_agreement":null},{"id":"W4385384974","doi":"10.1007/978-3-031-33242-5_9","title":"Hyperparameter Tuning for an Enhanced Self-Attention-Based Actor-Critical DDPG Framework","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes on data engineering and communications technologies","topic":"Reinforcement Learning in Robotics","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 Windsor","funders":"","keywords":"Reinforcement learning; Computer science; Hyperparameter; Architecture; Artificial intelligence; Inverted pendulum; Machine learning","score_opus":0.06311031849023004,"score_gpt":0.3056693980039892,"score_spread":0.24255907951375916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385384974","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":[0.0000074951818,0.00048024525,0.9907029,0.0028261545,0.00019531159,0.00034367634,0.00008577348,0.004871539,0.00048690368],"genre_scores_gemma":[0.14316645,0.0007331693,0.85474044,0.00013138597,0.000037495145,0.00011237718,0.00074779,0.00009435896,0.00023655505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984213,0.00001830921,0.0003303148,0.00066712167,0.00023195408,0.00033096987],"domain_scores_gemma":[0.9879205,0.0042807446,0.00012810093,0.007509772,0.000111598536,0.000049251925],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00023424975,0.00040614355,0.00035698118,0.00042112742,0.0003213283,0.00036201376,0.005578144,0.00070586335,0.0000014247073],"category_scores_gemma":[0.0027490384,0.0003925905,0.00007206591,0.0001752033,0.00016971801,0.0002730217,0.0019937146,0.0013255032,0.000017393653],"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":[0.000007361226,0.000049202423,0.0000053461367,0.00029408312,0.0001711314,0.0000022515258,0.00011407718,0.17625809,0.0006711471,0.75350183,0.00012125952,0.06880422],"study_design_scores_gemma":[0.00011386799,0.00026385154,0.000005577229,0.00062320486,0.00006806601,0.000002654926,0.00000903564,0.96691436,0.0002913662,0.014181681,0.016991872,0.0005344502],"about_ca_topic_score_codex":0.0000020133575,"about_ca_topic_score_gemma":0.0000028810803,"teacher_disagreement_score":0.79065627,"about_ca_system_score_codex":0.000046859564,"about_ca_system_score_gemma":0.000054211803,"threshold_uncertainty_score":0.9998526},"labels":[],"label_agreement":null},{"id":"W4385462630","doi":"10.1016/j.artint.2023.103989","title":"Learning reward machines: A study in partially observable reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University; Vector Institute; University of Toronto","funders":"Fondo Nacional de Desarrollo Científico y Tecnológico; Agencia Nacional de Investigación y Desarrollo; Government of Ontario; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; Microsoft Research","keywords":"Reinforcement learning; Observable; Computer science; Set (abstract data type); Artificial intelligence; Task (project management); Function (biology); Optimization problem; Representation (politics); Decomposition; Learning automata; Mathematical optimization; Automaton; Machine learning; Mathematics; Algorithm","score_opus":0.08641297792112246,"score_gpt":0.3260962182458153,"score_spread":0.23968324032469285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385462630","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":[0.16838296,0.000014518183,0.82701784,0.00041295937,0.0006477088,0.00062924804,8.705469e-8,0.0009692112,0.001925457],"genre_scores_gemma":[0.9948818,0.0000402415,0.0017606,0.00009517563,0.00008656549,0.0000838156,0.000008110535,0.000030514284,0.0030131675],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962094,0.0003721899,0.0009968728,0.0007415404,0.00078878907,0.0008912185],"domain_scores_gemma":[0.99842334,0.00040133696,0.00024484063,0.000660705,0.0001281915,0.00014161652],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002094184,0.0002994337,0.0003382525,0.00046845237,0.0004220884,0.0004494473,0.0013269538,0.00009308235,0.000091166985],"category_scores_gemma":[0.0010601531,0.00031035696,0.00009511101,0.0027417077,0.000063539854,0.0006937476,0.00080298504,0.00083091826,0.0022258621],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018299952,0.00006121002,0.033358257,0.000012811449,0.000016841568,0.00010644226,0.007663286,0.9251564,0.0002581961,0.007792035,0.00003468876,0.02552153],"study_design_scores_gemma":[0.00007223813,0.0008037677,0.0037602312,0.000048376143,0.000006812252,0.0000026363475,0.0028678318,0.98841316,0.0009733525,0.0016674137,0.0010358011,0.00034837992],"about_ca_topic_score_codex":0.00044180793,"about_ca_topic_score_gemma":0.00030596714,"teacher_disagreement_score":0.82649887,"about_ca_system_score_codex":0.00013651018,"about_ca_system_score_gemma":0.00011429001,"threshold_uncertainty_score":0.99993485},"labels":[],"label_agreement":null},{"id":"W4385473744","doi":"10.48550/arxiv.2307.16062","title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Leverage (statistics); Computer science; Generalizability theory; Robot; Artificial intelligence; Heuristic; Motion planning; Motion (physics); Kinematics; Simulation; Mathematics","score_opus":0.212502004908271,"score_gpt":0.26361457496936935,"score_spread":0.051112570061098345,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385473744","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":[0.15204947,0.000013524275,0.8455384,0.000047700527,0.000470788,0.0013785876,0.0000061256383,0.0003799072,0.0001155348],"genre_scores_gemma":[0.97325426,0.000032898235,0.02322102,0.00008413937,0.00003346554,0.000021138932,0.000070434624,0.00005260733,0.0032300397],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970641,0.000111032554,0.00044960034,0.0014354673,0.00021257512,0.00072721834],"domain_scores_gemma":[0.9981001,0.00020471548,0.0004684317,0.0007389038,0.00023813845,0.0002497102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005679645,0.0004866892,0.00045755922,0.00060151797,0.00054573634,0.00031755387,0.0009417218,0.00025166635,0.0000038735766],"category_scores_gemma":[0.000117787524,0.00062452076,0.00018646407,0.00048931007,0.000061705825,0.00043764935,0.003092192,0.0006906686,0.000020700665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002786666,0.000013837913,0.002840456,0.00013280244,0.00009481981,0.000061002323,0.0014351571,0.9890439,0.0010825898,0.0048355483,0.000009202362,0.00042280616],"study_design_scores_gemma":[0.00053419854,0.00024571142,0.004816094,0.00034162714,0.00013370317,0.0000024539754,0.00043848762,0.99193,0.00018084832,0.0007173356,0.00004694022,0.00061260094],"about_ca_topic_score_codex":0.00022827768,"about_ca_topic_score_gemma":0.000009984131,"teacher_disagreement_score":0.82231736,"about_ca_system_score_codex":0.00088242575,"about_ca_system_score_gemma":0.00012609508,"threshold_uncertainty_score":0.9996206},"labels":[],"label_agreement":null},{"id":"W4385484633","doi":"10.1109/ijcnn54540.2023.10191867","title":"Reducing the Cost of Cycle-Time Tuning for Real-World Policy Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Alberta Machine Intelligence Institute","keywords":"Benchmark (surveying); Baseline (sea); Task (project management); Computer science; Robotics; Artificial intelligence; Reinforcement learning; Machine learning; Robot; Engineering","score_opus":0.028349866026891192,"score_gpt":0.30427996305451016,"score_spread":0.27593009702761895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385484633","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":[0.00012455822,0.000001219803,0.9716912,0.0024609254,0.00010936027,0.0002990605,5.927057e-7,0.00026276574,0.02505031],"genre_scores_gemma":[0.35041907,0.00007166573,0.56756645,0.00071786315,0.00039764203,0.00008981256,0.00004769876,0.000054932378,0.08063485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914354,0.000035488505,0.00023247638,0.00016617007,0.00019190683,0.00023040806],"domain_scores_gemma":[0.9989524,0.00035996173,0.00013214075,0.0004337408,0.00008841417,0.000033362656],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004955489,0.00007473396,0.00010235361,0.0002312999,0.00016165932,0.0000933044,0.0006009797,0.00002367409,0.000019564415],"category_scores_gemma":[0.00022331986,0.00005577572,0.00004702137,0.0012711759,0.00003280766,0.0002249345,0.00022318272,0.000058808484,0.000038153306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014371408,0.0000022196512,0.000036893878,0.000008040071,0.000007635924,1.8627732e-7,0.0003444977,0.9599922,0.00029476816,0.03521689,0.001641591,0.0024536785],"study_design_scores_gemma":[0.00012352961,0.000027746824,0.00021733492,0.000021085487,0.0000035803155,5.447799e-7,0.00002566171,0.99803036,0.0005059605,0.00017206791,0.00080674805,0.00006537166],"about_ca_topic_score_codex":0.00020201878,"about_ca_topic_score_gemma":0.00000284129,"teacher_disagreement_score":0.40412474,"about_ca_system_score_codex":0.00004619506,"about_ca_system_score_gemma":0.000084965344,"threshold_uncertainty_score":0.2274468},"labels":[],"label_agreement":null},{"id":"W4385729101","doi":"10.1016/j.ins.2023.119481","title":"Reward shaping using convolutional neural network","year":2023,"lang":"en","type":"article","venue":"Information Sciences","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"","keywords":"Computer science; Markov decision process; Reinforcement learning; Convolutional neural network; Stochastic matrix; Representation (politics); Convolution (computer science); Artificial intelligence; Matrix (chemical analysis); Function (biology); Markov chain; Bellman equation; Algorithm; Artificial neural network; Markov process; Machine learning; Mathematical optimization; Mathematics; Statistics","score_opus":0.12628818183703894,"score_gpt":0.3253652114570306,"score_spread":0.19907702961999169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385729101","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":[0.018145045,0.000011360731,0.9736726,0.0007472765,0.0011271706,0.00009504554,5.391678e-7,0.00041892013,0.005782017],"genre_scores_gemma":[0.95292807,0.000007130563,0.0454482,0.001337666,0.00014203197,0.000005111736,0.000008024496,0.0000025816735,0.000121179444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998474,0.00003210565,0.0003232408,0.00012391001,0.00068090076,0.00036586748],"domain_scores_gemma":[0.9993793,0.000112444046,0.00018094828,0.00017170909,0.00010007141,0.00005555179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011189037,0.00007925187,0.000077191275,0.00023496118,0.0006526841,0.0006398838,0.00082929735,0.000032595395,0.00001799436],"category_scores_gemma":[0.00013688585,0.00007138437,0.000035891553,0.0020450894,0.00014725317,0.0051175486,0.00030056218,0.00008608896,0.0005075623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.9540194e-7,4.4119471e-7,0.0015300572,0.0000035214089,0.0000016383923,4.0641453e-7,0.00038717187,0.96949375,0.000009187403,0.02513359,0.0014456772,0.0019941872],"study_design_scores_gemma":[0.000068604415,0.000022698712,0.0047035087,0.000014019974,9.1147854e-7,0.000009371443,0.00009180405,0.9880069,0.0000114748955,0.0007492065,0.00622582,0.00009566577],"about_ca_topic_score_codex":0.000016749125,"about_ca_topic_score_gemma":5.199238e-7,"teacher_disagreement_score":0.93478304,"about_ca_system_score_codex":0.00004090004,"about_ca_system_score_gemma":0.00013742829,"threshold_uncertainty_score":0.6523856},"labels":[],"label_agreement":null},{"id":"W4385763897","doi":"10.24963/ijcai.2023/776","title":"Multi-Agent Advisor Q-Learning (Extended Abstract)","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta; Vector Institute; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Government of Canada; Vector Institute; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Sample complexity; Artificial intelligence; Heuristic; Action (physics); Convergence (economics); Software deployment; Q-learning; Point (geometry); Operations research; Machine learning; Software engineering; Mathematics","score_opus":0.03721342908507978,"score_gpt":0.288069363828437,"score_spread":0.2508559347433572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385763897","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":[0.0032716794,0.000009575539,0.98022544,0.00073212705,0.0004931325,0.00013772868,1.2904701e-7,0.0019662078,0.01316395],"genre_scores_gemma":[0.8279019,0.000037885744,0.10730927,0.00031523916,0.0000583399,0.00001582379,0.000008738451,0.000022894967,0.0643299],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985472,0.00003476228,0.000256207,0.00034633637,0.0003793199,0.00043615274],"domain_scores_gemma":[0.9991485,0.00012526564,0.000090387424,0.00046228696,0.000058592563,0.000114968956],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039353236,0.00013943104,0.0001240671,0.00017338054,0.00018573679,0.00021326962,0.0008013536,0.00005838366,0.00018763842],"category_scores_gemma":[0.00017730646,0.00012617132,0.00007316285,0.00063076935,0.000024550021,0.00036047495,0.00043647242,0.00026962266,0.0060202964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015245795,0.00002408379,0.0009200611,0.000016718468,0.000021854637,0.000051078496,0.00066595466,0.9718513,0.0018579175,0.0060466463,0.004909544,0.013633345],"study_design_scores_gemma":[0.00027684614,0.000050893945,0.039520975,0.000010229274,0.0000022629235,0.0000035849598,0.00008863756,0.929755,0.00048047933,0.00004509867,0.029586371,0.00017967043],"about_ca_topic_score_codex":0.00001662455,"about_ca_topic_score_gemma":0.0000017078683,"teacher_disagreement_score":0.8729162,"about_ca_system_score_codex":0.000038672897,"about_ca_system_score_gemma":0.000041213993,"threshold_uncertainty_score":0.99475366},"labels":[],"label_agreement":null},{"id":"W4385764251","doi":"10.24963/ijcai.2023/783","title":"Rethinking Formal Models of Partially Observable Multiagent Decision Making (Extended Abstract)","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Grantová Agentura České Republiky","keywords":"Rotation formalisms in three dimensions; Computer science; Observable; Theoretical computer science; Regret; Mathematical economics; Artificial intelligence; Mathematics; Machine learning","score_opus":0.08508064556629286,"score_gpt":0.30600609572622145,"score_spread":0.2209254501599286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385764251","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":[0.03008366,0.000011989016,0.96338946,0.00013359508,0.00037317086,0.00016548435,3.74914e-7,0.00045998424,0.0053822654],"genre_scores_gemma":[0.76136076,0.0000173886,0.23799126,0.00013877486,0.000019944344,0.000005189249,0.00000231774,0.000011125718,0.00045321934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99787563,0.000024679508,0.00054815836,0.00031883086,0.0007312096,0.0005015141],"domain_scores_gemma":[0.99856186,0.00033134132,0.00021548865,0.0006761405,0.00014863811,0.00006652487],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009938983,0.00014590223,0.0001945036,0.00016441726,0.00016667171,0.00015149485,0.0010194407,0.00008920785,0.00004900998],"category_scores_gemma":[0.00015408087,0.0001307208,0.00009936622,0.00057018065,0.000026769796,0.0014815823,0.0007884424,0.00018271015,0.00012654641],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008491506,0.000011831767,0.00009394862,0.00002096859,0.000012274144,0.000014609304,0.0013989684,0.9400269,0.00044840763,0.038291834,0.00036552036,0.019306289],"study_design_scores_gemma":[0.0002345943,0.00005352352,0.0028810622,0.000108345004,0.0000042202228,0.00000258938,0.000038551512,0.97322613,0.0017273431,0.02136404,0.00021313828,0.00014648106],"about_ca_topic_score_codex":0.000027297809,"about_ca_topic_score_gemma":0.000010330767,"teacher_disagreement_score":0.7312771,"about_ca_system_score_codex":0.00004916579,"about_ca_system_score_gemma":0.000084258216,"threshold_uncertainty_score":0.53306395},"labels":[],"label_agreement":null},{"id":"W4385767620","doi":"10.24963/ijcai.2023/31","title":"Towards a Better Understanding of Learning with Multiagent Teams","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Knowledge management; Computer science; Team learning; Population; Work (physics); Artificial intelligence; Cooperative learning; Engineering; Psychology; Mathematics education","score_opus":0.04272918891291047,"score_gpt":0.26190074510621725,"score_spread":0.21917155619330678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385767620","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":[0.012070817,0.000002288161,0.9732201,0.0005976019,0.000086505184,0.0000851896,6.399122e-8,0.0003836135,0.013553786],"genre_scores_gemma":[0.94860584,0.000004880336,0.048917007,0.00009140793,0.000014904101,0.0000034480906,0.0000016696284,0.000010027633,0.0023507893],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896145,0.00004725015,0.00016416192,0.00019837456,0.00038055255,0.00024823868],"domain_scores_gemma":[0.9994731,0.00009567134,0.000083242165,0.0002653605,0.000034300978,0.00004833903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003338373,0.00009287083,0.000117940326,0.00015639077,0.000112577014,0.00007311144,0.00038595765,0.000031279604,0.00003246724],"category_scores_gemma":[0.00004654093,0.0000697994,0.000034981727,0.00064016186,0.000041998654,0.0002120451,0.0002356658,0.0001817874,0.00008555702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003664538,0.0000071421287,0.012639886,0.00002613973,0.000036303725,0.00001726828,0.001987696,0.95188844,0.00041431875,0.029903188,0.00041512653,0.0026608044],"study_design_scores_gemma":[0.00032484953,0.00020582761,0.00172148,0.00004023063,0.000005125733,0.0000039234346,0.0015693969,0.9933735,0.0015496027,0.00025669747,0.0008068754,0.00014249279],"about_ca_topic_score_codex":0.000026722035,"about_ca_topic_score_gemma":0.0000020926243,"teacher_disagreement_score":0.93653506,"about_ca_system_score_codex":0.00007426323,"about_ca_system_score_gemma":0.00004604058,"threshold_uncertainty_score":0.28463367},"labels":[],"label_agreement":null},{"id":"W4385791631","doi":"10.1017/9781009258227.004","title":"Agent Architectures and Hierarchical Control","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Code generation; Artificial intelligence; Software engineering; Data science; Programming language; Key (lock)","score_opus":0.020991266457942914,"score_gpt":0.1998834696065149,"score_spread":0.178892203148572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791631","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012931539,0.00003136068,0.29891104,0.00006584934,0.0002454641,0.0002803433,0.000026056654,0.00035621383,0.70007074],"genre_scores_gemma":[0.0023560144,0.00005245573,0.0010328158,0.00016295486,0.00009198375,6.4578586e-7,0.000009766826,0.0000387664,0.9962546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99838406,0.000057418067,0.00018705698,0.0006185618,0.00040719827,0.0003457207],"domain_scores_gemma":[0.99855435,0.00023961611,0.00017558747,0.0007252022,0.00007215329,0.00023309734],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00013312967,0.00034653317,0.00037029822,0.00026758926,0.0002140455,0.00014015297,0.0010793551,0.00026931043,0.0000011138964],"category_scores_gemma":[0.00002248483,0.00038343042,0.00015276154,0.000011859203,0.00027986904,0.000053267224,0.0010837485,0.0007279896,0.000029667588],"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":[0.000022925085,0.0000018832419,0.000002456896,0.00005083156,0.00013139517,0.00044636312,0.000071634015,0.0036768552,0.000008886372,0.98800164,0.0050827106,0.0025024374],"study_design_scores_gemma":[0.00097324,0.00013987896,0.000106071224,0.00015573653,0.000116482115,0.000037814767,0.0000045014185,0.04702767,0.00002560624,0.00009527992,0.9506971,0.00062060385],"about_ca_topic_score_codex":0.000025746913,"about_ca_topic_score_gemma":5.9978476e-7,"teacher_disagreement_score":0.98790634,"about_ca_system_score_codex":0.00006322186,"about_ca_system_score_gemma":0.00008594085,"threshold_uncertainty_score":0.9998618},"labels":[],"label_agreement":null},{"id":"W4385791640","doi":"10.1017/9781009258227.019","title":"Multiagent Systems","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Generative grammar; Implementation; Code (set theory); Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.0399365295312654,"score_gpt":0.2061894574563037,"score_spread":0.16625292792503832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791640","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":[8.898233e-7,0.00003688678,0.29868734,0.000010021084,0.0011297609,0.0003408965,0.000021416003,0.0006674388,0.6991054],"genre_scores_gemma":[0.00020474411,0.00008682682,0.00062521955,0.00003191311,0.00012368314,8.867807e-7,0.000025345074,0.000057217094,0.99884415],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808085,0.000044713106,0.00025452496,0.00066909776,0.00056302623,0.00038779408],"domain_scores_gemma":[0.9979104,0.00012125693,0.0003253374,0.0012632277,0.00017826661,0.00020151158],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016108547,0.0003910234,0.00039405425,0.00028880447,0.00021707479,0.0002189444,0.001938919,0.00035407083,0.0000010810065],"category_scores_gemma":[0.000014446737,0.00047046438,0.00021113236,0.000017470225,0.0001147929,0.00016277128,0.001510204,0.00054318947,0.00030473963],"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":[0.000004923295,0.0000019458812,5.1314373e-7,0.000090546164,0.000116730575,0.00053960655,0.00004262573,0.01615115,0.0000053992535,0.9469221,0.03580108,0.00032338093],"study_design_scores_gemma":[0.00029685302,0.000046206,0.0000046630016,0.00021287934,0.000062540865,0.000013024784,0.000011409517,0.09238041,0.000021722806,0.000002654429,0.9064702,0.00047745075],"about_ca_topic_score_codex":0.00009931141,"about_ca_topic_score_gemma":3.107184e-7,"teacher_disagreement_score":0.94691944,"about_ca_system_score_codex":0.00026950106,"about_ca_system_score_gemma":0.00011999455,"threshold_uncertainty_score":0.9997747},"labels":[],"label_agreement":null},{"id":"W4385791672","doi":"10.1017/9781009258227.018","title":"Reinforcement Learning","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Reinforcement learning; Implementation; Artificial intelligence; Software engineering; Programming language","score_opus":0.031001316819717507,"score_gpt":0.2074911771978943,"score_spread":0.1764898603781768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791672","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":[6.441454e-7,0.000011517064,0.34731874,0.00001810652,0.00040943697,0.00023233231,0.0000024834264,0.0007755655,0.65123117],"genre_scores_gemma":[0.00035237666,0.00013301575,0.00081657973,0.0000665623,0.000107445274,8.1163677e-7,0.000041937816,0.000069079346,0.9984122],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99776214,0.00004519873,0.00030602276,0.0007180468,0.0006730067,0.00049559784],"domain_scores_gemma":[0.9979794,0.00013501261,0.00041610457,0.0010694084,0.00018627403,0.00021377504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021323145,0.00046026608,0.00041349806,0.00036752562,0.00036507976,0.00019209264,0.0019021067,0.0003718145,0.000004967153],"category_scores_gemma":[0.000030158511,0.0005741868,0.00026444864,0.000026240778,0.00013807745,0.0002345822,0.0020376516,0.0010116963,0.00036189644],"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":[0.000008818396,0.0000012171039,8.473967e-7,0.0000536023,0.00011543275,0.00033043287,0.0000619454,0.081424624,0.000006857847,0.8992195,0.017940018,0.0008366802],"study_design_scores_gemma":[0.00036063197,0.00011336686,0.0000036508047,0.00017989804,0.00006646642,0.000009365604,0.000011326125,0.075574934,0.000059851685,0.000010659057,0.9230297,0.00058013096],"about_ca_topic_score_codex":0.000042408094,"about_ca_topic_score_gemma":2.871921e-7,"teacher_disagreement_score":0.9050897,"about_ca_system_score_codex":0.0003067334,"about_ca_system_score_gemma":0.0001545214,"threshold_uncertainty_score":0.999671},"labels":[],"label_agreement":null},{"id":"W4385791676","doi":"10.1017/9781009258227.005","title":"Reasoning and Planning with Certainty","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Generative grammar; Code (set theory); Implementation; Artificial intelligence; Space (punctuation); Data science; Software engineering; Programming language","score_opus":0.026440709450536913,"score_gpt":0.20447680039054347,"score_spread":0.17803609094000655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791676","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000025733054,0.000025472187,0.23039135,0.00001125136,0.00014066177,0.00017417742,0.0000062882323,0.00040361797,0.7688214],"genre_scores_gemma":[0.0007197194,0.00002898821,0.0034352373,0.000039202718,0.000060334387,3.74428e-7,0.000012806576,0.000044127333,0.99565923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986127,0.0000252867,0.00013332978,0.0005763792,0.00033991833,0.0003123828],"domain_scores_gemma":[0.9987476,0.00012458871,0.00022363024,0.0006268072,0.00011831926,0.00015907666],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000118738346,0.00031954484,0.00030310228,0.00021420722,0.00026088484,0.00016921443,0.0007806942,0.00021176209,6.018963e-7],"category_scores_gemma":[0.000016487025,0.00034122355,0.00006254689,0.000016940725,0.00016053153,0.00017907773,0.00095288083,0.00052241073,0.000009793327],"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":[0.00002250061,8.601867e-7,0.00001591956,0.000055831188,0.00010582065,0.00085754495,0.00017394587,0.008107828,0.000002036039,0.98604465,0.004007942,0.00060510315],"study_design_scores_gemma":[0.0010629051,0.00024873667,0.00015367541,0.0014291174,0.00018784907,0.00009982747,0.00010952537,0.097011045,0.000046762296,0.000020296698,0.89839673,0.0012335166],"about_ca_topic_score_codex":0.000053768712,"about_ca_topic_score_gemma":6.0216536e-7,"teacher_disagreement_score":0.9860244,"about_ca_system_score_codex":0.00010354515,"about_ca_system_score_gemma":0.0000881549,"threshold_uncertainty_score":0.999904},"labels":[],"label_agreement":null},{"id":"W4385791677","doi":"10.1017/9781009258227.009","title":"Deterministic Planning","year":2023,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Computer science; Implementation; Generative grammar; Code (set theory); Artificial intelligence; Data science; Software engineering; Programming language","score_opus":0.04680683511438593,"score_gpt":0.2268041648941649,"score_spread":0.17999732977977898,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385791677","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000020169646,0.0000129235295,0.28456512,0.000008120976,0.00051042903,0.00016715967,0.000012580817,0.00059425924,0.7141274],"genre_scores_gemma":[0.0003829805,0.000018921264,0.0012785535,0.000060607967,0.000100472076,4.3995232e-7,0.000020200177,0.00005427257,0.99808353],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983279,0.00002858797,0.00021845811,0.00061499554,0.000427807,0.0003822261],"domain_scores_gemma":[0.99825,0.0001824317,0.00028352288,0.0010041511,0.00010577002,0.0001740898],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011843092,0.00036597476,0.0003495573,0.00029864756,0.00024407665,0.00016728428,0.0018179776,0.00031252863,0.000001336676],"category_scores_gemma":[0.000023372018,0.00046061393,0.00017945921,0.000016692555,0.00013669294,0.00014960911,0.0014225245,0.0005804419,0.00017228008],"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":[0.0000075050375,0.0000012345869,0.0000013021893,0.000057039724,0.00007403753,0.001398814,0.000066307715,0.0056675607,0.0000046150362,0.9761041,0.015858853,0.0007586685],"study_design_scores_gemma":[0.00031711278,0.000085067295,0.000016354677,0.00032205592,0.00008600649,0.000026702644,0.000009163032,0.050554313,0.000029590326,0.00002520073,0.94790274,0.0006257047],"about_ca_topic_score_codex":0.000013188439,"about_ca_topic_score_gemma":1.167911e-7,"teacher_disagreement_score":0.97607887,"about_ca_system_score_codex":0.00016059625,"about_ca_system_score_gemma":0.00013330606,"threshold_uncertainty_score":0.9997845},"labels":[],"label_agreement":null},{"id":"W4385890042","doi":"10.48550/arxiv.2308.07591","title":"Approximations and Learning for Continuous State and Action MDPs under Average Cost Criteria","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Mathematics; Markov decision process; Discretization; Ergodicity; Mathematical optimization; Applied mathematics; Convergence (economics); Markov process; Computer science; Mathematical analysis","score_opus":0.13854735717401917,"score_gpt":0.24295794452381714,"score_spread":0.10441058734979797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385890042","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":[0.07766631,0.000011817043,0.9207278,0.00012123102,0.0003974777,0.00053839287,0.000006461507,0.0002453154,0.00028522653],"genre_scores_gemma":[0.98127383,0.0002643009,0.005341294,0.000045663888,0.00003333943,0.0000045843444,0.00003699449,0.0000246065,0.012975374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986457,0.00012653453,0.00017212803,0.00070802594,0.00006938222,0.00027822977],"domain_scores_gemma":[0.99881864,0.00031017902,0.00024106582,0.00039267068,0.0001292825,0.00010818149],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033933812,0.000216548,0.00024218073,0.0002306963,0.0003659081,0.00038341162,0.00039469136,0.00015089424,0.00000683991],"category_scores_gemma":[0.00009482027,0.00026698594,0.00006194524,0.00021833496,0.00009059488,0.00040800072,0.0010879118,0.00051660143,0.000020545463],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013284118,0.000008119237,0.00080209645,0.00013015984,0.000054066444,0.000014848152,0.00045255947,0.9828573,0.000040523173,0.014846964,0.000116163086,0.0006639106],"study_design_scores_gemma":[0.00046724235,0.00006197443,0.0024275118,0.0000656309,0.000037486283,0.000003547727,0.00018624589,0.98663706,0.000024440387,0.0090935165,0.0007212873,0.00027408198],"about_ca_topic_score_codex":0.0000534124,"about_ca_topic_score_gemma":0.000015077957,"teacher_disagreement_score":0.9153865,"about_ca_system_score_codex":0.000103846556,"about_ca_system_score_gemma":0.00006331969,"threshold_uncertainty_score":0.99997824},"labels":[],"label_agreement":null},{"id":"W4386001266","doi":"10.1007/s10514-023-10127-3","title":"Learning scalable and efficient communication policies for multi-robot collision avoidance","year":2023,"lang":"en","type":"article","venue":"Autonomous Robots","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Office of Naval Research; Instituto de Ciencias del Mar y Limnología, Universidad Nacional Autónoma de México; Office of Naval Research Global; Canadian Institute for Advanced Research","keywords":"Computer science; Robot; Collision avoidance; Scalability; Robustness (evolution); Collision; Distributed computing; Broadcasting (networking); Artificial intelligence; Generalization; Reinforcement learning; Human–computer interaction; Computer security","score_opus":0.039689917230473715,"score_gpt":0.29919854479417823,"score_spread":0.2595086275637045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386001266","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":[0.034585748,0.00017655588,0.9623419,0.0010425296,0.00020800259,0.00049928285,0.0000011208521,0.00075375085,0.00039112777],"genre_scores_gemma":[0.78694755,0.0001643494,0.2045214,0.00018628928,0.000032271764,0.000102335616,0.00002768875,0.00003429803,0.007983825],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850225,0.000101689846,0.00031779057,0.00038841314,0.00021897483,0.00047085102],"domain_scores_gemma":[0.99857086,0.00039281088,0.00018702977,0.0006306738,0.00012258087,0.00009603245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006870024,0.00017855725,0.00021354282,0.0001980051,0.00074717915,0.00031823525,0.00073725474,0.0000891226,0.0000021096635],"category_scores_gemma":[0.00027413457,0.00018298427,0.00005641007,0.00060344493,0.00009181034,0.0002563695,0.0006463495,0.0002167293,0.00012053542],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031190746,0.000017751147,0.00064408215,0.000026564125,0.0000096661615,9.635405e-7,0.0016317081,0.98717207,0.000647268,0.005840889,0.0002957963,0.0037101323],"study_design_scores_gemma":[0.0005191239,0.00012124481,0.008595988,0.000054924327,0.0000065663444,0.0000047533513,0.00012385381,0.9859338,0.00088076974,0.00007266118,0.0034787015,0.00020764157],"about_ca_topic_score_codex":0.00007049863,"about_ca_topic_score_gemma":0.0000070202254,"teacher_disagreement_score":0.7578205,"about_ca_system_score_codex":0.00009883515,"about_ca_system_score_gemma":0.00007003299,"threshold_uncertainty_score":0.7461882},"labels":[],"label_agreement":null},{"id":"W4386120402","doi":"10.1137/22m1515112","title":"Satisficing Paths and Independent Multiagent Reinforcement Learning in Stochastic Games","year":2023,"lang":"en","type":"article","venue":"SIAM Journal on Mathematics of Data Science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Satisficing; Reinforcement learning; Computer science; Mathematical economics; Convergence (economics); Multi-agent system; Mathematical optimization; Mathematics; Artificial intelligence; Economics","score_opus":0.05739997469785349,"score_gpt":0.321028057988703,"score_spread":0.2636280832908495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386120402","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":[0.06393119,0.000033678873,0.93499553,0.0002225082,0.00022494144,0.00019774375,0.0000011812937,0.00006142143,0.00033178125],"genre_scores_gemma":[0.9453029,0.00015244857,0.054364048,0.000035974135,0.000021210575,0.000002232171,0.00000278563,0.000010015246,0.00010836139],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996744,0.000056135075,0.00073375663,0.000420705,0.001559784,0.00048567195],"domain_scores_gemma":[0.9976904,0.00053952495,0.0005637755,0.00091741217,0.00011729581,0.00017160964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005090278,0.00016810234,0.0002643533,0.0008002027,0.0002957416,0.0004029368,0.0026535348,0.000037879156,0.000009267184],"category_scores_gemma":[0.0020823365,0.00014188442,0.000027284168,0.0012836909,0.00021724205,0.0018938634,0.0019319754,0.0005155555,0.0000350412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000235808,0.000025256164,0.000236299,0.000046050427,0.000006953676,0.000028003999,0.0024015575,0.9801537,0.0013350991,0.008564341,0.000033839115,0.0071665617],"study_design_scores_gemma":[0.00034442364,0.00020572172,0.0017212959,0.0004496714,0.00000511549,0.00006190273,0.00071767555,0.99518776,0.00024766286,0.0008690692,0.00004020522,0.00014951358],"about_ca_topic_score_codex":0.0000055938453,"about_ca_topic_score_gemma":0.0000017426448,"teacher_disagreement_score":0.88137174,"about_ca_system_score_codex":0.00009853833,"about_ca_system_score_gemma":0.00024337476,"threshold_uncertainty_score":0.5785879},"labels":[],"label_agreement":null},{"id":"W4386126338","doi":"10.1007/s10994-023-06368-z","title":"Cautious policy programming: exploiting KL regularization for monotonic policy improvement in reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Japan Society for the Promotion of Science","keywords":"Reinforcement learning; Monotonic function; Computer science; Mathematical optimization; Regularization (linguistics); Bellman equation; Entropy (arrow of time); Maximization; Upper and lower bounds; Exploit; Artificial intelligence; Mathematics","score_opus":0.017741848969039416,"score_gpt":0.2845911047478464,"score_spread":0.26684925577880697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386126338","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":[0.0110484725,0.00004146834,0.9820335,0.0023141736,0.00018918801,0.0012707292,4.9940707e-7,0.0014688879,0.0016330769],"genre_scores_gemma":[0.97342724,0.000081385086,0.013475663,0.00026140906,0.00034145504,0.0004352007,0.0001714327,0.0000896411,0.011716554],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99629915,0.00018813222,0.00083687104,0.0007455106,0.00064096734,0.0012893492],"domain_scores_gemma":[0.99840784,0.00025492333,0.0005125187,0.00052582665,0.00013415693,0.00016474414],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016207938,0.00038847976,0.00037628587,0.001513009,0.0007072092,0.00048120605,0.00082759955,0.00014846823,0.000007689317],"category_scores_gemma":[0.0020856345,0.00042440154,0.00013539505,0.0029763384,0.00004557974,0.0005990695,0.00076985604,0.0007320837,0.00006062848],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012706826,0.000016148872,0.004871021,0.0000923164,0.000025271258,0.000009722112,0.002248586,0.89706147,0.0012234851,0.024919651,0.000020754394,0.06949887],"study_design_scores_gemma":[0.0011907064,0.0006953932,0.00095463457,0.00009464132,0.000008343748,0.0000058344567,0.0002380562,0.9772773,0.00057432905,0.0006633642,0.017874127,0.0004233024],"about_ca_topic_score_codex":0.0007558073,"about_ca_topic_score_gemma":0.000025527042,"teacher_disagreement_score":0.96855783,"about_ca_system_score_codex":0.00070828036,"about_ca_system_score_gemma":0.0003482175,"threshold_uncertainty_score":0.99982077},"labels":[],"label_agreement":null},{"id":"W4386185082","doi":"10.48550/arxiv.2308.12445","title":"An Intentional Forgetting-Driven Self-Healing Method For Deep Reinforcement Learning Systems","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Forgetting; Reinforcement learning; Convergence (economics); Adaptation (eye); Computer science; Reinforcement; Artificial intelligence; Cognitive psychology; Psychology; Social psychology; Neuroscience","score_opus":0.08574056855884084,"score_gpt":0.2481800766699188,"score_spread":0.16243950811107793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386185082","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":[0.0009958767,0.000027279038,0.9938477,0.00006954416,0.0019860836,0.0010749277,0.0000029990717,0.001548549,0.00044701897],"genre_scores_gemma":[0.84618056,0.00007423031,0.14811239,0.0000602069,0.00027185353,0.000019090718,0.00021312493,0.00008159578,0.004986956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99641913,0.0003795134,0.0005996358,0.0015289937,0.00030009236,0.0007726168],"domain_scores_gemma":[0.99647534,0.0005151676,0.00085966155,0.0013080543,0.0005578719,0.00028390108],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011658556,0.00049138785,0.00054642436,0.00057269173,0.00057833275,0.0005151475,0.0026059553,0.0004256863,0.000008851622],"category_scores_gemma":[0.00018693991,0.00060139,0.0003891685,0.00059526257,0.000046450412,0.00065242994,0.0020586895,0.0010306939,0.00007919655],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016553342,0.000024604884,0.00085996353,0.0003295614,0.00023012112,0.000037926144,0.00055225025,0.87977606,0.000024035882,0.11797027,0.00008219687,0.000096448544],"study_design_scores_gemma":[0.0005738736,0.000245586,0.00008797117,0.00022942935,0.00013297108,0.0000048336888,0.00047112114,0.9946494,0.000022215094,0.0019903425,0.0009751945,0.0006170762],"about_ca_topic_score_codex":0.00016358912,"about_ca_topic_score_gemma":0.000009326922,"teacher_disagreement_score":0.8457353,"about_ca_system_score_codex":0.00062384404,"about_ca_system_score_gemma":0.00027149738,"threshold_uncertainty_score":0.99964374},"labels":[],"label_agreement":null},{"id":"W4386431062","doi":"10.1007/978-3-031-43111-1_23","title":"Model-Based Policy Optimization with Neural Differential Equations for Robotic Arm Control","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Reinforcement learning; Robotic arm; Artificial intelligence; Trajectory; Process (computing); Artificial neural network; Task (project management); Node (physics); Robot; Sample (material); System dynamics; Machine learning; Engineering","score_opus":0.028591916689053084,"score_gpt":0.26111853006638336,"score_spread":0.23252661337733027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386431062","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":[0.0000011971067,0.000013236105,0.9960095,0.001501114,0.0008872649,0.0010174918,0.0000058350006,0.00034458126,0.00021973855],"genre_scores_gemma":[0.35455987,0.0000033658412,0.6427855,0.0012344106,0.00042453417,0.000055064884,0.00003980728,0.00007598224,0.00082147226],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964967,0.000030510799,0.00051623856,0.001186056,0.001017698,0.00075279735],"domain_scores_gemma":[0.9968965,0.0010165519,0.0003954096,0.0011028037,0.0004206031,0.00016812877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003489279,0.0005288715,0.00051060016,0.0012106075,0.00039690326,0.00076642865,0.0023052294,0.00024604317,0.0000059925937],"category_scores_gemma":[0.0002546618,0.00046121582,0.00014542002,0.00078749936,0.00044835982,0.000473662,0.0003677889,0.0005281125,0.0000109077355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013312975,0.000015547994,0.0000050575954,0.00003325493,0.000013650092,0.000005930549,0.000113192495,0.9644946,0.000011439756,0.025336908,0.0000039932497,0.009953125],"study_design_scores_gemma":[0.0009060277,0.0004092178,0.000007710353,0.00016960452,0.000026478496,0.0000044857256,4.93909e-8,0.9896081,0.000035966943,0.008316916,0.000006502275,0.00050894223],"about_ca_topic_score_codex":0.000010792681,"about_ca_topic_score_gemma":0.000021296637,"teacher_disagreement_score":0.35455868,"about_ca_system_score_codex":0.0003433249,"about_ca_system_score_gemma":0.001214238,"threshold_uncertainty_score":0.99978393},"labels":[],"label_agreement":null},{"id":"W4386473849","doi":"10.1007/978-3-031-43264-4_6","title":"Exploiting Reward Machines with Deep Reinforcement Learning in Continuous Action Domains","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"York University","keywords":"Counterfactual thinking; Reinforcement learning; Computer science; Task (project management); Artificial intelligence; Action (physics); Machine learning","score_opus":0.022827126539405374,"score_gpt":0.2547727152913582,"score_spread":0.2319455887519528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386473849","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":[0.0002623951,0.00005035457,0.9927163,0.00036985776,0.0012244284,0.0005568345,2.2039823e-7,0.0005631367,0.004256434],"genre_scores_gemma":[0.6191608,0.00019760214,0.3716422,0.0011043282,0.0007873236,0.000063938984,0.000030274046,0.00020331256,0.0068102395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99487156,0.0000734806,0.00083808805,0.001566872,0.001598723,0.0010512754],"domain_scores_gemma":[0.9971562,0.00069377007,0.0006441565,0.001117127,0.0002237154,0.00016503042],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014305,0.0006804811,0.0006912414,0.0015368273,0.00039250185,0.0007773743,0.002454758,0.00031198186,0.000014676283],"category_scores_gemma":[0.00026168654,0.0006110641,0.000110736364,0.0012489271,0.00042683756,0.0009494318,0.0014307499,0.0018218203,0.00008156888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000109279945,0.000005778495,0.0006427105,0.0000475105,0.000011961455,0.0001772359,0.0011658667,0.8598932,0.000038926126,0.0040142704,0.0000026324353,0.13398899],"study_design_scores_gemma":[0.00052812893,0.00043785994,0.00030101143,0.00090099144,0.000008691947,0.00006487283,0.0000028806726,0.99140847,0.00018044809,0.0050163674,0.00040276657,0.00074749143],"about_ca_topic_score_codex":0.00007933777,"about_ca_topic_score_gemma":0.00027690205,"teacher_disagreement_score":0.62107414,"about_ca_system_score_codex":0.0006432075,"about_ca_system_score_gemma":0.00038777868,"threshold_uncertainty_score":0.9996341},"labels":[],"label_agreement":null},{"id":"W4386735338","doi":"10.1007/978-3-031-43520-1_13","title":"A Relaxed Variant of Distributed Q-Learning Algorithm for Cooperative Matrix Games","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Algorithm; Computer science; Convergence (economics); Population-based incremental learning; Matrix (chemical analysis); Distributed algorithm; Q-learning; Weighted Majority Algorithm; Function (biology); Distributed learning; Artificial intelligence; Wake-sleep algorithm; Machine learning; Unsupervised learning; Reinforcement learning; Distributed computing; Genetic algorithm","score_opus":0.016378660899373284,"score_gpt":0.245987240694854,"score_spread":0.22960857979548072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386735338","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":[0.0000013334959,0.0024395692,0.9943643,0.000060574486,0.0011637292,0.0008833242,0.000034991488,0.0001342621,0.000917878],"genre_scores_gemma":[0.5454763,0.008866083,0.16448416,0.00036953212,0.006496724,0.0008723319,0.0035626988,0.001153404,0.26871875],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978741,0.00009782355,0.0007495906,0.0005741296,0.00030956816,0.0003948195],"domain_scores_gemma":[0.9971587,0.0015536022,0.0005793747,0.0004202499,0.00021317424,0.00007490973],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00065821316,0.0004021736,0.00084707496,0.00018857338,0.00012977379,0.0002279668,0.00045429944,0.00061999477,0.0000029642074],"category_scores_gemma":[0.00019913542,0.0003464777,0.00012719026,0.0001982946,0.000079008576,0.000087446446,0.00023921384,0.000800179,0.0000031110935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007072085,0.000003139758,0.000025307727,0.00013698016,0.00010490501,0.00003306567,0.0002333634,0.95704955,0.0000017546503,0.034120947,0.00019325195,0.008090639],"study_design_scores_gemma":[0.00041693597,0.00026546122,0.000010314955,0.0010714805,0.000033842403,0.000026871727,0.00000674777,0.99060005,0.0000024437663,0.0009367491,0.0062831063,0.0003459768],"about_ca_topic_score_codex":0.000036630605,"about_ca_topic_score_gemma":0.0000102833665,"teacher_disagreement_score":0.8298802,"about_ca_system_score_codex":0.0000762246,"about_ca_system_score_gemma":0.00007183641,"threshold_uncertainty_score":0.99989873},"labels":[],"label_agreement":null},{"id":"W4386815360","doi":"10.14428/esann/2023.es2023-181","title":"Multi-Fidelity Reinforcement Learning with Control Variates","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Microsoft (Canada)","funders":"","keywords":"Reinforcement learning; Estimator; Fidelity; Control variates; Computer science; Variance (accounting); Variance reduction; High fidelity; Monte Carlo method; Mathematical optimization; Bellman equation; Artificial intelligence; Sample (material); Function (biology); Machine learning; Mathematics; Statistics; Engineering","score_opus":0.021197303717907963,"score_gpt":0.2544386487722293,"score_spread":0.23324134505432137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386815360","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":[0.00081535673,0.0000052127075,0.9910876,0.00056200824,0.00014857315,0.00023903711,1.0069865e-7,0.0013958324,0.005746242],"genre_scores_gemma":[0.9121383,0.000010347519,0.071288496,0.00044688617,0.000029827203,0.000025117733,0.000007024358,0.00001486548,0.016039146],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983176,0.000077999575,0.00029800803,0.00036344214,0.00046532496,0.0004776058],"domain_scores_gemma":[0.9989127,0.00019829835,0.0001283404,0.0005196753,0.00012996799,0.000111047884],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00065366714,0.00017324406,0.00018207314,0.00014311791,0.00023651333,0.0002365648,0.00066663895,0.000051694642,0.00007709967],"category_scores_gemma":[0.00014618196,0.00013156384,0.000048553782,0.00069149886,0.000039023766,0.0004464422,0.000249838,0.00024649064,0.0009033906],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006494822,0.000006631789,0.0038545365,0.000008890083,0.000036035282,0.0000141858,0.00027324533,0.98471445,0.00028384905,0.009918606,0.000324511,0.0005585857],"study_design_scores_gemma":[0.0010937781,0.00020756545,0.0069828015,0.000015229499,0.0000074714585,0.000003933282,0.000058496677,0.9881801,0.00017970108,0.000035368386,0.0030349998,0.00020056781],"about_ca_topic_score_codex":0.00006956869,"about_ca_topic_score_gemma":0.000004306017,"teacher_disagreement_score":0.91979915,"about_ca_system_score_codex":0.000049017493,"about_ca_system_score_gemma":0.000065650835,"threshold_uncertainty_score":0.99987453},"labels":[],"label_agreement":null},{"id":"W4387394630","doi":"10.1609/aiide.v19i1.27526","title":"Herd’s Eye View: Improving Game AI Agent Learning with Collaborative Perception","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Reinforcement Learning in Robotics","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":"Memorial University of Newfoundland","funders":"","keywords":"Reinforcement learning; Perception; Computer science; Perspective (graphical); Artificial intelligence; Context (archaeology); Human–computer interaction; Psychology","score_opus":0.025858606414871924,"score_gpt":0.280315566260375,"score_spread":0.2544569598455031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387394630","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":[0.6521212,0.000014981748,0.32753438,0.005245426,0.0005214351,0.0013133956,0.000009021406,0.0003077661,0.012932423],"genre_scores_gemma":[0.99808073,0.000062122315,0.00017825763,0.00023756952,0.00003184906,0.00004998617,0.0000038723556,0.000017275017,0.0013383164],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803364,0.000023566865,0.00045794857,0.00053643424,0.0005724081,0.00037601005],"domain_scores_gemma":[0.9985988,0.000089283065,0.0004263949,0.00018096091,0.00060729234,0.00009724344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024052903,0.00028752614,0.0002664647,0.00018517769,0.00020607712,0.0010034933,0.0007187706,0.000056547633,0.000026766449],"category_scores_gemma":[0.0002407609,0.00020100441,0.00008407025,0.00064571993,0.00021453337,0.0015984846,0.000548888,0.000417257,0.000111261346],"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":[0.0010836252,0.00057981577,0.008242342,0.0003125737,0.0003652069,0.00001284106,0.053498868,0.05546365,0.064616255,0.19342269,0.000393551,0.62200856],"study_design_scores_gemma":[0.00016981947,0.0029209103,0.0018474852,0.0010093467,0.000029825103,0.000008728286,0.025626527,0.87564164,0.08672374,0.0039570816,0.0014442457,0.00062062166],"about_ca_topic_score_codex":0.000012395306,"about_ca_topic_score_gemma":0.0000016651713,"teacher_disagreement_score":0.82017803,"about_ca_system_score_codex":0.0001451927,"about_ca_system_score_gemma":0.000063448584,"threshold_uncertainty_score":0.9676709},"labels":[],"label_agreement":null},{"id":"W4387423117","doi":"10.1007/978-981-99-6882-4_73","title":"LSTM-TD3-Based Control for Delayed Drone Combat Strategies","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in electrical engineering","topic":"Reinforcement Learning in Robotics","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":"Ministry of Education and Child Care","funders":"","keywords":"Reinforcement learning; Computer science; Battlefield; Battle; Latency (audio); Artificial intelligence; Simulation; Operations research; Engineering; Telecommunications","score_opus":0.010792545237382075,"score_gpt":0.2205415140318213,"score_spread":0.20974896879443922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387423117","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":[0.0000032333305,0.00042906805,0.99521863,0.00034662243,0.0005554499,0.0007321366,0.0000075882685,0.0008281167,0.0018791545],"genre_scores_gemma":[0.8198695,0.00016271892,0.16286965,0.0016651924,0.0013550731,0.00044055784,0.00027545964,0.00086377375,0.012498027],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736416,0.000017686643,0.00059295015,0.0006771662,0.0005070695,0.00084098836],"domain_scores_gemma":[0.99653345,0.0024202499,0.00018245626,0.00062524446,0.000111275614,0.00012734864],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028328673,0.0006123249,0.0007221913,0.0006440768,0.000074844356,0.0002495066,0.0010074769,0.00068486144,0.000010674574],"category_scores_gemma":[0.00056193303,0.0006249928,0.00025380225,0.00037618878,0.00003171909,0.0001555295,0.00006852566,0.0013540984,0.00003330756],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002065996,0.0000065366025,0.0000017246208,0.00007545839,0.000074956406,0.00003161406,0.00002409353,0.88333887,0.00027782444,0.11160767,0.000043340926,0.0044972445],"study_design_scores_gemma":[0.0009632577,0.00039723187,0.000010774871,0.00014391672,0.000039516493,0.0000052546834,1.3653028e-7,0.98443675,0.0003094937,0.009914371,0.003140968,0.00063834747],"about_ca_topic_score_codex":0.000009488631,"about_ca_topic_score_gemma":0.00000885049,"teacher_disagreement_score":0.832349,"about_ca_system_score_codex":0.0003271562,"about_ca_system_score_gemma":0.00025409108,"threshold_uncertainty_score":0.99962014},"labels":[],"label_agreement":null},{"id":"W4387725412","doi":"10.48550/arxiv.2310.10502","title":"Adaptive Robot Assistance: Expertise and Influence in Multi-User Task Planning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Partially observable Markov decision process; Computer science; Heuristics; Task (project management); Scalability; Robot; Markov decision process; Unobservable; Artificial intelligence; Process (computing); Human–computer interaction; Domain (mathematical analysis); Machine learning; Markov process; Markov chain; Engineering; Markov model; Systems engineering","score_opus":0.1377794439627749,"score_gpt":0.23352530018644124,"score_spread":0.09574585622366635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387725412","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":[0.10944886,0.000084382315,0.88925135,0.000044131903,0.00038469257,0.0002796519,0.0000031042318,0.00030767077,0.00019613386],"genre_scores_gemma":[0.9853516,0.00014686125,0.010711,0.000078892204,0.00002032411,0.0000030757403,0.000005523239,0.000027466362,0.0036552162],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976927,0.00014611035,0.00028679124,0.0012530687,0.00014666798,0.00047464293],"domain_scores_gemma":[0.9982641,0.00017897357,0.00028890828,0.0009740792,0.00013433293,0.00015961686],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028636344,0.0003564268,0.00036773641,0.000426356,0.00013944758,0.00022205952,0.0014780504,0.00030258237,0.00000258439],"category_scores_gemma":[0.00013638247,0.00043338482,0.00008376416,0.0007070743,0.00012453497,0.000728338,0.0028559333,0.00089075684,0.000058008092],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019789511,0.000019533207,0.042039152,0.00004022729,0.000033941356,0.0006584982,0.0011546096,0.94731647,0.000033159562,0.008573049,0.000040454477,0.000071093],"study_design_scores_gemma":[0.00056840136,0.000042250344,0.062348112,0.00041455743,0.000015280353,0.0000016798144,0.00027444714,0.93513733,0.000019518708,0.0006324197,0.00009275489,0.00045326684],"about_ca_topic_score_codex":0.00027281133,"about_ca_topic_score_gemma":0.000052131036,"teacher_disagreement_score":0.8785404,"about_ca_system_score_codex":0.00034343766,"about_ca_system_score_gemma":0.0001505699,"threshold_uncertainty_score":0.99981177},"labels":[],"label_agreement":null},{"id":"W4387883591","doi":"10.1109/icc45041.2023.10279552","title":"Optimized Provisioning Techniques for Geo-Distributed SDP-Enabled Next Generation Networks Security","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Guelph","funders":"","keywords":"Computer science; Provisioning; Scalability; Distributed computing; Software-defined networking; Reinforcement learning; Cloud computing; Next-generation network; Computer security; The Internet; Computer network; Artificial intelligence","score_opus":0.04171480449560785,"score_gpt":0.2806764264405227,"score_spread":0.23896162194491485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387883591","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":[0.0003691028,0.0000149756725,0.99494195,0.0006886694,0.0003410197,0.00088132283,0.0000014076147,0.0020999059,0.00066165545],"genre_scores_gemma":[0.14164647,0.00006237653,0.85428727,0.00045582544,0.0003892311,0.00032721815,0.00047097285,0.000033421828,0.002327238],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983901,0.00006722576,0.00036952645,0.0004252001,0.00026897877,0.00047900475],"domain_scores_gemma":[0.9988266,0.00019617494,0.0001470841,0.00052454654,0.00022027885,0.00008528867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008335812,0.00017477716,0.00020444981,0.00013806006,0.00035527415,0.0006382159,0.00064830796,0.00013904074,0.000023834962],"category_scores_gemma":[0.00022068874,0.00015795468,0.00009196729,0.00077878113,0.000023423327,0.0007633269,0.00036124839,0.0001756546,0.000028675924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008866736,0.000009276742,0.000015983735,0.000013175581,0.000013807886,0.0000026876269,0.000082636434,0.9616873,0.0004715589,0.011088859,0.02192317,0.0046826485],"study_design_scores_gemma":[0.0003734884,0.00012838341,0.000017829745,0.000017363729,0.000006803872,0.0000020391417,0.000016532349,0.98860717,0.002489869,0.0003834954,0.0077537554,0.00020326304],"about_ca_topic_score_codex":0.00001649396,"about_ca_topic_score_gemma":0.0000012340178,"teacher_disagreement_score":0.14127737,"about_ca_system_score_codex":0.000071706345,"about_ca_system_score_gemma":0.00006840905,"threshold_uncertainty_score":0.64412045},"labels":[],"label_agreement":null},{"id":"W4387964087","doi":"10.48550/arxiv.2310.16686","title":"Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Division of Mathematical Sciences; Canadian Institute for Advanced Research","keywords":"Adapter (computing); Reinforcement learning; Computer science; Architecture; Artificial intelligence; Robot; Context (archaeology); Machine learning; Human–computer interaction","score_opus":0.10101501291661223,"score_gpt":0.20956679359048505,"score_spread":0.10855178067387282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387964087","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":[0.024104467,0.000010743967,0.97292465,0.00025595838,0.0006288942,0.00043237215,0.0000028233771,0.00051609863,0.0011239699],"genre_scores_gemma":[0.98948914,0.00013812157,0.0007988569,0.00011353478,0.000062774576,0.0000033693866,0.000116324634,0.00003786135,0.009240012],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975517,0.00024777465,0.00042222734,0.0009916623,0.0002220411,0.00056461344],"domain_scores_gemma":[0.9980485,0.00016612562,0.00051670504,0.00093669916,0.0002000241,0.00013195284],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042469695,0.0004136624,0.00041450994,0.0007159407,0.00020955576,0.00018151452,0.0016457152,0.0003593396,0.000015647809],"category_scores_gemma":[0.000071166774,0.0005238581,0.00015629717,0.00092619297,0.00011370334,0.0005039945,0.0026939057,0.0011610178,0.00017168892],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014584672,0.000011153953,0.0050349534,0.00003657587,0.00005671212,0.000107739965,0.0008288207,0.87514657,0.000004607648,0.11845672,0.000051106832,0.00025045214],"study_design_scores_gemma":[0.00043008925,0.00012235105,0.0019863828,0.00015218419,0.000026436543,0.0000017421098,0.00049789646,0.9918402,0.00002206967,0.0043434794,0.00007517868,0.0005020034],"about_ca_topic_score_codex":0.0024693783,"about_ca_topic_score_gemma":0.0007139996,"teacher_disagreement_score":0.9721258,"about_ca_system_score_codex":0.0013527267,"about_ca_system_score_gemma":0.00021731594,"threshold_uncertainty_score":0.9997213},"labels":[],"label_agreement":null},{"id":"W4388040445","doi":"10.1109/pimrc56721.2023.10293845","title":"DRJLRA: A Deep Reinforcement Learning-Based Joint Load and Resource Allocation in Heterogeneous Coded Distributed Computing","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Alberta Innovates","keywords":"Computer science; Benchmark (surveying); Reinforcement learning; Distributed computing; Computation; Task (project management); Set (abstract data type); Resource allocation; Resource management (computing); Scheme (mathematics); Artificial intelligence; Theoretical computer science; Algorithm; Computer network","score_opus":0.020413338865493815,"score_gpt":0.24458704463290457,"score_spread":0.22417370576741075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388040445","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":[0.020718852,0.000022411738,0.9766407,0.00086941494,0.000078751546,0.00031385533,1.8528927e-7,0.00066471106,0.00069112465],"genre_scores_gemma":[0.9942302,0.000008261767,0.0047499374,0.00034019884,0.000019973906,0.000012808916,0.000073454605,0.000016544374,0.00054858194],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977474,0.00014628598,0.0005335688,0.0004827067,0.0005633375,0.0005266581],"domain_scores_gemma":[0.998929,0.00021054142,0.00019433262,0.00043818465,0.000104013445,0.0001239309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088690064,0.00021238172,0.00023692843,0.00024787817,0.00021096593,0.00024669387,0.00041985168,0.000088576526,0.000014632688],"category_scores_gemma":[0.00028132604,0.00021363005,0.000052289317,0.0009794378,0.000056893034,0.00016502272,0.0004719464,0.00028602703,0.0000887258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008059282,0.000010580039,0.0010926322,0.00002857058,0.000010568746,0.000026623518,0.0005811678,0.99533665,0.00018814446,0.0008194187,0.00015156709,0.0017459864],"study_design_scores_gemma":[0.00081020594,0.00016912981,0.0023748646,0.000057017,0.0000043193277,0.000007745185,0.00008631056,0.99358773,0.0010716784,0.000029399996,0.0015627755,0.00023881877],"about_ca_topic_score_codex":0.00007541026,"about_ca_topic_score_gemma":0.000026297059,"teacher_disagreement_score":0.9735114,"about_ca_system_score_codex":0.00025093622,"about_ca_system_score_gemma":0.000090399866,"threshold_uncertainty_score":0.871158},"labels":[],"label_agreement":null},{"id":"W4388191662","doi":"10.1016/j.asoc.2023.110975","title":"Ensemble reinforcement learning: A survey","year":2023,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"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":"Science and Technology Innovation Group of Shanxi Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Popularity; Generalization; Field (mathematics); Ensemble learning; Artificial intelligence; Machine learning; Open research; Selection (genetic algorithm); Data science","score_opus":0.03247530673738754,"score_gpt":0.2652782368121937,"score_spread":0.23280293007480615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388191662","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":[0.013813726,0.0000069253992,0.9646641,0.00010524147,0.00039153558,0.0002606582,1.0757764e-7,0.0019251142,0.018832581],"genre_scores_gemma":[0.9833896,0.000005195251,0.014130751,0.00029827142,0.00007735335,0.00001009498,0.000045124634,0.000031675376,0.0020119422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974181,0.00010903689,0.00047761237,0.00056440546,0.0006407648,0.00079007377],"domain_scores_gemma":[0.998013,0.00086151774,0.00024214892,0.00064754515,0.00009679159,0.00013899365],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018971154,0.0002481542,0.00026988657,0.00023738916,0.00051800435,0.00031920418,0.0011255982,0.00009335207,0.00001779605],"category_scores_gemma":[0.00026076063,0.00026557592,0.000071292125,0.0015293709,0.000047669524,0.00015179897,0.0011990537,0.0004373861,0.0017341779],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037707232,0.000005998801,0.0017765622,0.000015843674,0.000022554937,0.0000084243975,0.0009975538,0.9639947,0.00040033364,0.017513704,0.001179397,0.014081193],"study_design_scores_gemma":[0.000341124,0.000059585527,0.008140815,0.000016566506,0.000003512279,0.0000036963252,0.00006727902,0.9863053,0.00038146655,0.00028000344,0.004084138,0.00031653812],"about_ca_topic_score_codex":0.000042500844,"about_ca_topic_score_gemma":0.0000030781132,"teacher_disagreement_score":0.9695759,"about_ca_system_score_codex":0.00007569789,"about_ca_system_score_gemma":0.00008675491,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W4388342252","doi":"10.1002/aisy.202300352","title":"A Multiobjective Collaborative Deep Reinforcement Learning Algorithm for Jumping Optimization of Bipedal Robot","year":2023,"lang":"en","type":"article","venue":"Advanced Intelligent Systems","topic":"Reinforcement Learning in Robotics","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":"McMaster University","funders":"Government of Jiangsu Province; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Markov decision process; Convergence (economics); Robot; Jumping; Artificial intelligence; Q-learning; Nonlinear system; Robotics; Mathematical optimization; Machine learning; Markov process; Mathematics","score_opus":0.020510999090521592,"score_gpt":0.28889894933451854,"score_spread":0.268387950243997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388342252","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":[0.000043432177,0.00018570806,0.9957889,0.000029611554,0.0013510198,0.0016748908,0.0000027332383,0.00040978083,0.00051393],"genre_scores_gemma":[0.4048792,0.0005286456,0.5892338,0.000042909833,0.00018827732,0.00071287714,0.00019149149,0.000084128646,0.004138645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751353,0.00013468119,0.0008376179,0.00051036285,0.00051207247,0.0004917468],"domain_scores_gemma":[0.9974212,0.00048996194,0.0007004862,0.00042618674,0.0008680056,0.00009413905],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006121793,0.00026274813,0.00040996884,0.0004109449,0.0002643362,0.00012631236,0.0005544971,0.00010014166,0.000004850736],"category_scores_gemma":[0.00038383057,0.00026732293,0.00011678896,0.0015521462,0.00005284964,0.0006581635,0.00020349926,0.00017760744,0.000042879536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012709668,0.000012577406,0.00003596405,0.00009142965,0.00008115228,0.0000020312507,0.002291591,0.98028755,0.00046821957,0.002697453,0.0000400501,0.01397929],"study_design_scores_gemma":[0.0004941155,0.0005045191,0.000009198601,0.00018684528,0.000014069879,0.000002557438,0.0024149586,0.98635375,0.008029197,0.000025276751,0.0016944817,0.0002710313],"about_ca_topic_score_codex":0.000024584795,"about_ca_topic_score_gemma":0.0000011961442,"teacher_disagreement_score":0.4065551,"about_ca_system_score_codex":0.00024479855,"about_ca_system_score_gemma":0.00010042754,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W4388483498","doi":"10.1109/ase56229.2023.00121","title":"An Intentional Forgetting-Driven Self-Healing Method for Deep Reinforcement Learning Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal","funders":"","keywords":"Forgetting; Reinforcement learning; Convergence (economics); Computer science; Adaptation (eye); Reinforcement; Artificial intelligence; Cognitive psychology; Engineering; Psychology","score_opus":0.02687934710323557,"score_gpt":0.31674026995211785,"score_spread":0.28986092284888226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388483498","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":[0.00014914315,0.000015974936,0.9940841,0.00027205076,0.0008620894,0.00061397656,2.3705175e-7,0.0019771447,0.0020252557],"genre_scores_gemma":[0.2708358,0.00001252804,0.7227693,0.00020844386,0.00022907768,0.00017396524,0.00008834493,0.000040372506,0.0056421366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997539,0.00015785042,0.0005693902,0.000522044,0.0005652551,0.00064647343],"domain_scores_gemma":[0.9983258,0.00045267135,0.00025468034,0.0005145029,0.00028356066,0.00016876851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013889028,0.00021110404,0.00024576468,0.0003069564,0.0004861941,0.000475961,0.000960285,0.000099920086,0.000014111772],"category_scores_gemma":[0.00019112119,0.00020151396,0.0001341706,0.00060759933,0.000014677742,0.0007108888,0.00031145773,0.00023758275,0.000131771],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003016686,0.000008771099,0.00034677447,0.000075793265,0.00004797367,0.000002297498,0.00076737336,0.90098345,0.00036434835,0.095927835,0.00047544218,0.0009969312],"study_design_scores_gemma":[0.00039899256,0.00031700433,0.000081243066,0.000037050377,0.000014642271,0.000008061917,0.0005903228,0.9904234,0.00022518488,0.00018728549,0.0074605127,0.0002563418],"about_ca_topic_score_codex":0.000034220895,"about_ca_topic_score_gemma":0.0000016821717,"teacher_disagreement_score":0.2713148,"about_ca_system_score_codex":0.00013216912,"about_ca_system_score_gemma":0.00007502726,"threshold_uncertainty_score":0.8217501},"labels":[],"label_agreement":null},{"id":"W4388551180","doi":"10.1007/s10458-023-09628-3","title":"ASN: action semantics network for multiagent reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","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":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Semantics (computer science); Artificial intelligence; Action (physics); Action selection; Artificial neural network; Multi-agent system; Programming language; Perception","score_opus":0.08029373040729547,"score_gpt":0.3143184978309977,"score_spread":0.2340247674237022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388551180","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":[0.008090792,0.00015103132,0.9851484,0.00023033164,0.0037038159,0.0016368243,0.0000024482165,0.00082482287,0.00021156958],"genre_scores_gemma":[0.9615466,0.0004706599,0.0124610895,0.00019558103,0.00040360802,0.00030669232,0.00011481148,0.00006315859,0.024437811],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971378,0.0001312546,0.00073053234,0.0006728976,0.00044849075,0.0008790228],"domain_scores_gemma":[0.99845046,0.0001743862,0.00044548634,0.000565514,0.0001308376,0.00023332835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010337839,0.00035626823,0.00039801045,0.00019897136,0.0007791067,0.00052977115,0.00053371384,0.00015583173,0.00000768313],"category_scores_gemma":[0.000086183274,0.0003407899,0.00014375444,0.00041192258,0.000038957623,0.00039022163,0.0004270154,0.00023500316,0.00021467087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005528162,0.000022948416,0.0022446648,0.00019711796,0.00011520873,0.00001463633,0.000990572,0.9843906,0.00013604155,0.0022028617,0.0062565664,0.0034232272],"study_design_scores_gemma":[0.0009559125,0.0001681401,0.0030614536,0.00009140838,0.000030612053,0.000009899033,0.00024248086,0.85126024,0.00005534204,0.0000061089995,0.143784,0.0003344143],"about_ca_topic_score_codex":0.0001284435,"about_ca_topic_score_gemma":0.000006025089,"teacher_disagreement_score":0.9726873,"about_ca_system_score_codex":0.00019095761,"about_ca_system_score_gemma":0.00006483382,"threshold_uncertainty_score":0.9999044},"labels":[],"label_agreement":null},{"id":"W4388741154","doi":"10.1016/j.engappai.2023.107518","title":"Reinforcement learning to achieve real-time control of triple inverted pendulum","year":2023,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Inverted pendulum; Markov decision process; Process (computing); Convergence (economics); Sample (material); Artificial intelligence; Machine learning; Markov process","score_opus":0.01839544774908922,"score_gpt":0.26089423124250033,"score_spread":0.2424987834934111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388741154","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":[0.002082914,0.000006787484,0.9962185,0.000222101,0.000112810776,0.00055221975,0.0000017739541,0.00039087477,0.000412033],"genre_scores_gemma":[0.9699894,0.000029741868,0.029205093,0.000015226259,0.00003885068,0.00015697604,0.000012693142,0.00001908825,0.00053291523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834156,0.00002586033,0.0006874096,0.00028540505,0.00035966517,0.00030007746],"domain_scores_gemma":[0.99862903,0.00022919156,0.00020373738,0.00063392916,0.00019719123,0.000106901534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005185108,0.00014882322,0.00024833222,0.00042898668,0.000081308346,0.00003806972,0.00091036584,0.0000600626,0.000027264852],"category_scores_gemma":[0.0002703928,0.00017010617,0.00007718653,0.0019030954,0.00003794937,0.00014433869,0.0002007195,0.00016491744,0.0004448163],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073167216,0.000013973939,0.000014504924,0.000027072554,0.000019808735,3.8864937e-7,0.00049961585,0.9021786,0.04348249,0.043214303,0.0000647976,0.010477165],"study_design_scores_gemma":[0.000029503684,0.00017534294,0.000063649335,0.000030285632,0.000007565319,5.6270574e-7,0.00006739946,0.95404404,0.044216715,0.0002881996,0.00093331886,0.00014340562],"about_ca_topic_score_codex":0.00005954454,"about_ca_topic_score_gemma":7.0655943e-7,"teacher_disagreement_score":0.9679065,"about_ca_system_score_codex":0.000044784632,"about_ca_system_score_gemma":0.000049241185,"threshold_uncertainty_score":0.69367284},"labels":[],"label_agreement":null},{"id":"W4388761312","doi":"10.17760/d20486919","title":"Bayesian partially observable reinforcement learning","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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":"Science North","funders":"","keywords":"Computer science; Reinforcement learning; Inference; State (computer science); Bayesian inference; Artificial intelligence; Bayesian probability","score_opus":0.025291122515353624,"score_gpt":0.27267902967139845,"score_spread":0.24738790715604483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388761312","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014663569,0.00002897001,0.86074436,0.00012648125,0.002398156,0.00033618402,1.00962694e-7,0.0015793446,0.13463977],"genre_scores_gemma":[0.058416974,0.00014746003,0.0132295145,0.00020389965,0.00018569437,0.00008719543,0.00071763986,0.000104973,0.92690665],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99691135,0.000077184035,0.00068310235,0.00068394834,0.00095228123,0.0006921338],"domain_scores_gemma":[0.99819577,0.00013482518,0.0004296711,0.00088584906,0.00018836693,0.00016549646],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004655158,0.0004190374,0.00039610334,0.00028204164,0.00033263725,0.00059104786,0.0015910155,0.0003270063,0.0003303113],"category_scores_gemma":[0.00021468043,0.00041992753,0.00018687856,0.00068969914,0.000014105834,0.0004705326,0.00024872276,0.0007559665,0.0022742439],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006656617,0.000005767454,0.00011901953,0.000113132985,0.00006251719,0.000024002315,0.0009960781,0.97850305,0.00006356441,0.012173253,0.004873233,0.0030597528],"study_design_scores_gemma":[0.00021714668,0.00018214768,0.0005649876,0.00017032806,0.000027580129,0.0000014936845,0.00036353368,0.97132736,0.00074495934,0.00025627087,0.02556098,0.00058323465],"about_ca_topic_score_codex":0.00014171214,"about_ca_topic_score_gemma":0.00012690054,"teacher_disagreement_score":0.84751487,"about_ca_system_score_codex":0.00012402362,"about_ca_system_score_gemma":0.0003114757,"threshold_uncertainty_score":0.99982524},"labels":[],"label_agreement":null},{"id":"W4388820294","doi":"10.1109/tie.2023.3331074","title":"Model-Based Reinforcement Learning With Probabilistic Ensemble Terminal Critics for Data-Efficient Control Applications","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"National Research Foundation of Korea","keywords":"Reinforcement learning; Probabilistic logic; Computer science; Trajectory; Artificial intelligence; Machine learning","score_opus":0.06410995923129628,"score_gpt":0.2901327633149109,"score_spread":0.2260228040836146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388820294","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":[0.00018848007,0.000007846822,0.99621075,0.0004541579,0.00028661932,0.002086681,0.000023829496,0.00058306695,0.00015858022],"genre_scores_gemma":[0.986236,0.000010593213,0.01128578,0.00017306341,0.00013511805,0.0011297265,0.00009946088,0.000051686366,0.00087858055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997257,0.00008175996,0.00050052104,0.0007024992,0.00061214174,0.0008460675],"domain_scores_gemma":[0.99754435,0.00060059736,0.00019296832,0.0011874358,0.00031907228,0.00015557681],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006959062,0.00030058922,0.00029200144,0.00030089068,0.00073705247,0.00022469198,0.00114448,0.00019446886,0.000005890893],"category_scores_gemma":[0.00008640592,0.0002903224,0.000096407115,0.000984404,0.00008987563,0.00021897105,0.000009444285,0.00086949056,0.00003825974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013538824,0.00008741302,0.0000013543984,0.000027049527,0.000054281747,0.000001724933,0.000049779715,0.98736787,0.00009751274,0.0029289504,0.00021667678,0.009032027],"study_design_scores_gemma":[0.0026635795,0.0011856237,2.351949e-7,0.00003921394,0.00012756568,0.000003967035,0.000014194154,0.98777837,0.0012717254,0.00010983627,0.0064814948,0.00032420398],"about_ca_topic_score_codex":0.0000064129977,"about_ca_topic_score_gemma":0.000008097918,"teacher_disagreement_score":0.9860475,"about_ca_system_score_codex":0.0003695061,"about_ca_system_score_gemma":0.001309889,"threshold_uncertainty_score":0.9999549},"labels":[],"label_agreement":null},{"id":"W4388904319","doi":"10.1016/j.ifacol.2023.10.924","title":"Reinforcement Learning with Partial Parametric Model Knowledge","year":2023,"lang":"en","type":"article","venue":"IFAC-PapersOnLine","topic":"Reinforcement Learning in Robotics","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":"Honeywell (Canada); University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Ignorance; Bridge (graph theory); Parametric statistics; Control (management); Linear-quadratic regulator; Complete information; Partial least squares regression; Mathematical optimization; Artificial intelligence; Mathematics; Machine learning; Mathematical economics; Statistics; Law","score_opus":0.031056413427376525,"score_gpt":0.27725972538507326,"score_spread":0.24620331195769674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388904319","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":[0.016241295,0.000055235843,0.9737559,0.0007541433,0.00026463225,0.0002917163,8.7653063e-7,0.0012136163,0.0074225804],"genre_scores_gemma":[0.59378994,0.000100668396,0.3781015,0.00026223998,0.00019762955,0.00005227608,0.0000643363,0.000055191762,0.027376221],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997424,0.000075478245,0.00041075982,0.000606055,0.00068288564,0.00080083497],"domain_scores_gemma":[0.9985473,0.00020734344,0.00019081461,0.0006948176,0.00014005355,0.00021964165],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00050634006,0.00032298072,0.00031019707,0.00044797963,0.00033810613,0.00022277779,0.0009497675,0.0001123135,0.000039665283],"category_scores_gemma":[0.00020793325,0.00027211284,0.00010467277,0.0024101613,0.00007943751,0.0004942676,0.00046790327,0.000501024,0.001112853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015426238,0.00002588973,0.000615198,0.000025711175,0.000041304887,0.00002670484,0.0010715133,0.98994255,0.0001864165,0.0036557508,0.00005106312,0.004342497],"study_design_scores_gemma":[0.00072676426,0.00037727779,0.00021283104,0.00004567804,0.00001958028,0.000009769219,0.000102891354,0.9947497,0.00030628545,0.000033627988,0.003040003,0.00037557588],"about_ca_topic_score_codex":0.000014275315,"about_ca_topic_score_gemma":0.0000046287323,"teacher_disagreement_score":0.59565437,"about_ca_system_score_codex":0.00011596687,"about_ca_system_score_gemma":0.00019967587,"threshold_uncertainty_score":0.9999731},"labels":[],"label_agreement":null},{"id":"W4389218123","doi":"10.48550/arxiv.2311.17855","title":"Maximum Entropy Model Correction in Reinforcement Learning","year":2023,"lang":"en","type":"preprint","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Principle of maximum entropy; Computer science; Convergence (economics); Bellman equation; Entropy (arrow of time); Algorithm; Mathematical optimization; Function (biology); Applied mathematics; Mathematics; Artificial intelligence","score_opus":0.021591920548086455,"score_gpt":0.25046835554405456,"score_spread":0.2288764349959681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389218123","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":[0.0024475495,0.00017736378,0.98743296,0.0022263518,0.0018318715,0.0014256398,0.0000034247812,0.0034330345,0.0010218327],"genre_scores_gemma":[0.73167986,0.001111707,0.24045035,0.0011396136,0.0002556717,0.0024258466,0.00018575924,0.00024727793,0.02250391],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942796,0.00030860398,0.0013453836,0.001412543,0.0011550126,0.0014988503],"domain_scores_gemma":[0.99602604,0.0002163035,0.00090871216,0.0022880516,0.0002094884,0.0003513815],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016991539,0.00083732104,0.0008208701,0.0017295824,0.0003174828,0.0009110686,0.0027384476,0.00096350774,0.000020233558],"category_scores_gemma":[0.0006161855,0.00097121834,0.00031628428,0.0011143193,0.000080167876,0.0006284907,0.004505764,0.0035824503,0.00013707629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028800941,0.000051284744,0.005247109,0.000093837094,0.00004957698,0.0000855842,0.0006549489,0.97500795,0.00035274742,0.011898374,0.0028664481,0.0036633566],"study_design_scores_gemma":[0.00044162388,0.00016694503,0.0022482814,0.00036622348,0.000024299889,0.000024410929,0.000046999026,0.98707664,0.0008483538,0.0072286334,0.0006655133,0.0008620569],"about_ca_topic_score_codex":0.0070067593,"about_ca_topic_score_gemma":0.0007627544,"teacher_disagreement_score":0.7469826,"about_ca_system_score_codex":0.0023646674,"about_ca_system_score_gemma":0.0008435045,"threshold_uncertainty_score":0.99960566},"labels":[],"label_agreement":null},{"id":"W4389339279","doi":"10.1145/3618338","title":"Scene-Aware Activity Program Generation with Language Guidance","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Reinforcement Learning in Robotics","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":"National Natural Science Foundation of China","keywords":"Computer science; Executable; Generalizability theory; Encoder; Scene graph; Graph; Artificial intelligence; Rationality; Perception; Representation (politics); Key (lock); Machine learning; Theoretical computer science; Human–computer interaction; Natural language processing; Programming language","score_opus":0.03607292347747975,"score_gpt":0.29635666487959256,"score_spread":0.2602837414021128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389339279","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":[0.025317168,0.000008519701,0.9716925,0.0010014718,0.00025630675,0.00032541368,0.000003676531,0.0012572319,0.00013769133],"genre_scores_gemma":[0.95587045,0.000059453,0.043024864,0.00022117772,0.00004326203,0.0001245917,0.00001267701,0.00002289109,0.0006206182],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986527,0.00006665247,0.00014435103,0.00037497343,0.00044855624,0.0003127927],"domain_scores_gemma":[0.9985778,0.0000903501,0.000074808224,0.0010854944,0.00009109535,0.000080473896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020808046,0.00016791129,0.00012067207,0.00028536873,0.0003460107,0.00018174031,0.0007064979,0.00008747775,0.000009356332],"category_scores_gemma":[0.00002185623,0.0001504833,0.0000734197,0.0018735904,0.00006524364,0.00046055418,0.000016699494,0.00032300377,0.00007552962],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001960758,0.00019902964,0.00036739136,0.00004104069,0.000083441926,0.000048414884,0.0010332082,0.79604214,0.0017750406,0.0016005475,0.00034823618,0.19844192],"study_design_scores_gemma":[0.00037467104,0.0004940488,0.0027238156,0.00003784065,0.000018685494,0.000014029066,0.000045649565,0.9871818,0.007758359,0.00010950368,0.00095593365,0.00028567473],"about_ca_topic_score_codex":0.000031205556,"about_ca_topic_score_gemma":0.00006828428,"teacher_disagreement_score":0.9305533,"about_ca_system_score_codex":0.00003574556,"about_ca_system_score_gemma":0.00006205454,"threshold_uncertainty_score":0.6136531},"labels":[],"label_agreement":null},{"id":"W4389395619","doi":"10.1007/s10458-023-09607-8","title":"Uniformly constrained reinforcement learning","year":2023,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"Exploratory Research for Advanced Technology","keywords":"Reinforcement learning; Markov decision process; Mathematical optimization; Operator (biology); Counterexample; Probabilistic logic; Context (archaeology); Computer science; Heuristic; Constraint (computer-aided design); Monotonic function; Markov process; Mathematics; Artificial intelligence","score_opus":0.04139100013431038,"score_gpt":0.2750660092176482,"score_spread":0.2336750090833378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389395619","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":[0.015674375,0.00010920692,0.97427344,0.00025668944,0.0018581221,0.0009206998,0.000002094269,0.0012979449,0.0056074355],"genre_scores_gemma":[0.96231294,0.00015136905,0.0019914228,0.0001536921,0.000069280635,0.000061981424,0.000041164483,0.000029116605,0.035189047],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757385,0.000114213595,0.0006312952,0.00054372643,0.0004529827,0.0006839052],"domain_scores_gemma":[0.99874604,0.000089537425,0.00030103337,0.0005279179,0.0000851294,0.0002503404],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00074255466,0.00030240935,0.0003325786,0.0002737012,0.0004747839,0.00050435634,0.0006014588,0.00011317356,0.000020900048],"category_scores_gemma":[0.00006675496,0.00027725744,0.000086998414,0.00045127945,0.00007357893,0.0004049147,0.000494472,0.00024553793,0.0006371072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002131181,0.000018612991,0.0027192184,0.00009860898,0.00009120273,0.00007282429,0.0019423934,0.9805279,0.0002079779,0.009686578,0.0016769199,0.0029556423],"study_design_scores_gemma":[0.00086010736,0.00012705283,0.0031269474,0.000067068824,0.0000130056715,0.000026528745,0.0004760858,0.93540925,0.000035951103,0.000004595324,0.05953708,0.00031630645],"about_ca_topic_score_codex":0.00020153598,"about_ca_topic_score_gemma":0.0000021967378,"teacher_disagreement_score":0.972282,"about_ca_system_score_codex":0.00012330066,"about_ca_system_score_gemma":0.00009985054,"threshold_uncertainty_score":0.99996793},"labels":[],"label_agreement":null},{"id":"W4389482477","doi":"10.54254/2753-8818/19/20230542","title":"An evaluation of reinforcement learning performance in the iterated prisoner’s dilemma","year":2023,"lang":"en","type":"article","venue":"Theoretical and Natural Science","topic":"Reinforcement Learning in Robotics","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":"University of Cambridge","keywords":"Reinforcement learning; Dilemma; Iterated function; Prisoner's dilemma; Reinforcement; Computer science; Artificial neural network; Artificial intelligence; Psychology; Social psychology; Mathematics","score_opus":0.01822272713279608,"score_gpt":0.29486063010059416,"score_spread":0.27663790296779805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389482477","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":[0.98297894,0.000018900257,0.014621918,0.00040439572,0.00010633175,0.00020020794,4.8681876e-8,0.00005431203,0.0016149328],"genre_scores_gemma":[0.9994277,0.000021412232,0.00043177852,0.00007236525,0.000012080971,0.000007727088,0.0000022926674,0.0000020216664,0.000022633098],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99791336,0.00019565021,0.00020509289,0.0002423571,0.00114636,0.00029718567],"domain_scores_gemma":[0.9992829,0.00014683987,0.0000668538,0.00026838755,0.00018544601,0.000049588707],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058752294,0.000080326994,0.00008648589,0.00015803296,0.00022403983,0.00015799119,0.000916195,0.000025812582,0.000013692816],"category_scores_gemma":[0.000408822,0.00004772685,0.000013721275,0.0018430881,0.0007572473,0.000718865,0.0001971275,0.0002316549,0.000010659978],"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":[0.0000080783975,0.0000073290194,0.0019777361,0.000007717783,0.0000010431916,9.1092437e-7,0.0018719329,0.4512439,0.0024823502,0.52585465,0.000002632169,0.01654175],"study_design_scores_gemma":[0.00017349378,0.00018702961,0.048968233,0.000022336266,0.0000032650269,0.000003469582,0.00007608065,0.9470074,0.0013694207,0.002086489,0.00003137153,0.000071408715],"about_ca_topic_score_codex":0.000004817482,"about_ca_topic_score_gemma":3.1984854e-7,"teacher_disagreement_score":0.5237681,"about_ca_system_score_codex":0.000031924345,"about_ca_system_score_gemma":0.000086801425,"threshold_uncertainty_score":0.27901092},"labels":[],"label_agreement":null},{"id":"W4389551935","doi":"10.3390/su152416741","title":"Harnessing Online Knowledge Transfer for Enhanced Search and Rescue Decisions via Multi-Agent Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Sustainability","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Benchmark (surveying); Transformative learning; Process (computing); Artificial intelligence; Internet of Things; Machine learning; Computer security","score_opus":0.05112242449648516,"score_gpt":0.35154827041862424,"score_spread":0.30042584592213906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389551935","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":[0.18736838,0.00004409457,0.8102975,0.0006984736,0.00018578349,0.0010025967,0.0000012003223,0.00036451133,0.000037493624],"genre_scores_gemma":[0.97906166,0.00004240898,0.016276341,0.00004321732,0.00005129068,0.00010647799,0.00003504809,0.000026469135,0.004357061],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99727803,0.00023956544,0.0005369823,0.000737682,0.00038363683,0.00082408334],"domain_scores_gemma":[0.9973239,0.00072272256,0.00003161901,0.00072031363,0.0009867966,0.00021465677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019000317,0.0002485411,0.00029885973,0.0002776781,0.0007208951,0.00022550568,0.0006194186,0.000119641016,0.00000942725],"category_scores_gemma":[0.0023283698,0.00023703874,0.0001314668,0.00091273425,0.0001570376,0.00042818053,0.0006099474,0.0004080176,0.000018733037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031897045,0.00007067675,0.00041846433,0.0002385061,0.000020010415,0.000006500335,0.004810723,0.93288046,0.0007493428,0.0019113178,0.0000210628,0.058841053],"study_design_scores_gemma":[0.0009989963,0.00026597714,0.008180598,0.000047779497,0.000011639712,0.0000019337633,0.0010688001,0.98532146,0.0015976158,0.00049653073,0.0017393609,0.0002693324],"about_ca_topic_score_codex":0.000057129564,"about_ca_topic_score_gemma":0.000039720126,"teacher_disagreement_score":0.7940211,"about_ca_system_score_codex":0.00058192125,"about_ca_system_score_gemma":0.00046342582,"threshold_uncertainty_score":0.9666159},"labels":[],"label_agreement":null},{"id":"W4389650673","doi":"10.48550/arxiv.2312.05822","title":"Toward Open-ended Embodied Tasks Solving","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Embodied cognition; Task (project management); Computer science; Robot; Human–computer interaction; Artificial intelligence; Control (management); State (computer science); Plan (archaeology); Engineering","score_opus":0.19266900952023353,"score_gpt":0.23433942826683515,"score_spread":0.04167041874660163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389650673","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":[0.002448974,0.000014369888,0.9616395,0.0002973884,0.0018555013,0.000542903,0.0000059454005,0.0009348637,0.032260522],"genre_scores_gemma":[0.9697731,0.00013037764,0.008403449,0.00017943543,0.00009359023,0.0000023528669,0.000035029527,0.000046384495,0.021336237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99703157,0.00018170197,0.00034241745,0.0015858379,0.00020284457,0.00065565226],"domain_scores_gemma":[0.99669105,0.00019649358,0.00044956987,0.0022325434,0.00019353844,0.00023679253],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0005252946,0.0004452148,0.00050992845,0.00039295066,0.0002892461,0.0008924401,0.0078120995,0.00038412955,0.000050822222],"category_scores_gemma":[0.00014433924,0.0005438408,0.00023981066,0.00081848097,0.00010729424,0.0007768567,0.017281452,0.0010780816,0.0009281358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009469233,0.000020540823,0.000544984,0.00006793738,0.000102404425,0.00044744706,0.00034001816,0.8300888,0.000010584582,0.1662102,0.0020440896,0.000113545255],"study_design_scores_gemma":[0.00054036936,0.00005570442,0.0006207081,0.00016000435,0.000054415188,0.0000036057772,0.00010002897,0.97033906,0.000048752332,0.02605478,0.0013728453,0.0006497447],"about_ca_topic_score_codex":0.00030522855,"about_ca_topic_score_gemma":0.000024679666,"teacher_disagreement_score":0.9673242,"about_ca_system_score_codex":0.0003616072,"about_ca_system_score_gemma":0.00040056524,"threshold_uncertainty_score":0.99984974},"labels":[],"label_agreement":null},{"id":"W4389665442","doi":"10.1109/iros55552.2023.10342281","title":"Asynchronous, Option-Based Multi-Agent Policy Gradient: A Conditional Reasoning Approach","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada); Simon Fraser University","funders":"","keywords":"Asynchronous communication; Computer science; Action (physics); State (computer science); Artificial intelligence; Machine learning; Algorithm","score_opus":0.03117581096845054,"score_gpt":0.28274496944238203,"score_spread":0.25156915847393146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389665442","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":[0.0007558363,0.000007329154,0.99116963,0.000735798,0.0001679711,0.00021122937,0.000002623507,0.00093232153,0.0060172793],"genre_scores_gemma":[0.5901712,0.000004894121,0.40618184,0.0006326204,0.000113223105,0.00005515968,0.00016010026,0.000017150129,0.0026637998],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99835646,0.000064389926,0.0002492693,0.00040750238,0.00046250387,0.0004598761],"domain_scores_gemma":[0.99907774,0.000105431776,0.00009758392,0.0004943217,0.00007797981,0.00014692478],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033654182,0.00016359586,0.00013600718,0.00038700653,0.00027164948,0.00021314842,0.0006837245,0.00006239525,0.000039715505],"category_scores_gemma":[0.0001464908,0.00015578872,0.00009117073,0.0010982115,0.0000623173,0.00027992568,0.00021178312,0.00015492103,0.0007990986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.5249513e-7,0.000029905279,0.0005123624,0.000011484411,0.000012249325,0.000005414562,0.0001531459,0.7261214,0.000037668065,0.27204055,0.00069363945,0.00038127368],"study_design_scores_gemma":[0.0005047382,0.000046432728,0.00653971,0.000013186963,0.000003304298,0.0000069723696,0.000033681237,0.99078995,0.0001226664,0.00029851575,0.0014529969,0.00018781838],"about_ca_topic_score_codex":0.00006523596,"about_ca_topic_score_gemma":0.000001327431,"teacher_disagreement_score":0.5894154,"about_ca_system_score_codex":0.00018144606,"about_ca_system_score_gemma":0.0002531043,"threshold_uncertainty_score":0.9999789},"labels":[],"label_agreement":null},{"id":"W4389665609","doi":"10.1109/iros55552.2023.10341979","title":"Discovering Adaptable Symbolic Algorithms from Scratch","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McMaster University","funders":"","keywords":"Computer science; Scratch; Task (project management); Modular design; Robot; Swift; Artificial neural network; Control (management); Artificial intelligence; Inference; Algorithm; Programming language; Engineering","score_opus":0.025361716209531874,"score_gpt":0.2546971839649778,"score_spread":0.22933546775544594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389665609","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":[0.007630117,0.000015810996,0.97422135,0.00077417056,0.00059925433,0.000076519456,0.0000010734227,0.0009285289,0.015753193],"genre_scores_gemma":[0.698522,0.00008705466,0.23351689,0.0012611107,0.0003707528,0.00002850469,0.000034955225,0.000045183635,0.066133566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879754,0.000021509917,0.00017357885,0.00031029916,0.0003371108,0.00035997253],"domain_scores_gemma":[0.999172,0.000098438904,0.000042129825,0.00058236124,0.000025671847,0.00007945418],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00015470301,0.00011283337,0.00012383005,0.00009117099,0.0001194439,0.00032310365,0.00083089643,0.00004075256,0.00009473386],"category_scores_gemma":[0.00003337388,0.00010105062,0.00004437521,0.0007046573,0.000018014229,0.0006213255,0.0005920838,0.00011649446,0.0019993244],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.6906573e-7,0.000007853979,0.0016795123,0.0000049165524,0.000027564241,0.00002643821,0.00072914356,0.952851,0.0008192683,0.02518501,0.011181933,0.007486493],"study_design_scores_gemma":[0.00012804869,0.0000207359,0.002648326,0.000012346336,0.0000023449695,3.747111e-7,0.00008261792,0.98927486,0.0010801418,0.002216882,0.00438286,0.00015043562],"about_ca_topic_score_codex":0.00048003322,"about_ca_topic_score_gemma":0.000007522142,"teacher_disagreement_score":0.7407044,"about_ca_system_score_codex":0.000030510582,"about_ca_system_score_gemma":0.000039674884,"threshold_uncertainty_score":0.99877775},"labels":[],"label_agreement":null},{"id":"W4389667406","doi":"10.1109/iros55552.2023.10342408","title":"Dynamic Decision Frequency with Continuous Options","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada); University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hyperparameter; Computer science; Reinforcement learning; Abstraction; Duration (music); Task (project management); Control (management); Action (physics); Variable (mathematics); Artificial intelligence; Mathematics; Engineering","score_opus":0.010684387379290488,"score_gpt":0.2540970301951204,"score_spread":0.24341264281582994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389667406","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":[0.009984938,0.0000106261095,0.9769101,0.00045694681,0.00019311465,0.00010342447,2.3769518e-7,0.00081605447,0.011524569],"genre_scores_gemma":[0.49403194,0.00003467214,0.49562314,0.00015003777,0.000009240625,0.000011408935,0.0000057653415,0.000011274237,0.010122534],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909014,0.00001607174,0.0001527337,0.00022230268,0.00028664904,0.0002320938],"domain_scores_gemma":[0.999218,0.00012112873,0.000045614725,0.00049392565,0.00006359854,0.000057760906],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00017501564,0.00008323101,0.00008909691,0.00014035057,0.00011323211,0.00014845117,0.00057141087,0.00003138984,0.000051546685],"category_scores_gemma":[0.000047453956,0.00006167525,0.000026081452,0.000786954,0.000027232121,0.00030436265,0.00016185675,0.00009046515,0.0013471424],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024384717,0.000012456119,0.0025210178,0.000004865369,0.000017094495,0.00006001864,0.00021345622,0.8347567,0.00035071702,0.1437329,0.0021463905,0.016181987],"study_design_scores_gemma":[0.00021944566,0.0001348197,0.008464767,0.000027000797,0.0000028530635,0.000015214791,0.000032653767,0.98736584,0.00002940472,0.0025963301,0.0009777251,0.00013395234],"about_ca_topic_score_codex":0.000013945327,"about_ca_topic_score_gemma":0.000012967042,"teacher_disagreement_score":0.484047,"about_ca_system_score_codex":0.000030981093,"about_ca_system_score_gemma":0.000041798423,"threshold_uncertainty_score":0.9994304},"labels":[],"label_agreement":null},{"id":"W4390489156","doi":"10.1109/ssci52147.2023.10371909","title":"Hierarchical Reinforcement Learning for Non-Stationary Environments","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University; Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Process (computing); Temporal difference learning; Action (physics); Differential game; Term (time); Artificial intelligence; Mathematical optimization; Mathematics","score_opus":0.02224100655619201,"score_gpt":0.2667573711172034,"score_spread":0.24451636456101136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390489156","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":[0.0007232288,0.0000016333578,0.9895923,0.00081499777,0.00022792387,0.00031989365,1.560502e-7,0.00030902412,0.008010803],"genre_scores_gemma":[0.78163034,0.000040087303,0.09370934,0.0006912585,0.000103529055,0.00016401435,0.00011703569,0.000028606957,0.12351578],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986373,0.000026070114,0.0002565327,0.00030022845,0.00039560502,0.00038426576],"domain_scores_gemma":[0.9992494,0.00025793436,0.00007375539,0.00031154772,0.000016895021,0.000090497015],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00033691243,0.00012000994,0.000107484506,0.00015142941,0.00024236513,0.000092484195,0.00052825577,0.000048202695,0.000054654203],"category_scores_gemma":[0.00008943519,0.00011442979,0.00006782429,0.0003036234,0.00003150682,0.00031353268,0.00034513042,0.00015127475,0.0008292332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040252175,0.0000054596803,0.0003525137,0.0000101398255,0.0000145298045,0.0000033550507,0.00028465228,0.970359,0.00040921933,0.021286847,0.0033503058,0.0039199465],"study_design_scores_gemma":[0.00036558637,0.00017658972,0.0022152346,0.000007083129,0.0000026519976,0.0000012656145,0.000032564796,0.9449158,0.0004151643,0.00053644873,0.051191904,0.00013972672],"about_ca_topic_score_codex":0.0000022289446,"about_ca_topic_score_gemma":1.12835004e-7,"teacher_disagreement_score":0.895883,"about_ca_system_score_codex":0.000052379197,"about_ca_system_score_gemma":0.000034110846,"threshold_uncertainty_score":0.99994874},"labels":[],"label_agreement":null},{"id":"W4390708456","doi":"10.1007/978-3-031-23161-2_18","title":"StarCraft Bots and Competitions","year":2024,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Computer science","score_opus":0.008624342207372153,"score_gpt":0.21474381820000343,"score_spread":0.20611947599263128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390708456","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00009166666,0.0067050373,0.5573963,0.0009266167,0.001415885,0.00032963327,0.000029985527,0.00023567828,0.43286923],"genre_scores_gemma":[0.010575516,0.1289442,0.15853256,0.0014990945,0.0016637022,0.000028721008,0.00013025117,0.00026479427,0.69836116],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983361,0.000015395965,0.00046437696,0.00056601287,0.00038700126,0.00023116167],"domain_scores_gemma":[0.9987927,0.00022205646,0.00020262932,0.00052393024,0.00011287661,0.00014579532],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00016657631,0.00037464403,0.00046958585,0.00045116362,0.00009251113,0.00022182471,0.00047964006,0.00022253796,0.000019070343],"category_scores_gemma":[0.0000053719837,0.00035515963,0.0001330362,0.00009185656,0.00031689613,0.00018339923,0.0008107791,0.0005238231,0.000014259326],"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":[0.000001189437,0.0000061189253,0.00008375365,0.00022018526,0.00010378799,0.000027231868,0.00035887767,0.00039557018,3.043882e-7,0.9905342,0.0024133797,0.005855395],"study_design_scores_gemma":[0.00019736611,0.00028817297,0.00058621174,0.0006292528,0.00008067647,0.000040861367,0.0000033191156,0.078765064,0.0000010892179,0.15689899,0.76199603,0.00051294296],"about_ca_topic_score_codex":0.000007623481,"about_ca_topic_score_gemma":0.0000051960055,"teacher_disagreement_score":0.8336352,"about_ca_system_score_codex":0.000009871227,"about_ca_system_score_gemma":0.00006143681,"threshold_uncertainty_score":0.99989},"labels":[],"label_agreement":null},{"id":"W4390709078","doi":"10.1007/978-3-031-23161-2_524","title":"Trustworthy Embodied Virtual Agents","year":2024,"lang":"en","type":"book-chapter","venue":"Encyclopedia of Computer Graphics and Games","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Embodied cognition; Trustworthiness; Computer science; Embodied agent; Human–computer interaction; Internet privacy; Artificial intelligence","score_opus":0.012367909730939588,"score_gpt":0.22788966891602597,"score_spread":0.21552175918508637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390709078","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000047971826,0.0018296649,0.34377986,0.00022872175,0.002760661,0.00028234796,0.000012726233,0.00022849115,0.65082955],"genre_scores_gemma":[0.0059851683,0.028185824,0.023591977,0.0009589986,0.0014661255,0.000015964026,0.000074782,0.00018832908,0.9395328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99752474,0.000021171121,0.0006918216,0.00076134823,0.0006648034,0.0003361423],"domain_scores_gemma":[0.998328,0.00018753755,0.0003643937,0.000810148,0.00013514471,0.00017479055],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024486278,0.0005369665,0.00066240015,0.00058650546,0.00008464149,0.00023365837,0.0010175176,0.00036090534,0.000049053768],"category_scores_gemma":[0.000008391982,0.0005027326,0.0003008374,0.00013492533,0.00023737187,0.00021434082,0.0010359467,0.00069914054,0.00007661011],"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":[0.0000031411173,0.000008982362,0.000059547434,0.00012686694,0.00019914749,0.000055940804,0.0004101511,0.0021988824,8.453455e-8,0.9664025,0.010136327,0.020398483],"study_design_scores_gemma":[0.00023541416,0.0003853677,0.0001902272,0.00042795757,0.00009015622,0.000018890869,0.0000025055183,0.13790506,0.0000010603854,0.07097058,0.7891835,0.00058925664],"about_ca_topic_score_codex":0.0000051775933,"about_ca_topic_score_gemma":0.0000025230659,"teacher_disagreement_score":0.8954319,"about_ca_system_score_codex":0.000017839857,"about_ca_system_score_gemma":0.00008798605,"threshold_uncertainty_score":0.99974245},"labels":[],"label_agreement":null},{"id":"W4390722476","doi":"10.48550/arxiv.2401.03529","title":"Quantifying stability of non-power-seeking in artificial agents","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Shutdown; Computer science; Metric (unit); Stability (learning theory); Core (optical fiber); Shut down; Power (physics); Mathematical optimization; Economics; Engineering; Mathematics; Operations management; Machine learning","score_opus":0.1637298112787587,"score_gpt":0.24617750634206914,"score_spread":0.08244769506331043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390722476","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":[0.4696531,0.000013827907,0.527483,0.000020743277,0.0008060845,0.00019413253,0.0000025914871,0.000086694556,0.001739847],"genre_scores_gemma":[0.9980719,0.000021099619,0.0017131576,0.000016622114,0.000025455249,5.546926e-7,0.000005020796,0.000018400053,0.00012776056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977836,0.00014136908,0.00045953607,0.0010488239,0.00018154754,0.00038514065],"domain_scores_gemma":[0.9980652,0.00013908387,0.0003279748,0.0012625481,0.000115980954,0.00008926551],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006720972,0.0002862285,0.0004124135,0.0004914309,0.000064361135,0.00013649296,0.0017166182,0.00026512277,0.000041629373],"category_scores_gemma":[0.000085332664,0.0003506594,0.00021945809,0.00096517,0.00010987327,0.00022371428,0.004180653,0.0010081643,0.000086635584],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001360562,0.00005043391,0.0209698,0.0003161082,0.000040383708,0.00020058955,0.0010125283,0.9428027,0.00033081474,0.03408356,0.0000216762,0.00015774847],"study_design_scores_gemma":[0.00013766147,0.000042920696,0.0047955196,0.0003464942,0.000026935362,7.0938887e-7,0.00014153813,0.9870346,0.0006443466,0.006496675,0.000029642288,0.00030293746],"about_ca_topic_score_codex":0.00020881993,"about_ca_topic_score_gemma":0.00006791888,"teacher_disagreement_score":0.52841884,"about_ca_system_score_codex":0.00032879884,"about_ca_system_score_gemma":0.0002721719,"threshold_uncertainty_score":0.99989456},"labels":[],"label_agreement":null},{"id":"W4391021135","doi":"10.1109/cdc49753.2023.10383590","title":"Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"National Science Foundation","keywords":"Bounding overwatch; Norm (philosophy); Function (biology); Computer science; Algorithm; Discrete mathematics; Combinatorics; Mathematics; Artificial intelligence; Philosophy","score_opus":0.026072486934639563,"score_gpt":0.2568377678037991,"score_spread":0.2307652808691595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391021135","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":[0.015147999,0.0000014989976,0.94289285,0.00064616004,0.000101350204,0.00032731838,3.4616912e-7,0.00049634365,0.04038613],"genre_scores_gemma":[0.8284571,0.0000120584455,0.15814552,0.00055579294,0.000029414934,0.000071036404,0.000028892928,0.000026311043,0.01267384],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852645,0.000035051937,0.00023925793,0.00036683833,0.00045759784,0.00037481912],"domain_scores_gemma":[0.99914527,0.00008111032,0.000078540215,0.0005638045,0.00006182838,0.00006945916],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003300397,0.00016131264,0.00014544903,0.00031303955,0.00012701677,0.00031653082,0.0006034238,0.00006849067,0.000014818358],"category_scores_gemma":[0.000020272979,0.00012809382,0.000028588616,0.0009775144,0.000041015686,0.0004297538,0.00016351798,0.0002089187,0.00044450982],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008803408,0.000019749094,0.00043471777,0.00001144855,0.000005350366,0.000005624247,0.00042343512,0.8351998,0.000028193559,0.16082451,0.00043505407,0.0026033646],"study_design_scores_gemma":[0.00050230365,0.00016793431,0.0006111042,0.000030407462,0.000002192239,0.0000029765004,0.000049742346,0.9959995,0.00017987132,0.0017087733,0.0005581803,0.00018699453],"about_ca_topic_score_codex":0.000043679316,"about_ca_topic_score_gemma":0.00006432424,"teacher_disagreement_score":0.81330913,"about_ca_system_score_codex":0.00015674168,"about_ca_system_score_gemma":0.0001114827,"threshold_uncertainty_score":0.5713423},"labels":[],"label_agreement":null},{"id":"W4391021298","doi":"10.1109/cdc49753.2023.10383636","title":"Asymmetric Actor-Critic with Approximate Information State","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Representation (politics); Markov decision process; Partially observable Markov decision process; State (computer science); Artificial intelligence; Observable; Complete information; Mathematical optimization; Markov chain; Theoretical computer science; Machine learning; Markov process; Algorithm; Mathematical economics; Markov model; Mathematics","score_opus":0.011392651288327471,"score_gpt":0.22457048515747524,"score_spread":0.21317783386914776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391021298","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":[0.002074535,0.0000022303318,0.9729562,0.00032171168,0.0001421373,0.00014193357,4.4944662e-7,0.0009270727,0.023433771],"genre_scores_gemma":[0.9163602,0.00003145115,0.07760529,0.00070955156,0.000021106463,0.000025176696,0.000027552405,0.000014075502,0.0052056173],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893594,0.000020011608,0.00019230282,0.00012743843,0.00041410569,0.000310221],"domain_scores_gemma":[0.9993137,0.00008377449,0.00006845812,0.00037140748,0.00009354133,0.000069114554],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002451022,0.000099530596,0.00008847409,0.0004374763,0.00008871476,0.00036908963,0.00049263804,0.00002383702,0.000011437568],"category_scores_gemma":[0.00006766589,0.00007541777,0.000020417401,0.0021189046,0.000021304022,0.0019640154,0.00018602614,0.00010073035,0.0013287731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000717828,0.000011391606,0.0017691691,0.00009645347,0.000033063552,0.0000150335045,0.0013527543,0.876563,0.000028730674,0.059536293,0.006095842,0.054491084],"study_design_scores_gemma":[0.00026071645,0.00010957202,0.004341302,0.00001066343,0.0000023288678,0.0000057096786,0.000045581874,0.9874638,0.00040991706,0.00031285518,0.006884916,0.00015269153],"about_ca_topic_score_codex":0.00001312102,"about_ca_topic_score_gemma":7.21118e-7,"teacher_disagreement_score":0.91428566,"about_ca_system_score_codex":0.00003443486,"about_ca_system_score_gemma":0.00004562846,"threshold_uncertainty_score":0.99944884},"labels":[],"label_agreement":null},{"id":"W4391093351","doi":"10.1109/bigdata59044.2023.10386490","title":"GPT-in-the-Loop: Supporting Adaptation in Multiagent Systems","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Adaptation (eye); Computer science; Loop (graph theory); Distributed computing; Neuroscience; Mathematics; Biology","score_opus":0.051188804408088005,"score_gpt":0.29544630193895277,"score_spread":0.24425749753086476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391093351","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":[0.03243621,0.000011831517,0.9608605,0.000705797,0.00045770942,0.0003318139,9.040608e-8,0.00022422246,0.004971839],"genre_scores_gemma":[0.993718,0.0000061338233,0.00369681,0.00013121995,0.000022626486,0.000026634461,0.0000041596545,0.000005219923,0.0023891805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987181,0.0001055254,0.00034761126,0.00019633916,0.00033693004,0.00029552248],"domain_scores_gemma":[0.9993492,0.00020175232,0.00008967058,0.00031277977,0.000022985923,0.000023624129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012673612,0.000073602525,0.00008846403,0.00020066701,0.000045083594,0.00016860089,0.00056949304,0.000032160548,0.000005476654],"category_scores_gemma":[0.00011739824,0.000057037578,0.000022391087,0.0009203041,0.000008960512,0.00025754177,0.00011235142,0.000122617,0.0003181505],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[3.7018685e-7,0.000006334235,0.0030587625,0.000013248191,0.0000013794045,0.00004241185,0.003041038,0.98129237,0.000041133397,0.010598496,0.0005082113,0.0013962329],"study_design_scores_gemma":[0.00016275451,0.000021707356,0.0068387655,0.000021997295,6.372909e-7,0.0000032496205,0.0015090121,0.9906808,0.0000340043,0.000033553795,0.00062109565,0.00007239714],"about_ca_topic_score_codex":0.00029038056,"about_ca_topic_score_gemma":0.000055872464,"teacher_disagreement_score":0.9612818,"about_ca_system_score_codex":0.000046358033,"about_ca_system_score_gemma":0.000031485986,"threshold_uncertainty_score":0.40892872},"labels":[],"label_agreement":null},{"id":"W4391157052","doi":"","title":"Using Confounded Data in Latent Model-Based Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","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":"Ubisoft (Canada); Montfort Hospital; Minnow Environmental (Canada)","funders":"Canada First Research Excellence Fund; Canada Excellence Research Chairs, Government of Canada","keywords":"Reinforcement learning; Computer science; Reinforcement; Latent inhibition; Artificial intelligence; Cognitive psychology; Machine learning; Psychology; Statistics; Social psychology; Mathematics","score_opus":0.06579403889571468,"score_gpt":0.28468535235101183,"score_spread":0.21889131345529717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391157052","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":[0.012310685,0.0000347036,0.9752958,0.002671332,0.00010717382,0.000252816,0.0000017026853,0.00046931292,0.008856501],"genre_scores_gemma":[0.8784171,0.00005263145,0.11613174,0.00012868691,0.0000066530856,0.000012447967,0.00024822785,0.000025706002,0.0049768444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960001,0.0016793252,0.00052971113,0.0006724807,0.00061083207,0.00050751265],"domain_scores_gemma":[0.995411,0.0008303006,0.00029922547,0.002753653,0.000572909,0.00013291094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00632547,0.00021060914,0.00022453364,0.0003612063,0.0003482745,0.00046570878,0.0026998934,0.00009846928,0.000027859525],"category_scores_gemma":[0.0012981493,0.00023471397,0.00006276241,0.0012871677,0.00010542583,0.0006019183,0.0018401442,0.0003962555,0.000097350814],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002733753,0.000037413974,0.0019895888,0.00002448442,0.000010651081,0.000006381752,0.0016720813,0.9525897,0.000991044,0.03996837,0.00009593351,0.002611628],"study_design_scores_gemma":[0.0005704779,5.03907e-7,0.00062970154,0.000313151,0.0000066847497,0.0000021071462,0.000032547512,0.99359196,0.0027129822,0.0003570626,0.0015444743,0.00023832613],"about_ca_topic_score_codex":0.00041329287,"about_ca_topic_score_gemma":0.0001575918,"teacher_disagreement_score":0.8661064,"about_ca_system_score_codex":0.00017079858,"about_ca_system_score_gemma":0.00034991882,"threshold_uncertainty_score":0.9571358},"labels":[],"label_agreement":null},{"id":"W4391237386","doi":"10.1109/cvci59596.2023.10397147","title":"Continual Reinforcement Learning for Autonomous Driving with Application on Velocity Control under Various Environment","year":2023,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Intelligent Mechatronic Systems (Canada); University of Waterloo","funders":"","keywords":"Reinforcement learning; Adaptability; Computer science; Forgetting; Task (project management); Artificial intelligence; Control engineering; Engineering","score_opus":0.01069531595903084,"score_gpt":0.22723260846090212,"score_spread":0.2165372925018713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391237386","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":[0.0018405155,0.0000019659165,0.99239886,0.00090947613,0.00008448843,0.00094954943,2.402078e-7,0.00066903915,0.0031458423],"genre_scores_gemma":[0.973882,0.0000053170343,0.016161455,0.00051527785,0.000048435246,0.00027595664,0.000023064526,0.00002472269,0.009063726],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998238,0.000044882298,0.0003095101,0.00048435933,0.00044770155,0.00047552199],"domain_scores_gemma":[0.99880165,0.00035501976,0.00020485805,0.00049527816,0.0000457385,0.00009743888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051097013,0.00020708692,0.00020486482,0.00012593721,0.00032836557,0.00016473823,0.00048267347,0.000070954295,0.000021238158],"category_scores_gemma":[0.000039402836,0.00017704062,0.00005983565,0.00021438608,0.000044235436,0.0002086776,0.000145079,0.00020226081,0.00032202378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016721842,0.0000134875245,0.0004917196,0.000007778415,0.000042225347,0.000001549497,0.0002153282,0.9514227,0.00019069285,0.041940812,0.00021681462,0.0054402],"study_design_scores_gemma":[0.0012545345,0.0006685466,0.003518289,0.000013061075,0.000014092818,0.0000021536953,0.00006150073,0.9815721,0.00029778492,0.00017254439,0.012182335,0.000243066],"about_ca_topic_score_codex":0.000017564334,"about_ca_topic_score_gemma":0.000002703476,"teacher_disagreement_score":0.9762374,"about_ca_system_score_codex":0.00021942711,"about_ca_system_score_gemma":0.000058291058,"threshold_uncertainty_score":0.7219507},"labels":[],"label_agreement":null},{"id":"W4391494285","doi":"10.1007/s13042-023-02063-6","title":"Expected Lenient Q-learning: a fast variant of the Lenient Q-learning algorithm for cooperative stochastic Markov games","year":2024,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Reinforcement Learning in Robotics","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":"Université du Québec à Rimouski","funders":"Centre National pour la Recherche Scientifique et Technique","keywords":"Algorithm; Convergence (economics); Reinforcement learning; Markov chain; Computer science; Q-learning; Rate of convergence; Artificial intelligence; Markov decision process; Mathematics; Markov process; Machine learning; Key (lock)","score_opus":0.007476805942429175,"score_gpt":0.25780049233344815,"score_spread":0.250323686391019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391494285","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":[0.010013301,0.0014664397,0.98508674,0.001273839,0.0016053468,0.00017395972,0.0000052229284,0.00006320367,0.00031193704],"genre_scores_gemma":[0.969007,0.00027728884,0.026317218,0.00005901456,0.00031443321,0.0000074254203,0.000009309568,0.000035284207,0.003972988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973768,0.00032931427,0.00075377134,0.00030466917,0.00096140866,0.0002740317],"domain_scores_gemma":[0.99742615,0.0008045321,0.0006740268,0.0001411209,0.00084584416,0.00010831647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00085655873,0.00025003633,0.0003251078,0.00030445127,0.00019923506,0.00045454613,0.00092061324,0.00008797869,0.00003550599],"category_scores_gemma":[0.0009930161,0.0001813006,0.00023245928,0.00028678373,0.00012802711,0.00025232977,0.00042917565,0.001253746,0.0000038334197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005177798,0.00006199234,0.000847643,0.00003242887,0.00045986447,0.000053148044,0.0050735604,0.8793574,0.00051656365,0.0045626354,0.00017438222,0.10880862],"study_design_scores_gemma":[0.00081562705,0.0008114401,0.00058770296,0.00045783937,0.00006953004,0.00048127427,0.00044606003,0.9793282,0.00026175482,0.00015417373,0.016392022,0.00019434035],"about_ca_topic_score_codex":0.000021296482,"about_ca_topic_score_gemma":0.000001770802,"teacher_disagreement_score":0.95899373,"about_ca_system_score_codex":0.00011480334,"about_ca_system_score_gemma":0.00019013669,"threshold_uncertainty_score":0.73932236},"labels":[],"label_agreement":null},{"id":"W4392123244","doi":"10.1007/978-3-031-52554-4_1","title":"Reinforcement Learning Background","year":2024,"lang":"en","type":"book-chapter","venue":"SpringerBriefs in computer science","topic":"Reinforcement Learning in Robotics","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":"McMaster University; Memorial University of Newfoundland","funders":"","keywords":"Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; Social psychology","score_opus":0.026025942293179557,"score_gpt":0.25863785593703387,"score_spread":0.2326119136438543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392123244","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000012861423,0.00020280453,0.65724003,0.00019578304,0.0029467451,0.00028132388,2.268841e-7,0.0004595176,0.33866072],"genre_scores_gemma":[0.058744602,0.00047741312,0.14959665,0.0009858321,0.0013443371,0.0000342999,0.000010788424,0.00021323287,0.7885929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936343,0.000022879487,0.0010316644,0.0020823057,0.00207535,0.0011534999],"domain_scores_gemma":[0.99694616,0.00017210285,0.0004066377,0.0019266953,0.0002391075,0.0003092773],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018699872,0.00074859796,0.00062882795,0.0014923777,0.00037046723,0.0020693915,0.005044467,0.0003035032,0.00014706208],"category_scores_gemma":[0.00003774422,0.00078196375,0.00022845178,0.00080658135,0.00073867495,0.0013229096,0.005372089,0.0020025945,0.001819593],"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":[0.0000013220381,0.0000038621315,0.000010168164,0.0000665575,0.0000153247,0.00014469132,0.00023481683,0.47076005,0.000014120976,0.5169913,0.00009506342,0.011662712],"study_design_scores_gemma":[0.00018858523,0.00022119984,0.000043838972,0.0007795667,0.0000120854165,0.000049281,0.0000020770576,0.8716282,0.00007110373,0.011770313,0.11436597,0.0008677229],"about_ca_topic_score_codex":0.000023589733,"about_ca_topic_score_gemma":0.0000055340847,"teacher_disagreement_score":0.5076434,"about_ca_system_score_codex":0.0010011091,"about_ca_system_score_gemma":0.00070580986,"threshold_uncertainty_score":0.99946314},"labels":[],"label_agreement":null},{"id":"W4392240640","doi":"10.3390/math12050709","title":"Dimensionless Policies Based on the Buckingham π Theorem: Is This a Good Way to Generalize Numerical Results?","year":2024,"lang":"en","type":"article","venue":"Mathematics","topic":"Reinforcement Learning in Robotics","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":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Context (archaeology); Inverted pendulum; Scaling; Mathematics; Linear-quadratic regulator; Controller (irrigation); Control theory (sociology); Optimal control; Dimensionless quantity; Control (management); Mathematical optimization; Computer science; Applied mathematics; Artificial intelligence; Nonlinear system; Geometry; Physics","score_opus":0.030967814446170003,"score_gpt":0.27863134035175635,"score_spread":0.24766352590558635,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392240640","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":[0.0011124974,0.000023952205,0.94231224,0.029297909,0.00037402712,0.00031036214,0.0000066350763,0.00040289565,0.026159462],"genre_scores_gemma":[0.7435096,0.000008823019,0.2224275,0.016651189,0.00022784156,0.00006660734,0.000004988065,0.00008321948,0.017020272],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979848,0.000094718926,0.0004176725,0.0003776419,0.00073964236,0.00038549548],"domain_scores_gemma":[0.99732995,0.0011286815,0.00009216938,0.0012738466,0.00006888911,0.00010644872],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00079512317,0.0002408992,0.00022198034,0.00014753474,0.00020777513,0.00061819144,0.0011676963,0.00007342712,0.0001016896],"category_scores_gemma":[0.00032627292,0.0001447029,0.00012599895,0.0007713966,0.000056107085,0.000102915335,0.0003692062,0.00027749533,0.0010463562],"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":[0.0000063253665,0.00007232949,0.0000044443113,0.000103590784,0.000039254337,0.00002161742,0.015567122,0.12945801,0.00028344663,0.81985456,0.032585036,0.002004243],"study_design_scores_gemma":[0.00008183692,0.00013173734,0.000007863973,0.00023362276,0.000013996037,0.000007975489,0.000070605216,0.96688545,0.0021858718,0.006163333,0.02401535,0.00020234835],"about_ca_topic_score_codex":0.000027011027,"about_ca_topic_score_gemma":4.2117415e-7,"teacher_disagreement_score":0.83742744,"about_ca_system_score_codex":0.00007834911,"about_ca_system_score_gemma":0.00005564681,"threshold_uncertainty_score":0.9997314},"labels":[],"label_agreement":null},{"id":"W4392909880","doi":"10.1109/icassp48485.2024.10447501","title":"A Robust Quantile Huber Loss with Interpretable Parameter Adjustment in Distributional Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Quantile; Reinforcement learning; Computer science; Artificial intelligence; Econometrics; Robustness (evolution); Reinforcement; Mathematical optimization; Mathematics; Machine learning; Statistics; Engineering","score_opus":0.01965315354986084,"score_gpt":0.24414673776042978,"score_spread":0.22449358421056895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392909880","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":[0.0033849177,0.00013294272,0.98680717,0.00043810718,0.00033130383,0.00024411193,5.862289e-7,0.00034286117,0.008317998],"genre_scores_gemma":[0.9649628,0.000025493191,0.025860596,0.00017350113,0.00003905186,0.000054484655,0.000030142715,0.000016446651,0.008837488],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980224,0.00006143612,0.00037990583,0.0005068422,0.0005319986,0.00049743574],"domain_scores_gemma":[0.99920493,0.00020435375,0.000058667298,0.00038198612,0.000057691417,0.00009235526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035868387,0.0002221338,0.00019522202,0.00018895643,0.000078702586,0.00045498196,0.0005051593,0.0000637198,0.0003851342],"category_scores_gemma":[0.00005200717,0.00016846044,0.00006730282,0.00060685916,0.00006017849,0.0008083151,0.00034116258,0.00043993728,0.00026377823],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012460741,0.00001846899,0.002028555,0.000038200316,0.00003938969,0.000058363385,0.000303337,0.9177274,0.000018652718,0.07789334,0.0006427308,0.0012190631],"study_design_scores_gemma":[0.00027807287,0.00028475383,0.0008781701,0.00023524117,0.000009406431,0.000040981737,0.000047917973,0.98824835,0.00021648695,0.00011486482,0.009395664,0.000250104],"about_ca_topic_score_codex":0.000073294104,"about_ca_topic_score_gemma":0.000011313597,"teacher_disagreement_score":0.9615779,"about_ca_system_score_codex":0.00028054006,"about_ca_system_score_gemma":0.00013495237,"threshold_uncertainty_score":0.6869617},"labels":[],"label_agreement":null},{"id":"W4392964256","doi":"10.1007/978-3-031-56027-9_20","title":"A Streaming Approach to Neural Team Formation Training","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Windsor","funders":"","keywords":"Computer science; Training (meteorology); Artificial intelligence; Artificial neural network; Multimedia","score_opus":0.03235137083435407,"score_gpt":0.2533138865639717,"score_spread":0.22096251572961761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392964256","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":[0.00001801077,0.00011329972,0.94872576,0.00038181292,0.0016921432,0.0005015071,0.0000015622048,0.00035730423,0.04820862],"genre_scores_gemma":[0.2624526,0.000007797261,0.733911,0.001232632,0.00056813855,0.000019620167,0.000010903066,0.000057418536,0.0017399276],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99604034,0.000021028449,0.0005937121,0.001361634,0.0012032816,0.00078001205],"domain_scores_gemma":[0.9980781,0.00023427999,0.00020732409,0.0011223876,0.00014055686,0.0002173542],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008092747,0.0005280123,0.00044845798,0.0012685782,0.00028459448,0.0013958053,0.0031168028,0.0002400971,0.0000042981883],"category_scores_gemma":[0.00009241093,0.00048619343,0.00013132519,0.0009266498,0.0002226465,0.0010465947,0.0016853152,0.0010635586,0.00010848232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000010758463,0.000004557843,0.0000017879481,0.000050716964,0.000005156813,0.000013748974,0.004004006,0.740985,0.000025683463,0.021031016,0.000018465858,0.2338588],"study_design_scores_gemma":[0.00009591738,0.00014580385,0.000009657121,0.0003810976,0.000007713285,0.00010418462,0.0000015866592,0.9836223,0.00011394751,0.0129734175,0.0020218615,0.0005225018],"about_ca_topic_score_codex":0.0000071795157,"about_ca_topic_score_gemma":0.0000071626205,"teacher_disagreement_score":0.2624346,"about_ca_system_score_codex":0.0004384701,"about_ca_system_score_gemma":0.00023906484,"threshold_uncertainty_score":0.99975896},"labels":[],"label_agreement":null},{"id":"W4393121880","doi":"10.1007/978-3-031-56855-8_22","title":"Using Evolution and Deep Learning to Generate Diverse Intelligent Agents","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Brock University","funders":"","keywords":"Computer science; Artificial intelligence; Deep learning","score_opus":0.04096502972223453,"score_gpt":0.2808853062363742,"score_spread":0.23992027651413966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393121880","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":[0.0003460841,0.00058291975,0.99487394,0.00016372802,0.002433451,0.00034183692,6.748523e-7,0.00018145518,0.001075925],"genre_scores_gemma":[0.29700378,0.0001275523,0.6987929,0.0008935118,0.0006108889,0.000005632332,0.000004119226,0.00007039929,0.0024912641],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965783,0.00003416457,0.00044176137,0.0014193269,0.0009030043,0.0006234831],"domain_scores_gemma":[0.9985622,0.00014401856,0.00017974662,0.00069741055,0.00017539259,0.0002412199],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000691447,0.00046843875,0.0003614538,0.0010859456,0.00036108305,0.0010191933,0.0015907607,0.00022078615,0.000016505719],"category_scores_gemma":[0.00009483551,0.00045496243,0.00008313771,0.00070506893,0.0002967458,0.0004671195,0.0030587735,0.0009269796,0.00013782489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017190616,0.000002937641,0.00007055759,0.00003154843,0.000010770794,0.00006178516,0.001136109,0.8740519,0.000104701976,0.009258924,0.000003050243,0.11526597],"study_design_scores_gemma":[0.00006919677,0.00014088553,0.00005091328,0.00039649205,0.000014804344,0.00004940513,8.725848e-7,0.9843608,0.00020930078,0.012744849,0.0014770384,0.00048540186],"about_ca_topic_score_codex":0.000032184165,"about_ca_topic_score_gemma":0.000016919405,"teacher_disagreement_score":0.29665768,"about_ca_system_score_codex":0.0007367555,"about_ca_system_score_gemma":0.00019807776,"threshold_uncertainty_score":0.9997902},"labels":[],"label_agreement":null},{"id":"W4393146382","doi":"10.1609/aaai.v38i20.30613","title":"Reward-Respecting Subtasks for Model-Based Reinforcement Learning (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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; Canadian Institute for Advanced Research","funders":"","keywords":"Reprint; Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; Social psychology; Physics","score_opus":0.10020869692937655,"score_gpt":0.3268577768747262,"score_spread":0.22664907994534966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393146382","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":[0.008410074,0.000022274819,0.9749536,0.0024696998,0.00059869216,0.00070521433,0.0000010497572,0.000387306,0.01245209],"genre_scores_gemma":[0.9834925,0.000016049571,0.01485545,0.00014135698,0.00009187429,0.00007202678,0.0000011894005,0.000030125098,0.0012994339],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971296,0.0000131663555,0.00085311115,0.0007581372,0.00071345596,0.00053251104],"domain_scores_gemma":[0.9980313,0.00034166744,0.0004312273,0.00042830606,0.00066487514,0.0001025819],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013788257,0.00030829263,0.00028758243,0.00024175292,0.00036792862,0.000845509,0.0020163995,0.0001231203,0.00004520314],"category_scores_gemma":[0.0012638832,0.00024862651,0.0002616786,0.00065961457,0.00016878858,0.0005421879,0.00039375538,0.00067406887,0.00008157375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003265151,0.00001953699,0.000024560439,0.00012119986,0.000016506714,4.578669e-7,0.0007804049,0.5530468,0.010568021,0.41961005,0.00009035451,0.015689429],"study_design_scores_gemma":[0.000024737457,0.0001936874,0.000010342484,0.0005155158,0.000015321222,0.0000021290934,0.00018343565,0.7680879,0.20214465,0.02838434,0.00022300846,0.00021493163],"about_ca_topic_score_codex":0.000017395943,"about_ca_topic_score_gemma":0.0000012973638,"teacher_disagreement_score":0.9750824,"about_ca_system_score_codex":0.0001631186,"about_ca_system_score_gemma":0.0002966257,"threshold_uncertainty_score":0.9999966},"labels":[],"label_agreement":null},{"id":"W4393157304","doi":"10.1609/aaai.v38i20.30606","title":"Exploiting Action Impact Regularity and Exogenous State Variables for Offline Reinforcement Learning (Abstract Reprint)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Reprint; Reinforcement learning; Action (physics); Reinforcement; State action; Computer science; Cognitive psychology; Psychology; Artificial intelligence; Social psychology; Political science; Law; Physics","score_opus":0.11101470799603334,"score_gpt":0.3391604714125966,"score_spread":0.22814576341656323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393157304","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":[0.12814492,0.000045535286,0.8670768,0.00077111344,0.00044586544,0.0006760526,0.0000020406467,0.00024867698,0.002588969],"genre_scores_gemma":[0.99091643,0.00012198776,0.008133444,0.000037416587,0.00008267952,0.000038041962,0.0000017374749,0.000020915284,0.00064736203],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977749,0.000015485526,0.0007009843,0.00059311005,0.00048522462,0.0004302964],"domain_scores_gemma":[0.998433,0.0002703144,0.0004107225,0.00027051425,0.0005181191,0.00009733391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013463566,0.00026380923,0.00026430163,0.00017221319,0.00034558974,0.00084004045,0.000872215,0.000088380126,0.000034822686],"category_scores_gemma":[0.00088803447,0.00020364257,0.00014518891,0.00044521512,0.00014413947,0.00080350204,0.00039971684,0.00048650778,0.000018253315],"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":[0.00010719578,0.000044307013,0.0001907569,0.00043208865,0.00008659933,0.0000014735446,0.0030860573,0.270412,0.09082403,0.4966014,0.00006841331,0.13814567],"study_design_scores_gemma":[0.000026504733,0.0003405552,0.00017140023,0.00043912907,0.000017772596,0.0000098304145,0.00032614043,0.76778626,0.19385913,0.03661331,0.00020724474,0.00020270087],"about_ca_topic_score_codex":0.00007923522,"about_ca_topic_score_gemma":0.0000026085577,"teacher_disagreement_score":0.8627715,"about_ca_system_score_codex":0.00013084708,"about_ca_system_score_gemma":0.00015524027,"threshold_uncertainty_score":0.8304303},"labels":[],"label_agreement":null},{"id":"W4393159809","doi":"10.1609/aaai.v38i10.28970","title":"Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Transfer of learning; Cognitive psychology; Machine learning; Psychology; Social psychology","score_opus":0.06539929613530107,"score_gpt":0.3236612521517399,"score_spread":0.25826195601643887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393159809","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":[0.024541277,0.00003481639,0.96240264,0.0011881875,0.0006325775,0.0007867698,0.0000012153452,0.00018012685,0.010232413],"genre_scores_gemma":[0.9971423,0.00003334369,0.0014013584,0.00012967203,0.00006486572,0.0001098107,0.0000021331052,0.000022439086,0.0010940486],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976549,0.000019620253,0.00076532376,0.0005735266,0.00053058175,0.00045603476],"domain_scores_gemma":[0.9988731,0.0003668294,0.00015890488,0.0002333999,0.00029139395,0.00007635111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069640344,0.00027831414,0.0002901996,0.00029576427,0.00022283234,0.00042600554,0.0012016563,0.00011439674,0.000063629566],"category_scores_gemma":[0.00045246803,0.0002227545,0.00015968464,0.000540514,0.00012823257,0.0005045348,0.00012919118,0.0007423408,0.0000712853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012220567,0.0000406045,0.00003064684,0.000100204394,0.000022242006,8.264607e-7,0.0047767013,0.5293257,0.017888531,0.42750472,0.000022980415,0.020164628],"study_design_scores_gemma":[0.000051516137,0.00056579366,0.00004953535,0.000660761,0.000011599355,0.0000019976949,0.0005071908,0.75777876,0.23406027,0.005842123,0.00026358388,0.00020683721],"about_ca_topic_score_codex":0.000026652828,"about_ca_topic_score_gemma":0.000008169053,"teacher_disagreement_score":0.97260106,"about_ca_system_score_codex":0.00012465223,"about_ca_system_score_gemma":0.00009956447,"threshold_uncertainty_score":0.9083665},"labels":[],"label_agreement":null},{"id":"W4393160751","doi":"10.1609/aaai.v38i18.30062","title":"Parallel Beam Search Algorithms for Domain-Independent Dynamic Programming","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dynamic programming; Computer science; Domain (mathematical analysis); Algorithm; Parallel computing; Mathematics","score_opus":0.07861063744368464,"score_gpt":0.33554137191464556,"score_spread":0.25693073447096093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393160751","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":[0.0072239186,0.00006131601,0.9849993,0.003615754,0.00089547265,0.0010987265,0.000003539742,0.00026796915,0.0018339964],"genre_scores_gemma":[0.91630596,0.000037215214,0.08228014,0.000082908875,0.00008458549,0.0001229437,0.0000015031775,0.000028196127,0.0010565268],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972025,0.000014517549,0.0006218798,0.00070903334,0.0008409186,0.0006111523],"domain_scores_gemma":[0.9985676,0.00019043422,0.00018685279,0.00036003592,0.00058133685,0.00011376722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010333207,0.0002808928,0.00026752867,0.00021429086,0.0002806983,0.0010294868,0.0025281007,0.00012233459,0.000025386114],"category_scores_gemma":[0.00018844684,0.00021327866,0.00021881296,0.00076284807,0.00024673555,0.0005159718,0.0005437853,0.0004862803,0.00010802346],"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":[0.000032569067,0.00006471068,0.000025677466,0.00020047197,0.000043557673,0.0000015100235,0.0019733363,0.012959845,0.007158876,0.8268394,0.00007580716,0.15062426],"study_design_scores_gemma":[0.000034682434,0.00039078417,0.000027682736,0.00039821691,0.000016190159,0.00000961669,0.0006522343,0.8709118,0.054822236,0.07142713,0.0010308684,0.00027860922],"about_ca_topic_score_codex":0.000016290443,"about_ca_topic_score_gemma":0.000003235454,"teacher_disagreement_score":0.90908206,"about_ca_system_score_codex":0.00013074744,"about_ca_system_score_gemma":0.00020366063,"threshold_uncertainty_score":0.9927365},"labels":[],"label_agreement":null},{"id":"W4393226450","doi":"10.1017/jfm.2023.1096","title":"Learn to flap: foil non-parametric path planning via deep reinforcement learning","year":2024,"lang":"en","type":"article","venue":"Journal of Fluid Mechanics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"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; Path (computing); Parametric statistics; Reinforcement; FOIL method; Motion planning; Artificial intelligence; Materials science; Robot; Mathematics; Computer network","score_opus":0.015150885779447175,"score_gpt":0.2633649266548724,"score_spread":0.2482140408754252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393226450","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":[0.0016190982,0.0007614478,0.99330217,0.00031827012,0.0028362477,0.00022739773,9.364272e-8,0.000122159,0.00081309886],"genre_scores_gemma":[0.91961265,0.00013961009,0.077963956,0.0003656565,0.0004110613,0.000008368592,0.0000015729964,0.000050799372,0.0014463526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965708,0.00010919546,0.0010198129,0.0003629375,0.0012762718,0.0006609294],"domain_scores_gemma":[0.9981263,0.0002839829,0.00039796164,0.00045169593,0.0003398549,0.00040016085],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020815437,0.00030182017,0.0004313447,0.0011098306,0.00020252122,0.0006347758,0.0012679655,0.00014083434,0.000044716275],"category_scores_gemma":[0.00056487933,0.00027066763,0.00027292746,0.0017365956,0.000009760135,0.00087187265,0.00048337365,0.0010883014,0.00025891146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018834937,0.0000135005175,0.000015720141,0.000067617555,0.00009564554,0.00033358517,0.0011945342,0.9705891,0.010560733,0.0044431724,0.00093294174,0.011734637],"study_design_scores_gemma":[0.00029822093,0.0014853786,0.000014710396,0.0004308271,0.000044985096,0.00031439806,0.00011564735,0.9744751,0.0041220346,0.00041043985,0.017993245,0.0002950144],"about_ca_topic_score_codex":0.000004850924,"about_ca_topic_score_gemma":1.484394e-7,"teacher_disagreement_score":0.91799355,"about_ca_system_score_codex":0.0003781095,"about_ca_system_score_gemma":0.00026404305,"threshold_uncertainty_score":0.99997455},"labels":[],"label_agreement":null},{"id":"W4394708838","doi":"10.48550/arxiv.2404.05870","title":"CoBT: Collaborative Programming of Behaviour Trees from One Demonstration for Robot Manipulation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"European Regional Development Fund; Science Foundation Ireland; European Commission; ADAPT - Centre for Digital Content Technology; Canadian Institute of Steel Construction","keywords":"Computer science; Robot; Human–computer interaction; Artificial intelligence","score_opus":0.09148361143653079,"score_gpt":0.220424809671624,"score_spread":0.1289411982350932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394708838","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":[0.07520881,0.00006734418,0.92277557,0.00006335495,0.0004759853,0.00086513493,0.000033609413,0.00019482456,0.0003153957],"genre_scores_gemma":[0.9381042,0.000024552473,0.061092716,0.0000077292225,0.00006102121,0.000005310573,0.00016378029,0.000019200354,0.0005214858],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845576,0.00008475036,0.00032506284,0.0007694682,0.0001410004,0.00022394741],"domain_scores_gemma":[0.9983177,0.00015327311,0.00047131366,0.000616266,0.00036989537,0.00007151339],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00019971172,0.00024773146,0.0003217406,0.000244949,0.000104111474,0.0001951074,0.00078922114,0.0002718422,0.0000073935303],"category_scores_gemma":[0.000042146683,0.00030665236,0.00015899443,0.00050704187,0.00007807593,0.00026770268,0.0008352454,0.00035833553,0.000013248517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022848972,0.000047504625,0.0030786465,0.00008915569,0.00012489366,0.000013794381,0.0004640972,0.89101005,0.000147615,0.10405875,0.000022052343,0.0009205958],"study_design_scores_gemma":[0.00034795524,0.00014940026,0.0032673485,0.00025380158,0.0002464161,3.3301848e-7,0.00015346256,0.97090465,0.0009139217,0.023436688,0.000030407615,0.00029561113],"about_ca_topic_score_codex":0.00017216323,"about_ca_topic_score_gemma":0.00010602714,"teacher_disagreement_score":0.86289537,"about_ca_system_score_codex":0.0002020299,"about_ca_system_score_gemma":0.00026980706,"threshold_uncertainty_score":0.99993855},"labels":[],"label_agreement":null},{"id":"W4395703972","doi":"10.2139/ssrn.4771123","title":"Autonomous Robot Navigation in Dynamic Environments: A Temporal-Difference Learning Approach","year":2024,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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 Windsor","funders":"","keywords":"Temporal difference learning; Computer science; Robot; Artificial intelligence; Human–computer interaction; Reinforcement learning","score_opus":0.007485515225629387,"score_gpt":0.23333869961515769,"score_spread":0.2258531843895283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395703972","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":[0.020642519,0.0015837139,0.9763583,0.00040615446,0.00023879549,0.00013911157,1.16223205e-7,0.00014676736,0.00048454019],"genre_scores_gemma":[0.98571724,0.0008065456,0.0068643154,0.000024660463,0.000054662676,0.000011247786,0.000011966356,0.000025762361,0.0064835744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968431,0.00017744528,0.00042394846,0.000421868,0.00043742123,0.0016962301],"domain_scores_gemma":[0.9994544,0.000056614175,0.00014528469,0.00025393683,0.00001530735,0.00007448324],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0016034073,0.00021241912,0.00018528229,0.0002799282,0.00017809597,0.00044972348,0.0008049934,0.00009845242,0.0000055622722],"category_scores_gemma":[0.000038751037,0.00019852401,0.00008942961,0.00048542288,0.000040990955,0.000674403,0.000149631,0.0035265784,0.00008274517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000046333475,0.000037269576,0.0013445854,0.00002149938,0.000056675195,0.000026805934,0.00079582253,0.8746239,0.000843854,0.06399391,0.000002923879,0.058248136],"study_design_scores_gemma":[0.00025711875,0.00023616593,0.00096142106,0.00008734901,0.0000089810255,0.0005058367,0.00024366428,0.9793207,0.000020738396,0.017299857,0.0008294879,0.00022869688],"about_ca_topic_score_codex":0.000026906315,"about_ca_topic_score_gemma":0.000014017227,"teacher_disagreement_score":0.969494,"about_ca_system_score_codex":0.002251383,"about_ca_system_score_gemma":0.0010310481,"threshold_uncertainty_score":0.9987723},"labels":[],"label_agreement":null},{"id":"W4396515242","doi":"10.22215/etd/2024-15896","title":"A Machine Learning Approach for Aerial Drones Playing the Pursuit-Evasion Game","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","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","funders":"","keywords":"Drone; Reinforcement learning; Popularity; Computer science; Artificial intelligence; Pursuit-evasion; Machine learning; Fuzzy logic; Range (aeronautics); Engineering; Aerospace engineering; Psychology","score_opus":0.024853440727771136,"score_gpt":0.2744335396824072,"score_spread":0.24958009895463606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396515242","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":[0.00048189954,0.0005791033,0.968351,0.00022372307,0.002971065,0.0009622539,0.000001747656,0.000547273,0.025881901],"genre_scores_gemma":[0.2482859,0.00034122387,0.21723473,0.00042376376,0.0022647833,0.0010250462,0.004247771,0.0003450185,0.52583176],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975944,0.00008784172,0.0004391675,0.0006894327,0.00074111106,0.00044800827],"domain_scores_gemma":[0.99873126,0.00026215453,0.00027384429,0.0005576915,0.00011159112,0.00006347435],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00078625197,0.00038835258,0.00033439056,0.0002027217,0.00045728224,0.0013338664,0.0018838084,0.00027935664,0.000032496428],"category_scores_gemma":[0.00020379687,0.00026055658,0.00024911485,0.0003487621,0.00002542018,0.00025760004,0.0002845107,0.000851845,0.00007721133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094394716,0.000033108852,0.000029442108,0.0009463908,0.00020022925,0.0000056541544,0.007176453,0.89719766,0.0009887161,0.07603459,0.002793086,0.014500288],"study_design_scores_gemma":[0.0002571227,0.00013966374,0.000026404994,0.00009768834,0.00006934922,0.0000075578487,0.0003585621,0.9800146,0.00020922416,0.0003884481,0.018093375,0.00033799166],"about_ca_topic_score_codex":0.0000566186,"about_ca_topic_score_gemma":0.000012673303,"teacher_disagreement_score":0.75111634,"about_ca_system_score_codex":0.000077583754,"about_ca_system_score_gemma":0.00014444157,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W4396534955","doi":"10.1109/tvt.2024.3394350","title":"You Only Look at Once for Real-Time and Generic Multi-Task","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Vehicular Technology","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":62,"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":"Canada Research Chairs","keywords":"Task (project management); Computer science; Engineering; Embedded system; Systems engineering","score_opus":0.014429421417233796,"score_gpt":0.25014116532074776,"score_spread":0.23571174390351396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396534955","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":[0.019812373,0.0003081732,0.9760202,0.001490878,0.00048426085,0.0003866265,0.000009477215,0.0014155444,0.00007243268],"genre_scores_gemma":[0.7783414,0.00062408624,0.21061121,0.00021186347,0.000042578788,0.00020269328,0.0000070297383,0.00007221132,0.009886907],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857223,0.000028025479,0.0002472349,0.00061127683,0.00017150209,0.00036974595],"domain_scores_gemma":[0.9990914,0.00010458186,0.000048706657,0.0006342997,0.00005624046,0.000064789434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015254912,0.00020985858,0.0002087791,0.0004813795,0.0002715345,0.00010296799,0.0005073877,0.000286889,0.0000147357805],"category_scores_gemma":[0.000008850115,0.00020588342,0.00010526123,0.000639696,0.00016380381,0.00019888229,0.000014626735,0.0003157916,0.00021106529],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018790102,0.0001071618,0.000024598836,0.00013055395,0.00022406311,0.0001103279,0.00030948754,0.74272156,0.13111804,0.005832078,0.0003804572,0.119022906],"study_design_scores_gemma":[0.00036632555,0.00031567537,0.000015786227,0.000058179165,0.000044087574,0.00017152983,0.000013010589,0.9522987,0.035885837,0.0001535838,0.010431564,0.00024572603],"about_ca_topic_score_codex":0.000010923747,"about_ca_topic_score_gemma":0.000011246819,"teacher_disagreement_score":0.76540905,"about_ca_system_score_codex":0.00015397956,"about_ca_system_score_gemma":0.00007816145,"threshold_uncertainty_score":0.8395682},"labels":[],"label_agreement":null},{"id":"W4397048993","doi":"10.48550/arxiv.2405.09999","title":"Reward Centering","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; DeepMind; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Psychology","score_opus":0.07759720201491045,"score_gpt":0.18758010996262264,"score_spread":0.10998290794771219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4397048993","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":[0.018288754,0.000070576985,0.961003,0.0001804083,0.0022117847,0.00017309123,0.0000028209565,0.0007669141,0.017302627],"genre_scores_gemma":[0.98556346,0.00012051567,0.003222283,0.00008434789,0.00010274895,4.4421327e-7,0.0000070556193,0.000025457583,0.010873663],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822414,0.00006615894,0.00019171294,0.0010252419,0.000114524555,0.00037819368],"domain_scores_gemma":[0.9982241,0.000048937436,0.00014667228,0.0013651962,0.00007581094,0.00013929763],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019046455,0.00029063618,0.0002468593,0.00028845598,0.00010872157,0.00033426206,0.002240355,0.00022539166,0.000031609026],"category_scores_gemma":[0.000025639,0.00034329228,0.0002207001,0.00047233587,0.000059626196,0.00019912697,0.0077920756,0.0009733264,0.0008129932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030475867,0.0000080256905,0.00030078963,0.00012913512,0.00006291679,0.00043292376,0.00015163494,0.85984135,0.00001123578,0.13825475,0.00057641976,0.00022778938],"study_design_scores_gemma":[0.0001239164,0.00003001141,0.00011186184,0.00023314929,0.00004277514,0.000005615753,0.000019934077,0.97449327,0.0000512772,0.020842936,0.0036821968,0.0003630801],"about_ca_topic_score_codex":0.000041280287,"about_ca_topic_score_gemma":0.0000034227774,"teacher_disagreement_score":0.9672747,"about_ca_system_score_codex":0.00027243892,"about_ca_system_score_gemma":0.00015139216,"threshold_uncertainty_score":0.999965},"labels":[],"label_agreement":null},{"id":"W4398186376","doi":"10.1145/3605098.3635992","title":"Explainable Artificial Intelligence (XAI) Approach for Reinforcement Learning Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence","score_opus":0.051292487425204716,"score_gpt":0.28274909395273246,"score_spread":0.23145660652752775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398186376","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":[0.0000123547725,0.00023860268,0.96475184,0.00015333688,0.001075897,0.00066197943,1.936151e-7,0.0008889484,0.03221686],"genre_scores_gemma":[0.8228628,0.000026623835,0.14384301,0.00007235365,0.00028255972,0.00026773429,0.00002139821,0.000032152904,0.03259138],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99789894,0.000051113708,0.00051175687,0.00055779377,0.00043607003,0.0005443094],"domain_scores_gemma":[0.9990044,0.0002411841,0.000077701225,0.00046124577,0.000111191686,0.000104280814],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00092563214,0.00020990126,0.00019884983,0.0002143626,0.00027925224,0.0014106983,0.0008281581,0.000088203305,0.000024292267],"category_scores_gemma":[0.00010874529,0.0001832174,0.00011297026,0.0005293974,0.000037298367,0.0007157383,0.00027481274,0.00027394833,0.0001789076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001977705,0.000005312395,0.000002236095,0.00016954317,0.000017289101,0.0000028376219,0.00030414163,0.5688107,0.0000553596,0.42672297,0.00055566535,0.0033519804],"study_design_scores_gemma":[0.000028768558,0.0002086209,3.937417e-7,0.00006503908,0.00000922395,0.000012330051,0.0005397657,0.9751132,0.0012936055,0.00079116126,0.021699317,0.00023855675],"about_ca_topic_score_codex":0.000030126346,"about_ca_topic_score_gemma":2.1462019e-7,"teacher_disagreement_score":0.8228504,"about_ca_system_score_codex":0.00013721702,"about_ca_system_score_gemma":0.00010493853,"threshold_uncertainty_score":0.9996259},"labels":[],"label_agreement":null},{"id":"W4398850169","doi":"10.48550/arxiv.2405.14664","title":"Fisher Flow Matching for Generative Modeling over Discrete Data","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Engineering and Physical Sciences Research Council; Center for Evolutionary and Theoretical Immunology","keywords":"Matching (statistics); Flow (mathematics); Computer science; Generative grammar; Generative model; Mathematics; Econometrics; Algorithm; Artificial intelligence; Statistics; Geometry","score_opus":0.15335958160201563,"score_gpt":0.23882465678278314,"score_spread":0.08546507518076751,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398850169","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":[0.006708623,0.000072970266,0.9889687,0.00020012047,0.0015084076,0.00046889245,0.00009152482,0.000343045,0.0016377536],"genre_scores_gemma":[0.8880226,0.000084687694,0.10451411,0.00018668207,0.0003137579,0.000001994188,0.00030643292,0.00005835283,0.0065113846],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99738115,0.000081136306,0.00026777037,0.0016898162,0.00014895394,0.00043119764],"domain_scores_gemma":[0.99688613,0.0001227508,0.0001709062,0.0025801829,0.00011374521,0.00012630907],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0003820933,0.00038419224,0.0003369712,0.0002123043,0.00019480282,0.00060833484,0.003861013,0.0002563518,0.000024756326],"category_scores_gemma":[0.00004650881,0.00041833546,0.0001944686,0.00030952223,0.000046152323,0.00071112247,0.011748785,0.0008470593,0.0000784116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009443727,0.0000075327484,0.000019505474,0.00013992628,0.00015278469,0.00008119994,0.0003644479,0.9381698,0.00000885168,0.059622314,0.0012576891,0.00016651732],"study_design_scores_gemma":[0.00022837565,0.000024216655,0.0000038016422,0.00017229149,0.000112548776,0.0000013811821,0.000041553674,0.9442938,0.000008638495,0.05405101,0.0006078,0.00045456944],"about_ca_topic_score_codex":0.000099184035,"about_ca_topic_score_gemma":0.000023396602,"teacher_disagreement_score":0.88445455,"about_ca_system_score_codex":0.00021393206,"about_ca_system_score_gemma":0.00024431618,"threshold_uncertainty_score":0.99982685},"labels":[],"label_agreement":null},{"id":"W4399019070","doi":"10.1016/j.eswa.2024.124310","title":"Bridging the simulation-to-real gap of depth images for deep reinforcement learning","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Encoder; Bridging (networking); Bridge (graph theory); Perception; Virtual reality; Machine learning; Deep learning; Computer vision","score_opus":0.025106323295264334,"score_gpt":0.3069211344319391,"score_spread":0.2818148111366747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399019070","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":[0.000037474885,0.00032460786,0.9934549,0.00072794757,0.00014748557,0.0017712585,7.592361e-7,0.0002830974,0.0032525212],"genre_scores_gemma":[0.9752614,0.000019080917,0.020172946,0.00006463689,0.0002284108,0.0020624488,0.000011876917,0.000025775049,0.0021534385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986287,0.000040417228,0.00038749963,0.0003365624,0.00035353273,0.0002532832],"domain_scores_gemma":[0.9984215,0.00056073774,0.00014264826,0.0006136386,0.000187033,0.00007444128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034270738,0.0001481958,0.0001620464,0.00012664398,0.00033339814,0.00032213755,0.00061354623,0.000035938232,0.0000033180127],"category_scores_gemma":[0.000044368648,0.000102227605,0.000059534297,0.00054717524,0.000041915402,0.00023210702,0.00010791754,0.000114397735,0.000040622974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003168279,0.0000050034737,0.000095922675,0.00007208832,0.000036775313,3.3242208e-7,0.0015807417,0.9514202,0.00032003084,0.042975195,0.00067449216,0.0028160324],"study_design_scores_gemma":[0.0000873264,0.000085623135,0.00005423594,0.000121004996,0.000009617309,0.0000046527753,0.0002382525,0.9482096,0.00023369578,0.000016892569,0.05081067,0.00012847257],"about_ca_topic_score_codex":0.00012437956,"about_ca_topic_score_gemma":0.0000032939047,"teacher_disagreement_score":0.9752239,"about_ca_system_score_codex":0.00008074779,"about_ca_system_score_gemma":0.000080009,"threshold_uncertainty_score":0.41687208},"labels":[],"label_agreement":null},{"id":"W4399116101","doi":"10.48550/arxiv.2405.16899","title":"Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.12975458227712403,"score_gpt":0.22997985085964243,"score_spread":0.1002252685825184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399116101","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":[0.0034977011,0.000036109297,0.9910259,0.0000853773,0.00087375706,0.00089005503,0.0000062871054,0.0006614026,0.0029233934],"genre_scores_gemma":[0.95850366,0.00002744783,0.036801845,0.00012644722,0.0001009746,0.000013054337,0.00003025439,0.000058899604,0.0043374025],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969181,0.0001092392,0.00041959237,0.0015577723,0.0002633648,0.0007319546],"domain_scores_gemma":[0.9977904,0.00016911623,0.00041639205,0.0011229715,0.00026400984,0.00023710866],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004892426,0.0005460226,0.00046022554,0.0004592842,0.00033889827,0.00036392096,0.0020201213,0.00037970097,0.000011438083],"category_scores_gemma":[0.000054404503,0.00065610674,0.00047949172,0.0004722781,0.0000924883,0.00043906155,0.003347677,0.0012210148,0.000055730532],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004222946,0.000014367481,0.000010850022,0.00013580619,0.000113300564,0.000043652606,0.00021140707,0.6908047,0.000010726485,0.3083305,0.00017502095,0.000107384716],"study_design_scores_gemma":[0.00059322023,0.00017084001,9.482919e-7,0.00029340107,0.00016171037,6.709436e-7,0.000031343116,0.938963,0.00022724524,0.058730524,0.00019972536,0.00062736165],"about_ca_topic_score_codex":0.000038564984,"about_ca_topic_score_gemma":0.0000018323601,"teacher_disagreement_score":0.95500594,"about_ca_system_score_codex":0.00065115344,"about_ca_system_score_gemma":0.00058827887,"threshold_uncertainty_score":0.999589},"labels":[],"label_agreement":null},{"id":"W4399284119","doi":"10.1016/j.neucom.2024.127963","title":"Multi-fidelity reinforcement learning with control variates","year":2024,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","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":"Microsoft (Canada)","funders":"Argonne National Laboratory; Office of Science; Laboratory Computing Resource Center; Advanced Scientific Computing Research; U.S. Department of Energy","keywords":"Reinforcement learning; Variance reduction; Estimator; Fidelity; Control variates; Computer science; Variance (accounting); High fidelity; Mathematical optimization; Reduction (mathematics); Function (biology); Artificial intelligence; Machine learning; Monte Carlo method; Mathematics; Statistics","score_opus":0.014987009506667814,"score_gpt":0.24923637087076794,"score_spread":0.23424936136410013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399284119","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":[0.0024406286,0.0000870123,0.9931993,0.0003704693,0.0005148958,0.00028742515,1.09034175e-7,0.0014200853,0.001680097],"genre_scores_gemma":[0.9203309,0.000004956421,0.078359246,0.00047376638,0.00013461876,0.000009492223,0.0000021288706,0.000029844052,0.0006550598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978154,0.0001368426,0.00041305964,0.00063360785,0.00046752373,0.0005335707],"domain_scores_gemma":[0.9988007,0.00043372906,0.0001273685,0.00042469302,0.00009872337,0.00011477464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005802858,0.00025392158,0.00021918166,0.00015639781,0.0003154669,0.0008363657,0.0006927305,0.00005663038,0.000013799969],"category_scores_gemma":[0.00011284288,0.00021224693,0.00007941309,0.00053104764,0.000038873244,0.0005006167,0.0003142136,0.0006517294,0.0001475185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004346655,0.000008398336,0.000922157,0.000055596724,0.000036959053,0.00008780636,0.00045972085,0.98652565,0.00082088925,0.0047562066,0.000054676286,0.0062676063],"study_design_scores_gemma":[0.0005189651,0.00022961282,0.0014756918,0.00013652878,0.000015640298,0.00004801731,0.0000144489195,0.99126524,0.00018165371,0.000022126087,0.0058494494,0.00024264584],"about_ca_topic_score_codex":0.000022468266,"about_ca_topic_score_gemma":6.627552e-7,"teacher_disagreement_score":0.91789025,"about_ca_system_score_codex":0.0000667252,"about_ca_system_score_gemma":0.00009816005,"threshold_uncertainty_score":0.86551785},"labels":[],"label_agreement":null},{"id":"W4399376477","doi":"10.1109/iciprob62548.2024.10543232","title":"Proximity-Based Reward Systems for Multi-Agent Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Swarm behaviour; Artificial intelligence; Swarm intelligence; Swarm robotics; Machine learning; Euclidean distance; Robot; Particle swarm optimization","score_opus":0.05601974589692608,"score_gpt":0.29988563588308553,"score_spread":0.24386588998615946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399376477","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":[0.000053687778,0.00028198102,0.9924129,0.00048995967,0.0016733106,0.0010182811,4.0237455e-7,0.0013283448,0.0027410928],"genre_scores_gemma":[0.66886455,0.000034421893,0.2671626,0.00044636463,0.00020974883,0.000444713,0.000031052663,0.000059112703,0.06274744],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99800324,0.00006750062,0.00044961987,0.00052575744,0.00046712114,0.0004867713],"domain_scores_gemma":[0.99892485,0.00021199667,0.00009100315,0.00051835494,0.00012838366,0.00012538568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081149663,0.00022205702,0.00020221499,0.00020998776,0.00021536111,0.00093274924,0.0006946292,0.000086079985,0.000023067167],"category_scores_gemma":[0.00013467026,0.0001875044,0.0001512928,0.00035531935,0.000028112892,0.0005110207,0.00018479305,0.00025953812,0.0002506297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000037472544,0.0000105784,0.00007298837,0.0003494443,0.000035178105,0.000008779937,0.00021924572,0.930145,0.00009138038,0.06610437,0.0019435278,0.0010157605],"study_design_scores_gemma":[0.0003461271,0.00023599401,0.000010726533,0.00014225187,0.000012407216,0.0000036120366,0.000035238678,0.859709,0.00042890353,0.000015106329,0.13883972,0.0002208848],"about_ca_topic_score_codex":0.000028738215,"about_ca_topic_score_gemma":7.4586876e-7,"teacher_disagreement_score":0.72525036,"about_ca_system_score_codex":0.00019124834,"about_ca_system_score_gemma":0.00018576467,"threshold_uncertainty_score":0.89945227},"labels":[],"label_agreement":null},{"id":"W4399729340","doi":"10.1109/syscon61195.2024.10553598","title":"Deep Reinforcement Learning Agents for Decision Making for Gameplay","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Human–computer interaction; Artificial intelligence; Reinforcement; Psychology; Social psychology","score_opus":0.03155200176925009,"score_gpt":0.32377764727110686,"score_spread":0.29222564550185676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399729340","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":[0.000074257216,0.00010496567,0.99233365,0.0002079504,0.001312819,0.00076345896,1.8432743e-7,0.0005442775,0.0046584345],"genre_scores_gemma":[0.5422846,0.000016538908,0.44440797,0.00039134707,0.00013847332,0.00014363196,0.000008754382,0.000031696352,0.012577013],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825495,0.000017961373,0.00039745576,0.00048459266,0.00037223782,0.00047276984],"domain_scores_gemma":[0.99817836,0.001185948,0.00007936288,0.00037853213,0.0001068784,0.00007092162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006176462,0.00018476717,0.00016390346,0.00020262772,0.00025946897,0.0007283938,0.0006903261,0.00007705544,0.000095036856],"category_scores_gemma":[0.0004553054,0.00016108724,0.0001780359,0.00027784015,0.000016478638,0.0005421124,0.00027862666,0.00015163988,0.000113327704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001255581,0.0000034940067,0.000027523414,0.0000818822,0.000028917822,0.0000026543946,0.0003618436,0.8421382,0.000033853292,0.08924555,0.003992436,0.06407109],"study_design_scores_gemma":[0.00022670826,0.00025720807,0.000020097428,0.00019601423,0.000012808963,0.0000047495746,0.000032372915,0.8685865,0.00015004225,0.0015092602,0.12881649,0.00018774749],"about_ca_topic_score_codex":0.0000015017746,"about_ca_topic_score_gemma":0.000001129609,"teacher_disagreement_score":0.5479257,"about_ca_system_score_codex":0.00012314372,"about_ca_system_score_gemma":0.000057443536,"threshold_uncertainty_score":0.7023918},"labels":[],"label_agreement":null},{"id":"W4399828133","doi":"10.1007/978-3-031-54071-4_22","title":"Reinforcement Learning for Partially Observable Models","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Observable; Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Physics; Social psychology","score_opus":0.037490925067643545,"score_gpt":0.24043671886862947,"score_spread":0.20294579380098593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828133","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.1662763e-7,0.0017828643,0.68428564,0.0001885046,0.002414158,0.0017175452,0.000004864303,0.00051508396,0.30909118],"genre_scores_gemma":[0.072048195,0.00007520263,0.001128017,0.00018367474,0.0007853753,0.00038416547,0.000047836038,0.00014581472,0.9252017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996206,0.000042057858,0.0011600766,0.00093611004,0.0008998691,0.0007559045],"domain_scores_gemma":[0.9972788,0.00032048736,0.000673633,0.0011472187,0.00037934326,0.0002005301],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009342499,0.00065722014,0.0009635909,0.0002474385,0.0002572504,0.0010031931,0.0013302994,0.00047622647,0.000030081397],"category_scores_gemma":[0.00005085647,0.00062489166,0.0004670891,0.000061209335,0.000045433648,0.000504249,0.0003007988,0.000748935,0.00070496],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009444318,0.0000013011881,6.4669865e-7,0.00028218565,0.00021109132,0.00001307835,0.00008308941,0.52716386,0.000009371398,0.4704048,0.0016285422,0.0001925915],"study_design_scores_gemma":[0.00055151543,0.00022200143,1.0370544e-7,0.00055953383,0.00010998409,0.000008053787,0.000005599295,0.62445045,0.0000019865727,0.0061115962,0.36757928,0.00039986882],"about_ca_topic_score_codex":0.00004307641,"about_ca_topic_score_gemma":0.0000035721616,"teacher_disagreement_score":0.6831576,"about_ca_system_score_codex":0.00032450334,"about_ca_system_score_gemma":0.00030678822,"threshold_uncertainty_score":0.99962026},"labels":[],"label_agreement":null},{"id":"W4399828205","doi":"10.1007/978-3-031-54071-4_21","title":"Reinforcement Learning for Fully Observable Models: Convergence to Near Optimality under Weak Feller Continuity","year":2024,"lang":"en","type":"book-chapter","venue":"Systems & control","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Observable; Reinforcement learning; Convergence (economics); Reinforcement; Computer science; Mathematics; Mathematical optimization; Artificial intelligence; Psychology; Economics; Physics; Social psychology","score_opus":0.04009775781671515,"score_gpt":0.2557781574063045,"score_spread":0.21568039958958934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399828205","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000033955548,0.0010507856,0.78030413,0.0004068262,0.0032968612,0.0034005165,0.000011672529,0.00057054946,0.21095525],"genre_scores_gemma":[0.20242666,0.00004690098,0.0030898782,0.00046334363,0.00045885338,0.00043430462,0.00004391496,0.00015816337,0.792878],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99435437,0.000101573685,0.0016005237,0.0015458788,0.0012879503,0.0011097079],"domain_scores_gemma":[0.99579483,0.00044262144,0.0008115174,0.0016803115,0.0008216332,0.0004490616],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017686634,0.0009509522,0.0014345039,0.00024104428,0.00047339918,0.0014694169,0.0019309504,0.000613287,0.000113705755],"category_scores_gemma":[0.00010047837,0.00093671685,0.0005746553,0.00014639179,0.00011062137,0.0006165334,0.00068986625,0.0010197764,0.0012793324],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003709975,0.0000037022057,0.0000048490297,0.0003200187,0.0002754617,0.000008128967,0.00019476989,0.57095826,0.000014566915,0.42498982,0.0030778425,0.00011549479],"study_design_scores_gemma":[0.0007621445,0.00032912905,0.0000033116894,0.0006064234,0.00012544877,0.0000089545965,0.000032954875,0.67441934,0.0000024327098,0.002832348,0.32019645,0.00068106304],"about_ca_topic_score_codex":0.00026021755,"about_ca_topic_score_gemma":0.000013211103,"teacher_disagreement_score":0.7772143,"about_ca_system_score_codex":0.00066032034,"about_ca_system_score_gemma":0.00052196556,"threshold_uncertainty_score":0.99956715},"labels":[],"label_agreement":null},{"id":"W4400146922","doi":"10.1016/j.knosys.2024.112190","title":"DiffSkill: Improving Reinforcement Learning through diffusion-based skill denoiser for robotic manipulation","year":2024,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"China Scholarship Council; Science and Technology Commission of Shanghai Municipality","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Materials science; Composite material","score_opus":0.025444150437695098,"score_gpt":0.27644692360467316,"score_spread":0.25100277316697805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400146922","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":[0.00068524614,0.0012578283,0.98737246,0.00021158709,0.0050466605,0.0016687202,0.0000010772499,0.0013494997,0.0024069357],"genre_scores_gemma":[0.9795758,0.0000049798355,0.010622883,0.00010215015,0.00043820444,0.0004024135,0.00009984796,0.00010923205,0.008644469],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961361,0.0002618084,0.0010212598,0.0010087523,0.0007051964,0.0008668394],"domain_scores_gemma":[0.9969445,0.0011908961,0.00033577142,0.0009714749,0.0003706055,0.0001867835],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009859328,0.00053605204,0.00052579015,0.00043105407,0.0006179193,0.001273181,0.0009876929,0.00024532783,0.00002086762],"category_scores_gemma":[0.00031077748,0.00048955245,0.00034717,0.00085709407,0.00006504292,0.0007186047,0.00020651915,0.00045690624,0.0003331944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012746207,0.000051122104,0.00035086033,0.0015933543,0.000047784997,0.000012001785,0.0009492659,0.9780678,0.0011207085,0.015719837,0.0007034482,0.0013710595],"study_design_scores_gemma":[0.0010242092,0.0003923628,0.000093900446,0.0010710986,0.000067955516,0.0000053851936,0.000094075585,0.9836732,0.0009835804,0.00006869056,0.011933476,0.00059202284],"about_ca_topic_score_codex":0.00014421334,"about_ca_topic_score_gemma":0.00001256819,"teacher_disagreement_score":0.9788906,"about_ca_system_score_codex":0.00068629853,"about_ca_system_score_gemma":0.00050211686,"threshold_uncertainty_score":0.9997636},"labels":[],"label_agreement":null},{"id":"W4400374283","doi":"10.48550/arxiv.2407.02231","title":"Safety-Driven Deep Reinforcement Learning Framework for Cobots: A Sim2Real Approach","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute of Steel Construction","keywords":"Reinforcement learning; Artificial intelligence; Reinforcement; Computer science; Psychology; Social psychology","score_opus":0.06038632336708043,"score_gpt":0.21454467826030085,"score_spread":0.15415835489322044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400374283","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":[0.00040835742,0.000095446274,0.9840886,0.00014611288,0.0012241624,0.0011486786,0.0000040253713,0.0008986976,0.011985927],"genre_scores_gemma":[0.88865745,0.00021989433,0.101509824,0.00014630173,0.00026270316,0.000013275565,0.00012690088,0.00007949297,0.008984131],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99630225,0.00017461916,0.0005387634,0.0018399348,0.00028731386,0.00085714785],"domain_scores_gemma":[0.99678797,0.0004933114,0.00052421505,0.0016534874,0.00025425243,0.00028674435],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005285402,0.0006533519,0.0006387206,0.00047914893,0.00043940108,0.000520174,0.0029545447,0.0007203493,0.000036368343],"category_scores_gemma":[0.00022700096,0.00075510197,0.0005430238,0.000842308,0.00015214425,0.00030405523,0.005651602,0.002453248,0.00022241997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035591118,0.000020526308,0.000096937976,0.00030581927,0.00019720232,0.00004757063,0.0005391258,0.60973006,0.0000018018306,0.38861147,0.00012232883,0.0002915382],"study_design_scores_gemma":[0.00047771947,0.00019518212,0.00002143074,0.00033355746,0.0001889992,0.000004979908,0.0001900791,0.95306253,0.000013700183,0.041843858,0.0029146785,0.0007532896],"about_ca_topic_score_codex":0.000039345618,"about_ca_topic_score_gemma":0.0000030031822,"teacher_disagreement_score":0.8882491,"about_ca_system_score_codex":0.0006969724,"about_ca_system_score_gemma":0.00036496556,"threshold_uncertainty_score":0.9998481},"labels":[],"label_agreement":null},{"id":"W4400947559","doi":"10.3390/app14156432","title":"Environmental-Impact-Based Multi-Agent Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Reinforcement Learning in Robotics","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":"Brock University","funders":"Alliance de recherche numérique du Canada","keywords":"Computer science","score_opus":0.027554366087087664,"score_gpt":0.2775524108106826,"score_spread":0.24999804472359494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400947559","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":[0.005780279,0.00017843545,0.98415375,0.00024689114,0.00040041213,0.0002440889,3.432595e-7,0.00048229637,0.008513499],"genre_scores_gemma":[0.9676826,0.000017555416,0.030722246,0.00028490528,0.000042964122,0.0000327277,0.000004560681,0.000012142914,0.0012002982],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997619,0.000039588933,0.00030235478,0.00064338994,0.0008455828,0.0005501373],"domain_scores_gemma":[0.9992289,0.00016347825,0.00008507592,0.0003708727,0.0000074377276,0.0001442277],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00084185856,0.0002284818,0.00015255672,0.0002505466,0.00050615164,0.0008770356,0.0011895205,0.00005712078,0.00019077536],"category_scores_gemma":[0.000020489737,0.00018124966,0.000104850085,0.00068646966,0.00028583148,0.00045004586,0.00031498756,0.00028282413,0.0010398675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012899886,0.000013500272,0.00043589686,0.000012403116,0.000013197521,0.000008440308,0.0004240107,0.9751956,0.003893755,0.013291624,0.00024292555,0.0064673703],"study_design_scores_gemma":[0.0001714891,0.0001717536,0.0007106818,0.000026033504,0.0000066412454,0.000003565345,0.00007362636,0.9853235,0.0033349914,0.00006883451,0.009858531,0.00025037458],"about_ca_topic_score_codex":0.000010947698,"about_ca_topic_score_gemma":4.8651356e-7,"teacher_disagreement_score":0.9619023,"about_ca_system_score_codex":0.00018539175,"about_ca_system_score_gemma":0.00017376279,"threshold_uncertainty_score":0.9997379},"labels":[],"label_agreement":null},{"id":"W4401023823","doi":"10.24963/ijcai.2024/587","title":"Towards Debiased Generalized Category Discovery","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Government of Jiangsu Province; Hong Kong Baptist University","keywords":"Computer science; Set (abstract data type); Artificial intelligence; Programming language","score_opus":0.022507952834753153,"score_gpt":0.26828201683960556,"score_spread":0.2457740640048524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401023823","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":[0.0012009272,0.00021426093,0.9454881,0.0012417657,0.001068555,0.00007668912,3.2499224e-7,0.00071103056,0.049998358],"genre_scores_gemma":[0.85973155,0.000041588675,0.07489354,0.0011561392,0.000145553,0.000012810368,0.0000072346634,0.000018762577,0.063992806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896073,0.000035564557,0.00017487853,0.0003033607,0.0002822084,0.00024324433],"domain_scores_gemma":[0.99939185,0.000055986122,0.000018459534,0.0004480583,0.000023352266,0.000062265746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018404862,0.00011648241,0.00010232879,0.0001031812,0.000055362354,0.0009754315,0.0006264391,0.00004301566,0.000110843815],"category_scores_gemma":[0.000026642629,0.00008946383,0.00008097135,0.00033521888,0.000025349895,0.0009760039,0.00023466833,0.00012325721,0.0004403887],"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":[0.0000018168996,0.000008554616,0.00005034089,0.00003629386,0.000036977814,0.000072072864,0.0003209398,0.13093382,0.0011194021,0.83712065,0.018280929,0.012018184],"study_design_scores_gemma":[0.00011674452,0.00003760157,0.0001662843,0.00001618123,0.000005848209,0.000011685826,0.000008469436,0.9576981,0.0031008923,0.002190518,0.036475364,0.00017233286],"about_ca_topic_score_codex":0.00009155741,"about_ca_topic_score_gemma":0.000002553201,"teacher_disagreement_score":0.87059456,"about_ca_system_score_codex":0.000052952593,"about_ca_system_score_gemma":0.0001543608,"threshold_uncertainty_score":0.9406109},"labels":[],"label_agreement":null},{"id":"W4401023970","doi":"10.24963/ijcai.2024/427","title":"Α Descent-based Method on the Duality Gap for Solving Zero-sum Games","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; Korea Advanced Institute of Science and Technology","keywords":"Reinforcement learning; Diversification (marketing strategy); Computer science; Reinforcement; Artificial intelligence; Business; Engineering; Marketing","score_opus":0.0741761737187263,"score_gpt":0.3404508027115267,"score_spread":0.2662746289928004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401023970","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":[0.000119245895,0.000040774103,0.9847815,0.007835894,0.00066494255,0.0003229463,8.504846e-7,0.00045058437,0.005783264],"genre_scores_gemma":[0.35942,0.0000035343814,0.62902826,0.0041642035,0.000097725555,0.00005883103,0.0000030378342,0.000023498556,0.007200934],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986774,0.00010881319,0.00021613616,0.00036172516,0.00032110955,0.00031484905],"domain_scores_gemma":[0.9971903,0.0020398712,0.000045614117,0.00061564817,0.00005621047,0.000052381587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014936868,0.00013899717,0.00011720929,0.00007025235,0.0001745618,0.0006357504,0.00074669585,0.000047132264,0.000059026937],"category_scores_gemma":[0.00030029495,0.000085640764,0.00012921299,0.00025787778,0.00003080182,0.00018659211,0.00014147631,0.00018064705,0.00010474819],"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":[0.0000049528876,0.000015789607,0.000046107773,0.000078634635,0.00003071481,0.0000034217824,0.00028681516,0.24919964,0.00055878557,0.7191944,0.01709422,0.013486511],"study_design_scores_gemma":[0.00009969786,0.0000862807,0.00004789803,0.000063574764,0.000008648819,0.000001156296,0.000021113854,0.9676938,0.009442455,0.0029898887,0.019421699,0.00012376317],"about_ca_topic_score_codex":0.000012460355,"about_ca_topic_score_gemma":0.0000012148051,"teacher_disagreement_score":0.7184942,"about_ca_system_score_codex":0.00006182046,"about_ca_system_score_gemma":0.000099340505,"threshold_uncertainty_score":0.6130556},"labels":[],"label_agreement":null},{"id":"W4401024442","doi":"10.24963/ijcai.2024/507","title":"Reasoning About Causal Knowledge in Nondeterministic Domains","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"York University; University of Regina","funders":"Youth Innovation Promotion Association; Tencent; National Key Research and Development Program of China; Youth Innovation Promotion Association of the Chinese Academy of Sciences; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Operator (biology); Artificial intelligence","score_opus":0.015185618027503484,"score_gpt":0.2941535458412524,"score_spread":0.2789679278137489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401024442","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":[0.0027106141,0.00021744025,0.872934,0.00012733442,0.0008301409,0.000079230624,1.8190165e-7,0.000391781,0.12270927],"genre_scores_gemma":[0.9483964,0.00001383954,0.037219103,0.00008775131,0.000085137675,0.00000994485,0.0000013210713,0.000013403109,0.014173125],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988955,0.000043785512,0.00023352525,0.00033696546,0.00017339861,0.0003167728],"domain_scores_gemma":[0.99930304,0.0002090732,0.000021214635,0.00037724522,0.000021282982,0.00006811778],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032143993,0.00012212471,0.00011903536,0.00020688624,0.000053353884,0.0004143257,0.0005566031,0.000054461427,0.000059805574],"category_scores_gemma":[0.00006080088,0.00010844622,0.000041481708,0.00055695494,0.000032975604,0.00034544058,0.00027578863,0.00022553187,0.00077348616],"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":[0.0000019582162,0.00002818014,0.0013231938,0.0001139074,0.000019550505,0.00046568853,0.0029114108,0.060078815,0.00021342936,0.9132812,0.00262883,0.018933844],"study_design_scores_gemma":[0.00010953084,0.000052113282,0.0018231471,0.00016240602,0.0000029752782,0.00002739509,0.000023190547,0.98238355,0.0000888842,0.00041631795,0.014754698,0.00015579959],"about_ca_topic_score_codex":0.000019158462,"about_ca_topic_score_gemma":0.000028500683,"teacher_disagreement_score":0.94568574,"about_ca_system_score_codex":0.000098822034,"about_ca_system_score_gemma":0.0001429571,"threshold_uncertainty_score":0.99418575},"labels":[],"label_agreement":null},{"id":"W4401024943","doi":"10.24963/ijcai.2024/964","title":"DGL: Dynamic Global-Local Information Aggregation for Scalable VRP Generalization with Self-Improvement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"BC Research (Canada)","funders":"Grantová Agentura České Republiky; Ministerstvo Školství, Mládeže a Tělovýchovy","keywords":"Computer science; Imperfect; Perfect information; Algorithm; Mathematics; Mathematical economics","score_opus":0.004381780029235462,"score_gpt":0.22670872808770698,"score_spread":0.22232694805847153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401024943","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":[0.0014390784,0.000031934575,0.9934969,0.00044462128,0.00035550134,0.000506789,0.0000010508036,0.0010797884,0.0026443258],"genre_scores_gemma":[0.7535954,0.000030007737,0.24390404,0.00036319744,0.00004107634,0.00008620473,0.00013830203,0.000015403732,0.0018263839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987732,0.000023869467,0.00030089938,0.00024319267,0.00038283906,0.0002759792],"domain_scores_gemma":[0.99939764,0.00003933919,0.000101814636,0.00022551,0.00017651045,0.00005916683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002866539,0.00015201158,0.00010173372,0.00011158768,0.00018243137,0.0008127431,0.0002712359,0.00006671597,0.000012911123],"category_scores_gemma":[0.00002485919,0.00012549215,0.000041216677,0.0005827565,0.000019360645,0.00236516,0.00009146895,0.00009794771,0.000088305096],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044646017,0.000006276439,0.0001421806,0.00011396335,0.000028797482,5.7603063e-7,0.00025278583,0.8698249,0.00003650431,0.06063905,0.0003448666,0.06860563],"study_design_scores_gemma":[0.0003034257,0.00036900275,0.0001016207,0.000060732473,0.000017058826,0.000006765534,0.00005875653,0.980464,0.00046672422,0.00036607924,0.017609451,0.00017642397],"about_ca_topic_score_codex":0.000031066542,"about_ca_topic_score_gemma":0.000010466793,"teacher_disagreement_score":0.7521563,"about_ca_system_score_codex":0.00041182383,"about_ca_system_score_gemma":0.00013637356,"threshold_uncertainty_score":0.78373003},"labels":[],"label_agreement":null},{"id":"W4401157207","doi":"10.21203/rs.3.rs-4678044/v1","title":"Speeding up hierarchical reinforcement learning using state-independent temporal skills","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; State (computer science); Artificial intelligence; Psychology; Social psychology; Algorithm","score_opus":0.07600609675111851,"score_gpt":0.39778746747497096,"score_spread":0.32178137072385243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401157207","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":[0.02877787,0.0007151171,0.95315176,0.0008981748,0.0037960303,0.002124368,0.000008380561,0.001049426,0.0094789],"genre_scores_gemma":[0.9647744,0.00031477472,0.017570196,0.000043322838,0.00072121393,0.000094119845,0.000101583115,0.00015304958,0.016227338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9876817,0.0010876874,0.001230943,0.0020168852,0.0057255924,0.002257187],"domain_scores_gemma":[0.99545443,0.0007084313,0.0003579416,0.0019394787,0.00086019066,0.0006795331],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006198273,0.0007438136,0.0007666172,0.0019635255,0.0008339138,0.003503547,0.003559808,0.0005986782,0.00017695615],"category_scores_gemma":[0.0007981302,0.00072628364,0.00045850972,0.0014727212,0.00029262897,0.00043124615,0.022824753,0.011446997,0.0008204652],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020504276,0.000041106297,0.0012806999,0.001392507,0.00015851863,0.00043213286,0.0030488034,0.9817831,0.00020818337,0.0059750783,0.0009001109,0.0047592805],"study_design_scores_gemma":[0.00038447962,0.0003758324,0.00020492668,0.0027109052,0.00002013951,0.00003591127,0.00025941216,0.98026556,0.0005796783,0.008068682,0.0063278712,0.0007665865],"about_ca_topic_score_codex":0.00050015433,"about_ca_topic_score_gemma":0.000010116256,"teacher_disagreement_score":0.93599653,"about_ca_system_score_codex":0.0019886405,"about_ca_system_score_gemma":0.0020284571,"threshold_uncertainty_score":0.9999575},"labels":[],"label_agreement":null},{"id":"W4401413897","doi":"10.1109/icra57147.2024.10610017","title":"Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Reinforcement learning; Robot; Computer science; Domain (mathematical analysis); Randomization; Artificial intelligence; Mathematics","score_opus":0.009420998089325656,"score_gpt":0.26129184082772616,"score_spread":0.2518708427384005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401413897","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":[0.0014369644,0.0002581674,0.98175144,0.00038651898,0.00042876616,0.0009403551,9.786444e-7,0.00038999715,0.014406831],"genre_scores_gemma":[0.83939934,0.000040054532,0.15144393,0.00008537838,0.000058101778,0.00006506871,0.000041102536,0.000037417187,0.008829618],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973543,0.00012694763,0.00090527616,0.00055512023,0.0005281763,0.0005301367],"domain_scores_gemma":[0.99859565,0.00045896915,0.00027288232,0.0004850594,0.00010650604,0.000080908074],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015588863,0.00026770664,0.00040113536,0.00044444596,0.00014788478,0.00029074287,0.00087893434,0.00011048641,0.000045508074],"category_scores_gemma":[0.0004050131,0.00024544753,0.00011953741,0.00096216035,0.000044290802,0.00061687216,0.00039530318,0.00033726887,0.000005060403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036198126,0.0000150047,0.00014479138,0.00018674767,0.000024711848,0.0000029911805,0.0031874517,0.95886284,0.00236815,0.03126712,0.0007815732,0.0031224426],"study_design_scores_gemma":[0.0019460345,0.00017195765,0.00008742305,0.00022871894,0.0000120951545,0.0000014221959,0.000086824184,0.9905757,0.004259308,0.0005787855,0.001784825,0.00026694362],"about_ca_topic_score_codex":0.0005233681,"about_ca_topic_score_gemma":0.000051090752,"teacher_disagreement_score":0.8379624,"about_ca_system_score_codex":0.00027935833,"about_ca_system_score_gemma":0.00023012834,"threshold_uncertainty_score":0.99999976},"labels":[],"label_agreement":null},{"id":"W4401422722","doi":"10.1145/3643658.3643919","title":"A Behavior-driven Development and Reinforcement Learning approach for videogame automated testing","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Reinforcement; Development (topology); Artificial intelligence; Human–computer interaction; Engineering","score_opus":0.04646166824848585,"score_gpt":0.2825911991807369,"score_spread":0.23612953093225103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401422722","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":[0.0027372998,0.00005628774,0.98717195,0.000054085136,0.00014672006,0.00053752185,1.00338994e-7,0.0028268918,0.006469163],"genre_scores_gemma":[0.40203297,0.0000020038478,0.594592,0.00005287226,0.000024450375,0.00015095322,0.0000117451145,0.000016909995,0.0031161315],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984391,0.00002535377,0.00036815222,0.00047760486,0.0002981018,0.00039171174],"domain_scores_gemma":[0.99930793,0.00020976046,0.000069255824,0.00022156125,0.000088187604,0.00010331794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041152438,0.00019416513,0.00016066944,0.00017816974,0.00026153363,0.00065001077,0.00037035247,0.000068256086,0.000006692445],"category_scores_gemma":[0.00012556753,0.00017267348,0.00003832821,0.00039011502,0.0000305618,0.00042849197,0.00037794004,0.00019718043,0.000023222668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000014419697,0.000009881548,0.00074211106,0.00014514962,0.000033120323,0.00000898167,0.0011676938,0.96228355,0.00042546788,0.010290671,0.00023696745,0.024654964],"study_design_scores_gemma":[0.0001906038,0.00012905012,0.00043922116,0.00006699758,0.000015709173,0.000024981255,0.00005126654,0.9902897,0.00054920965,0.000008643316,0.007995682,0.00023891908],"about_ca_topic_score_codex":0.000008258809,"about_ca_topic_score_gemma":2.8429366e-7,"teacher_disagreement_score":0.3992957,"about_ca_system_score_codex":0.000105185274,"about_ca_system_score_gemma":0.00014583542,"threshold_uncertainty_score":0.70414203},"labels":[],"label_agreement":null},{"id":"W4401540274","doi":"10.1109/infocomwkshps61880.2024.10620892","title":"Cascade: Enhancing Reinforcement Learning with Curriculum Federated Learning and Interference Avoidance — A Case Study in Adaptive Bitrate Selection","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Cascade; Selection (genetic algorithm); Interference (communication); Artificial intelligence; Machine learning; Computer network; Engineering","score_opus":0.014591500648883905,"score_gpt":0.2666688859663599,"score_spread":0.252077385317476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401540274","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":[0.35248813,0.00007459307,0.64560616,0.000030063453,0.0000865539,0.00037132326,2.02042e-8,0.00038412728,0.0009590229],"genre_scores_gemma":[0.9924251,0.000024844509,0.0049437257,0.000026086842,0.000027779084,0.00005732354,0.0000010330953,0.000024283047,0.0024698297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976453,0.00029778015,0.00046286988,0.0007593832,0.00034973497,0.00048491865],"domain_scores_gemma":[0.9993071,0.00018738651,0.00012653487,0.00013738353,0.00013597008,0.000105610525],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00076557166,0.000309902,0.00026511657,0.00037782962,0.00042131924,0.0010706749,0.00019479456,0.000071321476,0.000022028576],"category_scores_gemma":[0.00008471548,0.00025471562,0.000027218963,0.0013885596,0.000043365904,0.0010864825,0.00026624644,0.0012204344,0.000023951332],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018366774,0.00003754282,0.01693325,0.000054804983,0.000066808425,0.0023392905,0.009184074,0.9660449,0.0006829085,0.0010019392,0.0000073811866,0.0036287587],"study_design_scores_gemma":[0.00044728664,0.0021549095,0.00021471502,0.00034701911,0.000016300994,0.001523536,0.010850241,0.9829968,0.0010352081,0.000006334111,0.00006338385,0.00034425128],"about_ca_topic_score_codex":0.001679199,"about_ca_topic_score_gemma":0.00185012,"teacher_disagreement_score":0.64066243,"about_ca_system_score_codex":0.00023454316,"about_ca_system_score_gemma":0.00015812872,"threshold_uncertainty_score":0.9999905},"labels":[],"label_agreement":null},{"id":"W4401541260","doi":"10.1109/infocomwkshps61880.2024.10620663","title":"Maximizing the Social Welfare of Decentralized Knowledge Inference Through Evolutionary Game","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Inference; Computer science; Game theory; Welfare; Artificial intelligence; Social Welfare; Evolutionary game theory; Mathematical economics; Economics; Political science","score_opus":0.03654919925995269,"score_gpt":0.3297239862637389,"score_spread":0.2931747870037862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401541260","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":[0.0005318838,0.00073221064,0.96224564,0.005860084,0.00061471155,0.00012382072,8.56107e-7,0.00028434774,0.029606462],"genre_scores_gemma":[0.9774558,0.000055314864,0.020684324,0.000097652955,0.000056318484,0.000007674359,0.0000023721327,0.000008564921,0.0016319549],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889815,0.00008186148,0.00026019532,0.00022847536,0.0002755572,0.00025577424],"domain_scores_gemma":[0.9993106,0.00020653056,0.000054422573,0.0003084554,0.00009485236,0.000025151552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018483716,0.0001160009,0.00012876098,0.000047133897,0.00019425273,0.00016145485,0.00088222115,0.00005613522,0.00017665494],"category_scores_gemma":[0.000065908825,0.00007799095,0.0000992848,0.00053549616,0.00011320349,0.00047748734,0.00041780292,0.00019074194,0.0000927125],"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":[0.0000019804113,0.000012560867,0.000118189586,0.00004878867,0.000030335364,0.000003056671,0.004525854,0.015056342,0.00006522108,0.97357565,0.0025120655,0.0040499605],"study_design_scores_gemma":[0.00019065522,0.000043978696,0.0024011522,0.000060644565,0.000016622824,0.000008831725,0.00032834438,0.80758995,0.00026659746,0.005277961,0.1836303,0.00018496069],"about_ca_topic_score_codex":0.000023907316,"about_ca_topic_score_gemma":0.0000020667512,"teacher_disagreement_score":0.97692394,"about_ca_system_score_codex":0.00006293265,"about_ca_system_score_gemma":0.00013239948,"threshold_uncertainty_score":0.31803787},"labels":[],"label_agreement":null},{"id":"W4401567462","doi":"10.1109/jiot.2024.3443701","title":"Energy-Efficient Joint Optimization of Sensing and Computation in MEC-Assisted IoT Using Mean-Field Game","year":2024,"lang":"en","type":"article","venue":"IEEE Internet of Things Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Toyota Motor Corporation; National Natural Science Foundation of China","keywords":"Computer science; Server; Energy consumption; Computation offloading; Distributed computing; Computation; Efficient energy use; Computational complexity theory; Optimization problem; Edge computing; Mobile edge computing; Markov decision process; Field (mathematics); Internet of Things; Enhanced Data Rates for GSM Evolution; Markov process; Computer network; Artificial intelligence; Algorithm; Embedded system","score_opus":0.031434826967558574,"score_gpt":0.2754179182907363,"score_spread":0.24398309132317775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401567462","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":[0.12862284,0.00012648366,0.8700819,0.00012104035,0.0008577808,0.000035256875,7.939688e-8,0.000024716945,0.00012987031],"genre_scores_gemma":[0.82956916,0.000012833714,0.17028564,0.000062094565,0.000031629374,8.812484e-8,2.8397088e-7,0.000008425809,0.000029824008],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986043,0.00008755626,0.00061884144,0.00017029581,0.0003679398,0.0001510886],"domain_scores_gemma":[0.99920106,0.00013121849,0.00036814698,0.00009777072,0.00015301726,0.000048789527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00063223037,0.00010893853,0.00020366072,0.00044756974,0.000025269976,0.00024896424,0.00019858524,0.00006387472,0.000005076544],"category_scores_gemma":[0.00006167815,0.00010157181,0.00006594416,0.0002775367,0.000034452398,0.00029205353,0.00010063056,0.00027882218,3.641459e-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":[0.00000822906,0.0000125361,0.000021816424,0.000046951685,0.000027525262,0.000028997827,0.0038340024,0.9729222,0.008348951,0.00040760025,0.000030649564,0.014310555],"study_design_scores_gemma":[0.000190031,0.00011847252,0.000036092006,0.0010528134,0.000013147602,0.00036596967,0.000060284077,0.9794357,0.018471848,0.00015899102,0.000008342744,0.00008832437],"about_ca_topic_score_codex":0.00019368381,"about_ca_topic_score_gemma":0.0000020190676,"teacher_disagreement_score":0.70094633,"about_ca_system_score_codex":0.00011376167,"about_ca_system_score_gemma":0.0000640362,"threshold_uncertainty_score":0.4141978},"labels":[],"label_agreement":null},{"id":"W4401687215","doi":"10.1109/access.2024.3446310","title":"Finding the Optimal Security Policies for Autonomous Cyber Operations With Competitive Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Access","topic":"Reinforcement Learning in Robotics","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":"Defence Research and Development Canada; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Computer science; Computer security; Artificial intelligence","score_opus":0.030520465487766258,"score_gpt":0.3178122432086103,"score_spread":0.287291777720844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401687215","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":[0.01000819,0.000051376064,0.98095804,0.0016733287,0.0005767553,0.0005313461,0.0000018171374,0.00032473463,0.005874417],"genre_scores_gemma":[0.99064845,0.000014037708,0.005923388,0.00037389123,0.00019580423,0.00014331126,0.00001043214,0.000020743437,0.0026699337],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99869317,0.00005231023,0.0002444848,0.0003323001,0.00030282282,0.00037489383],"domain_scores_gemma":[0.99906534,0.00033597395,0.000059204423,0.0003552205,0.0001272756,0.000056987934],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00034210333,0.00018007797,0.00014407201,0.00011991815,0.00066443346,0.0023445145,0.0011516882,0.000046225683,0.000025556908],"category_scores_gemma":[0.00004537628,0.00012093886,0.000068365414,0.00042049048,0.000094478106,0.0012673,0.00027674116,0.0003334601,0.000034029923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004029276,0.000004693665,0.00010024796,0.00002594104,0.000051122617,0.000004897999,0.0037756949,0.88195443,0.000039270315,0.113310255,0.0004216278,0.00030781774],"study_design_scores_gemma":[0.0001774594,0.00016757924,0.00013169556,0.000090565765,0.000022114373,0.000015276684,0.00021186158,0.97762764,0.0016158897,0.000088331355,0.01965617,0.00019541371],"about_ca_topic_score_codex":0.00011139292,"about_ca_topic_score_gemma":0.000030905172,"teacher_disagreement_score":0.9806403,"about_ca_system_score_codex":0.000120121345,"about_ca_system_score_gemma":0.00018271134,"threshold_uncertainty_score":0.99869114},"labels":[],"label_agreement":null},{"id":"W4401883986","doi":"10.4018/979-8-3693-7668-3.ch015","title":"Harnessing Predictive Analytics for Workforce Optimization in a Transhuman Age","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in human resources management and organizational development book series","topic":"Reinforcement Learning in Robotics","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":"Yorkville University","funders":"","keywords":"Workforce; Analytics; Predictive analytics; Computer science; Data science; Political science","score_opus":0.012570200725336402,"score_gpt":0.23227836975743946,"score_spread":0.21970816903210305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401883986","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000017854933,0.0051436615,0.75623465,0.00012524184,0.00020915273,0.000992109,0.0000044017397,0.00018470493,0.23708822],"genre_scores_gemma":[0.0021958638,0.008954205,0.10684698,0.0001903093,0.00012139447,0.00012040625,0.00052109297,0.00014338281,0.88090634],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976769,0.000014597052,0.00075132056,0.0007538312,0.00048055884,0.00032276218],"domain_scores_gemma":[0.99929464,0.00006211023,0.00025096576,0.00024821627,0.00008888045,0.000055172502],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00022754341,0.0004422046,0.0003826553,0.00082538597,0.0002938477,0.00045157628,0.0005487951,0.00015565853,0.000058900434],"category_scores_gemma":[0.000011533374,0.00047955467,0.000044274555,0.00027222044,0.00015260992,0.001353995,0.00039429238,0.00025196778,0.0000053290128],"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":[0.000015035367,0.000008541936,0.00024666567,0.00045649792,0.000053731354,0.00003324077,0.0016478987,0.49062073,3.5030425e-7,0.5057898,0.00004565298,0.0010818562],"study_design_scores_gemma":[0.0008192461,0.00011652137,0.0005674394,0.00241355,0.00007768266,0.0000053430526,0.00017485121,0.064486384,0.00001762432,0.05386032,0.87642556,0.0010355006],"about_ca_topic_score_codex":3.4411082e-7,"about_ca_topic_score_gemma":0.000027068469,"teacher_disagreement_score":0.8763799,"about_ca_system_score_codex":0.00026921625,"about_ca_system_score_gemma":0.000044923872,"threshold_uncertainty_score":0.99976563},"labels":[],"label_agreement":null},{"id":"W4401911421","doi":"10.1080/09515089.2024.2393681","title":"Debt-free intelligence: ecological information in minds and machines","year":2024,"lang":"en","type":"article","venue":"Philosophical Psychology","topic":"Reinforcement Learning in Robotics","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":"Western University; University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Cognitive science; Ecology; Biology","score_opus":0.03319261259617537,"score_gpt":0.3323698577306866,"score_spread":0.29917724513451127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401911421","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":[0.006742903,0.00032648572,0.85987395,0.11369178,0.00088750786,0.00017421019,0.000001065388,0.00023891263,0.018063169],"genre_scores_gemma":[0.9882336,0.00008530918,0.0088693565,0.0026554437,0.00010916887,0.000016793647,0.0000037666007,0.0000052314604,0.00002132143],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987896,0.000082512306,0.00037783117,0.0003146328,0.00017331721,0.00026210817],"domain_scores_gemma":[0.99917185,0.00023881071,0.000038164973,0.00044320113,0.000025123152,0.00008286925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037209628,0.00013578567,0.00015989669,0.00029623802,0.00004101847,0.00015573275,0.0007924052,0.00019597987,0.000060141298],"category_scores_gemma":[0.00027949276,0.000112162124,0.000036493755,0.00044107356,0.0001553275,0.0005848688,0.00040151764,0.0004915523,0.0002357109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017294939,0.00004599719,0.0012853543,0.000037385904,0.000013840424,0.00007519326,0.000527085,0.0063525317,0.000024748624,0.8929522,0.0008119384,0.0978564],"study_design_scores_gemma":[0.00015930839,0.00020443727,0.009030313,0.000017321567,0.0000025937914,0.00008589954,0.0000027303718,0.37850752,0.0000066670123,0.60910684,0.0027490787,0.00012732173],"about_ca_topic_score_codex":0.00000404433,"about_ca_topic_score_gemma":0.0000018155622,"teacher_disagreement_score":0.98149073,"about_ca_system_score_codex":0.000028355864,"about_ca_system_score_gemma":0.000022491531,"threshold_uncertainty_score":0.45738387},"labels":[],"label_agreement":null},{"id":"W4401971650","doi":"10.1016/j.nlm.2024.107974","title":"A bio-inspired reinforcement learning model that accounts for fast adaptation after punishment","year":2024,"lang":"en","type":"article","venue":"Neurobiology of Learning and Memory","topic":"Reinforcement Learning in Robotics","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 Lethbridge; Mount Royal University","funders":"","keywords":"Reinforcement learning; Punishment (psychology); Adaptation (eye); Reinforcement; Artificial intelligence; Learning rule; Action (physics); Computer science; Psychology; Machine learning; Cognitive psychology; Artificial neural network; Cognitive science; Neuroscience; Social psychology","score_opus":0.02508569619655849,"score_gpt":0.25931858521347206,"score_spread":0.23423288901691358,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401971650","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":[0.08286841,0.00030238068,0.9144928,0.0004337201,0.0005042536,0.00032420157,0.0000010762465,0.00028544336,0.000787753],"genre_scores_gemma":[0.98547584,0.0002179417,0.008527992,0.00015173768,0.000045684716,0.00006868882,0.000021356745,0.000024221988,0.005466531],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985077,0.000117450145,0.00033030758,0.0005067187,0.00017618228,0.0003616897],"domain_scores_gemma":[0.99921894,0.00025747906,0.00016767578,0.00020771986,0.0000785169,0.00006968919],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004795923,0.00021443765,0.00025296098,0.00022811636,0.00017715173,0.00012077689,0.00026837084,0.00013346359,0.000010440929],"category_scores_gemma":[0.00009909277,0.00019901736,0.000099029035,0.0001474433,0.00011491878,0.0003223384,0.00022273308,0.00042643823,0.00001294063],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004170947,0.0000084848525,0.00065057224,0.00015848686,0.000037485115,0.000004156499,0.0021311303,0.98024684,0.00229437,0.0008184466,0.00008779423,0.013520492],"study_design_scores_gemma":[0.00037892343,0.0005967992,0.00026941817,0.00010890208,0.000030407527,0.0000108761915,0.00019718923,0.9906067,0.0014835428,0.00006614609,0.0060596312,0.00019141553],"about_ca_topic_score_codex":0.0000057498332,"about_ca_topic_score_gemma":9.073274e-7,"teacher_disagreement_score":0.9059648,"about_ca_system_score_codex":0.00003555101,"about_ca_system_score_gemma":0.00008938943,"threshold_uncertainty_score":0.8115692},"labels":[],"label_agreement":null},{"id":"W4402210774","doi":"10.1007/978-3-031-70903-6_16","title":"How to Better Fit Reinforcement Learning for Pentesting: A New Hierarchical Approach","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Machine learning","score_opus":0.03748018830220856,"score_gpt":0.26538449634167427,"score_spread":0.2279043080394657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402210774","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":[0.0000049324017,0.00014603903,0.9842208,0.0069440617,0.0016466198,0.0012730624,8.698652e-7,0.00040310362,0.005360494],"genre_scores_gemma":[0.02029405,0.000008970966,0.9358998,0.0028065445,0.0013817346,0.00005228753,0.000017071956,0.000097933276,0.03944161],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99420637,0.000026941063,0.00067734974,0.0022834707,0.0015787234,0.0012271302],"domain_scores_gemma":[0.99678403,0.00076334475,0.0002954463,0.0014113628,0.00024463583,0.0005011819],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010141964,0.00080095767,0.00068261696,0.0012657135,0.00037700107,0.0029208185,0.004173579,0.0003467645,0.000011893709],"category_scores_gemma":[0.0005012696,0.0007334244,0.00027446725,0.0008642529,0.00031363463,0.00061339076,0.002939074,0.0018204284,0.00008190775],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000057133175,0.0000064173196,0.000012563089,0.000110680456,0.000020000567,0.000024650008,0.0008369508,0.8483432,0.00003791574,0.024511477,0.00026651908,0.1258239],"study_design_scores_gemma":[0.0002730063,0.0005006066,0.000007016437,0.00053309515,0.000018725405,0.00005324405,3.569446e-7,0.9327112,0.00014519466,0.029412782,0.035554472,0.00079030625],"about_ca_topic_score_codex":0.000010992964,"about_ca_topic_score_gemma":0.0000040489717,"teacher_disagreement_score":0.1250336,"about_ca_system_score_codex":0.0004975828,"about_ca_system_score_gemma":0.0006945428,"threshold_uncertainty_score":0.99951166},"labels":[],"label_agreement":null},{"id":"W4402352014","doi":"10.1109/ijcnn60899.2024.10650768","title":"Conservative In-Distribution Q-Learning for Offline Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Distribution (mathematics); Reinforcement; Q-learning; Artificial intelligence; Machine learning; Engineering; Mathematics; Structural engineering","score_opus":0.02239324758151313,"score_gpt":0.2819598571834541,"score_spread":0.259566609601941,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402352014","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":[0.00092832494,0.000080699174,0.990263,0.0010098075,0.000362821,0.00036117047,3.8598623e-7,0.0005605489,0.0064332634],"genre_scores_gemma":[0.96164185,0.000032005682,0.015943233,0.00018653469,0.00007038907,0.0000659922,0.000110334666,0.000017168413,0.02193248],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984598,0.00007234428,0.00040119243,0.000393355,0.00027530326,0.00039800495],"domain_scores_gemma":[0.9990561,0.00048675644,0.00007810445,0.00019960194,0.00011689413,0.00006256639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061354163,0.00016569285,0.00017080536,0.00014758624,0.00015293296,0.00034606093,0.00036549638,0.000075151,0.00006512504],"category_scores_gemma":[0.00042962303,0.0001552802,0.00008167761,0.00061247393,0.00003357639,0.00058978336,0.00019257762,0.00043309253,0.000107997774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006626894,0.0000042548572,0.0005681082,0.000056632933,0.000017813521,0.000007807331,0.00039021685,0.8617268,0.00013512408,0.13232395,0.0011008393,0.0036617827],"study_design_scores_gemma":[0.00028556734,0.00024405515,0.00044183718,0.000097409626,0.000005000788,0.000004075858,0.00006890182,0.87756664,0.00049116835,0.00028432865,0.12034068,0.00017033197],"about_ca_topic_score_codex":0.00003423555,"about_ca_topic_score_gemma":0.000004996997,"teacher_disagreement_score":0.97431976,"about_ca_system_score_codex":0.00020253625,"about_ca_system_score_gemma":0.00012262221,"threshold_uncertainty_score":0.6332143},"labels":[],"label_agreement":null},{"id":"W4402353118","doi":"10.1109/cisce62493.2024.10653102","title":"Exploration of the Possibility for a Wider Range of the Discount Factor for Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Reinforcement; Range (aeronautics); Computer science; Factor (programming language); Artificial intelligence; Machine learning; Psychology; Engineering; Social psychology; Aerospace engineering; Programming language","score_opus":0.0494761660167853,"score_gpt":0.2979828257252523,"score_spread":0.24850665970846703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402353118","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":[0.005961839,0.000030159943,0.9903901,0.001321901,0.0006145237,0.0011737236,0.000003169336,0.000047857284,0.00045669734],"genre_scores_gemma":[0.9878234,0.0000033949586,0.006594393,0.00006956423,0.000030910363,0.00007718394,0.0000013396324,0.000008598074,0.0053911977],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887764,0.0000485964,0.0003772958,0.00020463034,0.0003319107,0.00015989486],"domain_scores_gemma":[0.99878156,0.00034955988,0.00017158885,0.00053581706,0.00014379366,0.000017683422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045358905,0.00009916408,0.00012683345,0.000032036205,0.00013264289,0.00009490874,0.00064456,0.000037724774,0.000016679316],"category_scores_gemma":[0.00030374769,0.000049852915,0.00020894731,0.00023674758,0.000064468586,0.0005448999,0.00023459786,0.000099430195,0.0000013592377],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001758576,0.0000131595225,0.0012331883,0.0003793097,0.000047074012,3.3007485e-8,0.0051480616,0.89572376,0.0013785328,0.09237392,0.00036358924,0.0033218],"study_design_scores_gemma":[0.00023791904,0.00015077018,0.0015140085,0.000097359974,0.000016810349,2.653226e-7,0.00015447714,0.98204976,0.0106959995,0.0014648753,0.0035389971,0.000078751975],"about_ca_topic_score_codex":0.000022278567,"about_ca_topic_score_gemma":0.0000095645055,"teacher_disagreement_score":0.98379576,"about_ca_system_score_codex":0.000059975227,"about_ca_system_score_gemma":0.0001120658,"threshold_uncertainty_score":0.20329428},"labels":[],"label_agreement":null},{"id":"W4402474348","doi":"10.1109/ccece59415.2024.10667224","title":"LLM4RL: Enhancing Reinforcement Learning with Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Western University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Human–computer interaction; Engineering","score_opus":0.010826491175834884,"score_gpt":0.24602232463981402,"score_spread":0.23519583346397913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402474348","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":[0.00088037987,0.00018432135,0.923036,0.00022360927,0.00020096124,0.00014287265,1.0023418e-7,0.0011859307,0.07414585],"genre_scores_gemma":[0.9292291,0.000018307075,0.03514673,0.0002781134,0.00006568448,0.000013770908,0.0000060838315,0.000024878665,0.03521733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983018,0.000037330145,0.00025309512,0.00040905696,0.0005089442,0.00048976805],"domain_scores_gemma":[0.99925727,0.00009417601,0.000048394973,0.00045581165,0.000047038164,0.00009729002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044723702,0.00018655643,0.00014656967,0.00016477446,0.00015816693,0.0005758511,0.0005315801,0.000051931685,0.00015821973],"category_scores_gemma":[0.0000218018,0.00014038272,0.00005593807,0.00046564682,0.000018519184,0.0011108431,0.00031883887,0.00036423383,0.0003385541],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018258899,0.0000038807934,0.000019835454,0.000039934588,0.000027681377,0.00006116562,0.0029357453,0.82542026,0.00034831936,0.1696953,0.00020480149,0.0012412494],"study_design_scores_gemma":[0.00016888797,0.00016041052,0.0000058709097,0.00012213399,0.000008464295,0.000020122316,0.00035690708,0.99028575,0.0023211124,0.00013843723,0.006189696,0.00022221253],"about_ca_topic_score_codex":0.000033369906,"about_ca_topic_score_gemma":0.000011718957,"teacher_disagreement_score":0.9283487,"about_ca_system_score_codex":0.00008418626,"about_ca_system_score_gemma":0.00009574617,"threshold_uncertainty_score":0.57246417},"labels":[],"label_agreement":null},{"id":"W4402474374","doi":"10.1109/ccece59415.2024.10667230","title":"Continuous Action Learning Automata: A Strategy for Dynamic Optimization of Invariant Kalman Filter Covariances","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Kalman filter; Learning automata; Automaton; Computer science; Invariant (physics); Control theory (sociology); Extended Kalman filter; Mathematical optimization; Artificial intelligence; Mathematics; Control (management)","score_opus":0.03360847323668419,"score_gpt":0.2998974205379099,"score_spread":0.2662889473012257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402474374","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":[0.00027744134,0.000051033203,0.99551165,0.00028229,0.00050770235,0.0002738935,0.0000011751961,0.0004787675,0.0026160418],"genre_scores_gemma":[0.7817357,0.00004041266,0.21254747,0.000037772206,0.00003579097,0.000025539888,0.000026920254,0.000015921914,0.0055344645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989555,0.000050909523,0.00030423992,0.00029190577,0.00019928851,0.0001981498],"domain_scores_gemma":[0.9993352,0.0001914894,0.000118692384,0.00022426166,0.00009656427,0.00003379139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034330043,0.00011738515,0.00015710399,0.00014246292,0.000086920336,0.00035185364,0.00032524494,0.00006909169,0.00005685544],"category_scores_gemma":[0.000074894546,0.000103859515,0.000063708256,0.00030632722,0.000027843329,0.0008031828,0.00008252293,0.00013453935,0.000015908716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000054446177,0.000008993996,0.000018094437,0.00011101446,0.00003256548,0.0000027707767,0.00017459199,0.9527302,0.000524427,0.03898971,0.00022280056,0.007179417],"study_design_scores_gemma":[0.00021519599,0.00028008912,0.00009073323,0.000073172574,0.00001431425,0.000009908558,0.00007224129,0.99710345,0.00044775815,0.00026827943,0.0013036196,0.00012123388],"about_ca_topic_score_codex":0.000022626375,"about_ca_topic_score_gemma":0.0000036322735,"teacher_disagreement_score":0.78296417,"about_ca_system_score_codex":0.00004923316,"about_ca_system_score_gemma":0.00009985879,"threshold_uncertainty_score":0.4235268},"labels":[],"label_agreement":null},{"id":"W4402550125","doi":"10.1098/rstb.2023.0416","title":"Elements of episodic memory: insights from artificial agents","year":2024,"lang":"en","type":"review","venue":"Philosophical Transactions of the Royal Society B Biological Sciences","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research","funders":"British Academy; UK Research and Innovation","keywords":"Episodic memory; Cognitive science; Computer science; Psychology; Cognitive psychology; Neuroscience; Cognition","score_opus":0.14850100404059183,"score_gpt":0.3432534744909159,"score_spread":0.1947524704503241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402550125","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000090190115,0.758414,0.23622562,0.0013550932,0.0018856784,0.00089259946,0.00009848826,0.00015793307,0.0008804069],"genre_scores_gemma":[0.05131763,0.9381339,0.0098541835,0.00014546515,0.0003164592,0.00006441752,0.000015783966,0.000021326612,0.00013085552],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960563,0.00042159786,0.0012744378,0.00086531404,0.0009863442,0.0003959903],"domain_scores_gemma":[0.9978842,0.00057267514,0.0006619379,0.00068635534,0.0000696354,0.00012518179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006070332,0.00044472085,0.0012628319,0.00007801725,0.00047252534,0.00011734323,0.004037928,0.0005299888,0.00011252382],"category_scores_gemma":[0.00010028664,0.00022253762,0.0021008744,0.001618288,0.0017652751,0.00013001419,0.00040175204,0.0009160045,0.000051566236],"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":[0.000014048867,0.0011151488,0.000048505484,0.006028198,0.0026823503,0.000008719994,0.0010677512,0.058240876,0.00004215631,0.086117595,0.000623023,0.8440116],"study_design_scores_gemma":[0.0005543566,0.0022689311,0.000080667734,0.0148489205,0.003995554,0.00001072465,0.000161606,0.43424705,0.00025989953,0.3613695,0.17946671,0.002736077],"about_ca_topic_score_codex":0.000050434766,"about_ca_topic_score_gemma":8.430491e-7,"teacher_disagreement_score":0.8412756,"about_ca_system_score_codex":0.00009608913,"about_ca_system_score_gemma":0.00023866292,"threshold_uncertainty_score":0.9074821},"labels":[],"label_agreement":null},{"id":"W4402596039","doi":"10.21203/rs.3.rs-4314484/v1","title":"On-policy Actor-Critic Reinforcement Learning for Multi-UAV Exploration","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","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 Regina","funders":"","keywords":"Reinforcement learning; Policy learning; Computer science; Reinforcement; Artificial intelligence; Psychology; Social psychology; Machine learning","score_opus":0.18191957642009787,"score_gpt":0.4539249079263171,"score_spread":0.27200533150621925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402596039","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":[0.00033339552,0.0002475957,0.98833007,0.0031774472,0.0010518125,0.0027251167,0.0000070307037,0.000654397,0.0034731398],"genre_scores_gemma":[0.94977313,0.00042012325,0.022943709,0.00016243906,0.0010723665,0.0019883183,0.00029906153,0.00014761808,0.023193229],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99376476,0.00055388495,0.00068972347,0.0013337255,0.0023118004,0.0013460893],"domain_scores_gemma":[0.99557036,0.0011794455,0.00018214893,0.0016561747,0.001090778,0.0003210884],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0028468645,0.0004898852,0.00044485103,0.0017489018,0.0006441653,0.002051524,0.0022002088,0.0004411205,0.00003916281],"category_scores_gemma":[0.0042020325,0.0004791894,0.00033969845,0.0010214048,0.00013606495,0.00041316095,0.00530884,0.003923276,0.00091744406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020923695,0.000037921727,0.000008435207,0.0018012947,0.00006239308,0.000019480185,0.001838867,0.83097744,0.000063813764,0.15822507,0.0024354148,0.004508956],"study_design_scores_gemma":[0.0004601771,0.0008375869,0.0000257683,0.0016752104,0.000010985447,0.0000017129923,0.00024027855,0.9671932,0.00049358926,0.018417744,0.010192253,0.00045151598],"about_ca_topic_score_codex":0.00013069123,"about_ca_topic_score_gemma":0.00000701592,"teacher_disagreement_score":0.96538633,"about_ca_system_score_codex":0.0012893237,"about_ca_system_score_gemma":0.0014823888,"threshold_uncertainty_score":0.99986047},"labels":[],"label_agreement":null},{"id":"W4402754120","doi":"10.1109/cvpr52733.2024.00042","title":"Quantifying Task Priority for Multi-Task Optimization","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development; National Research Foundation of Korea","keywords":"Computer science; Task (project management); Task analysis; Human–computer interaction; Systems engineering; Engineering","score_opus":0.07975036434683974,"score_gpt":0.3384239884084495,"score_spread":0.25867362406160976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402754120","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":[0.000055663586,0.0001057848,0.9968857,0.0003045078,0.00096358266,0.0002785557,8.345867e-7,0.0006705146,0.0007348183],"genre_scores_gemma":[0.13728015,0.000018690722,0.8597841,0.00013970071,0.000059303733,0.000016791331,0.000008225026,0.000012378321,0.0026805995],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908346,0.000020578693,0.00019216593,0.00031477297,0.00017184309,0.0002172026],"domain_scores_gemma":[0.99942976,0.00012216257,0.000033795277,0.00029983683,0.00006716611,0.000047291418],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029774045,0.00009947705,0.00008926517,0.00009384414,0.0001135472,0.00053259503,0.00040935128,0.00005253219,0.000017069235],"category_scores_gemma":[0.00009554717,0.000087621724,0.000063279134,0.00028376153,0.000015531514,0.0005843528,0.00013822947,0.0000973154,0.00007509078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[8.506209e-7,0.000007269905,0.00007941457,0.000056371417,0.000011948357,0.0000023155558,0.00024678864,0.9405119,0.00022143243,0.05401575,0.00056976726,0.004276185],"study_design_scores_gemma":[0.00014169473,0.000040415907,0.00004434762,0.000025055939,0.0000061068367,0.0000033099577,0.000009169051,0.99030155,0.00030939694,0.000033732456,0.008963899,0.00012131422],"about_ca_topic_score_codex":0.0000073857905,"about_ca_topic_score_gemma":0.0000015038597,"teacher_disagreement_score":0.1372245,"about_ca_system_score_codex":0.000045834116,"about_ca_system_score_gemma":0.000063342755,"threshold_uncertainty_score":0.51358265},"labels":[],"label_agreement":null},{"id":"W4402891929","doi":"10.1109/tro.2024.3468770","title":"Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Robotics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Cloning (programming); Robot; Computer science; Motion (physics); Motion planning; Movement (music); Artificial intelligence; Physics; Programming language","score_opus":0.06835264497984908,"score_gpt":0.3177744257784029,"score_spread":0.24942178079855384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402891929","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":[0.003652285,0.00005363506,0.9932698,0.0002831723,0.0011105768,0.0011054965,0.0000054025268,0.0004395275,0.00008011865],"genre_scores_gemma":[0.7871586,0.000020574078,0.21122646,0.00019051592,0.000027714763,0.00013943067,0.000007582877,0.000047882153,0.0011812288],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977111,0.000058686564,0.0005210499,0.0006915972,0.00042495283,0.0005926138],"domain_scores_gemma":[0.9989618,0.0002570988,0.000096967386,0.0003654767,0.000121238154,0.00019738519],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036645946,0.00034782282,0.00027594392,0.00048813486,0.00060043216,0.00051388744,0.0003128746,0.00011801916,0.0000067511824],"category_scores_gemma":[0.000016522768,0.00037548508,0.00014100115,0.00047319342,0.000042806732,0.0005442175,0.000019222347,0.00049144647,0.000020472975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015654541,0.00002752613,0.000016861715,0.00009346786,0.000071100876,0.000011966288,0.0019379108,0.9742511,0.008455491,0.0010342358,0.0000067680844,0.014077924],"study_design_scores_gemma":[0.00032280115,0.00058131723,0.00012675533,0.0002991245,0.00011652279,0.000017031194,0.00020738036,0.99299985,0.0047992766,0.00006207796,0.00007821134,0.00038962116],"about_ca_topic_score_codex":0.000029556919,"about_ca_topic_score_gemma":0.00000394457,"teacher_disagreement_score":0.78350633,"about_ca_system_score_codex":0.00048723444,"about_ca_system_score_gemma":0.00008023467,"threshold_uncertainty_score":0.9998697},"labels":[],"label_agreement":null},{"id":"W4403306447","doi":"10.1017/9781009302180.030","title":"Designing Dynamic Programming Algorithms via Reductions","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Computer science; Dynamic programming; Algorithm","score_opus":0.020499562192775475,"score_gpt":0.217772213590013,"score_spread":0.19727265139723754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403306447","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[4.1305432e-7,0.00010056607,0.5153124,0.000022276461,0.0006296034,0.00027596694,0.0000065966015,0.000533072,0.48311913],"genre_scores_gemma":[0.00017916542,0.00004542907,0.05099159,0.0000193882,0.000111342895,0.0000017498725,0.00002911826,0.00006529958,0.9485569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979122,0.00003105175,0.00027289515,0.00086802186,0.00045594608,0.0004598837],"domain_scores_gemma":[0.9983577,0.00006623013,0.00024605956,0.0009643568,0.00017035172,0.00019526482],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015943538,0.00045914177,0.00035521854,0.00042331993,0.00036569356,0.00035655647,0.0014487559,0.0003552857,0.000002039215],"category_scores_gemma":[0.0000074952413,0.00056459935,0.00027365232,0.00003773899,0.00021629962,0.00028854,0.0011677259,0.0009741419,0.00009596525],"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":[0.0000053929334,0.000005061694,1.4605435e-7,0.0001281777,0.0002530963,0.00058969227,0.00014653304,0.0051353923,0.000073781346,0.9746208,0.0031553116,0.015886586],"study_design_scores_gemma":[0.00017854363,0.00008722358,6.393117e-7,0.00035068957,0.00021694027,0.00010087604,0.00002535535,0.13881706,0.00012468506,0.000054299275,0.8594056,0.0006380967],"about_ca_topic_score_codex":0.000038867016,"about_ca_topic_score_gemma":4.6157197e-7,"teacher_disagreement_score":0.9745665,"about_ca_system_score_codex":0.0004896119,"about_ca_system_score_gemma":0.00016054977,"threshold_uncertainty_score":0.9996805},"labels":[],"label_agreement":null},{"id":"W4403429602","doi":"10.1145/3638530.3654415","title":"Generational Information Transfer with Neuroevolution on Control Tasks","year":2024,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Neuroevolution; Computer science; Control (management); Artificial intelligence; Artificial neural network","score_opus":0.0115250681987799,"score_gpt":0.2069122778195792,"score_spread":0.19538720962079928,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403429602","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":[0.078400195,0.000075936965,0.91823465,0.0016894911,0.00029480358,0.0003182642,0.0000049708015,0.000114272465,0.0008674274],"genre_scores_gemma":[0.9897164,0.000024964815,0.009931639,0.00018333798,0.000051039395,0.000017569322,0.000009211912,0.000006447408,0.000059398637],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987651,0.00002296265,0.0003169126,0.0002487046,0.00048733715,0.00015895098],"domain_scores_gemma":[0.99927753,0.00007548553,0.000088959845,0.00008949172,0.00041663548,0.000051917606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013913226,0.00015530999,0.00012982494,0.0001618563,0.0002164629,0.00028177095,0.00031195942,0.00005131758,0.000009106233],"category_scores_gemma":[0.000021569082,0.00011312003,0.000043799253,0.00035182337,0.00011348285,0.00091129343,0.00006284898,0.00016766811,0.000019880807],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043007047,0.000025359834,0.0027648662,0.000121927435,0.000040807667,3.4035037e-7,0.0006533072,0.75880843,0.0010217739,0.22536387,0.0015435998,0.009612711],"study_design_scores_gemma":[0.00035200134,0.00018410003,0.08282533,0.00013129984,0.000019504283,0.00004320388,0.000031077503,0.91272575,0.00018350675,0.0027622005,0.00061687845,0.00012512859],"about_ca_topic_score_codex":0.0000047648805,"about_ca_topic_score_gemma":2.992293e-7,"teacher_disagreement_score":0.9113162,"about_ca_system_score_codex":0.000055761753,"about_ca_system_score_gemma":0.00013245078,"threshold_uncertainty_score":0.4612901},"labels":[],"label_agreement":null},{"id":"W4403534366","doi":"10.1109/codit62066.2024.10708505","title":"Combining Dense and Sparse Rewards to Improve Deep Reinforcement Learning Policies in Reach-Avoid Games with Faster Evaders in Two vs. One Scenarios","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Royal Military College of Canada; Queen's University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Human–computer interaction; Psychology; Social psychology","score_opus":0.01728873881557427,"score_gpt":0.26571061302666155,"score_spread":0.24842187421108727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403534366","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":[0.2283738,0.00011582246,0.7630294,0.0023807373,0.0001984063,0.00062413944,1.1995603e-7,0.00030876705,0.004968803],"genre_scores_gemma":[0.97597414,0.00003609322,0.019724065,0.0009436496,0.000033384928,0.000042245465,0.0000026974753,0.000033252978,0.003210466],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974013,0.00011610973,0.0005365908,0.0006724984,0.0005643356,0.00070914504],"domain_scores_gemma":[0.99899304,0.00020302356,0.00008724924,0.00047888787,0.000059996848,0.00017778829],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008180325,0.00030765493,0.0003500469,0.0007277295,0.0000949125,0.00069601357,0.00046581612,0.00006753543,0.00002085898],"category_scores_gemma":[0.00013826435,0.00026980074,0.000037368554,0.00091589475,0.00008840823,0.0007248268,0.00060095685,0.0006530955,0.000050327613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046402165,0.00001699522,0.009320988,0.00009139796,0.000029699862,0.00007183191,0.02053024,0.9586486,0.00075415644,0.0055880444,0.00004481427,0.004856793],"study_design_scores_gemma":[0.0010767473,0.000754325,0.0032887722,0.0006608948,0.000012088022,0.000025289604,0.0018997279,0.9902411,0.000782813,0.000060828996,0.0007686502,0.00042877442],"about_ca_topic_score_codex":0.0012437971,"about_ca_topic_score_gemma":0.00070181396,"teacher_disagreement_score":0.7476004,"about_ca_system_score_codex":0.0002533821,"about_ca_system_score_gemma":0.00012962351,"threshold_uncertainty_score":0.99997544},"labels":[],"label_agreement":null},{"id":"W4403577538","doi":"10.48550/arxiv.2410.12062","title":"MFC-EQ: Mean-Field Control with Envelope Q-Learning for Moving Decentralized Agents in Formation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Envelope (radar); Mean field theory; Field (mathematics); Control (management); Decentralised system; Physics; Computer science; Mathematics; Artificial intelligence; Telecommunications; Pure mathematics; Condensed matter physics","score_opus":0.06673068477514002,"score_gpt":0.20929395275910592,"score_spread":0.1425632679839659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403577538","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":[0.048281923,0.000036861707,0.9484831,0.00016824361,0.00040206162,0.00080449757,0.0000019884633,0.00027393,0.0015473968],"genre_scores_gemma":[0.99260265,0.000110228335,0.005764163,0.00016774336,0.00003234901,0.0000065167947,0.000021875341,0.000028648243,0.0012658424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980502,0.00013992729,0.00033165643,0.00079629413,0.00016584019,0.0005160595],"domain_scores_gemma":[0.99851805,0.00030396145,0.00032681032,0.00058370584,0.00014655387,0.00012093948],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044824358,0.0003347008,0.00037506755,0.00044085114,0.00014841006,0.00031892245,0.0011712224,0.00026098287,0.000018424236],"category_scores_gemma":[0.00012450297,0.00035213926,0.00015332553,0.0005586609,0.00003333009,0.0005464137,0.0010049554,0.00094235264,0.000051514053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008995103,0.000015978372,0.0026590526,0.0002362732,0.00008438368,0.00011436491,0.0008732788,0.97014046,0.000012551701,0.025091305,0.00011166219,0.0005707389],"study_design_scores_gemma":[0.0015724988,0.00014308651,0.00035985105,0.0004222236,0.00007702156,0.0000036515291,0.00012388034,0.9928536,0.00013032518,0.0029420722,0.00096678647,0.00040500477],"about_ca_topic_score_codex":0.00009251073,"about_ca_topic_score_gemma":0.000065581444,"teacher_disagreement_score":0.94432074,"about_ca_system_score_codex":0.0004232533,"about_ca_system_score_gemma":0.00021122425,"threshold_uncertainty_score":0.99989307},"labels":[],"label_agreement":null},{"id":"W4403702578","doi":"10.48550/arxiv.2409.10096","title":"Robust Reinforcement Learning with Dynamic Distortion Risk Measures","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Reinforcement; Distortion (music); Computer science; Artificial intelligence; Psychology; Social psychology; Telecommunications","score_opus":0.052434498711610086,"score_gpt":0.1774675049997577,"score_spread":0.12503300628814762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403702578","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":[0.021217389,0.00010476184,0.97209466,0.00005738919,0.0007285826,0.00037289265,0.0000019276197,0.0008035357,0.00461889],"genre_scores_gemma":[0.9836692,0.00048671226,0.0027487618,0.000021516787,0.00004871909,0.0000023767345,0.00003665828,0.000044358127,0.012941671],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973621,0.00020263647,0.00030922252,0.0013138927,0.00031936337,0.00049281487],"domain_scores_gemma":[0.9977206,0.00010356309,0.0005268034,0.0012701184,0.00020061579,0.00017828467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004652517,0.00047591707,0.0003610263,0.00041454102,0.00033134146,0.00038428203,0.0015551766,0.0002759774,0.00002270236],"category_scores_gemma":[0.000082792954,0.00047812957,0.00021480858,0.00069741777,0.00012866747,0.0003288947,0.0026904596,0.002026927,0.0002612682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027261887,0.000014078753,0.0016086205,0.000110104345,0.00020982925,0.00020849441,0.0003565115,0.98198557,0.000004578091,0.01459169,0.00006555503,0.0008176956],"study_design_scores_gemma":[0.00030152628,0.00018972681,0.0004062285,0.0002838966,0.0002219973,0.0000047910667,0.000078040146,0.9949169,0.000018779663,0.002089095,0.00091282,0.00057619053],"about_ca_topic_score_codex":0.0001982544,"about_ca_topic_score_gemma":0.000061777944,"teacher_disagreement_score":0.96934587,"about_ca_system_score_codex":0.00084806903,"about_ca_system_score_gemma":0.00029137853,"threshold_uncertainty_score":0.99976707},"labels":[],"label_agreement":null},{"id":"W4403760022","doi":"10.1016/j.brachy.2024.08.113","title":"PSOR03 Presentation Time: 11:40 AM","year":2024,"lang":"en","type":"article","venue":"Brachytherapy","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; Centre hospitalier de l'Université Laval; Centre hospitalier universitaire de Québec","funders":"","keywords":"Medicine; Presentation (obstetrics); Surgery","score_opus":0.012872976264696955,"score_gpt":0.2754509554621671,"score_spread":0.2625779791974701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403760022","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":[0.005833251,0.0005165939,0.98254526,0.0017912537,0.00094327587,0.00026095018,4.5820033e-7,0.00076592684,0.0073430147],"genre_scores_gemma":[0.7575089,0.00049981725,0.09530075,0.0029529296,0.0012594066,0.00014129342,0.000042195963,0.00012191707,0.14217281],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885976,0.000066150984,0.00020628604,0.00031078377,0.00032999006,0.00022702552],"domain_scores_gemma":[0.9993028,0.00013567797,0.000047045603,0.00042372997,0.000035989236,0.000054745255],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023349578,0.0001258112,0.00012603577,0.00012277313,0.00007978488,0.00053169753,0.00048612113,0.00005338109,0.00021739474],"category_scores_gemma":[0.000020330153,0.00011021001,0.000084068146,0.00039238145,0.00002787508,0.0007006756,0.00006510709,0.0001304435,0.0014647507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063075066,0.00010558787,0.0017793024,0.00014252347,0.0002605558,0.00017690941,0.0052089384,0.38132194,0.010543468,0.20328787,0.116011254,0.28109857],"study_design_scores_gemma":[0.00038606164,0.000093806455,0.0012706937,0.000031690928,0.0000050316303,0.000019087222,0.0000063938996,0.87527335,0.0009137082,0.0010815802,0.12075237,0.00016623929],"about_ca_topic_score_codex":0.000007934944,"about_ca_topic_score_gemma":9.662849e-7,"teacher_disagreement_score":0.8872445,"about_ca_system_score_codex":0.000037773563,"about_ca_system_score_gemma":0.000058330217,"threshold_uncertainty_score":0.9993127},"labels":[],"label_agreement":null},{"id":"W4403793598","doi":"10.1007/978-3-031-75872-0_10","title":"Model-Driven Design and Generation of Training Simulators for Reinforcement Learning","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Regina; University of Toronto; York University","funders":"","keywords":"Computer science; Reinforcement learning; Training (meteorology); Artificial intelligence; Human–computer interaction; Simulation","score_opus":0.07555659613702641,"score_gpt":0.27975780820531954,"score_spread":0.20420121206829311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403793598","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":[0.0000375762,0.00016719292,0.99771506,0.00012945304,0.00065159204,0.00068411283,6.776695e-7,0.00011032418,0.0005039929],"genre_scores_gemma":[0.3517327,0.000031697724,0.6470833,0.00013423534,0.00015335645,0.000011496524,0.0000054853454,0.000030880557,0.0008168478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972311,0.000021298965,0.00060450356,0.0009884302,0.0007028051,0.0004518252],"domain_scores_gemma":[0.99830186,0.0005099087,0.00033102187,0.00053754373,0.0002157517,0.00010391543],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010052565,0.00038959773,0.0004478777,0.0006741695,0.00021093953,0.0003929912,0.0010816484,0.00023152884,0.0000027598542],"category_scores_gemma":[0.00011463027,0.00037041647,0.00010127953,0.0002818821,0.00031420408,0.00043443494,0.00066609087,0.00054618984,0.0000032370042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033001281,0.0000019066154,0.0000029923447,0.00007068712,0.000014672445,0.0000035053947,0.0021236741,0.91840947,0.00035796606,0.033758666,0.0000039125566,0.045249272],"study_design_scores_gemma":[0.00019899767,0.00034770495,6.0003515e-7,0.00032779222,0.000017415556,0.000007476012,3.7309366e-7,0.97694755,0.00091699796,0.020680035,0.00019670498,0.00035835413],"about_ca_topic_score_codex":0.0000018075543,"about_ca_topic_score_gemma":0.0000016561588,"teacher_disagreement_score":0.35169512,"about_ca_system_score_codex":0.00018395719,"about_ca_system_score_gemma":0.00041783712,"threshold_uncertainty_score":0.9998748},"labels":[],"label_agreement":null},{"id":"W4403906488","doi":"10.1007/978-3-031-73033-7_9","title":"Learning to Drive via Asymmetric Self-Play","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Human–computer interaction; Artificial intelligence","score_opus":0.00983572967448916,"score_gpt":0.23941293751926895,"score_spread":0.2295772078447798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403906488","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":[0.00001758368,0.00026139343,0.97258306,0.00078811083,0.0037153286,0.0005282825,8.8718485e-7,0.000827196,0.021278143],"genre_scores_gemma":[0.12667164,0.00006342736,0.8597542,0.002436509,0.0010272232,0.000020652993,0.0000072411904,0.00013536762,0.009883733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99412036,0.00004372432,0.0007070813,0.0022297557,0.0018184024,0.0010806815],"domain_scores_gemma":[0.99673945,0.00074011163,0.00028609304,0.0015496142,0.0003097407,0.00037500434],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012048571,0.0007622988,0.00064573233,0.0030042413,0.00036024788,0.001479997,0.0048223403,0.00041339963,0.00002610008],"category_scores_gemma":[0.00021877646,0.0007209025,0.00019814595,0.0028073124,0.0002655677,0.0006068602,0.0035797283,0.002198316,0.0014576245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013351486,0.000007801553,0.00003170535,0.000040946878,0.00002158109,0.00013821562,0.0016681413,0.7821914,0.000032602697,0.012486066,0.000038288206,0.20334195],"study_design_scores_gemma":[0.00012817718,0.0005204755,0.000047147078,0.00042154428,0.000018257953,0.000088134024,2.6180274e-7,0.9589888,0.00040290097,0.023022102,0.015473565,0.00088863005],"about_ca_topic_score_codex":0.000015464422,"about_ca_topic_score_gemma":0.0000096322565,"teacher_disagreement_score":0.20245332,"about_ca_system_score_codex":0.0007833436,"about_ca_system_score_gemma":0.0004981015,"threshold_uncertainty_score":0.99955654},"labels":[],"label_agreement":null},{"id":"W4403935894","doi":"10.1145/3652620.3676878","title":"Towards Model Repair by Human Opinion--Guided Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McMaster University","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Human–computer interaction; Engineering; Structural engineering","score_opus":0.037632307705128265,"score_gpt":0.3118472252698286,"score_spread":0.27421491756470034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403935894","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":[0.00013005798,0.00015543815,0.8770303,0.0006579119,0.00050617335,0.00016610665,2.366766e-7,0.0025968682,0.11875687],"genre_scores_gemma":[0.75584394,0.00010934555,0.09273491,0.00084148906,0.00016817906,0.000042940006,0.000050221064,0.000055401215,0.15015356],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779475,0.000049240334,0.00048826094,0.0005756591,0.0006315907,0.0004605095],"domain_scores_gemma":[0.9990118,0.000046706635,0.00006910231,0.0006586007,0.00007389968,0.00013990005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005511533,0.00023735175,0.00018438636,0.00016664618,0.00027207646,0.0005615367,0.000853961,0.00009055214,0.0001614399],"category_scores_gemma":[0.000052214356,0.00021393872,0.00017646581,0.00039586445,0.00004170812,0.00075608486,0.0005856923,0.000398566,0.00033069224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.5776667e-7,0.000004780109,0.000017545552,0.000039034603,0.000029878154,0.000003798047,0.0003319,0.74216497,0.0004358016,0.17981653,0.07633061,0.0008247086],"study_design_scores_gemma":[0.0001278768,0.00012447809,0.000006778143,0.000060972146,0.000005334046,0.0000066665807,0.000017527078,0.925166,0.0006729221,0.0006596722,0.0728878,0.00026393947],"about_ca_topic_score_codex":0.000059502767,"about_ca_topic_score_gemma":3.8719253e-7,"teacher_disagreement_score":0.78429544,"about_ca_system_score_codex":0.00016160867,"about_ca_system_score_gemma":0.00013840274,"threshold_uncertainty_score":0.8724168},"labels":[],"label_agreement":null},{"id":"W4404299250","doi":"10.2139/ssrn.4978973","title":"Ill-Posedness Evolved in the Deep: Adaptive Evolutionary Latent Optimization, An Application to Recovering Volatility","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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":"York University","funders":"","keywords":"Adaptive evolution; Volatility (finance); Econometrics; Economics; Mathematical optimization; Computer science; Artificial intelligence; Mathematics; Biology","score_opus":0.014087244054025633,"score_gpt":0.25577106849866643,"score_spread":0.2416838244446408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404299250","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":[0.005135755,0.0010594481,0.9903893,0.0015479913,0.0006907398,0.00080887496,0.0000019256472,0.0001231439,0.00024283364],"genre_scores_gemma":[0.95771694,0.00058437826,0.040717803,0.0002392343,0.00033974455,0.00012040013,0.000036236735,0.000040020674,0.0002052094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959556,0.00040661707,0.0006674088,0.00073225837,0.000737627,0.0015004863],"domain_scores_gemma":[0.99809283,0.00009086228,0.00034497314,0.000982189,0.00037908397,0.00011005907],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0033686338,0.0003371472,0.0002820461,0.0003568173,0.00026289915,0.000485208,0.0024115937,0.00022407767,0.0000065248855],"category_scores_gemma":[0.00011697962,0.0002815359,0.00014430504,0.00071899564,0.00003448575,0.0004221476,0.0010663812,0.0048708986,0.000032633674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023086533,0.000041029878,0.0003897635,0.000017663555,0.00006404124,0.0000035025082,0.0014968003,0.95551574,0.000006860279,0.036278397,0.000019802934,0.0061433394],"study_design_scores_gemma":[0.00013546817,0.00021481786,0.0011253066,0.00008386175,0.000025871836,0.00007628648,0.00039287208,0.8914801,0.0000021892993,0.1061041,0.00008993394,0.00026920982],"about_ca_topic_score_codex":0.00014531973,"about_ca_topic_score_gemma":0.0003105251,"teacher_disagreement_score":0.9525812,"about_ca_system_score_codex":0.003547895,"about_ca_system_score_gemma":0.00280348,"threshold_uncertainty_score":0.9999637},"labels":[],"label_agreement":null},{"id":"W4404317069","doi":"10.1109/tse.2024.3470368","title":"Scoping Software Engineering for AI: The TSE Perspective","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Software Engineering","topic":"Reinforcement Learning in Robotics","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; University of Alberta; Queen's University; University of Toronto","funders":"","keywords":"Computer science; Software engineering; Perspective (graphical); Software development; Software; Programming language; Artificial intelligence","score_opus":0.013694603385929241,"score_gpt":0.25763863923195046,"score_spread":0.24394403584602123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404317069","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":[0.00015571564,0.0004408632,0.9925846,0.0002926887,0.0032400724,0.0005796221,0.0000097175225,0.0026874326,0.000009302154],"genre_scores_gemma":[0.5478389,0.000058958227,0.44999886,0.00027351972,0.00037057998,0.0005647391,0.0000028735744,0.00017598267,0.0007155758],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838483,0.000014779666,0.00028649796,0.00049295294,0.0003299551,0.00049100566],"domain_scores_gemma":[0.9981085,0.0010861016,0.000029719391,0.00055663835,0.00011781626,0.00010119823],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00024796466,0.00031008304,0.00020761736,0.00032117666,0.0002627008,0.0004981641,0.0006504456,0.0001065934,0.00001748213],"category_scores_gemma":[0.00018227765,0.00027450183,0.00024113167,0.0006763317,0.00002216433,0.00063731,0.000008562674,0.0006413088,0.00005036776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000025760373,0.00001094269,0.0000023279465,0.00026923127,0.000089701665,0.000008806268,0.0008359654,0.99357617,0.00009763076,0.003206676,0.000092824375,0.0018071622],"study_design_scores_gemma":[0.00016807314,0.00009428107,0.000018891506,0.0010026821,0.000032032658,0.000028801343,0.000036537192,0.9927422,0.0036039688,0.000029546734,0.0018948532,0.00034816482],"about_ca_topic_score_codex":0.0000082167735,"about_ca_topic_score_gemma":0.0000012433494,"teacher_disagreement_score":0.5476832,"about_ca_system_score_codex":0.00031761595,"about_ca_system_score_gemma":0.0001145047,"threshold_uncertainty_score":0.99997073},"labels":[],"label_agreement":null},{"id":"W4404535976","doi":"10.3390/e26110995","title":"Information-Theoretic Generalization Bounds for Batch Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"Entropy","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Generalization; Reinforcement learning; Computer science; Information theory; Generalization error; Artificial intelligence; Prior information; Machine learning; Mathematics; Mathematical optimization; Unsupervised learning; Statistics","score_opus":0.008531388615068268,"score_gpt":0.24575923156269766,"score_spread":0.23722784294762939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404535976","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":[0.00032304958,0.00008718086,0.99252546,0.00076075573,0.0011209488,0.00030432752,4.8571934e-7,0.00049280445,0.00438496],"genre_scores_gemma":[0.94403803,0.000087694236,0.048148505,0.000585086,0.00027490937,0.00010344742,0.00013875133,0.000023459992,0.006600115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988223,0.00003468555,0.0003385514,0.0001608094,0.00033601496,0.00030766168],"domain_scores_gemma":[0.99936193,0.00011016853,0.00008396658,0.00027797287,0.00010092335,0.0000650506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003316423,0.00013749552,0.00010571788,0.00017382474,0.00021101783,0.00097275386,0.00040742636,0.000055938424,0.00009084577],"category_scores_gemma":[0.00014166393,0.0001288467,0.000082332364,0.00033263743,0.000029691268,0.0013456795,0.000119367825,0.00014424362,0.00033885305],"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":[0.0000020337209,0.0000012459052,0.000025644682,0.00004743548,0.0000127784115,5.289669e-7,0.0008578593,0.49530742,0.000054768014,0.49946657,0.0023523003,0.0018714042],"study_design_scores_gemma":[0.0001726649,0.0001099557,0.000017214701,0.000031084906,0.000008845355,0.0000033245888,0.000028386103,0.7784509,0.00043814938,0.0024033242,0.21821102,0.0001251027],"about_ca_topic_score_codex":0.0000049177956,"about_ca_topic_score_gemma":1.3084147e-7,"teacher_disagreement_score":0.944377,"about_ca_system_score_codex":0.0001265285,"about_ca_system_score_gemma":0.000090133195,"threshold_uncertainty_score":0.93802875},"labels":[],"label_agreement":null},{"id":"W4404688444","doi":"10.1109/tnnls.2024.3496492","title":"GenSafe: A Generalizable Safety Enhancer for Safe Reinforcement Learning Algorithms Based on Reduced Order Markov Decision Process Model","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"JST-Mirai Program; Natural Sciences and Engineering Research Council of Canada; Grant Foundation","keywords":"Markov decision process; Reinforcement learning; Computer science; Process (computing); Order (exchange); Machine learning; Markov process; Markov chain; Algorithm; Artificial intelligence; Mathematics; Business; Programming language; Statistics","score_opus":0.017102101971001402,"score_gpt":0.2699021736160693,"score_spread":0.25280007164506785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404688444","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":[0.0010497111,0.0003214628,0.9942598,0.00022176103,0.0022609117,0.0009769577,0.000002218709,0.0005673987,0.00033982808],"genre_scores_gemma":[0.97743416,0.00018270506,0.012759485,0.00018522577,0.0002508545,0.0002875197,0.00001734728,0.00008756954,0.00879513],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99661976,0.0002663509,0.0007417957,0.0009718071,0.000670812,0.00072948734],"domain_scores_gemma":[0.9981196,0.00080923724,0.00020127102,0.00044427134,0.0002179352,0.00020771168],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009948565,0.00047745655,0.0004470652,0.00034011618,0.0012190295,0.00086545554,0.00042651335,0.00024449863,0.00002115617],"category_scores_gemma":[0.000035149977,0.00042139244,0.00019224027,0.0007934652,0.000051110812,0.00048715717,0.000008938309,0.0013230942,0.000012098849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000173629,0.000024122568,0.0000022301485,0.00018333124,0.000057124806,0.000008067149,0.00032325325,0.96352404,0.00012246321,0.00014619541,0.00020584767,0.03522969],"study_design_scores_gemma":[0.0007578419,0.0008451684,0.000002133513,0.0006644305,0.00004887924,0.000018875364,0.00006180526,0.99442273,0.00018980843,0.0000064430888,0.002503985,0.00047791345],"about_ca_topic_score_codex":0.000029448884,"about_ca_topic_score_gemma":0.0000018323033,"teacher_disagreement_score":0.98150027,"about_ca_system_score_codex":0.00018225264,"about_ca_system_score_gemma":0.00012637385,"threshold_uncertainty_score":0.9998238},"labels":[],"label_agreement":null},{"id":"W4404815779","doi":"10.1093/pnasnexus/pgae540","title":"Modeling long-term nutritional behaviors using deep homeostatic reinforcement learning","year":2024,"lang":"en","type":"article","venue":"PNAS Nexus","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"Japan Society for the Promotion of Science; Japan Society for the Promotion of Science London; Japan Agency for Medical Research and Development","keywords":"Term (time); Reinforcement; Reinforcement learning; Psychology; Cognitive psychology; Computer science; Artificial intelligence; Social psychology; Physics","score_opus":0.034082258426414075,"score_gpt":0.2961966146611672,"score_spread":0.2621143562347531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404815779","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":[0.048547316,0.00069753546,0.94837785,0.00010709137,0.0008479847,0.00021921823,3.8550695e-7,0.00050476944,0.0006978334],"genre_scores_gemma":[0.97401595,0.00004485114,0.024821168,0.00009824531,0.00016054127,0.000020572461,0.000031615178,0.000036633228,0.0007704153],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775106,0.000065590044,0.00046560616,0.00049772556,0.00068674807,0.0005332874],"domain_scores_gemma":[0.9991875,0.00010671399,0.00007059146,0.00039114754,0.00009801062,0.00014600699],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003164302,0.00024768285,0.00020132617,0.00030810156,0.00030632317,0.00079558283,0.00060750765,0.00008464452,0.00009233502],"category_scores_gemma":[0.00005399047,0.0002584093,0.00012744676,0.0005254742,0.000041888914,0.0009148838,0.0003384818,0.00048319894,0.00018847751],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027894446,0.0000145113445,0.0005023884,0.00010861879,0.000030467954,0.00012698887,0.00083378697,0.9886747,0.0003087318,0.0063687195,0.000010856301,0.0030174619],"study_design_scores_gemma":[0.00021862648,0.000095508614,0.000109634704,0.00027018212,0.000037385515,0.00007693042,0.000041447343,0.9983129,0.000112608206,0.00029747572,0.00012842003,0.000298868],"about_ca_topic_score_codex":0.000030675405,"about_ca_topic_score_gemma":0.0000018800165,"teacher_disagreement_score":0.9254686,"about_ca_system_score_codex":0.00026484698,"about_ca_system_score_gemma":0.00013712766,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W4404864837","doi":"10.1016/j.iot.2024.101447","title":"Adaptive target localization under uncertainty using Multi-Agent Deep Reinforcement Learning with knowledge transfer","year":2024,"lang":"en","type":"article","venue":"Internet of Things","topic":"Reinforcement Learning in Robotics","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":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Transfer of learning; Knowledge transfer; Machine learning; Reinforcement; Knowledge management; Psychology; Social psychology","score_opus":0.03181315952003095,"score_gpt":0.27215590146951923,"score_spread":0.2403427419494883,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404864837","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":[0.002121664,0.0002816813,0.9955448,0.00005773412,0.00035083163,0.00023184059,1.3384795e-7,0.0002524864,0.0011588184],"genre_scores_gemma":[0.948199,0.000010101824,0.04883598,0.00013538885,0.00002839738,0.000007020275,0.00000790201,0.000030350971,0.0027458745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983236,0.000092975526,0.00042862192,0.00042253727,0.00041627238,0.00031594705],"domain_scores_gemma":[0.9992779,0.00009667114,0.00009007637,0.00026817346,0.00018577777,0.00008143492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036524836,0.00023940767,0.00023159594,0.00021867175,0.0000748799,0.00022554175,0.000587676,0.000088768495,0.00006787119],"category_scores_gemma":[0.00002805003,0.00019891026,0.000099090634,0.0004022272,0.00009514717,0.0008087065,0.00021117234,0.00036409422,0.000042516334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022193643,0.000021865622,0.000113686256,0.00009976851,0.00012937063,0.000011379221,0.014885773,0.9694164,0.0002487451,0.014232264,0.000039219223,0.00077935297],"study_design_scores_gemma":[0.0003292278,0.0003785714,0.000015138465,0.0005844649,0.000033607772,0.000013606653,0.00031708102,0.9935063,0.0024649235,0.000083717,0.002033628,0.0002397079],"about_ca_topic_score_codex":0.00025715542,"about_ca_topic_score_gemma":0.000008086403,"teacher_disagreement_score":0.9467088,"about_ca_system_score_codex":0.00029282423,"about_ca_system_score_gemma":0.000118612,"threshold_uncertainty_score":0.8111325},"labels":[],"label_agreement":null},{"id":"W4404954737","doi":"10.1109/ssrr62954.2024.10770028","title":"Monte Carlo Tree Search for Behavior Planning in Autonomous Driving","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Monte Carlo tree search; Monte Carlo method; Computer science; Tree (set theory); Artificial intelligence; Mathematics; Statistics","score_opus":0.039345796654000696,"score_gpt":0.3198587520506013,"score_spread":0.28051295539660065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404954737","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":[0.06215415,0.00010210281,0.9321442,0.00031974926,0.0004597619,0.00032222646,3.6348007e-7,0.0004090146,0.00408842],"genre_scores_gemma":[0.9415536,0.000001927268,0.051540587,0.000045090634,0.000051469167,0.00006748216,8.836432e-7,0.000015589107,0.006723407],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883044,0.000022964576,0.00022383983,0.0003395051,0.00021248826,0.00037074857],"domain_scores_gemma":[0.9993813,0.00021418868,0.000016917551,0.00029986128,0.000027909293,0.000059846505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037731673,0.0001104525,0.00011844423,0.00023845636,0.000065103166,0.00043963402,0.0005665125,0.000053878583,0.000011879216],"category_scores_gemma":[0.000022444665,0.00010260681,0.000060138726,0.00031164484,0.000017115271,0.0004283789,0.0002250983,0.0002047312,0.000034799246],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013252495,0.000012547751,0.013777108,0.000037556434,0.000009416273,0.00009552609,0.0020815071,0.9471742,0.00031985628,0.012149676,0.0005062267,0.02383509],"study_design_scores_gemma":[0.00013152465,0.00007998259,0.007966141,0.00006992993,0.0000044232115,0.000007970811,0.00006788737,0.9890859,0.0004393532,0.000017260782,0.001997048,0.00013257097],"about_ca_topic_score_codex":0.000066766064,"about_ca_topic_score_gemma":0.000018346445,"teacher_disagreement_score":0.8806036,"about_ca_system_score_codex":0.00012273974,"about_ca_system_score_gemma":0.00010440268,"threshold_uncertainty_score":0.42394012},"labels":[],"label_agreement":null},{"id":"W4405568984","doi":"10.1007/978-3-031-77688-5_42","title":"Leveraging Single and Multi-task Reinforcement Learning Algorithms for Autonomous Mobile Aloha Robot","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Aloha; Reinforcement learning; Computer science; Task (project management); Mobile robot; Artificial intelligence; Robot; Human–computer interaction; Throughput; Wireless; Engineering; Telecommunications","score_opus":0.02962780433733567,"score_gpt":0.250649203937621,"score_spread":0.22102139960028536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405568984","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":[0.000006024648,0.02166276,0.9712146,0.000057834273,0.0019398704,0.0013717393,0.0000016790938,0.00022991707,0.0035155888],"genre_scores_gemma":[0.82333106,0.0020771844,0.0367671,0.0003684604,0.0022607746,0.00046131428,0.00018578662,0.00036444716,0.1341839],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972091,0.000042746004,0.0008004297,0.0009956503,0.0003260931,0.00062603084],"domain_scores_gemma":[0.99829805,0.00059868133,0.00038308668,0.0004884237,0.00009115107,0.0001406343],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006145892,0.0006291286,0.00078207674,0.0002830209,0.00025385522,0.0009724975,0.00042279335,0.0006071363,0.000003844835],"category_scores_gemma":[0.00004278888,0.00057799753,0.00013440417,0.000102980026,0.00008679581,0.00016911722,0.00045716338,0.0011044198,0.000005631306],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047676217,0.0000046555615,0.000024495048,0.0003605336,0.00009349734,0.000031354168,0.0007976876,0.9670701,0.000011885826,0.003929107,0.000050546194,0.027621351],"study_design_scores_gemma":[0.00044164865,0.00036550115,0.0000023003236,0.0012734103,0.00004935327,0.00006414858,0.000012275608,0.95043063,0.000005647889,0.00044456997,0.046313807,0.00059672346],"about_ca_topic_score_codex":0.00006907739,"about_ca_topic_score_gemma":0.000013300076,"teacher_disagreement_score":0.93444747,"about_ca_system_score_codex":0.00023317176,"about_ca_system_score_gemma":0.000053322663,"threshold_uncertainty_score":0.99966717},"labels":[],"label_agreement":null},{"id":"W4405602545","doi":"10.1109/icsme58944.2024.00019","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Debugging; Reinforcement learning; Computer science; Algorithmic program debugging; Programming language; Artificial intelligence; Human–computer interaction; Software engineering","score_opus":0.030093056225010118,"score_gpt":0.24657515407600766,"score_spread":0.21648209785099753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405602545","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":[0.00024786574,0.00013980646,0.9575876,0.000819607,0.00029377703,0.00025789154,7.1991315e-9,0.002239997,0.038413472],"genre_scores_gemma":[0.9134021,0.00002085454,0.07743005,0.0002656351,0.00007361204,0.00005310401,0.0000070311753,0.000030555027,0.008717066],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980821,0.0000367481,0.000275659,0.00048100945,0.0005972069,0.0005272812],"domain_scores_gemma":[0.9992643,0.00006638492,0.00005382002,0.0004149719,0.00007115792,0.00012934039],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00029254385,0.0002246251,0.00015636928,0.00016958182,0.00014938411,0.0011136857,0.0006586008,0.000053530126,0.00011515454],"category_scores_gemma":[0.000023405719,0.00016184723,0.00007020561,0.0006487789,0.00004716589,0.0009369743,0.0003228016,0.00038347804,0.00047273954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003533825,0.000006523719,0.00033796302,0.000065555236,0.00006333589,0.00007998675,0.0021215437,0.88975155,0.000023869241,0.056987688,0.00017930512,0.050379142],"study_design_scores_gemma":[0.00014819027,0.00038548565,0.00003133493,0.00013712833,0.000014294913,0.000043554075,0.00015524295,0.9676232,0.0002661815,0.00012992304,0.030796867,0.00026864914],"about_ca_topic_score_codex":0.000019071354,"about_ca_topic_score_gemma":0.000002405924,"teacher_disagreement_score":0.91315424,"about_ca_system_score_codex":0.000109848435,"about_ca_system_score_gemma":0.00009867687,"threshold_uncertainty_score":0.9999232},"labels":[],"label_agreement":null},{"id":"W4405778651","doi":"10.1109/iros58592.2024.10802721","title":"Guiding Reinforcement Learning with Incomplete System Dynamics","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Honeywell (Canada); University of British Columbia","funders":"","keywords":"Reinforcement learning; Computer science; Dynamics (music); Artificial intelligence; Human–computer interaction; Psychology","score_opus":0.018374155161227892,"score_gpt":0.22859966066940193,"score_spread":0.21022550550817404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405778651","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":[0.0002841061,0.00004790878,0.90002555,0.00031078915,0.0004211914,0.00015813808,9.123053e-8,0.0017869202,0.096965306],"genre_scores_gemma":[0.9376165,0.0000058343962,0.04987761,0.00007348093,0.000062284096,0.000013436646,0.000007746096,0.000024768766,0.01231829],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998286,0.000048315873,0.0003269595,0.0004118777,0.0005322891,0.00039455894],"domain_scores_gemma":[0.9991691,0.00011807713,0.000071092734,0.00047220476,0.00007309166,0.000096394244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000431139,0.00019812095,0.00016931478,0.00020428037,0.00022035571,0.0008423779,0.00069812825,0.000049654875,0.000027230246],"category_scores_gemma":[0.000020541844,0.0001501285,0.000055965633,0.0006005722,0.000030743955,0.000623086,0.00037814563,0.00021812656,0.00033329477],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000012819554,9.357323e-7,0.00013939217,0.000097275,0.000029107317,0.000043507258,0.00017075175,0.617368,0.000022485996,0.38051584,0.00014684816,0.0014646135],"study_design_scores_gemma":[0.000112970854,0.00019090576,0.00002538988,0.00031179513,0.000010950381,0.000081177575,0.00023866964,0.9904788,0.00009506156,0.000022928378,0.008205851,0.00022550503],"about_ca_topic_score_codex":0.000042556636,"about_ca_topic_score_gemma":0.000004204845,"teacher_disagreement_score":0.93733245,"about_ca_system_score_codex":0.0004355278,"about_ca_system_score_gemma":0.000092755465,"threshold_uncertainty_score":0.81230694},"labels":[],"label_agreement":null},{"id":"W4405787662","doi":"10.1109/iros58592.2024.10801347","title":"PGA: Personalizing Grasping Agents with Single Human-Robot Interaction","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Computer science; Human–robot interaction; Robot; Human–computer interaction; Artificial intelligence","score_opus":0.06464383271075191,"score_gpt":0.31186956567148877,"score_spread":0.24722573296073685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405787662","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":[0.0043579573,0.00004639907,0.9600017,0.0004023012,0.0005603371,0.00008560932,3.8901465e-8,0.0005921341,0.033953533],"genre_scores_gemma":[0.9691497,0.0000025222507,0.024373561,0.00024392955,0.00008434444,0.000005329624,0.0000029247435,0.000016062459,0.0061215945],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989307,0.000026683265,0.00016338687,0.00033470403,0.00030782455,0.00023673457],"domain_scores_gemma":[0.99954903,0.00005144022,0.00004339914,0.00026182295,0.00004039111,0.00005388653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001361303,0.00012808757,0.00009228812,0.00014745515,0.00016110591,0.00079908664,0.00035526196,0.00003180466,0.00013349882],"category_scores_gemma":[0.000011846248,0.00010264477,0.00004718852,0.0003429534,0.000024661593,0.0009660605,0.00014743811,0.00019237657,0.00020229144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007280719,0.000076450335,0.0011060673,0.00023739685,0.00021854269,0.0002588754,0.006139339,0.849928,0.017207112,0.09602415,0.007426463,0.021370294],"study_design_scores_gemma":[0.00011574396,0.00022949591,0.0004932957,0.00028860287,0.000012113451,0.000055592645,0.00018454768,0.9876192,0.002558489,0.000105520085,0.008117781,0.00021961561],"about_ca_topic_score_codex":0.00003559814,"about_ca_topic_score_gemma":0.000006689861,"teacher_disagreement_score":0.9647918,"about_ca_system_score_codex":0.00012946015,"about_ca_system_score_gemma":0.000027342274,"threshold_uncertainty_score":0.7705611},"labels":[],"label_agreement":null},{"id":"W4405938060","doi":"10.1109/icdici62993.2024.10810955","title":"Reinforcement Learning in Cognitive Robots for Autonomous Path Planning","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Horizon College and Seminary","funders":"","keywords":"Reinforcement learning; Computer science; Motion planning; Robot; Path (computing); Mobile robot; Reinforcement; Human–computer interaction; Cognition; Artificial intelligence; Psychology; Computer network; Social psychology; Neuroscience","score_opus":0.036249807818978526,"score_gpt":0.308985041001481,"score_spread":0.2727352331825025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405938060","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":[0.00073611847,0.00017012714,0.9737679,0.00029068004,0.00045168417,0.0004113784,2.23106e-7,0.00063122483,0.023540715],"genre_scores_gemma":[0.9532957,0.000009846615,0.030345334,0.0002778973,0.00006909564,0.000066461405,0.00001596598,0.000020894191,0.015898783],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984892,0.00003375923,0.0003506898,0.00043410689,0.0002448206,0.0004473989],"domain_scores_gemma":[0.9991562,0.0004813391,0.0000577421,0.00018030412,0.000054991357,0.00006945773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005061384,0.00017302955,0.00016855542,0.0002629882,0.000100259575,0.00043308147,0.00038471815,0.00006971311,0.000042710206],"category_scores_gemma":[0.0001586712,0.00016158393,0.000075017764,0.00039128104,0.00002270702,0.0005691309,0.00021754745,0.00031041756,0.00010033171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005620841,0.0000054604125,0.00042608584,0.00004687181,0.000020517442,0.000039955983,0.0015924127,0.96034515,0.0000507411,0.028506953,0.000433258,0.0085269455],"study_design_scores_gemma":[0.00034798932,0.00025272276,0.00023414825,0.00031682226,0.0000068356485,0.00000777714,0.00014854985,0.99081254,0.00034142035,0.00025427202,0.007056763,0.00022016585],"about_ca_topic_score_codex":0.000016747415,"about_ca_topic_score_gemma":8.672284e-7,"teacher_disagreement_score":0.9525596,"about_ca_system_score_codex":0.00013115827,"about_ca_system_score_gemma":0.00014933858,"threshold_uncertainty_score":0.65892017},"labels":[],"label_agreement":null},{"id":"W4405956545","doi":"10.48550/arxiv.2412.20568","title":"Derivations of Animal Movement Models with Explicit Memory","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Movement (music); Computer science; Cognitive science; Neuroscience; Cognitive psychology; Psychology; Philosophy","score_opus":0.08297542405691738,"score_gpt":0.18774141870454697,"score_spread":0.10476599464762959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405956545","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":[0.11736671,0.000031867137,0.8726937,0.000095499556,0.00018147108,0.00027202704,0.000005055461,0.00020665844,0.009146988],"genre_scores_gemma":[0.98824465,0.00004285846,0.009559332,0.00007611528,0.00002784923,0.0000017703015,0.000008420531,0.000021795498,0.0020172242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985002,0.000046990357,0.00023689016,0.0007719732,0.00017779587,0.00026613122],"domain_scores_gemma":[0.99831116,0.000055914516,0.0001852153,0.0011709593,0.00018042639,0.00009629342],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014263263,0.00026732593,0.0002791363,0.00031513587,0.000076607444,0.00009886638,0.0014394954,0.00014720662,0.000019588915],"category_scores_gemma":[0.000008221271,0.00027820907,0.00013047372,0.00059952325,0.00007625575,0.00029888863,0.0029119665,0.00051797554,0.000035111552],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000114431905,0.000019623369,0.00008966036,0.00009322474,0.000086611435,0.000053109758,0.00028056797,0.6463854,0.000091755464,0.35278806,0.000073032876,0.00002753387],"study_design_scores_gemma":[0.00020172763,0.00015728282,0.00010260801,0.000185785,0.00007371862,0.0000012895823,0.00010858602,0.9659358,0.000688947,0.032236766,0.000024507903,0.00028295803],"about_ca_topic_score_codex":0.00009611786,"about_ca_topic_score_gemma":0.0000070255874,"teacher_disagreement_score":0.8708779,"about_ca_system_score_codex":0.00017740668,"about_ca_system_score_gemma":0.0002752662,"threshold_uncertainty_score":0.999967},"labels":[],"label_agreement":null},{"id":"W4406121228","doi":"10.1007/s11633-023-1482-0","title":"Latent Landmark Graph for Efficient Exploration-exploitation Balance in Hierarchical Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"Machine Intelligence Research","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Landmark; Reinforcement learning; Computer science; Reinforcement; Graph; Artificial intelligence; Balance (ability); Machine learning; Cognitive psychology; Psychology; Theoretical computer science; Social psychology; Neuroscience","score_opus":0.0638528454781579,"score_gpt":0.3792239764301926,"score_spread":0.31537113095203473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406121228","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":[0.0022985188,0.00015939976,0.99038863,0.0028649108,0.00028063316,0.0009823699,5.560393e-7,0.00011332038,0.002911665],"genre_scores_gemma":[0.98377556,0.00022968637,0.012623582,0.00009940509,0.000037030266,0.00039121974,0.000027675282,0.000014139344,0.0028016865],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996673,0.0003843857,0.0006364285,0.0005956942,0.0009215277,0.0007889479],"domain_scores_gemma":[0.9974938,0.0013411094,0.000090114896,0.0005466308,0.00042086423,0.00010750244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036803577,0.00018927398,0.00023139805,0.00110383,0.00040460913,0.00031351708,0.001190339,0.00009577036,0.000025723715],"category_scores_gemma":[0.0014888005,0.0001776398,0.00009071645,0.0021440515,0.00012956753,0.000328968,0.0005013053,0.0009305504,0.0000662504],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053035314,0.000052877225,0.003030382,0.000070767324,0.000013002186,0.0000047294775,0.0010205276,0.8872873,0.00014902453,0.08907425,0.00014561147,0.019098457],"study_design_scores_gemma":[0.00026501695,0.0002791925,0.0005471583,0.00015332282,0.0000020805362,8.8852545e-7,0.0001733245,0.98393637,0.0024286304,0.010043304,0.002010085,0.0001606124],"about_ca_topic_score_codex":0.00013403647,"about_ca_topic_score_gemma":0.000025795522,"teacher_disagreement_score":0.9814771,"about_ca_system_score_codex":0.00028251566,"about_ca_system_score_gemma":0.00020286157,"threshold_uncertainty_score":0.7243941},"labels":[],"label_agreement":null},{"id":"W4406132533","doi":"10.1007/s00521-024-10829-4","title":"Do as you teach: a multi-teacher approach to self-play in deep reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Curriculum; Reinforcement; Computational Science and Engineering; Artificial intelligence; State space; Space (punctuation); Baseline (sea); Mathematics education; Machine learning; Psychology; Pedagogy; Mathematics","score_opus":0.019547195795289605,"score_gpt":0.2921890384630919,"score_spread":0.2726418426678023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406132533","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":[0.0136849405,0.000070771384,0.9703644,0.00039513342,0.000054001288,0.00063623564,5.231239e-8,0.00035179988,0.014442666],"genre_scores_gemma":[0.92986387,0.000006761934,0.06791709,0.00045055695,0.000040862895,0.000084869425,0.0000057145185,0.000009879185,0.0016203871],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845433,0.00008784165,0.00035702833,0.00055228017,0.0001944171,0.00035409498],"domain_scores_gemma":[0.9991861,0.00011022219,0.00009904493,0.00044706033,0.000053433043,0.00010414576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003796594,0.00018133859,0.00018189485,0.00023542765,0.0003925006,0.00027666456,0.00061923877,0.00006983408,0.0000019263903],"category_scores_gemma":[0.00006064286,0.0001835248,0.00003973789,0.0008394683,0.000027041715,0.00011849326,0.0005562141,0.0004684703,0.000032876273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015504062,0.000059305792,0.005011878,0.000022265542,0.000010239983,5.4483786e-7,0.0015969763,0.94918364,0.000063985106,0.023990566,0.000048729406,0.020010307],"study_design_scores_gemma":[0.00035045913,0.000043083,0.004084371,0.000025871375,0.0000071640898,0.000005991801,0.00019677819,0.986515,0.0000310054,0.00006456093,0.008499518,0.00017622733],"about_ca_topic_score_codex":0.000042112486,"about_ca_topic_score_gemma":0.0000012428047,"teacher_disagreement_score":0.91617894,"about_ca_system_score_codex":0.00007653617,"about_ca_system_score_gemma":0.00003698978,"threshold_uncertainty_score":0.7483924},"labels":[],"label_agreement":null},{"id":"W4406171015","doi":"10.1109/tase.2025.3527327","title":"Behaviorally-Aware Multi-Agent RL With Dynamic Optimization for Autonomous Driving","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Automation Science and Engineering","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Autonomous agent; Vehicle dynamics; Control engineering; Engineering; Artificial intelligence; Automotive engineering","score_opus":0.011070599583617275,"score_gpt":0.2564603295386846,"score_spread":0.2453897299550673,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406171015","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":[0.0058462787,0.0000043762157,0.99278677,0.00019468741,0.00042951893,0.0003002954,9.544073e-7,0.0004195257,0.000017597358],"genre_scores_gemma":[0.74424434,0.000005622099,0.25551054,0.000038689603,0.0000022857769,0.000056731442,7.744109e-7,0.000006204878,0.00013483375],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990282,0.0000061316496,0.00018079318,0.00029994972,0.00026054098,0.00022437617],"domain_scores_gemma":[0.99943566,0.00004969877,0.000048599017,0.0002373803,0.00016765387,0.000060992574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027824534,0.00012062031,0.00009590693,0.00046790484,0.00038238335,0.00032276692,0.0003026976,0.00003853668,0.0000025907457],"category_scores_gemma":[0.000013395589,0.000115948,0.000023975159,0.0008712506,0.00005294733,0.0009301476,0.000004567111,0.000094730014,0.0000019669783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.924073e-7,0.000014835957,0.000007715691,0.000020385132,0.0000046959244,3.3342567e-7,0.00017101617,0.9842026,0.0011577634,0.00019790299,0.0000016901134,0.014220016],"study_design_scores_gemma":[0.00029057433,0.000061839935,0.0008048497,0.00007662392,0.000011722637,0.0000033114034,0.000027173033,0.9960453,0.0025089192,0.0000016022069,0.000041292427,0.0001268016],"about_ca_topic_score_codex":0.0000029633893,"about_ca_topic_score_gemma":0.0000029330893,"teacher_disagreement_score":0.738398,"about_ca_system_score_codex":0.00020451636,"about_ca_system_score_gemma":0.00014843959,"threshold_uncertainty_score":0.47282225},"labels":[],"label_agreement":null},{"id":"W4406209209","doi":"10.2139/ssrn.5024095","title":"Reinforcement Learning in Non-Markov Market-Making","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Reinforcement learning; Computer science; Markov decision process; Mathematical optimization; Maximization; Artificial intelligence; Limit (mathematics); Markov process; Mathematics","score_opus":0.008008819207830534,"score_gpt":0.2608087152248799,"score_spread":0.2527998960170494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406209209","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":[0.0005407828,0.0009906428,0.95309204,0.00080263504,0.0014373076,0.00041658006,2.2698102e-7,0.00015606507,0.042563736],"genre_scores_gemma":[0.940548,0.0058843372,0.008609671,0.00030519682,0.00035125835,0.00004154883,0.00000894476,0.000043422657,0.04420761],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99266195,0.00037415075,0.0011688853,0.00078922685,0.0009405027,0.00406527],"domain_scores_gemma":[0.99756724,0.00024012268,0.00096296775,0.0009316793,0.00019150159,0.000106468186],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005784168,0.0005729651,0.00063934526,0.0010176554,0.00035405607,0.0006889888,0.003317931,0.00042154806,0.000047051974],"category_scores_gemma":[0.0004256864,0.00060063595,0.0003348043,0.0006447955,0.000045135388,0.00044805295,0.003013681,0.015133234,0.000028347378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000025269163,0.000018719362,0.0013456848,0.00008374688,0.00018556783,0.000027516273,0.00042220304,0.9376694,0.0000053446074,0.030708442,0.00021684976,0.029291235],"study_design_scores_gemma":[0.0007502625,0.0002576695,0.00047676123,0.0012420997,0.000039007595,0.000116439696,0.0003010668,0.95850444,0.000011509793,0.034374464,0.003238751,0.0006875429],"about_ca_topic_score_codex":0.00007076726,"about_ca_topic_score_gemma":0.00011870248,"teacher_disagreement_score":0.9444823,"about_ca_system_score_codex":0.0046172542,"about_ca_system_score_gemma":0.007770895,"threshold_uncertainty_score":0.9996445},"labels":[],"label_agreement":null},{"id":"W4406267575","doi":"10.1177/02783649241312699","title":"Shared autonomy policy fine-tuning and alignment for robotic tasks","year":2025,"lang":"en","type":"article","venue":"The International Journal of Robotics Research","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University; McGill University","funders":"","keywords":"Reinforcement learning; Arbitration; Autonomy; Computer science; Human–computer interaction; Task (project management); Robot; Artificial intelligence; Controller (irrigation); Human–robot interaction; Distributed computing; Engineering; Systems engineering","score_opus":0.07345984979332178,"score_gpt":0.40580684606781176,"score_spread":0.33234699627449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406267575","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":[0.00029845352,0.00018784625,0.9375236,0.05949237,0.0007275732,0.00021363285,8.512745e-7,0.0000127851445,0.0015429035],"genre_scores_gemma":[0.86160463,0.00013896523,0.1290048,0.0008479972,0.0006345169,0.00001582519,0.000003659244,0.000017845909,0.007731771],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976901,0.0001476096,0.00050075795,0.00017384526,0.0011590383,0.00032866924],"domain_scores_gemma":[0.99655795,0.0013438003,0.0002289006,0.00032529913,0.0014528292,0.00009119244],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026827992,0.00011111373,0.00018033492,0.00074905984,0.00024635074,0.00072584534,0.002814197,0.000050542585,0.000006692352],"category_scores_gemma":[0.0012887478,0.00008164854,0.00009361804,0.00041949478,0.00013906004,0.0003426983,0.0009954352,0.00049172697,0.0000059309777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028662938,0.00002300621,0.00023268259,0.000013166366,0.00016567047,0.000010836149,0.00034597842,0.7455321,0.00043451416,0.24572766,0.0031096744,0.00437607],"study_design_scores_gemma":[0.00087342836,0.00021077083,0.00078245165,0.00021907705,0.000015034273,0.00006757109,0.000112816124,0.96657836,0.0006234076,0.02227117,0.008144974,0.00010094189],"about_ca_topic_score_codex":0.000025655812,"about_ca_topic_score_gemma":0.0000029957937,"teacher_disagreement_score":0.8613062,"about_ca_system_score_codex":0.00050018454,"about_ca_system_score_gemma":0.0010987798,"threshold_uncertainty_score":0.69993436},"labels":[],"label_agreement":null},{"id":"W4407253672","doi":"10.1007/978-981-97-8702-9_20","title":"Feature-Based Explainable Reinforcement Learning in Environments with Multiple Sources of Risk","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Reinforcement learning; Feature (linguistics); Artificial intelligence; Reinforcement; Engineering","score_opus":0.00814257528352944,"score_gpt":0.2077444555139946,"score_spread":0.19960188023046516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407253672","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":[0.00021200407,0.00017758088,0.9965682,0.00017977,0.00032388957,0.00053119747,0.0000013206762,0.000080669335,0.0019253842],"genre_scores_gemma":[0.63340634,0.000072174655,0.3631029,0.0003553917,0.00006921551,0.000020560896,0.000013726668,0.000038367132,0.002921291],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959362,0.00008151362,0.0005850417,0.0012676666,0.0013775657,0.00075201975],"domain_scores_gemma":[0.9966669,0.0010853409,0.0007601152,0.0012784415,0.000095884316,0.00011329838],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010222304,0.0005851423,0.0006673134,0.0013675168,0.00025194278,0.00024936226,0.002648032,0.0003042465,0.000010835087],"category_scores_gemma":[0.00029038885,0.00051690784,0.00011054389,0.0008165642,0.0005965838,0.00044274036,0.0010928025,0.0014683498,0.000008994716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002381033,0.000017604541,0.0067397514,0.0000661714,0.000013405497,0.00004332491,0.00058764,0.95684165,0.000024000885,0.0010566165,0.000005592628,0.034580406],"study_design_scores_gemma":[0.00090993557,0.00039298311,0.0007200005,0.0010303862,0.000013017669,0.0000051579905,9.607523e-7,0.9909505,0.0024807928,0.0009175166,0.002049192,0.00052951876],"about_ca_topic_score_codex":0.00008578223,"about_ca_topic_score_gemma":0.000075025244,"teacher_disagreement_score":0.6334653,"about_ca_system_score_codex":0.0005333312,"about_ca_system_score_gemma":0.0005994876,"threshold_uncertainty_score":0.99972826},"labels":[],"label_agreement":null},{"id":"W4407666659","doi":"10.1051/itmconf/20257301007","title":"Optimizing Robotic Arm Learning: Curiosity-Driven Deep Deterministic Policy Gradient","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Reinforcement Learning in Robotics","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":"Canada Research Chairs","funders":"","keywords":"Curiosity; Artificial intelligence; Computer science; Deep learning; Psychology; Human–computer interaction; Neuroscience","score_opus":0.021392008153920644,"score_gpt":0.2807801220522062,"score_spread":0.25938811389828553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407666659","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":[0.0053136162,0.00013175955,0.9241721,0.001043129,0.0005366243,0.00020012987,2.9542005e-7,0.00019022074,0.0684121],"genre_scores_gemma":[0.9802594,0.000096885764,0.017989112,0.00017873509,0.000045615237,0.000010814723,0.0000027982662,0.000007859134,0.0014087791],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99810874,0.00014391466,0.0005039679,0.0004130014,0.0003907501,0.00043961828],"domain_scores_gemma":[0.9984716,0.000384266,0.00031608334,0.00052116055,0.0002001152,0.000106774045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024247725,0.00023400287,0.00039876593,0.0005064252,0.0002146614,0.00026519547,0.001471779,0.00009535499,0.00003547387],"category_scores_gemma":[0.00044360285,0.0002238089,0.000118259086,0.000681583,0.00020474239,0.00026084535,0.000467405,0.0003215981,0.000029752808],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000047906665,0.00004240264,0.0066087306,0.00006121705,0.000050764575,0.000007934155,0.00061175646,0.6676418,0.00018586506,0.31857008,0.00003638608,0.006178261],"study_design_scores_gemma":[0.0003491732,0.00031967319,0.0025519065,0.0002037507,0.000032995664,0.0000049093155,0.0001310492,0.98835665,0.00071756507,0.002318525,0.0047709364,0.00024284708],"about_ca_topic_score_codex":0.00007445989,"about_ca_topic_score_gemma":0.000018601224,"teacher_disagreement_score":0.9749458,"about_ca_system_score_codex":0.000065785076,"about_ca_system_score_gemma":0.0014887304,"threshold_uncertainty_score":0.91266614},"labels":[],"label_agreement":null},{"id":"W4407786710","doi":"10.1007/s12530-025-09660-6","title":"Gradual task complexity scaling (GTCS-DRL): a deep reinforcement learning approach for training automated guided vehicle system","year":2025,"lang":"en","type":"article","venue":"Evolving Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Rimouski","funders":"","keywords":"Reinforcement learning; Computer science; Task (project management); Complex system; Scaling; Training (meteorology); Artificial intelligence; Reinforcement; Systems engineering; Psychology; Physics; Engineering","score_opus":0.05230198632052235,"score_gpt":0.2874851340864007,"score_spread":0.23518314776587834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407786710","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":[0.0018788015,0.00034499963,0.98114187,0.00007585041,0.0017770953,0.0016617357,0.000001176196,0.0038386143,0.009279859],"genre_scores_gemma":[0.9262715,0.0000020136433,0.071767375,0.00006997481,0.00018951671,0.00029554288,0.000061799925,0.000048124188,0.0012941835],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953072,0.00035582035,0.0014321073,0.00096087897,0.0008446119,0.0010993859],"domain_scores_gemma":[0.9971776,0.00044784506,0.0006832348,0.0010241623,0.00047455242,0.00019258204],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002459302,0.00049038127,0.00081453135,0.00045704682,0.0012003817,0.0012216424,0.0016143814,0.00022550713,0.0000018263344],"category_scores_gemma":[0.0004432442,0.0005010972,0.000249687,0.0010552114,0.00010511176,0.0006676554,0.0005248756,0.00047059183,0.000025272404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008275118,0.000017682762,0.00052023033,0.0011200432,0.0001539095,0.0000053458193,0.0026009649,0.9213308,0.000376343,0.07189037,0.0017725613,0.00020348937],"study_design_scores_gemma":[0.0012218734,0.00011343506,0.00024250531,0.0008715234,0.00005075714,0.00003253019,0.00209882,0.9939381,0.00008324758,0.000032459102,0.00083251554,0.00048226988],"about_ca_topic_score_codex":0.00017760496,"about_ca_topic_score_gemma":0.0000013971706,"teacher_disagreement_score":0.92439264,"about_ca_system_score_codex":0.000797694,"about_ca_system_score_gemma":0.00025803412,"threshold_uncertainty_score":0.99981517},"labels":[],"label_agreement":null},{"id":"W4407857640","doi":"10.1145/3696443.3708963","title":"Vectron: A Dynamic Programming Auto-vectorization Framework","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Victoria","funders":"","keywords":"Vectorization (mathematics); Computer science; Dynamic programming; Programming language; Parallel computing; Algorithm","score_opus":0.005537035072222719,"score_gpt":0.268197002878428,"score_spread":0.2626599678062053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407857640","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":[0.00015776732,0.000038387847,0.985374,0.0010590506,0.0006713697,0.00017076821,2.9076928e-8,0.0006244878,0.011904158],"genre_scores_gemma":[0.55702233,0.0000046329687,0.43471286,0.00039426246,0.000020491249,0.000017120876,0.0000025359177,0.000005754808,0.007819997],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991047,0.000029954914,0.00017119202,0.00025015144,0.00018875458,0.00025526498],"domain_scores_gemma":[0.99931103,0.000093902905,0.000051254796,0.0004580277,0.000053056156,0.000032699267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014037683,0.00009712102,0.00009169437,0.00011818576,0.00011837813,0.00027261846,0.0005835819,0.000076230164,0.000024252873],"category_scores_gemma":[0.00013067985,0.00009126684,0.00003785955,0.00079654215,0.000019645911,0.0002585655,0.00014727896,0.00018059113,0.000053267555],"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":[0.000001364195,0.00001665027,0.0012668986,0.000022125776,0.0000211982,0.0000021749047,0.0002713686,0.10429044,0.00012585243,0.8443048,0.00021535906,0.04946176],"study_design_scores_gemma":[0.000091467205,0.000041356776,0.0012920857,0.000050858554,0.0000051144816,0.0000010560832,0.000014880988,0.9764855,0.00017643154,0.0030502446,0.01867654,0.000114446084],"about_ca_topic_score_codex":0.0000061817186,"about_ca_topic_score_gemma":0.0000015741293,"teacher_disagreement_score":0.87219507,"about_ca_system_score_codex":0.00009943917,"about_ca_system_score_gemma":0.00008460169,"threshold_uncertainty_score":0.37217537},"labels":[],"label_agreement":null},{"id":"W4407870583","doi":"10.3390/risks13030040","title":"Deep Reinforcement Learning in Non-Markov Market-Making","year":2025,"lang":"en","type":"article","venue":"Risks","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Reinforcement learning; Artificial intelligence; Markov chain; Reinforcement; Computer science; Economics; Machine learning; Psychology; Social psychology","score_opus":0.016540782736329213,"score_gpt":0.2945006458921195,"score_spread":0.2779598631557903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407870583","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":[0.0008516671,0.00006819561,0.84061617,0.00028732867,0.00039004264,0.0001909487,1.48897685e-8,0.00014696184,0.15744866],"genre_scores_gemma":[0.9724175,0.00004521057,0.017787844,0.0004578778,0.000029230137,0.000023263356,0.0000015275001,0.0000101504165,0.009227424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983227,0.00010114019,0.00041556536,0.0003745089,0.0003179505,0.00046811096],"domain_scores_gemma":[0.9989645,0.00024195759,0.00014283373,0.000552358,0.000052587213,0.000045770426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069929584,0.00017725627,0.0002072018,0.00036207348,0.00016812333,0.0002072263,0.00089182757,0.00009555964,0.00008601549],"category_scores_gemma":[0.00030019056,0.00018509325,0.00006795049,0.0007939763,0.000031189105,0.0003393969,0.00060434756,0.00049911905,0.000075503856],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007835582,0.000008691246,0.0139854895,0.000030361989,0.000015919511,0.000017571492,0.00038239887,0.9497623,0.000024498044,0.0040308055,0.0006361229,0.031098012],"study_design_scores_gemma":[0.00037388224,0.000046202018,0.020388126,0.00017805559,0.000005418413,0.0000015207892,0.00006094736,0.9712558,0.00007499608,0.00020329768,0.0072329137,0.00017888339],"about_ca_topic_score_codex":0.000060209375,"about_ca_topic_score_gemma":0.000012814198,"teacher_disagreement_score":0.9715658,"about_ca_system_score_codex":0.00019348499,"about_ca_system_score_gemma":0.00008426786,"threshold_uncertainty_score":0.7547884},"labels":[],"label_agreement":null},{"id":"W4407914197","doi":"10.1007/978-3-031-81596-6_8","title":"Memory Augmented Multi-agent Reinforcement Learning for Cooperative Environment","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Computer science; Reinforcement learning; Human–computer interaction; Artificial intelligence","score_opus":0.022046313600716162,"score_gpt":0.25488716534788347,"score_spread":0.23284085174716732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407914197","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":[0.000003280512,0.00025110762,0.9924333,0.00046743665,0.0017261073,0.0016383326,0.0000021195992,0.00020621996,0.0032721055],"genre_scores_gemma":[0.0357178,0.00025907584,0.91173524,0.0026226481,0.00038630769,0.00017464085,0.00007059032,0.00008637872,0.048947297],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950135,0.00006317047,0.0009097791,0.001843709,0.0012095596,0.00096029666],"domain_scores_gemma":[0.9968978,0.0006828245,0.0005218316,0.0014284849,0.00026601847,0.00020305077],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011223338,0.00078464084,0.00070058554,0.00087750994,0.000644339,0.00058269425,0.0031161404,0.00034409223,0.0000592925],"category_scores_gemma":[0.00023561707,0.00075561425,0.00022726793,0.00038461684,0.0005436214,0.00049240474,0.0023021724,0.0011090834,0.0000731837],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008853331,0.00001932011,0.0000073853935,0.000062071565,0.00003808419,0.000016572743,0.00061089004,0.8789341,0.000096842414,0.0041321013,0.00005510189,0.116018675],"study_design_scores_gemma":[0.0008666466,0.00046929,0.000011969393,0.00045134063,0.000022652506,0.000007237004,8.1288937e-7,0.98397195,0.002386098,0.0009486482,0.010126005,0.0007373194],"about_ca_topic_score_codex":0.000011654377,"about_ca_topic_score_gemma":0.000005483226,"teacher_disagreement_score":0.11528136,"about_ca_system_score_codex":0.0011540274,"about_ca_system_score_gemma":0.0006868585,"threshold_uncertainty_score":0.9994895},"labels":[],"label_agreement":null},{"id":"W4407951213","doi":"10.1109/cdc56724.2024.10886523","title":"Design of Denial-of-Service Attack Strategy With Energy Constraint: An Approximate Dynamic Programming Approach","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"National Natural Science Foundation of China","keywords":"Computer science; Denial-of-service attack; Constraint (computer-aided design); Denial; Dynamic programming; Computer security; Service (business); Mathematical optimization; Distributed computing; Engineering; Algorithm; Operating system; Mathematics; Business; The Internet","score_opus":0.03830944495505354,"score_gpt":0.2737495941951317,"score_spread":0.23544014924007814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407951213","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":[0.0009503286,0.000069711714,0.9946515,0.000049572387,0.000064379965,0.00026487964,6.697601e-7,0.00030946298,0.0036395255],"genre_scores_gemma":[0.5270557,0.0000043351192,0.47265416,0.000027076969,0.000007697569,0.000015302789,0.000007956429,0.00001604531,0.00021176733],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982919,0.00010474336,0.00039951244,0.000454888,0.0004112199,0.00033774495],"domain_scores_gemma":[0.99890965,0.00010376883,0.0001439272,0.00059050694,0.00016119995,0.000090942944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038974904,0.0002087787,0.00025978484,0.00016302677,0.00004741948,0.00024368755,0.0008642212,0.00008164,0.000014082295],"category_scores_gemma":[0.000006341616,0.0001606632,0.00004028693,0.000843794,0.000135225,0.00058200763,0.00013738888,0.00014087875,0.0000036892743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010389236,0.000052531985,0.000018367136,0.0002876261,0.00006239007,0.000010437361,0.0006053765,0.87697023,0.0008118953,0.09541876,0.0000063000048,0.025745684],"study_design_scores_gemma":[0.00018449088,0.00049979176,0.000013121363,0.000083009116,0.00002132431,0.000049879112,0.00023294424,0.99722457,0.0012471196,0.00016714225,0.00007718288,0.00019942362],"about_ca_topic_score_codex":0.00008673317,"about_ca_topic_score_gemma":0.0000122688825,"teacher_disagreement_score":0.52610534,"about_ca_system_score_codex":0.00003225512,"about_ca_system_score_gemma":0.00027162873,"threshold_uncertainty_score":0.6551655},"labels":[],"label_agreement":null},{"id":"W4408012843","doi":"10.1007/978-981-96-0077-9_5","title":"Evolving Many-Model Agents with Vector and Matrix Operations in Tangled Program Graphs","year":2025,"lang":"en","type":"book-chapter","venue":"Genetic and evolutionary computation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Matrix (chemical analysis); Vector (molecular biology); Computer science; Mathematics; Biology; Materials science; Genetics","score_opus":0.013447265442516666,"score_gpt":0.2528431059099153,"score_spread":0.23939584046739865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408012843","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":[0.0011092036,0.001516664,0.9845021,0.00019064514,0.00011950063,0.00081179815,0.0000050415497,0.00013316721,0.0116118975],"genre_scores_gemma":[0.2179898,0.0006009319,0.7206598,0.00012536693,0.00005012479,0.000084490486,0.00017220897,0.00003829187,0.060278956],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986487,0.000027077218,0.00033259758,0.0004939462,0.00029268002,0.0002049664],"domain_scores_gemma":[0.99941677,0.00006080854,0.00010320142,0.00020828641,0.00014083582,0.00007009314],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00007849006,0.0002553466,0.00022486856,0.00035178594,0.00020756524,0.00017288285,0.0001899785,0.00014955309,0.000008494327],"category_scores_gemma":[0.00001192839,0.00025765164,0.00003272882,0.0001255271,0.000090992165,0.00021350232,0.0002029429,0.00021175582,0.000005224015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000064348524,0.000015793717,0.0004474648,0.00006588725,0.000036758574,0.000010533819,0.00017653065,0.943974,0.000001932448,0.04686469,0.0006642644,0.007735678],"study_design_scores_gemma":[0.0003986685,0.00017123614,0.01846027,0.00020083567,0.000033997872,0.000024501473,0.000006016594,0.9717559,2.0990697e-7,0.00838914,0.00030409938,0.00025508666],"about_ca_topic_score_codex":0.000012411233,"about_ca_topic_score_gemma":0.000011736411,"teacher_disagreement_score":0.26384225,"about_ca_system_score_codex":0.00010072376,"about_ca_system_score_gemma":0.00019805951,"threshold_uncertainty_score":0.99998754},"labels":[],"label_agreement":null},{"id":"W4408261083","doi":"10.1515/9781772127867","title":"Digital Memory Agents in Canada","year":2024,"lang":"en","type":"book","venue":"University of Alberta Press eBooks","topic":"Reinforcement Learning in Robotics","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":"Computer science","score_opus":0.01799329881715726,"score_gpt":0.18708337127741648,"score_spread":0.16909007246025923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408261083","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000038509806,0.000036796475,0.0052449433,0.000026633586,0.00038469254,0.00017751082,0.000010112302,0.000026211113,0.9940546],"genre_scores_gemma":[0.0022010235,0.000008818685,0.00024053239,0.000031112195,0.00001687731,1.0016541e-7,0.000019140547,0.000015733938,0.9974667],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99874806,0.000019282881,0.00018803313,0.00038304648,0.00042253264,0.00023903277],"domain_scores_gemma":[0.998951,0.00016356172,0.00016553265,0.0005833233,0.000045321147,0.00009121716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000040046918,0.00021040018,0.00029351155,0.00015009608,0.00003720252,0.00007003846,0.001572349,0.00012895456,0.000025294614],"category_scores_gemma":[0.000011908158,0.00026295104,0.00008852605,0.000021693111,0.00006939279,0.00016910199,0.0010395193,0.0003807654,0.000029198607],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049558446,0.00003133546,0.00020899679,0.0014692085,0.0007933807,0.0023075815,0.012008371,0.19636469,0.0000022728227,0.09310089,0.6674185,0.026245233],"study_design_scores_gemma":[0.0002781382,0.000029664187,0.000027679414,0.0004189538,0.000034860805,0.0000049860537,0.000044330573,0.04320762,0.000014203922,0.00014496695,0.95543617,0.00035842473],"about_ca_topic_score_codex":0.84157467,"about_ca_topic_score_gemma":0.7963944,"teacher_disagreement_score":0.2880177,"about_ca_system_score_codex":0.00081296085,"about_ca_system_score_gemma":0.0024899987,"threshold_uncertainty_score":0.9999823},"labels":[],"label_agreement":null},{"id":"W4408363681","doi":"10.1007/s10846-025-02235-2","title":"Risk-Sensitive Autonomous Exploration of Unknown Environments: A Deep Reinforcement Learning Perspective","year":2025,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Reinforcement Learning in Robotics","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":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Alberta","keywords":"Reinforcement learning; Perspective (graphical); Computer science; Artificial intelligence; Reinforcement; Human–computer interaction; Psychology; Social psychology","score_opus":0.018578048339738428,"score_gpt":0.2630788909470452,"score_spread":0.24450084260730676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408363681","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":[0.0005675891,0.0008292908,0.99294466,0.00021878634,0.0019326382,0.00041668367,1.2058591e-7,0.000031158328,0.0030590785],"genre_scores_gemma":[0.98936486,0.0005740204,0.006955797,0.000041342737,0.00012579236,0.000008003121,0.0000014857917,0.000016338738,0.0029123528],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963783,0.00048255996,0.0016697726,0.000302283,0.0008269323,0.00034013402],"domain_scores_gemma":[0.9958667,0.0004280891,0.0024882492,0.00046069914,0.0006364757,0.000119758115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014196435,0.00027824324,0.00064650126,0.00061777636,0.00017520894,0.00017756395,0.00077770377,0.00011798625,0.000008625922],"category_scores_gemma":[0.0006740517,0.000244981,0.00027650836,0.0005319497,0.00009310926,0.00095602387,0.0002328943,0.0005951573,0.000035092336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030147043,0.000064347776,0.00040498318,0.000047440037,0.00039553182,0.000021161395,0.0049808584,0.9525413,0.00029110687,0.040205088,0.00007951205,0.0009385065],"study_design_scores_gemma":[0.00047001062,0.00088348554,0.0002271646,0.00061247614,0.00013714192,0.000054988723,0.0083618155,0.98261976,0.0047134333,0.00031440772,0.0013851958,0.00022011968],"about_ca_topic_score_codex":0.0001073835,"about_ca_topic_score_gemma":0.0000023111238,"teacher_disagreement_score":0.9887973,"about_ca_system_score_codex":0.0010652258,"about_ca_system_score_gemma":0.00022624072,"threshold_uncertainty_score":0.9990036},"labels":[],"label_agreement":null},{"id":"W4408434866","doi":"10.1016/j.eswa.2025.127180","title":"Application of Soft Actor-Critic algorithms in optimizing wastewater treatment with time delays integration","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kruger (Canada)","funders":"H2020 Marie Skłodowska-Curie Actions; Horizon 2020; Research Executive Agency; Horizon 2020 Framework Programme; European Commission","keywords":"Computer science; Algorithm; Mathematical optimization; Artificial intelligence; Mathematics","score_opus":0.009996203683530259,"score_gpt":0.25450466053906284,"score_spread":0.24450845685553257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408434866","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":[0.00046597255,0.00021505702,0.99591804,0.00033314337,0.000037993177,0.0015721776,0.000001988487,0.00013421864,0.0013214212],"genre_scores_gemma":[0.86976546,0.000017487017,0.12459629,0.00004294313,0.00003973075,0.0041110427,0.00004836243,0.0000203106,0.0013583638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986165,0.00005516461,0.00043031524,0.0004261492,0.00024069169,0.0002311786],"domain_scores_gemma":[0.9986403,0.00010963824,0.00018404883,0.00084111805,0.00017134528,0.0000535532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013395281,0.00020294519,0.0002771663,0.00025985233,0.000113845024,0.00010666344,0.00045607146,0.00007314776,0.00000205154],"category_scores_gemma":[0.000004951493,0.00014551044,0.000031003994,0.0007646334,0.000060830633,0.00030172832,0.00005164117,0.00008892292,0.00002786082],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041260017,0.00032791184,0.001168278,0.00010847932,0.00013260156,0.0000028454556,0.0033558074,0.91456425,0.016555171,0.040302236,0.00015347645,0.023287674],"study_design_scores_gemma":[0.0006138649,0.00022459232,0.000085619955,0.00019175337,0.000013835584,0.0000103759185,0.00037047788,0.9885304,0.0047850385,0.000030707444,0.004960452,0.00018290078],"about_ca_topic_score_codex":0.00032490198,"about_ca_topic_score_gemma":0.000015520289,"teacher_disagreement_score":0.87132174,"about_ca_system_score_codex":0.00028146952,"about_ca_system_score_gemma":0.0001251661,"threshold_uncertainty_score":0.5933743},"labels":[],"label_agreement":null},{"id":"W4408518028","doi":"10.2139/ssrn.5182425","title":"Sage: Self-Evolving Agents with Reflective and Memory-Augmented Abilities","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Psychology; Cognitive psychology; SAGE; Computer science; Cognitive science; Physics","score_opus":0.009187574990174665,"score_gpt":0.2573514460157894,"score_spread":0.24816387102561474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408518028","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":[0.007290688,0.0031895777,0.98073965,0.00072799256,0.00062043866,0.00047643937,0.0000018555332,0.00027218822,0.006681173],"genre_scores_gemma":[0.9227465,0.010463784,0.043615773,0.00039470542,0.00037914855,0.000057646004,0.000010936342,0.00006626908,0.022265254],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955633,0.0002871233,0.00049268355,0.0007135098,0.0006922319,0.0022511492],"domain_scores_gemma":[0.99814117,0.00016049838,0.00054273923,0.000729967,0.00029584998,0.00012977625],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017953276,0.0004648862,0.0004668967,0.00037543455,0.00045452814,0.00072256627,0.0014497531,0.00022831702,0.00001558024],"category_scores_gemma":[0.00011942946,0.00040337778,0.00012670833,0.00032666113,0.00008749213,0.000469833,0.0014141954,0.0057519916,0.0000053803105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025159502,0.00039105982,0.008206787,0.0011452192,0.008365187,0.00013974836,0.02111485,0.7034021,0.000071347116,0.18691865,0.0011915886,0.068801895],"study_design_scores_gemma":[0.0037642848,0.0025114473,0.0029120245,0.0022513655,0.0006052136,0.0014042644,0.004596701,0.71787506,0.00026252697,0.26012814,0.0014333092,0.0022556733],"about_ca_topic_score_codex":0.00007735098,"about_ca_topic_score_gemma":0.00011261072,"teacher_disagreement_score":0.9371239,"about_ca_system_score_codex":0.002818191,"about_ca_system_score_gemma":0.0059132036,"threshold_uncertainty_score":0.9998418},"labels":[],"label_agreement":null},{"id":"W4408794490","doi":"10.1109/swc62898.2024.00346","title":"Simulating a Multi-Agent UAV System Coordinated by State Machines Using Godot","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Calgary; Athabasca University","funders":"","keywords":"Computer science; State (computer science); Multi-agent system; Distributed computing; Embedded system; Artificial intelligence; Programming language","score_opus":0.030465042359474837,"score_gpt":0.2919060881060475,"score_spread":0.2614410457465727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408794490","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":[0.012512931,0.00021418418,0.9837283,0.000082976934,0.0008382532,0.00020641564,0.0000023719713,0.0013218295,0.0010927327],"genre_scores_gemma":[0.8995517,0.0000021527696,0.09417327,0.000071982555,0.000027932558,0.0000033187496,0.00000454737,0.000025646947,0.0061394717],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99843794,0.00008660913,0.00037806385,0.00042056604,0.00030800345,0.0003688177],"domain_scores_gemma":[0.9992222,0.0001569169,0.0000784768,0.00037732883,0.00006882735,0.00009620425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037740753,0.00019760214,0.0001787205,0.0001261481,0.0001670019,0.0007644552,0.0005209721,0.000046760368,0.000019448846],"category_scores_gemma":[0.000042019627,0.00016396442,0.00006738703,0.00053391414,0.000022212602,0.00047138124,0.00035366561,0.00019332267,0.00014345623],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.619106e-7,0.000007886189,0.00029139346,0.00017190033,0.000038220176,0.000044281875,0.00039771205,0.99011093,0.0033418748,0.0021798834,0.0003924672,0.003022493],"study_design_scores_gemma":[0.00018024238,0.000029778726,0.000024395058,0.00018474214,0.000009465392,0.0000177012,0.000042731997,0.99729437,0.0007724057,0.00000730644,0.0012300698,0.00020679778],"about_ca_topic_score_codex":0.00024169535,"about_ca_topic_score_gemma":0.0000022285153,"teacher_disagreement_score":0.88955504,"about_ca_system_score_codex":0.00019677285,"about_ca_system_score_gemma":0.000051097188,"threshold_uncertainty_score":0.73716587},"labels":[],"label_agreement":null},{"id":"W4408891814","doi":"10.21203/rs.3.rs-6051145/v1","title":"Inequity Aversion Toward AI Counterparts","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Reinforcement Learning in Robotics","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 Waterloo; University of Toronto","funders":"","keywords":"Inequity aversion; Economics; Psychology; Cognitive psychology; Mathematics; Inequality","score_opus":0.09820482988377287,"score_gpt":0.4300601923562331,"score_spread":0.3318553624724602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408891814","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":[0.00056885846,0.000321841,0.9628872,0.0052742963,0.0015127433,0.0010377204,0.000023344008,0.00040057633,0.0279734],"genre_scores_gemma":[0.9599875,0.0008894685,0.012415826,0.0007418624,0.00045519957,0.00019154236,0.00015759948,0.00003649421,0.025124513],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944508,0.00065103214,0.00042128892,0.0010170221,0.0025121649,0.0009476759],"domain_scores_gemma":[0.99577475,0.00047199195,0.00012474836,0.0022144106,0.0011854151,0.0002287164],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0026836721,0.00030323383,0.00038280504,0.0007748598,0.00034804657,0.0010672288,0.0039336886,0.00043695376,0.00012102897],"category_scores_gemma":[0.0007416285,0.0002996844,0.00019683091,0.0008223561,0.00015432223,0.0003494035,0.01549123,0.0032233575,0.00045974817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005231351,0.00015526688,0.004490795,0.004666983,0.00014714105,0.00020357633,0.0034450814,0.7805945,0.000045998124,0.054372493,0.13543433,0.01639148],"study_design_scores_gemma":[0.00034409872,0.00023404622,0.0012166486,0.0020154133,0.000008670671,0.000003091388,0.000088238754,0.8623173,0.00038457406,0.0044316147,0.12850203,0.0004542686],"about_ca_topic_score_codex":0.00020509661,"about_ca_topic_score_gemma":0.000005526996,"teacher_disagreement_score":0.95941865,"about_ca_system_score_codex":0.00072015746,"about_ca_system_score_gemma":0.0014594875,"threshold_uncertainty_score":0.9999698},"labels":[],"label_agreement":null},{"id":"W4408954824","doi":"10.1007/s00521-025-11100-0","title":"Advances and applications in inverse reinforcement learning: a comprehensive review","year":2025,"lang":"en","type":"review","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"RUDN University; Monash University","keywords":"Computational Science and Engineering; Computer science; Reinforcement learning; Reinforcement; Inverse; Artificial intelligence; Machine learning; Applied mathematics; Mathematics; Geometry; Engineering; Structural engineering","score_opus":0.03519127845833417,"score_gpt":0.34493019071533093,"score_spread":0.3097389122569968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408954824","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[1.2993463e-7,0.6834531,0.31358534,0.00007456933,0.000029632569,0.0017560329,0.0000010224023,0.00013027125,0.0009699182],"genre_scores_gemma":[0.000020058607,0.99580574,0.0027475727,0.0003061039,0.00006448301,0.00062348123,0.000086233325,0.000016145263,0.00033016107],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976979,0.00018041939,0.0008106328,0.0007742105,0.00020928925,0.00032758195],"domain_scores_gemma":[0.9977801,0.00083506544,0.00053448085,0.00063848536,0.00009541095,0.00011645298],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00020378274,0.00041256307,0.001036733,0.00027349405,0.0004046538,0.00015637082,0.00072064024,0.00012645878,0.0000017981207],"category_scores_gemma":[0.00005181328,0.00037632053,0.00013068657,0.0011874681,0.000110103625,0.00016661148,0.0008274371,0.0007261074,0.0000122938],"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":[1.8198138e-7,0.000010360685,0.000014905951,0.0371617,0.000012939114,8.105666e-7,0.000029408382,0.02043149,4.5727163e-8,0.0056981076,0.000102005884,0.93653804],"study_design_scores_gemma":[0.00009770482,0.000028184128,0.0000045884913,0.012007429,0.00010579782,0.000016363478,0.000014785318,0.04592859,5.998701e-8,0.000074874624,0.94142514,0.00029648098],"about_ca_topic_score_codex":0.000008436875,"about_ca_topic_score_gemma":0.0000012832232,"teacher_disagreement_score":0.94132316,"about_ca_system_score_codex":0.000063191765,"about_ca_system_score_gemma":0.00011753181,"threshold_uncertainty_score":0.99986887},"labels":[],"label_agreement":null},{"id":"W4409147637","doi":"10.1038/s41586-025-08744-2","title":"Mastering diverse control tasks through world models","year":2025,"lang":"en","type":"article","venue":"Nature","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scratch; Reinforcement learning; Artificial intelligence; Robustness (evolution); Normalization (sociology); Machine learning; Control (management); Programming language","score_opus":0.015993840515038285,"score_gpt":0.27037089696356514,"score_spread":0.2543770564485269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409147637","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":[0.00015767111,0.00030049813,0.9303779,0.0019652513,0.0010137316,0.00012911252,0.0000010811309,0.00018046644,0.065874286],"genre_scores_gemma":[0.9470498,0.000009184555,0.03301218,0.0061743194,0.000055308985,0.0000056785325,0.0000017143959,0.0000059524136,0.013685862],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907726,0.00002995524,0.00013878648,0.00026230628,0.0002507815,0.00024090284],"domain_scores_gemma":[0.999282,0.0000745033,0.000055217886,0.00049178704,0.00006648724,0.00003000648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010830241,0.000119007076,0.00013340279,0.000104290695,0.00011460024,0.00015719661,0.0008452351,0.000308915,0.000017824075],"category_scores_gemma":[0.000033123186,0.000108934684,0.00005783586,0.00048263732,0.000023285602,0.00060750166,0.00032384164,0.0013181205,0.000033168115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005921775,0.0000065281083,0.00025523893,0.000015612128,0.00002867042,0.000011525682,0.00021309534,0.71067435,0.00007508358,0.27910432,0.0077077956,0.0019018457],"study_design_scores_gemma":[0.0005848581,0.000015064666,0.0003253783,0.000061275685,0.000011316269,0.0000013698194,0.000018358589,0.94206965,0.00018799397,0.0071519106,0.04943608,0.00013676629],"about_ca_topic_score_codex":0.0000065505683,"about_ca_topic_score_gemma":0.0000041584985,"teacher_disagreement_score":0.94689214,"about_ca_system_score_codex":0.000053443862,"about_ca_system_score_gemma":0.000040385,"threshold_uncertainty_score":0.5726651},"labels":[],"label_agreement":null},{"id":"W4409183409","doi":"10.1007/978-3-031-88714-7_35","title":"Retrieval-Augmented Neural Team Formation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 Toronto; University of Guelph","funders":"","keywords":"Computer science; Artificial neural network; Artificial intelligence; Human–computer interaction","score_opus":0.014930001063955195,"score_gpt":0.2470052268019763,"score_spread":0.2320752257380211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409183409","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":[0.000011005683,0.0001698784,0.97844195,0.000869303,0.002585505,0.00050086994,0.0000019372915,0.00030403546,0.017115496],"genre_scores_gemma":[0.15593413,0.00017754399,0.8184835,0.007948184,0.0009570524,0.000015400252,0.000057037236,0.00009036477,0.016336806],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960338,0.000043389326,0.0007150302,0.0011676252,0.0013366492,0.00070351054],"domain_scores_gemma":[0.9970862,0.00042636067,0.00042448894,0.0016008014,0.0003232884,0.00013883095],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008299758,0.0005271964,0.0004743096,0.0011751356,0.00032306384,0.00081115233,0.0038264717,0.0003322302,0.000020944188],"category_scores_gemma":[0.00023542823,0.0004989911,0.0001449503,0.0010075443,0.00038872217,0.001230736,0.0018945287,0.0010528514,0.00006584527],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007818333,0.000010046789,0.00001924222,0.00006809033,0.000010082972,0.000025633926,0.00037082745,0.7693766,0.00008259693,0.012222892,0.00025453698,0.21755168],"study_design_scores_gemma":[0.00026181596,0.00015852087,0.000032118798,0.00038657658,0.000008541737,0.000031731564,1.0810117e-7,0.98222244,0.0011223722,0.01195995,0.0033405684,0.00047523528],"about_ca_topic_score_codex":0.0000063551556,"about_ca_topic_score_gemma":0.0000065928593,"teacher_disagreement_score":0.21707644,"about_ca_system_score_codex":0.000572047,"about_ca_system_score_gemma":0.00048377604,"threshold_uncertainty_score":0.99974614},"labels":[],"label_agreement":null},{"id":"W4409347970","doi":"10.1609/aaai.v39i22.34490","title":"Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"Chinese Academy of Sciences","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.08210690364603603,"score_gpt":0.31301082425299065,"score_spread":0.23090392060695464,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409347970","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":[0.16279732,0.000025228026,0.82495266,0.0027272692,0.00019771341,0.00077230646,2.7954752e-7,0.0000902107,0.00843704],"genre_scores_gemma":[0.9893023,0.00002382644,0.0097704325,0.00016623018,0.00000886089,0.000043560613,0.0000010311032,0.000007968785,0.0006757884],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998159,0.00004453958,0.0006585265,0.00039343646,0.00043273106,0.00031180133],"domain_scores_gemma":[0.9984218,0.000104318715,0.00044158832,0.00042000652,0.0005679462,0.000044359644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069793826,0.00020619822,0.00022479454,0.0002453855,0.00027436158,0.00023214884,0.0014147977,0.00007667908,0.00001284296],"category_scores_gemma":[0.00035498734,0.00015730067,0.000056481167,0.00091545517,0.0002002413,0.000096419324,0.0004603557,0.00044320023,0.00002322452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025157318,0.000052801137,0.0005653755,0.000021246426,0.000009961904,1.9620072e-7,0.0008510516,0.63081485,0.011837993,0.35229218,0.000019208146,0.0035099916],"study_design_scores_gemma":[0.000079284,0.00013660216,0.00043271214,0.00034014246,0.000008356497,0.0000012941114,0.00044022288,0.8942902,0.10309552,0.0009873925,0.000042271724,0.00014597393],"about_ca_topic_score_codex":0.00008608641,"about_ca_topic_score_gemma":0.000026806378,"teacher_disagreement_score":0.826505,"about_ca_system_score_codex":0.00015614434,"about_ca_system_score_gemma":0.00014206172,"threshold_uncertainty_score":0.6414535},"labels":[],"label_agreement":null},{"id":"W4409361576","doi":"10.1609/aaai.v39i25.34864","title":"ModelDiff: Symbolic Dynamic Programming for Model-Aware Policy Transfer in Deep Q-Learning","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Computer science; Transfer of learning; Transfer (computing); Dynamic programming; Artificial intelligence; Programming language; Parallel computing; Algorithm","score_opus":0.04088646043850981,"score_gpt":0.31499908200665955,"score_spread":0.27411262156814975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409361576","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":[0.018381454,0.000018592913,0.97489953,0.002664498,0.00015046282,0.0008803745,0.0000012452384,0.00012893789,0.0028749134],"genre_scores_gemma":[0.98813874,0.000044103384,0.010659297,0.00019874878,0.00002032162,0.00014062731,0.0000010873174,0.000018260047,0.00077880244],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768275,0.00002032966,0.0007186862,0.00057840336,0.00040547497,0.00059435284],"domain_scores_gemma":[0.99879795,0.00013159939,0.00017915938,0.0003000364,0.0005232928,0.000067930756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054781314,0.00028651903,0.000358549,0.0004957999,0.0002505225,0.00031846465,0.0021932668,0.00014744916,0.0000043198543],"category_scores_gemma":[0.0004891427,0.00024475725,0.00016734951,0.0013475162,0.00017400156,0.00042224102,0.00032103644,0.00052175345,0.000007671167],"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":[0.00003149064,0.000049314855,0.00010262127,0.00008920532,0.000010291162,1.0390442e-7,0.0013300533,0.36419582,0.0019343144,0.577323,0.0000026440357,0.054931127],"study_design_scores_gemma":[0.00006132804,0.00011883569,0.0000412948,0.00032558417,0.000011151275,7.400587e-7,0.00038050546,0.90857077,0.02340014,0.06683898,0.00004569832,0.00020498308],"about_ca_topic_score_codex":0.000039346814,"about_ca_topic_score_gemma":0.000020942225,"teacher_disagreement_score":0.9697573,"about_ca_system_score_codex":0.00016941981,"about_ca_system_score_gemma":0.00024924395,"threshold_uncertainty_score":0.9980911},"labels":[],"label_agreement":null},{"id":"W4409361642","doi":"10.1609/aaai.v39i25.34887","title":"Flow Factorization for Efficient Generative Flow Networks","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"University of Toronto","keywords":"Flow (mathematics); Computer science; Generative grammar; Artificial intelligence; Mathematics; Geometry","score_opus":0.05156236654893604,"score_gpt":0.29477046231317067,"score_spread":0.24320809576423463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409361642","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":[0.0011744599,0.000014089812,0.990986,0.001817451,0.0012486272,0.0006973515,0.0000026241864,0.00009046893,0.0039689443],"genre_scores_gemma":[0.9660493,0.000016181148,0.032719087,0.00029279393,0.00008486226,0.000059641297,0.0000019906229,0.000010038887,0.0007660829],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828357,0.000017174967,0.00052880245,0.0004610231,0.0003610306,0.0003484077],"domain_scores_gemma":[0.99819475,0.00017149338,0.00032556133,0.00029826685,0.00095672475,0.000053213833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043225838,0.00021912382,0.00023704678,0.00014454965,0.00032120023,0.00034673163,0.0016449571,0.00011003695,0.000016815604],"category_scores_gemma":[0.0006048456,0.00016949726,0.0001281395,0.00081021525,0.00014880985,0.0002012488,0.00033889757,0.00023787284,0.00001384445],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020417563,0.00002983749,0.000026632075,0.000018926668,0.000012735727,3.106793e-8,0.00036491556,0.5367439,0.0019329445,0.44062966,0.00018097703,0.020039054],"study_design_scores_gemma":[0.000031050167,0.00010947763,0.000030502324,0.00013958407,0.000011930232,2.5523798e-7,0.00009284439,0.8445792,0.1342081,0.020513192,0.00014710583,0.00013672929],"about_ca_topic_score_codex":0.000004868024,"about_ca_topic_score_gemma":0.0000016210291,"teacher_disagreement_score":0.96487486,"about_ca_system_score_codex":0.00008368578,"about_ca_system_score_gemma":0.00012398824,"threshold_uncertainty_score":0.69118977},"labels":[],"label_agreement":null},{"id":"W4409563182","doi":"10.1007/s13042-025-02622-z","title":"Reward design in multi-agent systems using successor features and multi-information source bayesian optimization","year":2025,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Research Foundation of Korea","keywords":"Successor cardinal; Computational intelligence; Computer science; Bayesian probability; Artificial intelligence; Bayesian optimization; Multi-agent system; Machine learning; Data mining; Mathematics","score_opus":0.016699151340101286,"score_gpt":0.2864372175682467,"score_spread":0.2697380662281454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409563182","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":[0.0043060244,0.0008323691,0.9937345,0.00040731806,0.00053671055,0.0001007603,5.096571e-7,0.000021934255,0.000059883656],"genre_scores_gemma":[0.72278804,0.00044960083,0.2761483,0.00009559526,0.000033509154,0.0000010933423,0.0000034762113,0.0000069141797,0.00047350142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99865025,0.00020719577,0.0005251314,0.00011942401,0.0003615087,0.00013648497],"domain_scores_gemma":[0.99890035,0.0001676204,0.0004855854,0.00007559107,0.00031360352,0.000057261936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072166225,0.00012933774,0.00017529198,0.00048153344,0.000085299376,0.0005357607,0.00037607335,0.00007629701,0.0000019833012],"category_scores_gemma":[0.00042063816,0.0001188549,0.000033203964,0.0001613949,0.000034231947,0.00057623687,0.00017044654,0.00041385097,5.6217647e-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":[0.000025710171,0.000019677667,0.021773623,0.000018983437,0.0000482175,0.000010020512,0.0008407349,0.9709139,0.000039030336,0.0004142009,0.000016223545,0.0058797076],"study_design_scores_gemma":[0.0011678758,0.00006745873,0.0036316854,0.00024742016,0.000015289974,0.00014586748,0.00014069672,0.9936463,0.00003774311,0.000012426586,0.00078486884,0.00010232544],"about_ca_topic_score_codex":0.00013001096,"about_ca_topic_score_gemma":0.000003648725,"teacher_disagreement_score":0.71848196,"about_ca_system_score_codex":0.00010522994,"about_ca_system_score_gemma":0.00006442394,"threshold_uncertainty_score":0.5166353},"labels":[],"label_agreement":null},{"id":"W4409632503","doi":"10.1016/b978-0-443-14081-5.00070-2","title":"Multi-Agent Reinforcement Learning Under General Information Structures","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Psychology; Artificial intelligence; Social psychology","score_opus":0.018375270866169687,"score_gpt":0.24956501738888678,"score_spread":0.2311897465227171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409632503","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010325499,0.000095321484,0.4215192,0.000056089677,0.000802586,0.00044657674,0.0000012807226,0.00022986672,0.5768481],"genre_scores_gemma":[0.0005813891,0.000089166606,0.03509736,0.0014026538,0.00015692468,0.000029007011,0.00010628686,0.000036498466,0.9625007],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970117,0.000052566906,0.0009995865,0.00051006535,0.00089375617,0.0005322916],"domain_scores_gemma":[0.99767464,0.00006843439,0.0007442325,0.0010931365,0.00025783476,0.00016171992],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003207047,0.00065283134,0.0005315722,0.00051317015,0.00036068202,0.00054686575,0.001359247,0.00044245413,0.0001420896],"category_scores_gemma":[0.000049484057,0.0006355854,0.00029387558,0.000045033587,0.00009166418,0.0004908929,0.00107361,0.0011302963,0.0003469478],"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":[0.0000035378075,0.0000012530309,0.0000024107912,0.000091005655,0.000119315,0.0000049557625,0.0003392975,0.42677042,0.0000064143214,0.1308041,0.0003293587,0.44152793],"study_design_scores_gemma":[0.00043314046,0.00008203529,0.000025389741,0.00022377765,0.000054494132,0.0000071076647,0.000008180538,0.1867044,0.000036843954,0.001727714,0.81012297,0.00057396654],"about_ca_topic_score_codex":0.0000019306606,"about_ca_topic_score_gemma":0.0000022617255,"teacher_disagreement_score":0.8097936,"about_ca_system_score_codex":0.00039380664,"about_ca_system_score_gemma":0.00034703905,"threshold_uncertainty_score":0.99960953},"labels":[],"label_agreement":null},{"id":"W4409738260","doi":"10.1016/j.eswa.2025.127717","title":"CCMA: A framework for cascading cooperative multi-agent in autonomous driving merging using Large Language Models","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs","funders":"Hunan Provincial Key Laboratory of Materials Protection for Electric Power and Transportation, Changsha University of Science and Technology; Tsinghua Shenzhen International Graduate School; Science, Technology and Innovation Commission of Shenzhen Municipality","keywords":"Computer science; Artificial intelligence","score_opus":0.028189147063689083,"score_gpt":0.32765445691081624,"score_spread":0.29946530984712716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409738260","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":[0.0010476912,0.00089000136,0.99526685,0.00015466161,0.00017893,0.0019338132,0.0000032185612,0.00020578621,0.00031903316],"genre_scores_gemma":[0.64107305,0.000005836211,0.35662106,0.00011401523,0.00004980114,0.0017238545,0.0000054961124,0.000017632661,0.00038929333],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984321,0.00006874168,0.00040746407,0.0004960204,0.00017405071,0.00042163112],"domain_scores_gemma":[0.9986922,0.00027753098,0.00016661758,0.00067341013,0.00012112681,0.00006911844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033775056,0.00019896621,0.00027662594,0.00024557556,0.0004367441,0.0002609123,0.00057876715,0.00009942531,0.0000012027288],"category_scores_gemma":[0.00005166359,0.00018304317,0.000045564633,0.0007804606,0.000026883226,0.00037247254,0.0001708588,0.00019834905,0.0000050497624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016730537,0.000040573526,0.00024147675,0.000036064608,0.000028546236,0.0000020306045,0.0068659056,0.77872735,0.00056906627,0.21327767,0.00003156932,0.00017810764],"study_design_scores_gemma":[0.00046398366,0.00001584,0.000027251766,0.00039466948,0.000006707413,0.0000054196853,0.002503658,0.99420595,0.00022258819,0.00009095006,0.0018599154,0.00020305146],"about_ca_topic_score_codex":0.00021527917,"about_ca_topic_score_gemma":0.000036987003,"teacher_disagreement_score":0.6400253,"about_ca_system_score_codex":0.00037127893,"about_ca_system_score_gemma":0.00017421127,"threshold_uncertainty_score":0.7464284},"labels":[],"label_agreement":null},{"id":"W4409882931","doi":"10.1109/tai.2025.3564900","title":"Prescribed Performance Resilient Motion Coordination With Actor–Critic Reinforcement Learning Design for UAV-USV Systems","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Motion (physics); Reinforcement; Computer science; Aeronautics; Engineering; Artificial intelligence; Structural engineering","score_opus":0.04943525313310071,"score_gpt":0.2841132150108918,"score_spread":0.2346779618777911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409882931","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":[0.0015834029,0.000018629271,0.99451745,0.00033215605,0.0014312448,0.0014263517,0.00000105496,0.00032211258,0.00036761392],"genre_scores_gemma":[0.984109,0.000028711704,0.012254793,0.00007231086,0.000034209832,0.00036741453,0.0000038906874,0.000019902924,0.003109774],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976877,0.00015856524,0.00063997833,0.0005523888,0.00049499585,0.00046639828],"domain_scores_gemma":[0.998322,0.00044810836,0.0001828025,0.0005298094,0.00042925475,0.00008803325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006643851,0.00027402578,0.00023875626,0.0004193437,0.0007436706,0.0003996491,0.0005903162,0.00011713749,0.000014461228],"category_scores_gemma":[0.000058648773,0.0002625,0.000087047905,0.0008117918,0.00009556252,0.00069670036,0.0000063610773,0.0003882334,0.000057877114],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017008367,0.000074897405,0.0000056535114,0.00010476477,0.000041168325,0.0000010788214,0.00043756425,0.95195115,0.0013789186,0.01024619,0.000039758084,0.0355488],"study_design_scores_gemma":[0.00009802092,0.00081795565,0.000010661028,0.00023703754,0.00003584161,0.0000028275733,0.00017947872,0.84371406,0.15424404,0.00015828217,0.0002783477,0.00022345135],"about_ca_topic_score_codex":0.0000359802,"about_ca_topic_score_gemma":0.000006068922,"teacher_disagreement_score":0.9825256,"about_ca_system_score_codex":0.00031754968,"about_ca_system_score_gemma":0.00015102176,"threshold_uncertainty_score":0.9999827},"labels":[],"label_agreement":null},{"id":"W4409989961","doi":"10.1101/2025.04.28.651014","title":"Interaction between Model-based and Model-free Mechanisms in Motor Learning","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Reinforcement Learning in Robotics","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":"Department of Science and Technology, Ministry of Science and Technology, India","keywords":"Computer science; Motor learning; Psychology; Cognitive science; Neuroscience","score_opus":0.01913034100641843,"score_gpt":0.23865849655027113,"score_spread":0.2195281555438527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409989961","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":[0.037330773,0.00008658623,0.9604163,0.00030825546,0.0005407946,0.000624241,0.000028060547,0.00062787515,0.000037086378],"genre_scores_gemma":[0.770071,0.000040678988,0.22946726,0.00016215307,0.000063647654,0.00011204749,3.721456e-7,0.000049320166,0.000033495126],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996525,0.00020959914,0.0007372548,0.0013323762,0.0005632145,0.00063255406],"domain_scores_gemma":[0.9968552,0.00018962949,0.00051916554,0.0019144317,0.00030369867,0.00021788737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00097056123,0.00061218184,0.00065940316,0.0008727059,0.00019262743,0.0005881281,0.001929108,0.00060879026,0.0000032788753],"category_scores_gemma":[0.0004442997,0.0007325415,0.00012960148,0.0006031828,0.00006315476,0.0005208664,0.0024764244,0.0018885542,0.000010242644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010791101,0.000026573418,0.001687762,0.00027853626,0.000042683892,0.000010057409,0.000022352528,0.9766679,0.014067315,0.0071550086,0.00002412869,0.000006882832],"study_design_scores_gemma":[0.00056627515,0.000058582747,0.001863678,0.00062488567,0.000044785065,3.5494838e-9,0.0000013353074,0.9821255,0.013881212,0.00011084947,0.00008445506,0.0006384454],"about_ca_topic_score_codex":0.000038039958,"about_ca_topic_score_gemma":0.0000016291275,"teacher_disagreement_score":0.7327403,"about_ca_system_score_codex":0.0005155548,"about_ca_system_score_gemma":0.0008669163,"threshold_uncertainty_score":0.99951255},"labels":[],"label_agreement":null},{"id":"W4410235858","doi":"10.3390/jcp5020023","title":"Combining Supervised and Reinforcement Learning to Build a Generic Defensive Cyber Agent","year":2025,"lang":"en","type":"article","venue":"Journal of Cybersecurity and Privacy","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.017410837487859866,"score_gpt":0.26187635266903847,"score_spread":0.2444655151811786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410235858","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":[0.3912361,0.0006261439,0.6029814,0.0027289346,0.00043518658,0.00017700302,1.2981822e-7,0.00003031999,0.0017848089],"genre_scores_gemma":[0.9737915,0.0004035947,0.023739139,0.0015769701,0.000051235253,0.0000021406609,5.951337e-7,0.0000072649714,0.0004275584],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984765,0.00012156927,0.0005416075,0.00021711443,0.00036088904,0.00028232372],"domain_scores_gemma":[0.99878985,0.00020339753,0.00029174754,0.0002578055,0.00024191757,0.0002152738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067854516,0.00017492248,0.00032423227,0.0003165535,0.0002504875,0.00029606058,0.0004968419,0.00007187952,0.000011121241],"category_scores_gemma":[0.0004073135,0.00016006215,0.000081419545,0.00037664437,0.000049855113,0.00047899203,0.000716497,0.00047696516,0.000004538335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002478646,0.000120240846,0.024651749,0.000309511,0.0006491392,0.00028167674,0.07230311,0.75135726,0.003171063,0.08942847,0.006203859,0.051276032],"study_design_scores_gemma":[0.008505552,0.0035203379,0.035725303,0.0018074719,0.0003373107,0.0006460349,0.003637445,0.6262958,0.0035772792,0.007210657,0.30721137,0.0015253994],"about_ca_topic_score_codex":0.000020418542,"about_ca_topic_score_gemma":0.0000012979731,"teacher_disagreement_score":0.5825554,"about_ca_system_score_codex":0.000066336186,"about_ca_system_score_gemma":0.00011387693,"threshold_uncertainty_score":0.6527145},"labels":[],"label_agreement":null},{"id":"W4410431351","doi":"10.1016/j.neunet.2025.107574","title":"Multi-agent self-attention reinforcement learning for multi-USV hunting target","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Nexen (Canada)","funders":"National Major Science and Technology Projects of China; Major Science and Technology Project of Hainan Province; Hainan University; Natural Science Foundation of Hainan Province; National Natural Science Foundation of China","keywords":"Reinforcement learning; Reinforcement; Computer science; Artificial intelligence; Psychology; Social psychology","score_opus":0.025581076575169767,"score_gpt":0.2818252087779485,"score_spread":0.2562441322027787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410431351","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":[0.0011882198,0.00012511034,0.99459916,0.00031917726,0.0019465799,0.0007673032,1.4016685e-7,0.00064133597,0.00041299668],"genre_scores_gemma":[0.6949129,0.000034413748,0.29558793,0.0007885953,0.0001774093,0.00010185274,0.000034277335,0.000026843038,0.008335763],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99770314,0.00011602158,0.0005811553,0.000581905,0.0002867431,0.00073101505],"domain_scores_gemma":[0.99873936,0.000185264,0.0003007686,0.0005020934,0.00017333802,0.000099148616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000561269,0.0002871691,0.00027116117,0.00016962267,0.00059350766,0.00037502838,0.00083646225,0.00015589148,0.000013306486],"category_scores_gemma":[0.00014991053,0.00029058955,0.00020243903,0.00049928547,0.000028870376,0.00048241997,0.00051914377,0.000527957,0.000023560624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008099473,0.000032314263,0.006059031,0.000046685353,0.000049981943,0.0000030886608,0.00012242266,0.9868067,0.00014997052,0.0012549557,0.00056439673,0.004902349],"study_design_scores_gemma":[0.001217663,0.000104094346,0.0032980067,0.00006775096,0.000025848502,0.0000018880125,0.000028689765,0.98697376,0.00008775904,0.000008971099,0.007920093,0.00026546273],"about_ca_topic_score_codex":0.000013916095,"about_ca_topic_score_gemma":0.0000028764978,"teacher_disagreement_score":0.6990112,"about_ca_system_score_codex":0.00014402746,"about_ca_system_score_gemma":0.00003875303,"threshold_uncertainty_score":0.99995464},"labels":[],"label_agreement":null},{"id":"W4410537008","doi":"10.1007/s00521-025-11288-1","title":"Human-AI collaboration in real-world complex environment with reinforcement learning","year":2025,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Reinforcement Learning in Robotics","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":"Thales (Canada); Espace pour la vie; Network for Business Sustainability; University of Alberta","funders":"","keywords":"Computational Science and Engineering; Reinforcement learning; Computer science; Reinforcement; Artificial intelligence; Machine learning; Psychology; Social psychology","score_opus":0.019318648162714565,"score_gpt":0.3100600253669215,"score_spread":0.29074137720420695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410537008","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":[0.012606694,0.000015230008,0.97647536,0.0015073561,0.00002122183,0.00047812902,1.5821638e-7,0.0001635878,0.008732276],"genre_scores_gemma":[0.99000347,0.000010848704,0.007903192,0.0003998508,0.000025863977,0.000050040115,0.000016721662,0.0000061813107,0.001583823],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989268,0.000055226825,0.00029358675,0.00034189245,0.00017169163,0.00021079899],"domain_scores_gemma":[0.99941105,0.00007343954,0.000123409,0.00031057635,0.000038445058,0.00004309983],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016407191,0.00012936651,0.00013990806,0.0001867705,0.00046247695,0.00020571238,0.00028051177,0.000028398785,0.000004417128],"category_scores_gemma":[0.000004926492,0.00012503783,0.000015221198,0.0006932114,0.000057813257,0.0001391628,0.00022131173,0.00024503277,0.0000065332765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015721345,0.000012990952,0.009053546,0.0000148927065,0.0000054522525,6.5854147e-7,0.00013443666,0.90306044,0.00031562982,0.083406836,0.00010092337,0.003892601],"study_design_scores_gemma":[0.00037239323,0.00007267662,0.025451558,0.000034585708,0.000006253757,0.0000011368203,0.00006122151,0.9606989,0.0000852017,0.00022659636,0.012853456,0.000135997],"about_ca_topic_score_codex":0.000066953646,"about_ca_topic_score_gemma":0.000030706462,"teacher_disagreement_score":0.9773968,"about_ca_system_score_codex":0.00009029556,"about_ca_system_score_gemma":0.000030513342,"threshold_uncertainty_score":0.5098895},"labels":[],"label_agreement":null},{"id":"W4410629910","doi":"10.1016/j.neucom.2025.130470","title":"SAGE: Self-evolving Agents with Reflective and Memory-augmented Abilities","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"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":"Science and Technology Planning Project of Shenzhen Municipality","keywords":"Computer science; SAGE; Artificial intelligence; Cognitive science; Cognitive psychology; Psychology","score_opus":0.00843311187358675,"score_gpt":0.2504298560117046,"score_spread":0.24199674413811784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410629910","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":[0.07694993,0.000067855864,0.9038557,0.00038856725,0.000283982,0.0003206647,1.3091798e-7,0.00058493746,0.017548228],"genre_scores_gemma":[0.92985964,0.0000064958285,0.06842996,0.00081935007,0.000035334186,0.000007254879,5.2990106e-7,0.000012899711,0.00082855526],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985333,0.00011370031,0.00023916452,0.00050219335,0.0002601643,0.0003514651],"domain_scores_gemma":[0.99900943,0.00032378922,0.00012043195,0.00039263826,0.00009420092,0.000059501446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023859537,0.00018610955,0.00018190934,0.0001631511,0.0003616615,0.00033975413,0.0004688522,0.00004174175,0.0000047360636],"category_scores_gemma":[0.00009662323,0.00017084402,0.000029095794,0.00054098933,0.000051523282,0.00033663513,0.0005992646,0.00027321346,0.0000049590603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004621095,0.00019343247,0.052037,0.000728123,0.00038678042,0.00017685072,0.016357206,0.80672896,0.0017852881,0.01465836,0.0021878306,0.10471395],"study_design_scores_gemma":[0.00054881244,0.00015024969,0.021318212,0.00016821864,0.000016040594,0.000017796276,0.00014514342,0.9758537,0.00070454,0.00017583999,0.00071476336,0.00018670582],"about_ca_topic_score_codex":0.000014518023,"about_ca_topic_score_gemma":0.0000014108685,"teacher_disagreement_score":0.8529097,"about_ca_system_score_codex":0.000079156474,"about_ca_system_score_gemma":0.00007367175,"threshold_uncertainty_score":0.69668174},"labels":[],"label_agreement":null},{"id":"W4410742988","doi":"10.1007/978-3-031-91524-6_1","title":"Why AI and Security?","year":2025,"lang":"en","type":"book-chapter","venue":"Progress in IS","topic":"Reinforcement Learning in Robotics","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":"National Research Council Canada; McGill University; MacEwan University; York University; University of Toronto","funders":"","keywords":"Computer science","score_opus":0.01238897226127554,"score_gpt":0.2654781307917201,"score_spread":0.25308915853044456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410742988","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000031566492,0.00926057,0.20067453,0.007951704,0.00091399683,0.000605635,0.00000592982,0.00027491417,0.78030956],"genre_scores_gemma":[0.005834641,0.0019480143,0.038397573,0.017692085,0.00027828332,0.00008499129,0.000025270358,0.00008903464,0.9356501],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99872124,0.000013532178,0.00026545086,0.0004639852,0.00030722414,0.00022855612],"domain_scores_gemma":[0.9991233,0.000053466043,0.00012396235,0.0005832966,0.000064900436,0.000051074996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014208826,0.00023341183,0.00026306647,0.0002527747,0.00004991574,0.0002441701,0.00073556916,0.00023895962,0.00005699787],"category_scores_gemma":[0.000014155974,0.00024035556,0.00005099626,0.000066975044,0.00012444721,0.00018773839,0.0008065141,0.0005295078,0.000028386843],"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":[0.0000038436924,0.000010322023,0.0018381053,0.00030439824,0.00005315957,0.000080330734,0.0010203016,0.00017542469,3.9980115e-8,0.84729856,0.04117084,0.10804468],"study_design_scores_gemma":[0.00022320457,0.000064327345,0.000037017515,0.0006758501,0.000013952734,0.000006752979,0.0000015093334,0.08548592,0.000010581016,0.03641637,0.87670696,0.00035757845],"about_ca_topic_score_codex":0.000004193855,"about_ca_topic_score_gemma":0.0000032557612,"teacher_disagreement_score":0.8355361,"about_ca_system_score_codex":0.000047828784,"about_ca_system_score_gemma":0.000061871804,"threshold_uncertainty_score":0.98014146},"labels":[],"label_agreement":null},{"id":"W4410779232","doi":"10.2139/ssrn.5270695","title":"Decentralized Security for Multi-User Vr Applications Using Multi-Agent Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Computer science; Human–computer interaction; Reinforcement; Artificial intelligence; Engineering","score_opus":0.038889901537594175,"score_gpt":0.33001636359697195,"score_spread":0.29112646205937776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410779232","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":[0.00030995964,0.0023249206,0.99374616,0.00022522881,0.00096206524,0.0020601403,0.0000042353686,0.0002511105,0.000116192874],"genre_scores_gemma":[0.21389002,0.01899373,0.7284758,0.0005751559,0.000902122,0.0009492775,0.0002163058,0.0001881329,0.035809457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99342734,0.00027075532,0.0011703057,0.0009080509,0.00068004197,0.003543527],"domain_scores_gemma":[0.9968292,0.00014468607,0.001233558,0.0010063213,0.0005575772,0.00022865646],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0027425562,0.00062153564,0.0006394842,0.00044500778,0.0010102151,0.0006755762,0.002649835,0.00042400236,0.00001230574],"category_scores_gemma":[0.00023003675,0.00064872135,0.0005856213,0.00039091075,0.00006419433,0.000349156,0.0016393588,0.0061794543,0.000016886064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000020237048,0.00007932162,0.00027664055,0.00013057672,0.0004492542,0.0000013993111,0.0005118626,0.89850813,0.000047277033,0.09688313,0.000035037512,0.0030571108],"study_design_scores_gemma":[0.0019660033,0.00012977043,0.000017235187,0.00020912844,0.00017465481,0.000049893963,0.00025614264,0.9576027,0.00012614697,0.00805455,0.030796489,0.00061731425],"about_ca_topic_score_codex":0.000095828145,"about_ca_topic_score_gemma":0.000067438916,"teacher_disagreement_score":0.26527035,"about_ca_system_score_codex":0.0041313544,"about_ca_system_score_gemma":0.00645471,"threshold_uncertainty_score":0.9996916},"labels":[],"label_agreement":null},{"id":"W4410887809","doi":"10.1109/syscon64521.2025.11014852","title":"A Simulation Pipeline to Facilitate Real-World Robotic Reinforcement Learning Applications","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Pipeline (software); Computer science; Human–computer interaction; Artificial intelligence; Operating system","score_opus":0.0397107984912193,"score_gpt":0.3063709812696117,"score_spread":0.26666018277839243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410887809","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":[0.000020231293,0.0000067483043,0.89424866,0.0015546442,0.00012892035,0.00064952666,8.979202e-8,0.0005007023,0.10289049],"genre_scores_gemma":[0.66155624,0.000007925376,0.07036479,0.001272386,0.000031247844,0.00012391136,0.000013478348,0.000008856587,0.26662114],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983296,0.000057485227,0.00049176463,0.0004354267,0.0003325304,0.00035322979],"domain_scores_gemma":[0.9984962,0.00036795792,0.000097967015,0.0007233344,0.00019901515,0.00011554204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035431108,0.00017476712,0.00018599327,0.00046882592,0.00027265612,0.00020838164,0.00070348725,0.000041434676,0.00006439325],"category_scores_gemma":[0.00016613601,0.00017311644,0.00006387866,0.0015927863,0.000021720283,0.000307956,0.00043874397,0.00020140485,0.0005562619],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032596133,0.000008969954,0.00034684292,0.000018119239,0.000011281261,4.6688524e-7,0.00020110435,0.9102255,0.000054141947,0.0817546,0.0008812821,0.0064944457],"study_design_scores_gemma":[0.00017878806,0.000044903238,0.0003406303,0.000021108872,0.000008554109,1.1213919e-7,0.000022119553,0.90449697,0.000096084455,0.00033609677,0.09429802,0.00015661646],"about_ca_topic_score_codex":0.00012777618,"about_ca_topic_score_gemma":0.00003181683,"teacher_disagreement_score":0.8238839,"about_ca_system_score_codex":0.0001813766,"about_ca_system_score_gemma":0.00008176803,"threshold_uncertainty_score":0.7149807},"labels":[],"label_agreement":null},{"id":"W4410988898","doi":"10.1016/j.trc.2025.105183","title":"Curiosity-driven reinforcement learning with graph transformers for decision-making in connected and autonomous vehicles","year":2025,"lang":"en","type":"article","venue":"Transportation Research Part C Emerging Technologies","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Curiosity; Reinforcement learning; Transformer; Reinforcement; Graph; Engineering; Computer science; Artificial intelligence; Psychology; Electrical engineering; Theoretical computer science; Social psychology; Structural engineering","score_opus":0.027220519970360464,"score_gpt":0.3392383197203113,"score_spread":0.31201779974995086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410988898","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":[0.092258684,0.00016411029,0.90336585,0.0022519028,0.000053918844,0.0008688201,0.0000012855577,0.00082795083,0.00020750296],"genre_scores_gemma":[0.96131974,0.0004127856,0.03785317,0.00003227174,0.0000032767477,0.00026878045,0.000011307677,0.000013014108,0.0000856237],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978089,0.00006232943,0.00047702625,0.00052818394,0.0004973607,0.00062622945],"domain_scores_gemma":[0.9982701,0.0010510718,0.00009944676,0.00028863517,0.00025520084,0.000035521974],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008745898,0.00019368294,0.00025817635,0.0013123744,0.00051796605,0.00015641125,0.00061774714,0.00015116186,0.0000037673149],"category_scores_gemma":[0.00042875268,0.00017847073,0.0000490417,0.0018127485,0.0002932037,0.00046874312,0.000052826006,0.00064886303,0.0000013348144],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001322291,0.000026386648,0.027413301,0.00018531541,0.00006207504,0.000018739554,0.0014925395,0.84113634,0.00027527832,0.064804606,0.00017497342,0.0642782],"study_design_scores_gemma":[0.0021306805,0.0009266694,0.017978394,0.0021731318,0.000028181033,0.0000015125314,0.0050643375,0.9472235,0.0029715467,0.011688615,0.009250024,0.00056342286],"about_ca_topic_score_codex":0.00005026152,"about_ca_topic_score_gemma":0.00027973508,"teacher_disagreement_score":0.8690611,"about_ca_system_score_codex":0.00009590309,"about_ca_system_score_gemma":0.00014855736,"threshold_uncertainty_score":0.7277825},"labels":[],"label_agreement":null},{"id":"W4411173295","doi":"10.1109/icse-nier66352.2025.00008","title":"Listening to the Firehose: Sonifying Z3’s Behavior","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Active listening; Computer science; Speech recognition; Psychology; Communication","score_opus":0.014707942629321126,"score_gpt":0.2865948154057638,"score_spread":0.2718868727764427,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411173295","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":[0.0018941168,0.000028815917,0.9517076,0.0063779796,0.00062383205,0.00021034261,7.2031874e-8,0.00022053397,0.0389367],"genre_scores_gemma":[0.7920836,0.0000035049559,0.11982094,0.0051723463,0.000058145208,0.000060935377,6.7189836e-7,0.000007840476,0.082791984],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910975,0.000030441252,0.00017165016,0.00022579408,0.00021307744,0.00024926814],"domain_scores_gemma":[0.9991338,0.00010405374,0.000033317272,0.00063399156,0.000048910373,0.000045872996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027306302,0.000090276626,0.000080617545,0.00008049454,0.00027335816,0.0003727104,0.0012258271,0.000031476266,0.000034083758],"category_scores_gemma":[0.00008848348,0.00006208706,0.000045607656,0.00051761494,0.000015601063,0.00018286757,0.0006514541,0.00014410172,0.00020822119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032123469,0.00003072005,0.009154347,0.000021343134,0.000031740907,0.000019996813,0.002387032,0.5646279,0.0006134105,0.2611444,0.033908386,0.12805755],"study_design_scores_gemma":[0.00026301967,0.00008737538,0.02216016,0.00008612584,0.000024272738,0.0000079701,0.00021280108,0.7169843,0.0021847824,0.00015465221,0.2575166,0.0003179946],"about_ca_topic_score_codex":0.000043671564,"about_ca_topic_score_gemma":0.000009325174,"teacher_disagreement_score":0.83188665,"about_ca_system_score_codex":0.000044088894,"about_ca_system_score_gemma":0.000055047858,"threshold_uncertainty_score":0.35940552},"labels":[],"label_agreement":null},{"id":"W4411225534","doi":"10.1017/9781009504942.008","title":"Reinforcement learning","year":2025,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Waterloo; McMaster University","funders":"","keywords":"Reinforcement; Reinforcement learning; Psychology; Computer science; Artificial intelligence; Social psychology","score_opus":0.018228091514921805,"score_gpt":0.20180634372568926,"score_spread":0.18357825221076746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411225534","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.4538517e-7,0.000032126376,0.43453035,0.000018131217,0.00027869813,0.0002131652,0.0000019783547,0.00030473855,0.56462055],"genre_scores_gemma":[0.00034332994,0.00011896556,0.001796191,0.00013204069,0.00006784087,6.8072524e-7,0.000032351407,0.000027010712,0.9974816],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99800867,0.000048074697,0.0003030995,0.0006942856,0.0005218787,0.00042397509],"domain_scores_gemma":[0.9980142,0.00012064686,0.00037802334,0.0011039913,0.0002169944,0.0001661251],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001602345,0.0004576376,0.00042603948,0.0003713248,0.00036018714,0.00018359807,0.001961875,0.0003748809,0.0000064994074],"category_scores_gemma":[0.00002823884,0.0005726983,0.00026212586,0.000021709833,0.0001291934,0.00021995122,0.0020104554,0.0010056621,0.000057721183],"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":[0.000011668529,0.0000017796362,9.402425e-7,0.000078867524,0.00012869808,0.00015194673,0.000038921484,0.042006966,0.0000049790524,0.9219901,0.03377934,0.0018057902],"study_design_scores_gemma":[0.00037641134,0.00008500784,0.0000015664764,0.00025888503,0.00008478505,0.000005857046,0.000006624393,0.06631155,0.00008823236,0.0000063637976,0.9322852,0.00048954703],"about_ca_topic_score_codex":0.00004023209,"about_ca_topic_score_gemma":1.91217e-7,"teacher_disagreement_score":0.9219837,"about_ca_system_score_codex":0.00038603196,"about_ca_system_score_gemma":0.00026019374,"threshold_uncertainty_score":0.9996725},"labels":[],"label_agreement":null},{"id":"W4411597815","doi":"10.1101/2025.06.17.659642","title":"Biological Reasoning with Reinforcement Learning through Natural Language Enables Generalizable Zero-Shot Cell Type Annotations","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Zero (linguistics); Computer science; Reinforcement; Shot (pellet); One shot; Artificial intelligence; Natural (archaeology); Natural language; Psychology; Linguistics; Biology; Engineering; Chemistry; Social psychology","score_opus":0.01926935263878364,"score_gpt":0.24168362320151324,"score_spread":0.2224142705627296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411597815","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":[0.055342738,0.0022675707,0.9377534,0.00015885175,0.0015727467,0.000852253,0.0000110695355,0.0013131637,0.00072822685],"genre_scores_gemma":[0.8276032,0.00034112573,0.17063661,0.00041367344,0.00017068075,0.000100170844,0.000004051865,0.00005727754,0.00067320396],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961061,0.00027515602,0.0006736335,0.0013387396,0.0006586355,0.0009477491],"domain_scores_gemma":[0.99659604,0.00015925677,0.00067534065,0.0016876096,0.000700239,0.00018153517],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00057138683,0.00074817316,0.0006524271,0.0002993416,0.000550615,0.0007960511,0.0017642329,0.0004721738,0.00003415454],"category_scores_gemma":[0.00032729827,0.0006746102,0.00014657459,0.0012620192,0.00013738484,0.00053943414,0.0016780419,0.0016199594,0.000060743885],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027174448,0.00004795514,0.0023008152,0.00027431754,0.00015918817,0.0000864284,0.00021660642,0.9485704,0.03981308,0.007957068,0.00054515083,0.000001831747],"study_design_scores_gemma":[0.0017424681,0.00069530983,0.0043769474,0.0020214207,0.00024040461,2.1936273e-7,0.00007440286,0.8182184,0.14419755,0.000008182443,0.025110483,0.0033142162],"about_ca_topic_score_codex":0.0001741793,"about_ca_topic_score_gemma":0.0000013953464,"teacher_disagreement_score":0.7722605,"about_ca_system_score_codex":0.0003727903,"about_ca_system_score_gemma":0.0009052285,"threshold_uncertainty_score":0.9995705},"labels":[],"label_agreement":null},{"id":"W4411745406","doi":"10.1007/978-3-031-95976-9_9","title":"Reinforcement Learning-Based Heuristics to Guide Domain-Independent Dynamic Programming","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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 King's University; Canada Research Chairs; University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Heuristics; Domain (mathematical analysis); Artificial intelligence; Dynamic programming; Machine learning; Algorithm; Operating system; Mathematics","score_opus":0.009434525304242686,"score_gpt":0.2577204471215944,"score_spread":0.24828592181735173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411745406","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":[0.000005736638,0.00009065038,0.98751616,0.0013411206,0.0021793966,0.0011930335,0.0000011945789,0.0004519412,0.0072207674],"genre_scores_gemma":[0.048489306,0.000018743514,0.93538404,0.00289025,0.00020277401,0.000045730154,0.000025198906,0.00006842642,0.012875523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99288386,0.00007094348,0.0011880768,0.0021495684,0.0023580166,0.001349548],"domain_scores_gemma":[0.99566203,0.0005555755,0.0005652204,0.0022350005,0.0005949849,0.00038716482],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016368678,0.00091110705,0.0007779338,0.0017967062,0.00056499103,0.0013533166,0.00544934,0.00043674445,0.000033253753],"category_scores_gemma":[0.00041574813,0.00091946096,0.0002350707,0.0012291531,0.00043156592,0.00035988164,0.0030625144,0.0017225558,0.000121036],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000068381123,0.000013519347,0.00002661621,0.000076010314,0.000016213738,0.00009706894,0.00039864538,0.8340173,0.00001828312,0.006545266,0.000052977313,0.15873127],"study_design_scores_gemma":[0.0003858225,0.00051817595,0.000021618856,0.00086904713,0.000015994367,0.000016696253,5.646411e-7,0.9559399,0.00017100264,0.0045092865,0.03663498,0.0009169091],"about_ca_topic_score_codex":0.000027863704,"about_ca_topic_score_gemma":0.00006404025,"teacher_disagreement_score":0.15781437,"about_ca_system_score_codex":0.0017275995,"about_ca_system_score_gemma":0.001760539,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W4411745413","doi":"10.1007/978-3-031-95976-9_16","title":"Shaping Reward Signals in Reinforcement Learning Using Constraint Programming","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Constraint (computer-aided design); Artificial intelligence; Constraint programming; Reinforcement; Constraint satisfaction; Mathematical optimization; Psychology; Mathematics; Stochastic programming","score_opus":0.03778212600561777,"score_gpt":0.28212690686802855,"score_spread":0.2443447808624108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411745413","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":[0.000053778585,0.00022962863,0.99149597,0.00028795516,0.0011284695,0.0008245244,3.499963e-7,0.00024375894,0.005735582],"genre_scores_gemma":[0.2494271,0.00005357381,0.7479348,0.00093540817,0.0002466653,0.000017423135,0.000007848992,0.00005040571,0.0013267759],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99419606,0.000091363625,0.0012275372,0.0017661703,0.001454571,0.0012642774],"domain_scores_gemma":[0.997089,0.0005965916,0.0006491987,0.0011669915,0.00031691053,0.0001812826],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022067924,0.0007406882,0.00082105777,0.0020434516,0.00040141426,0.0011552821,0.0032501835,0.00043161603,0.000032970438],"category_scores_gemma":[0.00037993904,0.0007764628,0.00015820013,0.0013182171,0.0007034856,0.00080975966,0.002497962,0.0020509975,0.000017110871],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032814798,0.0000068764493,0.0001154879,0.000080023034,0.00001203196,0.00009558878,0.00074404065,0.78350043,0.00012176679,0.006227858,0.0000019651245,0.20909066],"study_design_scores_gemma":[0.00033842475,0.0001904972,0.000013046542,0.0026256319,0.000010535004,0.00003871673,0.0000013692803,0.9895552,0.00035478576,0.005071061,0.0010451732,0.00075557944],"about_ca_topic_score_codex":0.000058740858,"about_ca_topic_score_gemma":0.000023976621,"teacher_disagreement_score":0.24937332,"about_ca_system_score_codex":0.0011886067,"about_ca_system_score_gemma":0.0013775296,"threshold_uncertainty_score":0.9998816},"labels":[],"label_agreement":null},{"id":"W4412026837","doi":"10.1016/j.neucom.2025.130917","title":"A reinforcement learning-assisted genetic programming algorithm for team formation problem considering person-job matching","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Computer science; Matching (statistics); Genetic algorithm; Artificial intelligence; Genetic programming; Reinforcement; Mathematical optimization; Algorithm; Machine learning; Mathematics; Psychology","score_opus":0.020509647936770344,"score_gpt":0.25831666010610516,"score_spread":0.2378070121693348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412026837","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":[0.0028265747,0.000041634754,0.99164283,0.00029735654,0.00042400678,0.0014316625,1.514216e-7,0.0008242857,0.0025115018],"genre_scores_gemma":[0.2957373,0.0000036685738,0.70296276,0.0003490179,0.000084725805,0.00011010265,0.0000065612585,0.000027423415,0.0007184236],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997442,0.00011506258,0.00068923953,0.00059863017,0.00039969676,0.0007553568],"domain_scores_gemma":[0.9985097,0.00037619963,0.00042488668,0.00039950517,0.00019566684,0.000094024515],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00055106776,0.00031520514,0.0003064041,0.00032723782,0.0009170314,0.0007767195,0.0007174591,0.00009488881,0.0000018399169],"category_scores_gemma":[0.00012561656,0.00034213124,0.0001545993,0.00060265337,0.0000358962,0.00054151047,0.00047415262,0.00045894453,0.000010694935],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023216683,0.000010169486,0.00018780863,0.00017237951,0.000022786719,0.0000043928812,0.0011296232,0.6442512,0.00041737666,0.0011212522,0.00010826909,0.35257238],"study_design_scores_gemma":[0.0007797812,0.00019724651,0.0004920117,0.0002992639,0.000023573173,0.000046398047,0.00027284332,0.9891511,0.00051262544,0.00013501827,0.007793131,0.00029700546],"about_ca_topic_score_codex":0.00002138499,"about_ca_topic_score_gemma":0.0000013866896,"teacher_disagreement_score":0.35227537,"about_ca_system_score_codex":0.000177551,"about_ca_system_score_gemma":0.00012359326,"threshold_uncertainty_score":0.9999031},"labels":[],"label_agreement":null},{"id":"W4412614147","doi":"10.21105/joss.07728","title":"EvoVis: Dashboard for Visualizing Evolutionary Neural Architecture Search Algorithms","year":2025,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de Recherche du Québec - Santé; Bayerische Forschungsallianz","keywords":"Computer science; Evolutionary algorithm; Architecture; Dashboard; Artificial intelligence; Machine learning; Data mining; Algorithm; Data science; Geography; Archaeology","score_opus":0.03184052293001022,"score_gpt":0.3412038084290155,"score_spread":0.30936328549900527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412614147","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":[0.0022481156,0.00045854656,0.99191123,0.0041542226,0.00047980825,0.00047856855,0.0000019633753,0.000063335836,0.00020420692],"genre_scores_gemma":[0.35859543,0.00006459389,0.62566316,0.004398117,0.0006112679,0.000023343086,0.0000068654176,0.00006881647,0.010568423],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980179,0.00032549392,0.0005234929,0.00018720956,0.0005615355,0.0003843668],"domain_scores_gemma":[0.997493,0.0010555837,0.00034846622,0.0005702466,0.00043612838,0.00009654977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018397236,0.00017811036,0.00030273374,0.00021696243,0.00056819554,0.00052467384,0.004680907,0.00006781303,0.000013485533],"category_scores_gemma":[0.00041479044,0.000120761564,0.00017165348,0.0005376591,0.0000855574,0.0006364379,0.0015633806,0.00061754754,0.0000069833322],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011261239,0.000027829848,0.00092886237,0.000045191497,0.000117525175,0.0000068338195,0.002297796,0.94043344,0.000070738286,0.0009058807,0.008728236,0.046325054],"study_design_scores_gemma":[0.0020951922,0.0007884441,0.003037922,0.00048521347,0.00012355408,0.00037767546,0.0009823787,0.9188653,0.00034425472,0.0032714133,0.06924334,0.0003852736],"about_ca_topic_score_codex":0.00002012995,"about_ca_topic_score_gemma":7.673946e-7,"teacher_disagreement_score":0.36624807,"about_ca_system_score_codex":0.000116491945,"about_ca_system_score_gemma":0.0003338198,"threshold_uncertainty_score":0.86983675},"labels":[],"label_agreement":null},{"id":"W4413042885","doi":"10.2139/ssrn.5361139","title":"Symphony: Edge-powered Decentralized Multi-agent Framework for Autonomous Co-evolving Intelligence","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Reinforcement Learning in Robotics","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":"Symphony; Enhanced Data Rates for GSM Evolution; Computer science; Artificial intelligence; Art; Art history","score_opus":0.02840843717819469,"score_gpt":0.32375354165604603,"score_spread":0.29534510447785134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413042885","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":[0.0001305483,0.007268145,0.98496467,0.0008542293,0.0050595882,0.0011079345,0.000010474951,0.00033568512,0.00026875158],"genre_scores_gemma":[0.16610904,0.029643213,0.79357296,0.00077352836,0.001144753,0.00022196598,0.00007122449,0.0001418391,0.008321475],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99202466,0.0002804333,0.0012818995,0.0011048295,0.00072075863,0.004587433],"domain_scores_gemma":[0.9959439,0.0006301379,0.0011845445,0.0014516528,0.00050996215,0.00027980816],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003057628,0.0007392866,0.0008337998,0.00048332088,0.0006329377,0.0011606227,0.0048621357,0.0007120915,0.000034022723],"category_scores_gemma":[0.0010999847,0.0007551795,0.00070382515,0.00039987866,0.00009859536,0.0003575802,0.0014526346,0.007610787,0.00006528603],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00004998101,0.00012977936,0.00029533595,0.00017317178,0.00086278,0.000011810517,0.0011723513,0.49689165,0.000023238013,0.45845202,0.0003427088,0.041595157],"study_design_scores_gemma":[0.00069086556,0.00031851613,0.000045350866,0.00071931054,0.00012196148,0.00010992903,0.00026737255,0.68357205,0.00030269162,0.30812666,0.004891205,0.0008340988],"about_ca_topic_score_codex":0.000037478767,"about_ca_topic_score_gemma":0.000033179964,"teacher_disagreement_score":0.19139168,"about_ca_system_score_codex":0.005395744,"about_ca_system_score_gemma":0.012791863,"threshold_uncertainty_score":0.99987626},"labels":[],"label_agreement":null},{"id":"W4413180594","doi":"10.1109/isscs66034.2025.11105702","title":"Learning Optimal Agent Behavior From a Synthetic Reasoning Action Dataset","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Ministry of Research, Innovation and Science","keywords":"Computer science; Action (physics); Artificial intelligence; Machine learning","score_opus":0.025904225356853723,"score_gpt":0.3018162174335818,"score_spread":0.27591199207672806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413180594","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":[0.020062039,0.00001915974,0.9758779,0.00020050642,0.00058755884,0.0001331268,0.0000061214937,0.00029697127,0.002816614],"genre_scores_gemma":[0.78409815,0.000024900393,0.20740426,0.00037920143,0.000057087065,0.00004476226,0.00039366187,0.0000139778995,0.0075840186],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99880534,0.00008541227,0.00021698789,0.00039263206,0.00024694222,0.00025270387],"domain_scores_gemma":[0.99909973,0.00013142423,0.00008675769,0.00059119944,0.000032718403,0.000058156238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020979402,0.00013113057,0.00012739499,0.000114175826,0.00021959793,0.00032085148,0.0006700182,0.00006150799,0.00015827142],"category_scores_gemma":[0.0001372158,0.00012748534,0.00004311001,0.00027154988,0.000026071832,0.00043126463,0.00048598213,0.00028788132,0.00020983766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008773168,0.000052104202,0.004132252,0.000011497618,0.00004923611,0.000033424774,0.00032082296,0.93191886,0.0017178432,0.008931251,0.006713313,0.046110623],"study_design_scores_gemma":[0.00021974863,0.00006496137,0.004542383,0.000060701335,0.000039158596,0.0000031302236,0.00014144048,0.9526994,0.0017890375,0.000020248577,0.040238686,0.00018108955],"about_ca_topic_score_codex":0.00019592281,"about_ca_topic_score_gemma":0.0000044488847,"teacher_disagreement_score":0.7684736,"about_ca_system_score_codex":0.000086536675,"about_ca_system_score_gemma":0.0000561257,"threshold_uncertainty_score":0.5198701},"labels":[],"label_agreement":null},{"id":"W4413276903","doi":"10.2514/6.2025-3412.c1","title":"Correction: Hybrid Framework for UAV Mission Planning Using Logic-Based Imaging and Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Nexen (Canada)","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence","score_opus":0.03083045445267923,"score_gpt":0.3194727886290114,"score_spread":0.28864233417633217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413276903","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":[0.0005327357,0.00013470679,0.9926364,0.0007450386,0.0014756004,0.00028987564,6.4342096e-8,0.00032832674,0.0038572685],"genre_scores_gemma":[0.5763872,0.000004722265,0.41911036,0.0014007344,0.00006020399,0.000008477901,0.0000048999464,0.00001194937,0.0030114464],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986229,0.000048837646,0.00032496342,0.0004155425,0.0002207893,0.00036696316],"domain_scores_gemma":[0.9988034,0.0005332061,0.00016132735,0.00031335434,0.00011079563,0.000077930716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040008468,0.00018917276,0.00018536548,0.0002257653,0.0006118944,0.00038915622,0.00033641947,0.00005517081,0.000017115817],"category_scores_gemma":[0.0004997641,0.00017942871,0.00006250264,0.00030088116,0.000035064102,0.00032600827,0.0002480728,0.0003166226,0.0000028726938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014142689,0.000005198818,0.0035522403,0.000039952796,0.000010390519,0.000004320004,0.000093372124,0.9742778,0.00019812841,0.015906826,0.0011729265,0.004724686],"study_design_scores_gemma":[0.00037066927,0.000074192234,0.00014449893,0.00044204955,0.000014468069,0.000008152091,0.00014078306,0.9891835,0.0026369018,0.0015099227,0.0052751196,0.00019978327],"about_ca_topic_score_codex":0.000014406435,"about_ca_topic_score_gemma":6.717654e-8,"teacher_disagreement_score":0.5758545,"about_ca_system_score_codex":0.000113474576,"about_ca_system_score_gemma":0.00011558748,"threshold_uncertainty_score":0.73168904},"labels":[],"label_agreement":null},{"id":"W4413370993","doi":"10.1007/s10458-025-09721-9","title":"Designing policies for transition-independent multiagent systems that are robust to communication loss","year":2025,"lang":"en","type":"article","venue":"Autonomous Agents and Multi-Agent Systems","topic":"Reinforcement Learning in Robotics","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":"Army Research Laboratory; Air Force Research Laboratory; Army Research Office","keywords":"Transition (genetics); Computer science; Multi-agent system; Distributed computing; Artificial intelligence; Chemistry","score_opus":0.06207849552602331,"score_gpt":0.2945134472691957,"score_spread":0.23243495174317239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413370993","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":[0.008677289,0.0009966324,0.9845087,0.00083977205,0.0015918479,0.0029163202,0.000021708816,0.0002681827,0.00017953299],"genre_scores_gemma":[0.9727675,0.00013022551,0.022233611,0.0005256783,0.00005524897,0.00060153566,0.000032088385,0.000031177675,0.003622988],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99745625,0.00024503257,0.0007049081,0.00064217526,0.00038090468,0.0005707559],"domain_scores_gemma":[0.9979829,0.00020793849,0.0003757188,0.0010006205,0.00021336749,0.00021945068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008425469,0.00036099888,0.00048487278,0.00033305338,0.00072601566,0.0009636536,0.0010045862,0.00015825714,0.0000019779272],"category_scores_gemma":[0.000049042465,0.00034613966,0.00012293423,0.00027084682,0.00005047682,0.0003840046,0.00033327795,0.00017116686,0.00002600265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008751922,0.00008882831,0.002484124,0.00039094468,0.00015277855,0.0000075275084,0.0043788413,0.9864802,0.00020078447,0.003498037,0.0018536894,0.0004554999],"study_design_scores_gemma":[0.0013326879,0.000078908495,0.005863879,0.00068345474,0.000057723886,0.00001537061,0.0025440715,0.9722301,0.00035870113,0.0000046889772,0.016421149,0.00040926537],"about_ca_topic_score_codex":0.0010098661,"about_ca_topic_score_gemma":0.000032366333,"teacher_disagreement_score":0.96409017,"about_ca_system_score_codex":0.00036101826,"about_ca_system_score_gemma":0.000089108435,"threshold_uncertainty_score":0.9998991},"labels":[],"label_agreement":null},{"id":"W4413479704","doi":"10.36227/techrxiv.175606815.51615643/v1","title":"Real-Time Adaptive Loss Functions for Generative Models Using Reinforcement Learning and Meta-Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Meta learning (computer science); Generative grammar; Computer science; Reinforcement; Generative model; Artificial intelligence; Machine learning; Meta-analysis; Adaptive learning; Psychology; Engineering; Social psychology","score_opus":0.054915963465651696,"score_gpt":0.29324934567146044,"score_spread":0.23833338220580874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413479704","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":[0.0004679474,0.00007036919,0.97522694,0.00025247104,0.00012310894,0.00053120794,5.688764e-7,0.00031276024,0.023014607],"genre_scores_gemma":[0.29044807,0.00008093687,0.5783185,0.00036072073,0.00006005798,0.0001469359,0.000015971584,0.000033920038,0.13053489],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998168,0.00014880512,0.00041702925,0.0005539338,0.0002757909,0.0004364336],"domain_scores_gemma":[0.99876523,0.00037332013,0.00020241087,0.00028849713,0.0002851968,0.00008535111],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00053528283,0.00028010018,0.00041611955,0.00025450316,0.00084033865,0.000315671,0.00031645814,0.00009635152,0.00006815846],"category_scores_gemma":[0.000109163084,0.00024740206,0.00015801773,0.00043400106,0.00007786102,0.0008360609,0.0004595684,0.00029982463,0.000011610136],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014427569,0.0000064261526,0.000028965527,0.000013948374,0.0005936428,0.0000012514854,0.0004033006,0.9069794,0.0008192067,0.09066273,0.00015876706,0.00031797795],"study_design_scores_gemma":[0.00041274808,0.0002411004,0.0000046939313,0.0000134532265,0.000520029,0.000003665757,0.0002193594,0.9947951,0.0007014369,0.0011425777,0.0016970788,0.0002487831],"about_ca_topic_score_codex":0.000083868064,"about_ca_topic_score_gemma":0.0000019338086,"teacher_disagreement_score":0.39690846,"about_ca_system_score_codex":0.000145136,"about_ca_system_score_gemma":0.00014871957,"threshold_uncertainty_score":0.9999978},"labels":[],"label_agreement":null},{"id":"W4413513049","doi":"10.1016/j.engappai.2025.112037","title":"An adaptive reinforcement learning approach with trait-awareness for heterogeneous multi-robot cooperative pursuit","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Computer science; Reinforcement learning; Robot; Trait; Artificial intelligence; Machine learning; Human–computer interaction","score_opus":0.036737996253077866,"score_gpt":0.2972914045778988,"score_spread":0.26055340832482093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413513049","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":[0.00030192666,0.000037432044,0.998102,0.00005075778,0.00006505433,0.0011107475,0.0000021770747,0.00023582073,0.000094082425],"genre_scores_gemma":[0.6593128,0.000003929269,0.3398039,0.000015245697,0.000020856856,0.0006869469,0.000019239395,0.000014473021,0.00012261899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984481,0.00002744848,0.00048777103,0.00048661674,0.00023606888,0.00031399744],"domain_scores_gemma":[0.99858993,0.00016882342,0.00015795551,0.0006202117,0.00038313793,0.00007992197],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029201183,0.00022880698,0.00025128043,0.00024336223,0.00024538804,0.0001424019,0.0011033652,0.00007948499,0.0000031060194],"category_scores_gemma":[0.00005845053,0.00022713725,0.000062454405,0.0008053568,0.0000956571,0.00026705928,0.00010249553,0.0002108436,0.000004333265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021179061,0.00007900611,0.00000695878,0.00004337133,0.000048784295,2.40811e-7,0.00048673735,0.86888504,0.002063493,0.11825338,0.0000014449323,0.010110381],"study_design_scores_gemma":[0.00005824227,0.0003658988,0.000014772346,0.000040559375,0.000018369685,0.0000018987278,0.00018094681,0.9396976,0.05897706,0.00010345261,0.00032699376,0.00021419908],"about_ca_topic_score_codex":0.000034239645,"about_ca_topic_score_gemma":0.0000046033288,"teacher_disagreement_score":0.6590108,"about_ca_system_score_codex":0.000079558515,"about_ca_system_score_gemma":0.00013126057,"threshold_uncertainty_score":0.9262388},"labels":[],"label_agreement":null},{"id":"W4414128997","doi":"10.1007/978-3-032-04558-4_8","title":"Learning to Optimize Entropy in the Soft Actor-Critic","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Benchmarking; Regularization (linguistics); Entropy (arrow of time); Artificial neural network; Simulated annealing; Source code","score_opus":0.013576386183217663,"score_gpt":0.2525143598403673,"score_spread":0.23893797365714964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414128997","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":[0.000026271806,0.0001231734,0.9886744,0.003267117,0.0015200075,0.0006090696,7.0893213e-7,0.00014863817,0.005630631],"genre_scores_gemma":[0.19928756,0.0000699934,0.78179306,0.012526786,0.0006280174,0.000044620472,0.000008455723,0.00005958553,0.005581906],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954804,0.00013016156,0.00063647615,0.0014226915,0.0013902773,0.0009399636],"domain_scores_gemma":[0.99616146,0.0017261308,0.00020359959,0.0015789571,0.00019157154,0.00013827825],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0016076448,0.00055684923,0.0005371438,0.0011991293,0.00033883916,0.0011857098,0.006637934,0.00027652056,0.000023486291],"category_scores_gemma":[0.0007167882,0.0004484074,0.00013883991,0.0013140196,0.00036912973,0.00047628066,0.002038803,0.0019436986,0.00008268622],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036469091,0.00000972859,0.000068418696,0.000026684384,0.0000052106666,0.00006996774,0.002032591,0.88248706,0.000022800521,0.0141235385,0.000058886926,0.10109148],"study_design_scores_gemma":[0.0002492059,0.00025242337,0.000114776136,0.00059591915,0.000007519996,0.000026839129,0.0000015833994,0.9809591,0.0000957485,0.010274923,0.0068620252,0.0005599125],"about_ca_topic_score_codex":0.000023330958,"about_ca_topic_score_gemma":0.000022233813,"teacher_disagreement_score":0.20688131,"about_ca_system_score_codex":0.00042362712,"about_ca_system_score_gemma":0.00060774345,"threshold_uncertainty_score":0.99985117},"labels":[],"label_agreement":null},{"id":"W4414183195","doi":"10.1038/s42256-025-01109-4","title":"Aligning generalization between humans and machines","year":2025,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of British Columbia","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","keywords":"Generalization; Abstraction; Cognition; Generative grammar; Key (lock); Human intelligence","score_opus":0.00935696220116273,"score_gpt":0.29798816362097796,"score_spread":0.28863120141981524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414183195","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":[0.0016605493,0.0015040396,0.98896384,0.0014607017,0.00047412614,0.00014559322,0.0000015074437,0.00021757865,0.005572068],"genre_scores_gemma":[0.95478946,0.00011067038,0.042203326,0.0011198617,0.00009465216,0.0000054695997,0.00001736428,0.000010013579,0.0016491819],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99870926,0.00007142426,0.00030241773,0.00041910465,0.00025842534,0.00023935767],"domain_scores_gemma":[0.99910444,0.00018254078,0.00009998452,0.00045483463,0.00010119161,0.000056999706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003155791,0.00019143237,0.00018543004,0.00024643386,0.00022176176,0.00024131735,0.000862533,0.00019859667,0.000013182604],"category_scores_gemma":[0.00021514011,0.00017142584,0.000042835916,0.00065181556,0.000056817156,0.00029570083,0.0004366908,0.00059099565,0.00001278656],"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":[0.0000042295555,0.00001573165,0.12722863,0.00008746506,0.00007251012,0.000008876946,0.00056936604,0.13036968,0.00035765738,0.5805565,0.0010578332,0.15967152],"study_design_scores_gemma":[0.00011578773,0.00006360663,0.016993683,0.00011355143,0.000028680995,0.0000058078303,0.000011155237,0.9450496,0.009386623,0.016634157,0.011239593,0.00035775255],"about_ca_topic_score_codex":0.000048648533,"about_ca_topic_score_gemma":0.000010938527,"teacher_disagreement_score":0.95312893,"about_ca_system_score_codex":0.000036546975,"about_ca_system_score_gemma":0.000039758736,"threshold_uncertainty_score":0.6990543},"labels":[],"label_agreement":null},{"id":"W4414321910","doi":"10.1109/tai.2025.3610590","title":"Towards Sample-Efficiency and Generalization of Transfer and Inverse Reinforcement Learning: A Comprehensive Literature Review","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","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 New Brunswick; University of Windsor; Toronto Metropolitan University","funders":"","keywords":"Generalization; Inverse; Transfer (computing); Stability (learning theory); Calculus (dental)","score_opus":0.03715181315305159,"score_gpt":0.2995708591001717,"score_spread":0.2624190459471201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414321910","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":[0.00080991053,0.0014616486,0.9960649,0.0006163243,0.0003099856,0.0004171516,0.0000031412778,0.000075110045,0.00024182948],"genre_scores_gemma":[0.95866483,0.028515076,0.01131067,0.0011493934,0.000013223655,0.00003425372,0.0000067465394,0.000011471394,0.00029434837],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850774,0.00011510583,0.0005333903,0.0003709261,0.00026911814,0.00020369221],"domain_scores_gemma":[0.9991231,0.00017292135,0.00007568784,0.00030914214,0.00024600976,0.000073127],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020930002,0.00019561328,0.00026224979,0.00027207972,0.00021915464,0.00011166536,0.00027458454,0.00008592828,0.000025792775],"category_scores_gemma":[0.00004429177,0.00018806168,0.00007373361,0.0009797991,0.00015963902,0.0002670666,0.000008680337,0.00030030744,0.000003982702],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020811554,0.000037292157,0.0000047438125,0.0005878291,0.000030075056,0.0000021486944,0.0013451425,0.89187247,0.0011409689,0.03250888,0.000021535936,0.07242813],"study_design_scores_gemma":[0.00006744924,0.00030194645,0.000012690111,0.0016971385,0.000050522976,0.0000064518563,0.00009324472,0.94994235,0.04561146,0.0008558003,0.0011529607,0.00020800962],"about_ca_topic_score_codex":0.000038898557,"about_ca_topic_score_gemma":0.000010416181,"teacher_disagreement_score":0.9847542,"about_ca_system_score_codex":0.00003547206,"about_ca_system_score_gemma":0.00007136519,"threshold_uncertainty_score":0.76689327},"labels":[],"label_agreement":null},{"id":"W4414359474","doi":"10.24963/ijcai.2025/964","title":"DGL: Dynamic Global-Local Information Aggregation for Scalable VRP Generalization with Self-Improvement Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"BC Research (Canada)","funders":"","keywords":"Benchmark (surveying); Limiting; Scalability; Vehicle routing problem; Generalization; Context (archaeology); Node (physics)","score_opus":0.0033066275769797057,"score_gpt":0.22541397040296537,"score_spread":0.22210734282598568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414359474","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":[0.0016907584,0.000009937789,0.99022925,0.0005201818,0.0002300996,0.00059453445,5.799029e-7,0.00051663455,0.006208047],"genre_scores_gemma":[0.68016046,0.000019421594,0.31533372,0.0010106815,0.000015820697,0.000100984245,0.000111616966,0.000008094973,0.0032391502],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887174,0.000028478898,0.00032472517,0.00021279519,0.0002954868,0.00026676568],"domain_scores_gemma":[0.9991816,0.000036641304,0.00017890577,0.00027616363,0.00028363804,0.000043004893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002585907,0.00014414541,0.00011797485,0.00012226471,0.00025739282,0.0003753022,0.00033549298,0.000070432034,0.0000064017418],"category_scores_gemma":[0.00004508675,0.0001258004,0.00003501895,0.00064871396,0.000021263733,0.0015314568,0.00012193087,0.000080805214,0.000023412122],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008781682,0.000010964536,0.00092050224,0.00006269365,0.000027030814,1.129419e-7,0.00010606853,0.8761759,0.000028189572,0.07461551,0.00031988657,0.047724355],"study_design_scores_gemma":[0.00072314125,0.00025358528,0.0005454119,0.000042330237,0.000016632292,0.0000012474743,0.00007007464,0.98762465,0.000752502,0.00048546048,0.009336372,0.00014860899],"about_ca_topic_score_codex":0.000041030886,"about_ca_topic_score_gemma":0.000017157412,"teacher_disagreement_score":0.6784697,"about_ca_system_score_codex":0.00041235017,"about_ca_system_score_gemma":0.00015596172,"threshold_uncertainty_score":0.5129992},"labels":[],"label_agreement":null},{"id":"W4414360545","doi":"10.24963/ijcai.2025/19","title":"Combining Deep Reinforcement Learning and Search with Generative Models for Game-Theoretic Opponent Modeling","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Generative model; Scalability; Variety (cybernetics); Generative grammar; Class (philosophy); Tree (set theory); Adversary; Best response","score_opus":0.02852594522291188,"score_gpt":0.2784602814118119,"score_spread":0.2499343361889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414360545","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":[0.002115856,0.00008978613,0.98378384,0.00050514826,0.000076058655,0.00059136556,6.826706e-8,0.00018377637,0.012654104],"genre_scores_gemma":[0.827309,0.00005839809,0.16898555,0.0002920356,0.000012847915,0.00006681043,0.0000055156506,0.000014605622,0.0032551987],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998263,0.00007973488,0.00033424931,0.0004929551,0.00035582355,0.00047422253],"domain_scores_gemma":[0.99904704,0.00021636546,0.00007109724,0.0003251842,0.00023684677,0.000103440696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005745485,0.00022113684,0.00024308302,0.00021239783,0.00036679435,0.00038251185,0.00042867765,0.00006370566,0.000009712969],"category_scores_gemma":[0.00004426534,0.0001826935,0.000044756813,0.00028294974,0.000079376616,0.00047016362,0.00043830412,0.0002681398,0.0000027383128],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019545834,0.0000052126343,0.00003715758,0.00003319536,0.000034985183,0.0000010113699,0.0010357266,0.6190177,0.000055444056,0.3786981,0.000006373249,0.0010554912],"study_design_scores_gemma":[0.000969656,0.0003608415,0.0000014335644,0.000094609495,0.000019106901,0.000003532958,0.00058822526,0.9917475,0.0006747999,0.0052580833,0.00005775513,0.00022448598],"about_ca_topic_score_codex":0.000019492521,"about_ca_topic_score_gemma":0.0000022128363,"teacher_disagreement_score":0.82519317,"about_ca_system_score_codex":0.00007674155,"about_ca_system_score_gemma":0.0001242728,"threshold_uncertainty_score":0.74500245},"labels":[],"label_agreement":null},{"id":"W4414746796","doi":"10.3390/sym17101632","title":"A Survey of Maximum Entropy-Based Inverse Reinforcement Learning: Methods and Applications","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Ambiguity; Reinforcement learning; Benchmark (surveying); Principle of maximum entropy; Matching (statistics); Inverse","score_opus":0.02304166197990325,"score_gpt":0.32256258332432103,"score_spread":0.29952092134441777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414746796","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":[0.0004034847,0.00011525142,0.99267155,0.00014487033,0.00012221043,0.0002718118,6.0396013e-7,0.000090130015,0.0061800717],"genre_scores_gemma":[0.68319833,0.000027669768,0.31359237,0.0005152484,0.000015061568,0.000055234323,0.000025026917,0.000011949277,0.0025591026],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985995,0.00032157073,0.00035216552,0.00029578368,0.00021393818,0.00021699678],"domain_scores_gemma":[0.99845105,0.00055557286,0.00018950789,0.00057361525,0.00016285929,0.00006741226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012628202,0.00012991297,0.00021051308,0.00029928013,0.000114228016,0.00006687015,0.00052265107,0.00007252272,0.00001368364],"category_scores_gemma":[0.00044242284,0.0001302167,0.00004642011,0.0010708781,0.00009250328,0.000116066556,0.00032481173,0.00021017395,0.000012045266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020301528,0.0000570482,0.06662763,0.00026187906,0.00012217513,0.0000014840717,0.00016351114,0.6824363,0.0011855189,0.15775314,0.00079098967,0.09058003],"study_design_scores_gemma":[0.0005452492,0.00012541481,0.018336805,0.000036902995,0.000020362182,5.34881e-7,0.000028869888,0.9608366,0.003637938,0.000872127,0.015394536,0.00016464465],"about_ca_topic_score_codex":0.00012768708,"about_ca_topic_score_gemma":0.000004015497,"teacher_disagreement_score":0.68279487,"about_ca_system_score_codex":0.000050479575,"about_ca_system_score_gemma":0.00015800506,"threshold_uncertainty_score":0.5310083},"labels":[],"label_agreement":null},{"id":"W4415014469","doi":"10.1016/j.asoc.2025.114024","title":"Transformer-based dynamics model for sim-to-real reinforcement learning control of a quadrotor with limited experimental data","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Cultural Heritage Administration; Information Technology Research Centre; National Research Institute of Cultural Heritage; Ministry of Science and ICT, South Korea","keywords":"Reinforcement learning; Transformer; Experimental data; Scheme (mathematics); Actuator; Controller (irrigation); Robot; Replicate","score_opus":0.022281285446842915,"score_gpt":0.28204203000989225,"score_spread":0.2597607445630493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415014469","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":[0.0053482493,0.000008824315,0.9901378,0.00022211399,0.000087359556,0.0017927844,0.0000062630174,0.00028942587,0.0021071816],"genre_scores_gemma":[0.79842323,4.9233165e-7,0.200807,0.00042829648,0.00001704444,0.00006997729,0.00008306911,0.000025167396,0.0001456993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756426,0.00003298144,0.000672618,0.00069570274,0.00046128087,0.000573183],"domain_scores_gemma":[0.9978971,0.00055844063,0.00030579683,0.0009829628,0.00014083103,0.00011487609],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061154127,0.00031646737,0.00045943106,0.00024969826,0.00033644072,0.00013717827,0.0016775002,0.000093811876,0.0000016835265],"category_scores_gemma":[0.00005483857,0.00031034893,0.00007611766,0.0005297335,0.000071073715,0.0001811462,0.00030691168,0.0002580224,0.0000027585443],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002185667,0.00005677242,0.00020338752,0.00010070543,0.00008683498,6.8181174e-7,0.00070744875,0.9620515,0.0016845224,0.031689666,0.000039637882,0.0031602564],"study_design_scores_gemma":[0.0031354679,0.00036900066,0.00002112995,0.00012259817,0.0000401312,5.1418647e-7,0.00018998925,0.9933213,0.0023438549,0.00003044726,0.00011462585,0.00031091477],"about_ca_topic_score_codex":0.000028357063,"about_ca_topic_score_gemma":0.000007694974,"teacher_disagreement_score":0.793075,"about_ca_system_score_codex":0.00019088431,"about_ca_system_score_gemma":0.00032723745,"threshold_uncertainty_score":0.99993485},"labels":[],"label_agreement":null},{"id":"W4415048913","doi":"10.1109/tpami.2025.3619883","title":"Release the Potential of Memory Buffer in Continual Learning: A Dynamic System Perspective","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Forgetting; Overfitting; Memory model; Memory management; Dynamic random-access memory; Transformation (genetics); Adaptive memory; Perspective (graphical)","score_opus":0.007327819433915642,"score_gpt":0.25508305915173934,"score_spread":0.2477552397178237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415048913","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":[0.008386226,0.00014590385,0.99034554,0.00044965133,0.0001722322,0.0001573134,0.00000359375,0.0000498372,0.00028970974],"genre_scores_gemma":[0.9985979,0.00011017251,0.00027292382,0.000085601576,0.00000396578,0.000014152062,0.000001035239,0.000005511938,0.0009087142],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985488,0.0002210795,0.0004203863,0.00037525382,0.00025040787,0.00018404108],"domain_scores_gemma":[0.99908006,0.00019172468,0.00014357636,0.00041976984,0.00012448835,0.000040351497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035921973,0.00016385126,0.00030837502,0.00062486145,0.00015754874,0.00008119188,0.0004941377,0.00005661049,0.000018830076],"category_scores_gemma":[0.000014572366,0.00012439821,0.00021127857,0.001330306,0.00010111758,0.000115200506,0.0000119906945,0.00044661993,0.000006167758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016918042,0.000052352836,0.0003879697,0.000022837758,0.00035511723,0.000008760814,0.0008100545,0.94048667,0.00018377721,0.00059477054,0.0000014047486,0.057079364],"study_design_scores_gemma":[0.00012067145,0.00008142702,0.0019016729,0.00005015907,0.00029600287,0.00000438599,0.0018675898,0.9887359,0.006781001,0.00004315652,0.000005744302,0.00011225173],"about_ca_topic_score_codex":0.0022317285,"about_ca_topic_score_gemma":0.00070876896,"teacher_disagreement_score":0.9902117,"about_ca_system_score_codex":0.0001046498,"about_ca_system_score_gemma":0.000037471535,"threshold_uncertainty_score":0.5072812},"labels":[],"label_agreement":null},{"id":"W4415112009","doi":"10.48550/arxiv.2506.12622","title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Division of Electrical, Communications and Cyber Systems; Office of Naval Research; York University; National Science Foundation","keywords":"Robustness (evolution); Reinforcement learning; Robust control; Benchmark (surveying); Entropy (arrow of time); Convergence (economics); Robust optimization; Rate of convergence","score_opus":0.07787399934876577,"score_gpt":0.21875883121698483,"score_spread":0.14088483186821907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415112009","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":[0.0011988878,0.00003682864,0.99339515,0.00049458747,0.0010670031,0.0007715888,0.00002828117,0.00047474704,0.0025329245],"genre_scores_gemma":[0.95816976,0.00009569475,0.0038233763,0.00028126175,0.00012020143,0.000009762305,0.0004549765,0.000024382714,0.037020598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969191,0.00016728173,0.00047499026,0.0013841725,0.00027238432,0.0007820913],"domain_scores_gemma":[0.9967866,0.00064613443,0.00045422622,0.0012851636,0.00060342863,0.00022447425],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005051677,0.00054876634,0.00051507656,0.000333328,0.0005830358,0.00035153437,0.0025891648,0.00044545645,0.000059929647],"category_scores_gemma":[0.00032017234,0.0006640264,0.000451323,0.00061757903,0.00016513561,0.00044509396,0.0028953773,0.001147817,0.000046972556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030081976,0.000025692263,0.00030785092,0.00017928526,0.00015716287,0.000017741646,0.00006149175,0.75259054,0.0000052277496,0.24580705,0.0007155911,0.00010226301],"study_design_scores_gemma":[0.0007724131,0.00011805844,0.00015908077,0.00026266885,0.00013834366,0.000001635419,0.00009074399,0.98309034,0.000026029107,0.008317726,0.006379215,0.0006437732],"about_ca_topic_score_codex":0.00008939379,"about_ca_topic_score_gemma":0.000013398306,"teacher_disagreement_score":0.98957175,"about_ca_system_score_codex":0.0011657435,"about_ca_system_score_gemma":0.0009139068,"threshold_uncertainty_score":0.9995811},"labels":[],"label_agreement":null},{"id":"W4415318339","doi":"10.48550/arxiv.2510.07257","title":"Test-Time Graph Search for Goal-Conditioned Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Graph; Metric (unit); Bounding overwatch; Base (topology); Train; Learning to rank; Sequence (biology)","score_opus":0.048363397902601656,"score_gpt":0.2102282857347292,"score_spread":0.16186488783212755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415318339","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":[0.0031860177,0.000013020537,0.98548865,0.00019235411,0.00047686408,0.000989108,0.000015363332,0.00057710917,0.009061481],"genre_scores_gemma":[0.9076249,0.00010551968,0.0053832745,0.00018430965,0.000080452184,0.000009797863,0.0001750533,0.000025642237,0.08641105],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971841,0.0001595197,0.00040638927,0.0013128978,0.00024241155,0.00069469115],"domain_scores_gemma":[0.9967995,0.0007948693,0.00036973716,0.0013970382,0.00044148642,0.000197325],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00062700803,0.00045846257,0.00047767788,0.0007137726,0.0005411441,0.000301626,0.002525657,0.00038537872,0.00008552512],"category_scores_gemma":[0.0001962997,0.00057238614,0.00042033172,0.00085869525,0.00013314973,0.00045376198,0.002950499,0.0010604801,0.00020803048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026962787,0.000029541454,0.0005226924,0.00018134339,0.00013399163,0.000031914336,0.00020556638,0.9204964,0.0000749016,0.07749747,0.0006529156,0.00014630343],"study_design_scores_gemma":[0.0008508962,0.00022620904,0.00018999337,0.00019616281,0.00009412595,0.0000015890071,0.000046353503,0.9927149,0.0007355988,0.0028781977,0.0015085153,0.00055747706],"about_ca_topic_score_codex":0.000052231615,"about_ca_topic_score_gemma":0.0000016155258,"teacher_disagreement_score":0.9801054,"about_ca_system_score_codex":0.00040562786,"about_ca_system_score_gemma":0.00046754727,"threshold_uncertainty_score":0.9996728},"labels":[],"label_agreement":null},{"id":"W4415428256","doi":"10.3233/faia251090","title":"Skill-Enhanced Reinforcement Learning Acceleration from Heterogeneous Demonstrations","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research; Carleton University","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Downstream (manufacturing); Temporal difference learning; Acceleration; Supervised learning; Online machine learning; Reinforcement","score_opus":0.03288550673780755,"score_gpt":0.2740642108823426,"score_spread":0.24117870414453507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415428256","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":[0.000041470026,0.00082822185,0.9607646,0.0004032472,0.001039932,0.0020609084,0.000017027045,0.00014500217,0.034699608],"genre_scores_gemma":[0.8380992,0.012277848,0.10011569,0.0005036823,0.00084426865,0.0011845297,0.00074083445,0.00010163991,0.046132304],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99489105,0.00010143112,0.0021097336,0.0015864546,0.0006204594,0.0006908934],"domain_scores_gemma":[0.99712527,0.00031719526,0.0008455629,0.0011184426,0.00035354984,0.00023997601],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003853666,0.0007717366,0.00077643455,0.00076469796,0.0012259105,0.0009581471,0.001220861,0.0006489147,0.00026188174],"category_scores_gemma":[0.000116324314,0.0009502052,0.00022403637,0.0005776177,0.00053765933,0.0006053328,0.0005297823,0.0013559379,0.00019005022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015446914,0.000036462494,0.00006009252,0.00003059101,0.00008136958,0.0000027166855,0.00056701875,0.57499576,0.00009700574,0.1874231,0.000063891835,0.23662657],"study_design_scores_gemma":[0.000071843795,0.00015837402,0.000017983748,0.0004880268,0.00012631617,0.0000021980877,0.0005257343,0.89751625,0.005215156,0.08038431,0.0146297375,0.0008640615],"about_ca_topic_score_codex":0.00011701845,"about_ca_topic_score_gemma":0.000086151296,"teacher_disagreement_score":0.8606489,"about_ca_system_score_codex":0.0003349854,"about_ca_system_score_gemma":0.0003470031,"threshold_uncertainty_score":0.9992948},"labels":[],"label_agreement":null},{"id":"W4415428281","doi":"10.3233/faia251077","title":"DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-Domain Reinforcement Learning","year":2025,"lang":"","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Overfitting; Reinforcement learning; Domain (mathematical analysis); Key (lock); Artificial neural network; Sample (material); k-nearest neighbors algorithm","score_opus":0.04380986476356294,"score_gpt":0.3078464961854975,"score_spread":0.26403663142193456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415428281","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":[0.000023049273,0.0009732836,0.9793102,0.0006987151,0.00085927255,0.003654906,0.000035302717,0.000117400356,0.014327862],"genre_scores_gemma":[0.11735742,0.00924017,0.56973475,0.0010526723,0.0011750723,0.0031988507,0.00056075485,0.00022761973,0.29745272],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994057,0.000056582056,0.002445668,0.0017878689,0.00065959606,0.00099327],"domain_scores_gemma":[0.9964509,0.00034784837,0.0010302362,0.0013230428,0.00056603015,0.00028195942],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0010100524,0.00087855564,0.0009453405,0.0007224206,0.0015234181,0.00089010946,0.0017333382,0.0006714595,0.000054277225],"category_scores_gemma":[0.00021619035,0.001018749,0.00032339935,0.00053221796,0.0008653214,0.00051778986,0.0009213785,0.0012244574,0.000053340373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060532162,0.0000408219,0.00021062155,0.00013507814,0.000033879922,0.0000011840101,0.00040643234,0.5382848,0.000030904273,0.37592697,0.00023641693,0.08463238],"study_design_scores_gemma":[0.00012985966,0.00017305645,0.000013992,0.0004757703,0.000054505603,0.0000013342336,0.00018044934,0.8213257,0.00019874699,0.12004835,0.056653738,0.00074446655],"about_ca_topic_score_codex":0.000035008135,"about_ca_topic_score_gemma":0.000027718828,"teacher_disagreement_score":0.40957546,"about_ca_system_score_codex":0.0003663328,"about_ca_system_score_gemma":0.00042245912,"threshold_uncertainty_score":0.9997765},"labels":[],"label_agreement":null},{"id":"W4415588118","doi":"10.1021/acs.iecr.5c01979","title":"Hierarchical Reinforcement Learning with Dynamic Meta Agent for Adaptive Cut Selection in Integer Programming with Applications to Sensor Network Design","year":2025,"lang":"en","type":"article","venue":"Industrial & Engineering Chemistry Research","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"Science and Engineering Research Board; Indian Institute of Technology Delhi; Cornell University","keywords":"Reinforcement learning; Integer programming; Selection (genetic algorithm); Scalability; Cutting-plane method; Linear programming; Integer (computer science); Wireless sensor network","score_opus":0.08648733691679072,"score_gpt":0.3346498647927557,"score_spread":0.248162527875965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415588118","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":[0.00068871834,0.000020640753,0.9956962,0.0003844842,0.00003028047,0.00283656,3.7767248e-7,0.00018039896,0.00016235703],"genre_scores_gemma":[0.7592951,0.000007665003,0.22577594,0.00003107581,0.0003316631,0.008981423,0.000024023911,0.00007081157,0.0054822895],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747986,0.00009760024,0.0003568861,0.0005910439,0.0006012066,0.0008734307],"domain_scores_gemma":[0.9984391,0.00072075607,0.00006803806,0.00033422362,0.0002896056,0.00014829407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015316783,0.0002498578,0.00030900465,0.00025552345,0.00024441868,0.00026575485,0.00064562436,0.00018385556,0.000005958457],"category_scores_gemma":[0.00032428573,0.00021793398,0.00005720331,0.002444595,0.000054751075,0.00014227253,0.00024445067,0.0015372318,0.000003216055],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002221167,0.000022862663,0.00006904704,0.000058745052,0.00023730834,0.000004915533,0.00009124105,0.99125737,0.0045818132,0.0006594239,0.00009991454,0.002695269],"study_design_scores_gemma":[0.0008304409,0.0004954871,0.000010199698,0.00028575948,0.000042078016,0.0000066298862,0.000057289006,0.97249967,0.014015397,0.000013262012,0.011502848,0.00024095965],"about_ca_topic_score_codex":0.000023649241,"about_ca_topic_score_gemma":0.0000037181094,"teacher_disagreement_score":0.76992023,"about_ca_system_score_codex":0.00064255466,"about_ca_system_score_gemma":0.0004623753,"threshold_uncertainty_score":0.888709},"labels":[],"label_agreement":null},{"id":"W4415688799","doi":"10.1007/978-3-032-04339-9_15","title":"Enhancing Off-Policy Method SAC with KAN for Continuous Reinforcement Learning","year":2025,"lang":"en","type":"book-chapter","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","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 Regina","funders":"","keywords":"Reinforcement learning; Embedding; Architecture; Reinforcement; Artificial neural network","score_opus":0.02445174135414655,"score_gpt":0.3154284189345152,"score_spread":0.2909766775803686,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415688799","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":[0.0000011933678,0.000111990965,0.8438277,0.00076281815,0.00015000999,0.00068826193,0.0000017946514,0.000120403034,0.15433578],"genre_scores_gemma":[0.004356877,0.0013471133,0.97230244,0.0015038586,0.000058410835,0.000100257515,0.00007869597,0.000014887399,0.020237476],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99763435,0.000049501148,0.00097165164,0.0003775605,0.00056388613,0.0004030497],"domain_scores_gemma":[0.9957124,0.0007092893,0.000690995,0.0020223316,0.0007533414,0.00011161428],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019747883,0.00032174808,0.00041823144,0.0016462527,0.0008701669,0.00095491234,0.0034296117,0.00014324328,0.0000038648104],"category_scores_gemma":[0.00022765217,0.00030660557,0.00006701078,0.00069346325,0.0004835515,0.004485288,0.0024796834,0.00063104625,0.000014658189],"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":[0.0000045103516,0.0000037373104,0.000012706351,0.00006122538,0.000013423278,1.5460172e-7,0.0013805656,0.21618104,0.0000023986606,0.62596166,0.000106206644,0.1562724],"study_design_scores_gemma":[0.00039843132,0.0001701078,0.000033396744,0.00041245727,0.000009894019,0.000009753071,0.000028684697,0.76690054,0.00003111582,0.000995073,0.23072338,0.00028716843],"about_ca_topic_score_codex":0.000021545275,"about_ca_topic_score_gemma":0.000008748911,"teacher_disagreement_score":0.62496656,"about_ca_system_score_codex":0.0003296437,"about_ca_system_score_gemma":0.0010120324,"threshold_uncertainty_score":0.9999386},"labels":[],"label_agreement":null},{"id":"W4415935956","doi":"10.1016/j.cobeha.2025.101611","title":"Linking homeostasis to reinforcement learning: internal state control of motivated behavior","year":2025,"lang":"en","type":"article","venue":"Current Opinion in Behavioral Sciences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science; Conseil National de la Recherche Scientifique; Agence Nationale de la Recherche; Institut National de la Santé et de la Recherche Médicale; Engineers Nova Scotia","keywords":"Reinforcement learning; Adaptive behavior; Reinforcement; Cognition; Internal model; Control (management); Embodied cognition","score_opus":0.06681357893934883,"score_gpt":0.379216424393706,"score_spread":0.31240284545435715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415935956","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":[0.17021741,0.00028195253,0.8237003,0.0002596087,0.0045903926,0.0006482834,0.0000020458888,0.00010720404,0.00019277364],"genre_scores_gemma":[0.9973492,0.00009670608,0.0022787664,0.000027851376,0.000026140719,0.00007160545,0.0000062154195,0.0000057977913,0.00013770767],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971763,0.00014313021,0.00080467615,0.00055908447,0.0007828522,0.00053397584],"domain_scores_gemma":[0.9989546,0.00010106905,0.00030908908,0.0003399822,0.00017252726,0.00012274865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094707095,0.000227332,0.00032006358,0.00084575446,0.00020701613,0.00025314433,0.0016562412,0.00005524041,0.000022392362],"category_scores_gemma":[0.00009262889,0.00020984065,0.00009356905,0.0020734076,0.00021237443,0.00056287023,0.00057840906,0.0003810091,0.000015229316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016162197,0.00015166693,0.34982705,0.00005152413,0.000004369144,0.0000010991914,0.0008293801,0.53072804,0.00050825934,0.0032591766,0.000095470394,0.11452778],"study_design_scores_gemma":[0.004400811,0.0034459613,0.27819878,0.0047254306,0.000056106703,0.000006404521,0.00058313546,0.6794367,0.007008427,0.00050126977,0.020182043,0.0014549585],"about_ca_topic_score_codex":0.00011837549,"about_ca_topic_score_gemma":0.0000033941747,"teacher_disagreement_score":0.8271318,"about_ca_system_score_codex":0.0001737718,"about_ca_system_score_gemma":0.00020888871,"threshold_uncertainty_score":0.8557054},"labels":[],"label_agreement":null},{"id":"W4416036933","doi":"10.18653/v1/2025.emnlp-main.125","title":"REARANK: Reasoning Re-ranking Agent via Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Canadian Institute for Advanced Research; Nvidia","keywords":"Reinforcement learning; Control (management); Action (physics); Feature (linguistics); Stability (learning theory)","score_opus":0.016838529688993045,"score_gpt":0.26877404190024884,"score_spread":0.2519355122112558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416036933","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":[0.00029619294,0.0006530699,0.7269705,0.0013673787,0.0029902295,0.00074499083,1.2385357e-7,0.00058978674,0.2663877],"genre_scores_gemma":[0.7931597,0.00058121193,0.031381924,0.0018470789,0.00021457185,0.000038440314,0.000013470333,0.000058646023,0.17270492],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915388,0.0006086182,0.002170598,0.0018162259,0.0017943239,0.00207141],"domain_scores_gemma":[0.9953877,0.00048385866,0.00091590756,0.0023070842,0.0005247178,0.00038077563],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0029033856,0.0009929154,0.00094944314,0.00093579385,0.001965824,0.0019040739,0.0028045261,0.00047559067,0.0015753981],"category_scores_gemma":[0.00088762905,0.0010657985,0.0005102468,0.0027491287,0.00026169693,0.0013293779,0.0029189244,0.0020569363,0.0010024987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048836664,0.00004221054,0.0017921502,0.00022192523,0.00031623358,0.000058966,0.0021014262,0.88468045,0.0003136713,0.058228694,0.0020086467,0.050186764],"study_design_scores_gemma":[0.0012626641,0.00043400886,0.0006558656,0.001611205,0.00015469018,0.000014016775,0.00033029573,0.93459266,0.0013723888,0.000271043,0.058355037,0.0009461387],"about_ca_topic_score_codex":0.00037033594,"about_ca_topic_score_gemma":0.000012343218,"teacher_disagreement_score":0.79286355,"about_ca_system_score_codex":0.0009078495,"about_ca_system_score_gemma":0.00065324066,"threshold_uncertainty_score":0.99977535},"labels":[],"label_agreement":null},{"id":"W4416070655","doi":"10.48550/arxiv.2505.20290","title":"EgoZero: Robot Learning from Smart Glasses","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Office of Naval Research; York University; National Science Foundation","keywords":"Robot; Robot learning; Human–robot interaction; Scalability; Robotics; Programming by demonstration; Social robot","score_opus":0.05367968038562613,"score_gpt":0.2787033435342162,"score_spread":0.2250236631485901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416070655","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":[0.07441001,0.00033638775,0.91012204,0.0009896163,0.0037308584,0.00031490458,0.0000035658204,0.00092657236,0.009166069],"genre_scores_gemma":[0.9382875,0.00023661704,0.039525677,0.00071824464,0.0004124343,0.000057072353,0.00012771961,0.000042295935,0.020592438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965064,0.00027689198,0.00067071745,0.0013046376,0.0006057103,0.00063563674],"domain_scores_gemma":[0.9965848,0.0005336387,0.00050807704,0.002009255,0.00020487209,0.00015940503],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00039373164,0.0005520236,0.0006170747,0.00025317233,0.00030405118,0.0005294293,0.0031912643,0.00048486178,0.000116008036],"category_scores_gemma":[0.0005454928,0.00058578356,0.0002778386,0.0003988546,0.00008485375,0.00034636163,0.005896949,0.0022502155,0.00080230465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033381496,0.000018974211,0.4078862,0.0000594707,0.000116430885,0.000022172295,0.00035133795,0.58909917,0.0001212924,0.00061182195,0.0007323473,0.0009774104],"study_design_scores_gemma":[0.0006039542,0.00012848825,0.33815247,0.0009960487,0.00012716281,0.0000034800842,0.00007163896,0.61390924,0.0020857842,0.0011289526,0.04140708,0.0013857372],"about_ca_topic_score_codex":0.000618699,"about_ca_topic_score_gemma":0.000019405417,"teacher_disagreement_score":0.87059635,"about_ca_system_score_codex":0.00018803964,"about_ca_system_score_gemma":0.00042686283,"threshold_uncertainty_score":0.9999757},"labels":[],"label_agreement":null},{"id":"W4416125924","doi":"10.54254/2755-2721/2026.tj29489","title":"On-Policy Vs. Off-Policy Reinforcement Learning in ConnectX: Seat-Stratified Performance and the Role of Action Masking","year":2025,"lang":"","type":"article","venue":"Applied and Computational Engineering","topic":"Reinforcement Learning in Robotics","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":"Pooling; Robustness (evolution); Generalization; Masking (illustration); Reinforcement learning; Reinforcement; Lever; Set (abstract data type)","score_opus":0.005874809224640797,"score_gpt":0.2240839369894798,"score_spread":0.218209127764839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416125924","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":[0.11545411,0.0002629584,0.8754475,0.0008070526,0.00012927699,0.0005314215,5.2597073e-7,0.00006494929,0.0073021958],"genre_scores_gemma":[0.9974712,0.0003228918,0.0016619355,0.00023983422,0.00007209657,0.000038643626,0.0000070093965,0.0000141951705,0.00017218044],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982467,0.000043143787,0.00060806464,0.00036977232,0.000375631,0.00035663386],"domain_scores_gemma":[0.99866074,0.0007939984,0.00022020022,0.00019481129,0.00006821903,0.00006202263],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050754216,0.0002862678,0.00035927127,0.0006150053,0.00025757647,0.00020242824,0.0002749883,0.00009878605,0.0000032932887],"category_scores_gemma":[0.00013564777,0.0002701615,0.000045472574,0.00089684146,0.00014324124,0.00019590036,0.00027597926,0.00052674545,0.000002333285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007236317,0.0000066590515,0.00010312968,0.000108951055,0.00003231254,2.9298894e-7,0.0007853931,0.545228,0.00010303276,0.4238756,0.0000012450472,0.029683003],"study_design_scores_gemma":[0.001968435,0.00009958249,0.003890689,0.00028689113,0.000014690648,0.000004452263,0.00017099033,0.9880619,0.00052109436,0.0044415155,0.0003314248,0.00020834027],"about_ca_topic_score_codex":0.000057788566,"about_ca_topic_score_gemma":8.6791687e-7,"teacher_disagreement_score":0.8820171,"about_ca_system_score_codex":0.00013625373,"about_ca_system_score_gemma":0.0003008746,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W4416177363","doi":"10.48550/arxiv.2508.06836","title":"Multi-level Advantage Credit Assignment for Cooperative Multi-Agent Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada","keywords":"Counterfactual thinking; Reinforcement learning; Key (lock); Diversity (politics); Function (biology)","score_opus":0.11935644116154431,"score_gpt":0.3388184746199345,"score_spread":0.21946203345839016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416177363","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":[0.0021216066,0.0002024877,0.98919225,0.00051497505,0.003785552,0.0027552405,0.000032688236,0.000547563,0.0008476132],"genre_scores_gemma":[0.47858003,0.00041996554,0.4065465,0.0011939534,0.00045028815,0.0014910065,0.0005198748,0.000106096755,0.110692285],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947892,0.00027236348,0.0012873766,0.0017330965,0.0008366349,0.0010813309],"domain_scores_gemma":[0.99589586,0.00045535964,0.0009243965,0.001822512,0.00061547203,0.000286424],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001005797,0.00093529874,0.0008971014,0.00036762242,0.00066806085,0.00044969504,0.002743653,0.0005143566,0.00007323432],"category_scores_gemma":[0.00083649834,0.0009378311,0.00045001035,0.00032960373,0.00012280027,0.00044483738,0.0050477986,0.0017591572,0.0002175449],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024682136,0.00012577068,0.009800163,0.00032395392,0.00032541933,0.000020243562,0.0015558474,0.9840989,0.0005878258,0.00073646347,0.00095348904,0.0014472383],"study_design_scores_gemma":[0.002245718,0.00035582675,0.006223835,0.0006051159,0.00010191709,0.0000022697498,0.00025191874,0.9638681,0.0031535686,0.000010034761,0.022172473,0.001009264],"about_ca_topic_score_codex":0.000049032897,"about_ca_topic_score_gemma":0.0000095241385,"teacher_disagreement_score":0.5826458,"about_ca_system_score_codex":0.00092944317,"about_ca_system_score_gemma":0.00075175666,"threshold_uncertainty_score":0.9993072},"labels":[],"label_agreement":null},{"id":"W4416184234","doi":"10.1109/acsos-c66519.2025.00053","title":"Improving Adaptability in Agents Through Popperian Expectations","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ontario Tech University","funders":"","keywords":"Adaptability; Balance (ability); Reinforcement learning; Control (management); Flexibility (engineering); Behaviour change; Variety (cybernetics)","score_opus":0.030693769037560895,"score_gpt":0.3049711465294727,"score_spread":0.27427737749191183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416184234","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":[0.008828718,0.00018555374,0.90934455,0.002253085,0.001992766,0.00060691196,9.127225e-7,0.00013774903,0.07664973],"genre_scores_gemma":[0.91320324,0.000023556619,0.07594057,0.00060693134,0.000035259465,0.000032276526,0.0000028692366,0.000011347245,0.010143935],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965915,0.00026288428,0.0010170083,0.00093665044,0.0004446903,0.00074728136],"domain_scores_gemma":[0.9979436,0.00023738937,0.00020681304,0.0013692158,0.000154057,0.00008896794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046042222,0.0003301644,0.00036091972,0.0002723668,0.00035162503,0.00059893157,0.0014050171,0.00017973824,0.0005154509],"category_scores_gemma":[0.00059347495,0.0003573801,0.00014259102,0.0019156568,0.0001582788,0.0013971757,0.0010667306,0.00048175053,0.00021480664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023829718,0.00034512073,0.029426573,0.00024336393,0.00007533836,0.000023644985,0.017966177,0.722183,0.00027729463,0.18274549,0.0010769274,0.045613267],"study_design_scores_gemma":[0.00068573025,0.00008397352,0.019165501,0.000115830146,0.000014830884,9.82853e-7,0.0024303405,0.9743364,0.00041061168,0.001018945,0.00142147,0.00031537807],"about_ca_topic_score_codex":0.001035616,"about_ca_topic_score_gemma":0.00021827513,"teacher_disagreement_score":0.90437454,"about_ca_system_score_codex":0.00046132403,"about_ca_system_score_gemma":0.000621292,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W4416198962","doi":"10.3390/sym17111951","title":"Dynamic Heterogeneous Multi-Agent Inverse Reinforcement Learning Based on Graph Attention Mean Field","year":2025,"lang":"en","type":"article","venue":"Symmetry","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Ambiguity; Graph; Entropy (arrow of time); Principle of maximum entropy; Network topology; Inverse; Adversarial system","score_opus":0.013227040529980387,"score_gpt":0.2619231187260152,"score_spread":0.24869607819603481,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416198962","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":[0.004859031,0.000028663713,0.9894789,0.00054142176,0.0009863592,0.00027845745,2.3081788e-7,0.00030145954,0.003525469],"genre_scores_gemma":[0.9762488,0.000017743801,0.015956579,0.0024688884,0.000013056089,0.00002009725,0.000016708507,0.000014564535,0.005243538],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814194,0.00013202836,0.00038135258,0.00048612838,0.0004492575,0.00040929375],"domain_scores_gemma":[0.99873805,0.000169112,0.00016575746,0.00075844844,0.0000747771,0.000093831135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036623763,0.00023709678,0.00019573119,0.0005305798,0.00027065992,0.00016481798,0.0007076372,0.00012303622,0.000036496207],"category_scores_gemma":[0.00016547683,0.00024000453,0.00018350947,0.00071214203,0.00003523261,0.00016625502,0.00027206514,0.0004170209,0.00015288976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012495879,0.000038922313,0.001815487,0.00004779155,0.000041315863,0.000017162984,0.00007335102,0.99203163,0.0002171582,0.0015383797,0.00033205366,0.0038342397],"study_design_scores_gemma":[0.00072045025,0.0002995591,0.000779907,0.00012659516,0.000017853607,0.0000015773443,0.000034062265,0.99527407,0.001160177,0.000061312356,0.0013038088,0.0002206281],"about_ca_topic_score_codex":0.000038070466,"about_ca_topic_score_gemma":0.000011520765,"teacher_disagreement_score":0.9735223,"about_ca_system_score_codex":0.00020333448,"about_ca_system_score_gemma":0.00006558977,"threshold_uncertainty_score":0.9787101},"labels":[],"label_agreement":null},{"id":"W4416251251","doi":"10.1109/ijcnn64981.2025.11228644","title":"Leveraging World Model Disentanglement in Value-Based Multi-Agent Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Scalability; Sample (material); Function (biology); Graph; Range (aeronautics); Sample complexity; Sampling (signal processing)","score_opus":0.040929635774792084,"score_gpt":0.2967428688077293,"score_spread":0.25581323303293724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416251251","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":[0.0010095654,0.00022679659,0.9633641,0.0030353158,0.0015337849,0.0015406839,5.126176e-7,0.00032797133,0.028961254],"genre_scores_gemma":[0.7914082,0.00007583219,0.08786111,0.0034264792,0.00003884285,0.00010121235,0.000019464289,0.00004596055,0.11702294],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920519,0.0004720285,0.0023210195,0.0017011922,0.0015377859,0.001916066],"domain_scores_gemma":[0.9968648,0.00032800046,0.0005937073,0.0016436996,0.00022462053,0.00034518845],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019549238,0.0009565293,0.0008350281,0.0020871249,0.0007256573,0.0010376438,0.0021832979,0.00018554048,0.0004023419],"category_scores_gemma":[0.00021769099,0.0010415886,0.00040069394,0.003117971,0.00016954402,0.0007613654,0.0020138784,0.0014979444,0.00018264378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047856596,0.00027177355,0.013570672,0.00025502572,0.00010858723,0.000039547165,0.0015596615,0.9511117,0.00015832898,0.02697656,0.0005370868,0.005363252],"study_design_scores_gemma":[0.004420446,0.0001518935,0.00096884224,0.0012146943,0.00007818704,5.870787e-7,0.00030460107,0.9875208,0.0013860004,0.00012175362,0.0028834632,0.0009487397],"about_ca_topic_score_codex":0.0003215521,"about_ca_topic_score_gemma":0.00008857121,"teacher_disagreement_score":0.875503,"about_ca_system_score_codex":0.0024164293,"about_ca_system_score_gemma":0.0012521292,"threshold_uncertainty_score":0.9999994},"labels":[],"label_agreement":null},{"id":"W4416251343","doi":"10.1109/ijcnn64981.2025.11227725","title":"Navigation With QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Ubisoft (Canada)","funders":"","keywords":"Reinforcement learning; Trajectory; Planner; Image stitching; Motion planning; Path (computing); State space; Range (aeronautics); Function (biology)","score_opus":0.011123300682575932,"score_gpt":0.2746747569265827,"score_spread":0.2635514562440068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416251343","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":[0.007083448,0.000010090088,0.98064876,0.0012944983,0.00013559138,0.00024134143,1.7810682e-7,0.0003087634,0.01027733],"genre_scores_gemma":[0.8127837,0.0000018460552,0.18158495,0.000509922,0.000038301245,0.00003203453,0.0000138016185,0.00001039464,0.0050250357],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901456,0.00003431125,0.000192724,0.00029719213,0.000184725,0.00027651392],"domain_scores_gemma":[0.9992471,0.00028484577,0.00006646204,0.00027135824,0.00008502039,0.000045261622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024997638,0.0001136536,0.00012623606,0.00011132688,0.00020802267,0.00019411244,0.00042482585,0.000054955388,0.0000051436054],"category_scores_gemma":[0.000071459835,0.00008939203,0.000040689432,0.0003384083,0.0000295636,0.00027847034,0.00013759806,0.00022120372,0.000014083642],"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":[0.000021400961,0.00000958184,0.003245202,0.00003911014,0.00002959049,0.0000027186215,0.00021741865,0.4448135,0.000520051,0.5441787,0.00043180573,0.006490889],"study_design_scores_gemma":[0.0005030247,0.00022855513,0.0013364623,0.00009495637,0.000009102569,0.0000077168725,0.000049302562,0.98238564,0.0009552427,0.0016493696,0.012620643,0.00015998613],"about_ca_topic_score_codex":0.000013947632,"about_ca_topic_score_gemma":0.000001685507,"teacher_disagreement_score":0.80570024,"about_ca_system_score_codex":0.000035243484,"about_ca_system_score_gemma":0.00007383484,"threshold_uncertainty_score":0.36453012},"labels":[],"label_agreement":null},{"id":"W4416386275","doi":"10.48550/arxiv.2510.08526","title":"Convergence Theorems for Entropy-Regularized and Distributional Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Decoupling (probability); Entropy (arrow of time); Regularization (linguistics); Convergence (economics); Principle of maximum entropy","score_opus":0.028096724574999912,"score_gpt":0.27354029106517214,"score_spread":0.24544356649017224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416386275","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":[0.021099268,0.00016098814,0.97462285,0.0008614014,0.0014903198,0.0008638929,0.000013139189,0.0002620578,0.000626094],"genre_scores_gemma":[0.9748452,0.00021788703,0.014347185,0.00027989288,0.00017460703,0.00021131654,0.00035965082,0.000018387536,0.009545915],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973632,0.00012131618,0.0006129103,0.00089163,0.00045810515,0.00055285514],"domain_scores_gemma":[0.99785316,0.00038794128,0.00045285988,0.00087318424,0.00029057276,0.00014227268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067402807,0.00041654392,0.00045819982,0.00013666118,0.00039219292,0.00026173503,0.001296249,0.00029010707,0.00005274872],"category_scores_gemma":[0.00053958356,0.00041537257,0.00020881047,0.00019049153,0.00017060124,0.00021832767,0.0027647035,0.00079214975,0.000030649353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004330386,0.000021365015,0.05038478,0.00032291314,0.00021485047,0.000004878712,0.00038199243,0.6941576,0.0004852516,0.252959,0.00046502013,0.0005590425],"study_design_scores_gemma":[0.0009719594,0.00013981706,0.009572036,0.00028099385,0.00007318678,0.0000037241066,0.000030254494,0.9706381,0.0014821489,0.0033179151,0.012926965,0.00056287844],"about_ca_topic_score_codex":0.000027086842,"about_ca_topic_score_gemma":6.173638e-7,"teacher_disagreement_score":0.96027565,"about_ca_system_score_codex":0.00018818778,"about_ca_system_score_gemma":0.0003409201,"threshold_uncertainty_score":0.9998298},"labels":[],"label_agreement":null},{"id":"W4416429290","doi":"10.1109/tnnls.2025.3626050","title":"Universal Stabilization for Maximum Entropy Optimization in Reinforcement Learning","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Reinforcement Learning in Robotics","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":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Entropy (arrow of time); Kullback–Leibler divergence; Reinforcement learning; Principle of maximum entropy; Upper and lower bounds; Monotonic function; Maximum entropy spectral estimation; Divergence (linguistics)","score_opus":0.01099109538066441,"score_gpt":0.23014466149186183,"score_spread":0.2191535661111974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416429290","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":[0.0009118175,0.000088909845,0.9966233,0.00016034482,0.0011843136,0.00063741877,2.1147605e-7,0.00020613255,0.00018758979],"genre_scores_gemma":[0.9952481,0.00012743019,0.0018454681,0.000058634552,0.000038744318,0.00006258594,0.000009002853,0.000016733395,0.002593338],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99831307,0.0003431777,0.0004130312,0.00039313873,0.00018933625,0.00034827273],"domain_scores_gemma":[0.99906665,0.0004174136,0.00016498238,0.00019611526,0.00009485046,0.000060007882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052338745,0.00019714214,0.00023161196,0.00032685415,0.0005175739,0.0002986431,0.0002189867,0.00012812122,0.0000048613683],"category_scores_gemma":[0.000028263681,0.00020403313,0.00005635128,0.0005965194,0.000033548255,0.00039852192,0.000006482359,0.00059678074,0.0000010404997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040737028,0.000015267604,0.00023660387,0.000054955664,0.00002169095,0.0000015821166,0.00021485022,0.9935799,0.000024778283,0.0014190632,0.000021884103,0.0043686475],"study_design_scores_gemma":[0.00083876617,0.0003432804,0.000029657705,0.0001425531,0.000016991087,0.0000028607592,0.0002198299,0.9971748,0.000023948869,0.000005103098,0.0010266401,0.0001755475],"about_ca_topic_score_codex":0.000058786467,"about_ca_topic_score_gemma":0.000004855645,"teacher_disagreement_score":0.9947778,"about_ca_system_score_codex":0.00014337919,"about_ca_system_score_gemma":0.000032793854,"threshold_uncertainty_score":0.83202296},"labels":[],"label_agreement":null},{"id":"W4416447818","doi":"10.48550/arxiv.2505.16217","title":"Reward-Aware Proto-Representations in Reinforcement Learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Representation (politics); Reinforcement learning; Space (punctuation); Function (biology); Key (lock); Successor cardinal; Encoding (memory)","score_opus":0.05062451241968759,"score_gpt":0.31850417763202704,"score_spread":0.26787966521233947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416447818","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":[0.020478385,0.00007041843,0.9550361,0.0012835341,0.0012813832,0.0022735219,0.0000016446936,0.0005982428,0.018976755],"genre_scores_gemma":[0.9588622,0.00012813238,0.007982063,0.00042920062,0.00014954444,0.0009864456,0.00011572752,0.000033612796,0.031313106],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963307,0.0002676848,0.00096051744,0.001110442,0.0006676989,0.0006629514],"domain_scores_gemma":[0.99709016,0.00021470827,0.00051793474,0.0018217408,0.00022795245,0.00012748245],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00063863577,0.00046431212,0.00050493085,0.00059116975,0.00024158748,0.00030615745,0.002324416,0.00035673857,0.00007592674],"category_scores_gemma":[0.00046875482,0.0005089734,0.00017488998,0.0007667098,0.00007260733,0.00040573272,0.004629125,0.0020739664,0.00026971352],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004780491,0.00002019543,0.2251031,0.00017651512,0.000042728163,0.000022970997,0.0009547921,0.77163047,0.000019410827,0.0012190802,0.00034976093,0.00045619145],"study_design_scores_gemma":[0.0008307583,0.00015003681,0.08476085,0.0012136827,0.000037913167,0.0000040389514,0.00018786888,0.9005411,0.0006249871,0.0004278279,0.010307758,0.0009131517],"about_ca_topic_score_codex":0.00037606672,"about_ca_topic_score_gemma":0.00002333851,"teacher_disagreement_score":0.947054,"about_ca_system_score_codex":0.0003853601,"about_ca_system_score_gemma":0.00059570844,"threshold_uncertainty_score":0.9997362},"labels":[],"label_agreement":null},{"id":"W4416464763","doi":"10.1007/978-981-95-4367-0_40","title":"An Ensemble Method with Plans-Managed Policy for Proximal Policy Optimization","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","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":"Carleton University","funders":"","keywords":"Reinforcement learning; Ensemble learning; Policy learning; Optimization algorithm; Optimization problem; Ensemble forecasting","score_opus":0.015078387336756854,"score_gpt":0.29315041143452736,"score_spread":0.2780720240977705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416464763","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":[8.562074e-7,0.000028232413,0.9899431,0.0017682511,0.0004267686,0.001129636,0.0000075759,0.00028778572,0.006407803],"genre_scores_gemma":[0.0039760387,0.000014564139,0.99134904,0.0021526744,0.00064906693,0.000035096906,0.00002752715,0.0000446442,0.001751366],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959715,0.000073729396,0.0005313428,0.0016321401,0.0009252517,0.0008660621],"domain_scores_gemma":[0.99660057,0.00064313837,0.00039928974,0.0017352357,0.00042408906,0.00019765808],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010673254,0.00060690875,0.000575218,0.002245497,0.0004367622,0.00097310153,0.0037766972,0.00034079928,0.0000040073114],"category_scores_gemma":[0.00027389184,0.00053402764,0.00010667718,0.0014750372,0.00034702767,0.0009201613,0.00074836845,0.0006204875,0.000004199759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015604432,0.000012559428,0.0000075671596,0.000059940125,0.000014404994,0.000009211824,0.00034541573,0.7622108,0.000026946793,0.092487894,0.000013311547,0.14479634],"study_design_scores_gemma":[0.00045704597,0.00060313777,0.000011850077,0.00028856358,0.000014763517,0.000029677962,2.0164396e-7,0.9783231,0.0005214324,0.018103246,0.001067993,0.0005789774],"about_ca_topic_score_codex":0.00006621089,"about_ca_topic_score_gemma":0.000046695375,"teacher_disagreement_score":0.2161123,"about_ca_system_score_codex":0.00054701447,"about_ca_system_score_gemma":0.0025549775,"threshold_uncertainty_score":0.99971116},"labels":[],"label_agreement":null},{"id":"W4416524723","doi":"10.48550/arxiv.2507.00275","title":"Deep Double Q-learning","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Deep learning; Double loop; Double-precision floating-point format; Carry (investment); Double layered; Double layer (biology); Key (lock)","score_opus":0.043713119429636856,"score_gpt":0.2866334611570382,"score_spread":0.24292034172740135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416524723","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":[0.018187441,0.00023496027,0.93620914,0.0006596885,0.0024912073,0.00031978593,3.633385e-7,0.00078215316,0.041115247],"genre_scores_gemma":[0.90699685,0.00020101957,0.03956639,0.00079437357,0.00038297634,0.000086897475,0.000047176887,0.000041230574,0.051883113],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750245,0.000114029106,0.00048361957,0.0009047066,0.00045266064,0.00054250954],"domain_scores_gemma":[0.9976034,0.00014920485,0.00035178367,0.00159781,0.00017484407,0.00012291303],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00042046764,0.00038368165,0.00040468902,0.00024661433,0.00025028567,0.00035676692,0.0027164351,0.00036312905,0.00007404465],"category_scores_gemma":[0.00014491436,0.00040518126,0.0002063521,0.00038917834,0.000056144527,0.00025329224,0.005218663,0.0018330064,0.00071011455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000481295,0.000014012595,0.102441475,0.00011337064,0.00006515353,0.000017644423,0.00051788666,0.89068985,0.00001888215,0.004470807,0.00037128502,0.0012748241],"study_design_scores_gemma":[0.0006453138,0.000073213,0.024045598,0.00035315292,0.00004835023,0.000004866423,0.000039875555,0.9353493,0.0006721513,0.00044064588,0.03756536,0.00076219876],"about_ca_topic_score_codex":0.00007993696,"about_ca_topic_score_gemma":0.0000047412377,"teacher_disagreement_score":0.89664274,"about_ca_system_score_codex":0.00015535705,"about_ca_system_score_gemma":0.0002803777,"threshold_uncertainty_score":0.99984},"labels":[],"label_agreement":null},{"id":"W4416748794","doi":"10.1109/iros60139.2025.11246593","title":"RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Huawei Technologies (Canada)","funders":"","keywords":"Robotics; Scalability; Reinforcement learning; Task (project management); Robot; Adaptation (eye); Range (aeronautics); Adaptive sampling; Sampling (signal processing)","score_opus":0.037698156261299624,"score_gpt":0.2881238452098909,"score_spread":0.2504256889485913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416748794","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":[0.0002268431,0.0004931076,0.9272173,0.014512754,0.004213507,0.0018825061,0.000022024751,0.0005671159,0.050864853],"genre_scores_gemma":[0.35686445,0.00031923686,0.5829895,0.0040099216,0.0010151097,0.00011242479,0.000043126016,0.000101522965,0.05454469],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924535,0.0003454785,0.0019799597,0.0019622312,0.0011130137,0.002145809],"domain_scores_gemma":[0.9923905,0.0016262202,0.0009200693,0.0037971106,0.0008105677,0.00045549302],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015902723,0.0010512351,0.001221289,0.0013478199,0.0013972323,0.0010555472,0.004946425,0.0006404233,0.00015482995],"category_scores_gemma":[0.0035599433,0.0010690613,0.0005663876,0.0028095224,0.00045097744,0.0011087961,0.0026206297,0.0010068637,0.00007085325],"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":[0.000090506175,0.00009026353,0.00015903448,0.00014299098,0.00022019769,0.000016411997,0.0028886853,0.42328325,0.0002954056,0.53386223,0.0056619467,0.033289064],"study_design_scores_gemma":[0.0043849056,0.0016256073,0.0009056977,0.00086812396,0.00019729283,0.000016983548,0.0007531921,0.9560432,0.0004622009,0.029909316,0.0036922852,0.0011412228],"about_ca_topic_score_codex":0.00046823494,"about_ca_topic_score_gemma":0.000019851092,"teacher_disagreement_score":0.5327599,"about_ca_system_score_codex":0.0007825768,"about_ca_system_score_gemma":0.0025043846,"threshold_uncertainty_score":0.99998146},"labels":[],"label_agreement":null},{"id":"W4416749759","doi":"10.1109/iros60139.2025.11246340","title":"Generalizable Humanoid Manipulation with 3D Diffusion Policies","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Simon Fraser University","funders":"","keywords":"Humanoid robot; Teleoperation; Robot; Robot control; Robotics; Telerobotics","score_opus":0.019004686340609908,"score_gpt":0.2618350488401887,"score_spread":0.2428303624995788,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416749759","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":[0.009962545,0.0001382525,0.84303623,0.0009633016,0.0007747328,0.00041184635,2.4961403e-7,0.00021115743,0.1445017],"genre_scores_gemma":[0.63896286,0.000114852955,0.049565453,0.0012271984,0.00012837249,0.000014909871,0.000011304435,0.00002422699,0.30995083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737614,0.00013525583,0.0005621017,0.0006481059,0.00062256714,0.0006558427],"domain_scores_gemma":[0.9982869,0.000078387304,0.000230673,0.001100194,0.0002019107,0.00010193145],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002969643,0.00039771228,0.00034968156,0.00041674083,0.0007296593,0.00096338685,0.0009814289,0.00016471358,0.00034737508],"category_scores_gemma":[0.000031788524,0.00031787658,0.000079309684,0.0012187051,0.00014068479,0.00073721964,0.0008087367,0.00026615636,0.00015218154],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021883809,0.00003596257,0.009934918,0.00008964767,0.00004945537,0.000004551708,0.00041829937,0.8440044,0.00042163546,0.13924365,0.00201232,0.0037633132],"study_design_scores_gemma":[0.0008036067,0.00049422955,0.007909078,0.0002027585,0.000058614747,0.0000049299847,0.000043487446,0.9750865,0.0014192628,0.0001564866,0.013457462,0.00036354718],"about_ca_topic_score_codex":0.0005371544,"about_ca_topic_score_gemma":0.000032414802,"teacher_disagreement_score":0.79347074,"about_ca_system_score_codex":0.00018422828,"about_ca_system_score_gemma":0.00022696181,"threshold_uncertainty_score":0.99992734},"labels":[],"label_agreement":null},{"id":"W4416756242","doi":"10.1109/lra.2025.3632119","title":"X-Nav: Learning End-to-End Cross-Embodiment Navigation for Mobile Robots","year":2025,"lang":"en","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mobile robot; Robot; Reinforcement learning; Robot learning; Robotics; Generalizability theory; Mobile robot navigation","score_opus":0.010608148763294734,"score_gpt":0.2849909912877431,"score_spread":0.27438284252444833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416756242","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":[0.037026238,0.000026902644,0.95692444,0.0038993426,0.0010108695,0.00064289477,0.0000013520562,0.00029692266,0.00017103819],"genre_scores_gemma":[0.824947,0.000008968121,0.17085338,0.0029016421,0.00009620824,0.0001397702,0.000035969948,0.000020207835,0.0009968398],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984191,0.00005896256,0.00042472055,0.00043338933,0.00031123593,0.0003526017],"domain_scores_gemma":[0.9990526,0.00022462734,0.00018359433,0.00032458492,0.00012185569,0.00009274443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004205156,0.00020096805,0.00020448097,0.00023017607,0.0004231341,0.00066277356,0.000373037,0.00007995609,0.000005197604],"category_scores_gemma":[0.000058466765,0.00021285299,0.000072980794,0.0003772176,0.00005450021,0.00047974294,0.00012082222,0.00017877122,0.000026795731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003671609,0.000013259952,0.00069777423,0.00007005905,0.000027953089,0.0000015118311,0.00035905457,0.97485065,0.0068519632,0.008689193,0.0008151844,0.0076197484],"study_design_scores_gemma":[0.0004877783,0.00010890493,0.002542723,0.00011387357,0.000018660054,0.0000028690833,0.000017745157,0.98923385,0.0035946677,0.00018015451,0.0034664155,0.00023233423],"about_ca_topic_score_codex":0.000008735646,"about_ca_topic_score_gemma":5.0666324e-7,"teacher_disagreement_score":0.7879208,"about_ca_system_score_codex":0.00012452871,"about_ca_system_score_gemma":0.00004819098,"threshold_uncertainty_score":0.8679893},"labels":[],"label_agreement":null},{"id":"W4416828434","doi":"10.1016/j.cogsys.2025.101422","title":"Dual or unified: optimizing drive-based reinforcement learning for cognitive autonomous robots","year":2025,"lang":"en","type":"article","venue":"Cognitive Systems Research","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"Ministério da Ciência, Tecnologia e Inovação; Ministério da Ciência, Tecnologia, Inovações e Comunicações; Fundação de Amparo à Pesquisa do Estado de São Paulo; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Brazilian Institute of Neuroscience and Neurotechnology","keywords":"Reinforcement learning; Modular design; Dual (grammatical number); Cognition; Curiosity; Selection (genetic algorithm); Robot; Autonomous agent; Action selection","score_opus":0.10680813833711963,"score_gpt":0.39253079557312515,"score_spread":0.28572265723600554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416828434","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":[0.0009813146,0.00023407949,0.9706558,0.00031502242,0.00078310654,0.003678886,0.0000061040755,0.00037726626,0.022968434],"genre_scores_gemma":[0.95743155,0.000027722086,0.0045591746,0.0001731941,0.00017494662,0.0012484794,0.00009610111,0.000049557755,0.03623927],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9938876,0.0012038266,0.0008647979,0.001129712,0.0013904081,0.0015236547],"domain_scores_gemma":[0.98824835,0.006945475,0.00029206922,0.0005477358,0.0036975623,0.00026881986],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004107275,0.0004212589,0.0005863919,0.0013172098,0.0014723524,0.0011922539,0.0010762044,0.00026102705,0.000038967843],"category_scores_gemma":[0.005200153,0.0003865425,0.0001796693,0.0020256804,0.00037147698,0.00057485205,0.0008893273,0.001199908,0.00018095285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042899183,0.00007544095,0.0003554369,0.0005905496,0.00027535335,0.00009291891,0.0009713743,0.96935433,0.00023227907,0.018595563,0.0007797305,0.0082480125],"study_design_scores_gemma":[0.003459194,0.0013126123,0.0001914202,0.002303271,0.00004396985,0.000009928359,0.003299302,0.9825447,0.002901728,0.000057617974,0.0034158353,0.00046039606],"about_ca_topic_score_codex":0.000112521055,"about_ca_topic_score_gemma":0.0000073300685,"teacher_disagreement_score":0.96609664,"about_ca_system_score_codex":0.0005551752,"about_ca_system_score_gemma":0.0018816316,"threshold_uncertainty_score":0.9998587},"labels":[],"label_agreement":null},{"id":"W4417094986","doi":"10.48550/arxiv.2502.16772","title":"Model-Based Exploration in Monitored Markov Decision Processes","year":2025,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; University of Alberta; Alberta Machine Intelligence Institute; Alliance de recherche numérique du Canada; Mitacs; Canadian Institute for Advanced Research","keywords":"Markov decision process; Leverage (statistics); Exploit; Partially observable Markov decision process; Convergence (economics); Reinforcement learning; Process (computing); Markov process","score_opus":0.09140309050084275,"score_gpt":0.22014486556733345,"score_spread":0.1287417750664907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417094986","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":[0.017321624,0.00002736939,0.9797597,0.00008160986,0.0004289268,0.00036577682,0.0000036105776,0.00022336339,0.0017880183],"genre_scores_gemma":[0.9642405,0.00012478481,0.03390205,0.00006959899,0.00002184024,0.0000033224144,0.000022983711,0.000010300986,0.0016045993],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998232,0.000095421,0.00028078334,0.00093733333,0.00016233641,0.00029209515],"domain_scores_gemma":[0.9980543,0.00023313517,0.00024240969,0.0011010437,0.00028771837,0.00008135097],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025010292,0.0002855513,0.0002786808,0.0006444781,0.000102910955,0.00018029773,0.0018616938,0.00029304635,0.0000038151334],"category_scores_gemma":[0.00018724383,0.00034523886,0.00009393856,0.001232197,0.00004780241,0.0007239733,0.0013207556,0.0005273288,0.000021160875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037854315,0.00004234869,0.0024306478,0.00016993421,0.000011129319,0.00004690917,0.00014633717,0.99061143,0.0000026713049,0.0056351693,0.00009994454,0.0007656101],"study_design_scores_gemma":[0.00047157297,0.000027764905,0.00020862622,0.00042409232,0.000017929788,1.4553648e-7,0.000025984187,0.98526365,0.000109186076,0.013092882,0.00005633954,0.00030184299],"about_ca_topic_score_codex":0.000040134753,"about_ca_topic_score_gemma":0.000032685577,"teacher_disagreement_score":0.9469189,"about_ca_system_score_codex":0.00035698368,"about_ca_system_score_gemma":0.00093629584,"threshold_uncertainty_score":0.9999},"labels":[],"label_agreement":null},{"id":"W4417239585","doi":"10.1038/s41467-025-66009-y","title":"Discovery of the reward function for embodied reinforcement learning agents","year":2025,"lang":"en","type":"article","venue":"Nature Communications","topic":"Reinforcement Learning in Robotics","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 Victoria","funders":"National Key Research and Development Program of China; State Key Laboratory of Industrial Control Technology; State Key Laboratory of Mechanical Transmissions; Huazhong University of Science and Technology; National Natural Science Foundation of China","keywords":"Embodied cognition; Reinforcement learning; Regret; Maximization; Adaptability; Cognition; Function (biology); Cognitive robotics","score_opus":0.025178428916446973,"score_gpt":0.30649491024565473,"score_spread":0.2813164813292078,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417239585","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":[0.00022997583,0.00042783102,0.9718778,0.004635181,0.00068880804,0.0004633837,8.631596e-7,0.00007309895,0.021603042],"genre_scores_gemma":[0.9787047,0.000095136325,0.012339107,0.00069960975,0.000012278515,0.000058978592,0.000021663123,0.0000055271116,0.008063007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910146,0.000116712625,0.00028746633,0.00014919568,0.00020137485,0.00014381828],"domain_scores_gemma":[0.99690825,0.0003764687,0.00022682267,0.0022749803,0.00019940094,0.000014071876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003360526,0.0000919375,0.00011441676,0.00009565994,0.0004981177,0.00009270881,0.0027063652,0.00012776186,0.000001390452],"category_scores_gemma":[0.0005102294,0.00007186548,0.000120812365,0.00054104824,0.000079711965,0.00029411967,0.0012338633,0.00062572275,0.0000026182652],"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":[0.00000988184,0.000025811063,0.002691945,0.000030024059,0.00007324777,1.868942e-8,0.00023203368,0.26205844,0.0002885651,0.72661144,0.0067137615,0.0012648678],"study_design_scores_gemma":[0.00064304564,0.00009930681,0.015805097,0.00017554336,0.000080888174,5.169005e-7,0.00011138044,0.6962799,0.001123049,0.0031674025,0.2823335,0.0001803829],"about_ca_topic_score_codex":0.000006912497,"about_ca_topic_score_gemma":0.000013094453,"teacher_disagreement_score":0.97847474,"about_ca_system_score_codex":0.00007570995,"about_ca_system_score_gemma":0.00010782268,"threshold_uncertainty_score":0.5029145},"labels":[],"label_agreement":null},{"id":"W4417251985","doi":"10.1109/lra.2025.3643304","title":"An Intention-Guided Reinforcement Learning Approach With Dirichlet Energy Constraint for Heterogeneous Multi-Robot Cooperation","year":2025,"lang":"","type":"article","venue":"IEEE Robotics and Automation Letters","topic":"Reinforcement Learning in Robotics","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 Guelph","funders":"National Natural Science Foundation of China","keywords":"Reinforcement learning; Observability; Constraint (computer-aided design); Adaptability; Process (computing); Robot; Variety (cybernetics); Convergence (economics); Software deployment","score_opus":0.022887647404219565,"score_gpt":0.26651502927352133,"score_spread":0.24362738186930177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417251985","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":[0.0017738162,0.00008328824,0.9931938,0.0023403568,0.0010243682,0.0011621013,0.0000030877611,0.00030884266,0.00011035586],"genre_scores_gemma":[0.7805316,0.00008799412,0.2154958,0.0027324688,0.000091625785,0.00012525068,0.00018569075,0.000044723445,0.000704894],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960561,0.000297859,0.0012502288,0.0010885517,0.0005433047,0.00076399185],"domain_scores_gemma":[0.99755746,0.0001692713,0.0007370053,0.00072257465,0.0005824842,0.00023122413],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00068011513,0.0006469145,0.00059307384,0.0005244253,0.0010880915,0.0015956692,0.0006197892,0.00024055717,0.0000083338155],"category_scores_gemma":[0.00008615583,0.00063662406,0.00015151114,0.0006543679,0.00038367513,0.00095804647,0.00013043426,0.00037933612,0.0000041668595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035890986,0.00012839546,0.00018395488,0.00028075455,0.00027573196,0.000006242256,0.00072765024,0.9746766,0.0054431665,0.012637107,0.0002777412,0.005326747],"study_design_scores_gemma":[0.0025116669,0.0006510589,0.00017227975,0.00033215844,0.00019041734,0.000042410564,0.000094654446,0.99296325,0.0019360404,0.000014902432,0.00040108783,0.0006900642],"about_ca_topic_score_codex":0.00005920162,"about_ca_topic_score_gemma":0.000008002096,"teacher_disagreement_score":0.77875775,"about_ca_system_score_codex":0.00027319067,"about_ca_system_score_gemma":0.00023476683,"threshold_uncertainty_score":0.9996085},"labels":[],"label_agreement":null},{"id":"W4417293150","doi":"10.63282/3117-5481/aijcst-v3i5p102","title":"How Citizen Developers Changed the Game","year":2021,"lang":"","type":"article","venue":"American International Journal of Computer Science and Technology","topic":"Reinforcement Learning in Robotics","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":"Microsemi (Canada)","funders":"","keywords":"Task (project management); Benchmarking; Deliverable; Modular design; Reinforcement learning; Action (physics); Autonomy; Software deployment; Intelligent agent","score_opus":0.012055228329681152,"score_gpt":0.2542565824229696,"score_spread":0.24220135409328847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417293150","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":[0.025563926,0.0004995838,0.79330873,0.17682368,0.0035644055,0.000071563016,9.1942235e-7,0.000029736952,0.00013744661],"genre_scores_gemma":[0.93015456,0.0011620156,0.064897,0.0030712525,0.0004989555,0.0000020426878,3.7006487e-7,0.000010352894,0.00020345757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961751,0.00011161627,0.000608854,0.0005240153,0.0020281894,0.00055222854],"domain_scores_gemma":[0.9914539,0.00019951454,0.001278217,0.0005756752,0.006319484,0.00017322548],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0013309836,0.00025078404,0.0004303811,0.0011827124,0.0003400748,0.0021157814,0.0054730647,0.000079077145,0.000010112465],"category_scores_gemma":[0.0008382897,0.00018859674,0.00009959025,0.003994206,0.005347661,0.0011990545,0.0026252791,0.00075565086,0.00000722925],"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":[0.000013230275,0.000053015938,0.0018685554,0.0000051834045,0.00027603062,0.0006350305,0.0016262456,0.003342379,0.001653451,0.0335164,0.0007050817,0.9563054],"study_design_scores_gemma":[0.0020515176,0.0026013341,0.010233822,0.00049930747,0.00010518543,0.018516561,0.003353642,0.8048435,0.015491871,0.0045577427,0.13669956,0.0010459741],"about_ca_topic_score_codex":0.000008056141,"about_ca_topic_score_gemma":0.000003092338,"teacher_disagreement_score":0.95525944,"about_ca_system_score_codex":0.0002493852,"about_ca_system_score_gemma":0.0021234225,"threshold_uncertainty_score":0.9999078},"labels":[],"label_agreement":null},{"id":"W4417338215","doi":"10.1109/icmlc66258.2025.11280109","title":"Learning to Communicate in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Defence Research and Development Canada; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Battle; Autonomous agent; Error-driven learning; Intelligent agent; Game theory; Reinforcement; Limit (mathematics)","score_opus":0.04737860407282586,"score_gpt":0.31586286264509655,"score_spread":0.2684842585722707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417338215","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":[0.0029055378,0.00027951406,0.9729749,0.0027500927,0.0012331012,0.002858126,3.9076667e-7,0.00039388245,0.016604466],"genre_scores_gemma":[0.758519,0.00023534513,0.11295179,0.0017698344,0.00002998921,0.0003171676,0.000014965029,0.000051568622,0.12611032],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99299365,0.0006498458,0.0021770129,0.0014870458,0.0007113567,0.0019811087],"domain_scores_gemma":[0.9954557,0.0011387087,0.0006052031,0.0019385854,0.0004628344,0.00039899585],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0030253555,0.0008295411,0.0009464354,0.0011581498,0.0012721526,0.0011087437,0.0038517064,0.00035650472,0.00016873695],"category_scores_gemma":[0.0018248967,0.0009287493,0.00036242604,0.002266018,0.00018399014,0.00074552995,0.004552958,0.0020130794,0.00050459604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007075955,0.000114459195,0.006681448,0.00018377631,0.00010340265,0.000009627306,0.007071712,0.94613475,0.0002702565,0.0112866005,0.00034458106,0.027728653],"study_design_scores_gemma":[0.002402449,0.0009225266,0.002413886,0.0007654966,0.000047085752,0.0000028037257,0.0010793835,0.9194852,0.0007305978,0.000038176582,0.071255706,0.00085665577],"about_ca_topic_score_codex":0.00055053364,"about_ca_topic_score_gemma":0.00013718846,"teacher_disagreement_score":0.8600231,"about_ca_system_score_codex":0.0012677099,"about_ca_system_score_gemma":0.0007059305,"threshold_uncertainty_score":0.9999282},"labels":[],"label_agreement":null},{"id":"W4417531150","doi":"10.48550/arxiv.2512.16848","title":"Meta-RL Induces Exploration in Language Agents","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Canadian Institute for Advanced Research; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Reinforcement learning; Task (project management); Adaptation (eye); Generalization; Key (lock); Constructed language; Language model","score_opus":0.19891014669402876,"score_gpt":0.33922926549410454,"score_spread":0.14031911880007578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417531150","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":[0.4124493,0.00050605956,0.5767218,0.0013150012,0.0018203384,0.0005315147,0.000003792863,0.00031366546,0.0063385773],"genre_scores_gemma":[0.98342496,0.00011359606,0.007960121,0.0005951169,0.00009874441,0.0001350186,0.000052985455,0.0000141866985,0.007605242],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980005,0.00018808355,0.0004807347,0.00064768805,0.00038097537,0.00030199473],"domain_scores_gemma":[0.99830806,0.00010134246,0.00028482362,0.0011772383,0.000072409304,0.00005612988],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004897697,0.00029351166,0.0004369344,0.00034020847,0.00006255194,0.0001957987,0.0016079134,0.00024623403,0.000051469862],"category_scores_gemma":[0.00015533327,0.0002768718,0.00017125762,0.0004188255,0.00002691276,0.0005298262,0.0021215093,0.0007733636,0.00019976692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004224997,0.00006947588,0.03941293,0.00019791113,0.0006757928,0.000077701654,0.009270216,0.94518614,0.00023839623,0.0015901829,0.0010260997,0.0022509573],"study_design_scores_gemma":[0.0019914801,0.00025024568,0.22801442,0.0012487628,0.0014886826,0.000006053463,0.0012315704,0.727092,0.02009915,0.0034649516,0.011772393,0.0033402785],"about_ca_topic_score_codex":0.0001978858,"about_ca_topic_score_gemma":0.000033607004,"teacher_disagreement_score":0.5709757,"about_ca_system_score_codex":0.00011495456,"about_ca_system_score_gemma":0.0001701235,"threshold_uncertainty_score":0.99996835},"labels":[],"label_agreement":null},{"id":"W4417538955","doi":"10.48550/arxiv.2506.16608","title":"Distributions as Actions: A Unified Framework for Diverse Action Spaces","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Action (physics); Parameterized complexity; Simple (philosophy); Boundary (topology); Space (punctuation); Distribution (mathematics); Variance (accounting)","score_opus":0.12962069525450415,"score_gpt":0.36849466999100305,"score_spread":0.2388739747364989,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417538955","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":[0.016824735,0.000049176462,0.9730045,0.002815196,0.0040997025,0.00073999976,0.000047307924,0.0005132295,0.0019061492],"genre_scores_gemma":[0.8049205,0.00043305336,0.17276768,0.0005951984,0.0006532207,0.00054556853,0.00040647326,0.00003241758,0.019645913],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981575,0.00008279797,0.00035087316,0.0007169602,0.00029397965,0.0003979121],"domain_scores_gemma":[0.9973892,0.0005322296,0.00037726713,0.0013294609,0.00026369782,0.00010813767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023660681,0.00031229787,0.00030068078,0.0002048132,0.00043206912,0.00037188857,0.0013082309,0.00048451958,0.000033537104],"category_scores_gemma":[0.0009838697,0.00033518142,0.0002533597,0.00044813452,0.000075585645,0.0003489606,0.001588138,0.0010285433,0.00018653003],"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":[0.000046895108,0.00015192507,0.028499978,0.00046635067,0.00046952022,0.000010191837,0.00094819034,0.46652475,0.00010305587,0.48923093,0.009328101,0.0042201234],"study_design_scores_gemma":[0.0017299849,0.0006090534,0.061028134,0.0027895772,0.0008052226,0.000017622837,0.0015313113,0.40567997,0.0049192416,0.12684408,0.39096645,0.0030793757],"about_ca_topic_score_codex":0.0001223681,"about_ca_topic_score_gemma":0.000010689861,"teacher_disagreement_score":0.8002368,"about_ca_system_score_codex":0.00030910654,"about_ca_system_score_gemma":0.0003970901,"threshold_uncertainty_score":0.99991},"labels":[],"label_agreement":null},{"id":"W627618803","doi":"10.71781/10765","title":"Modèle informatique du coapprentissage des ganglions de la base et du cortex : l'apprentissage par renforcement et le développement de représentations","year":2009,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Humanities; Political science; Philosophy","score_opus":0.052661862367999884,"score_gpt":0.3434632231230554,"score_spread":0.29080136075505547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W627618803","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":[0.08840853,0.00007948453,0.8122406,0.002364243,0.0005648368,0.0018886415,0.000047289388,0.000035350924,0.09437103],"genre_scores_gemma":[0.64563775,0.00062144507,0.3386494,0.0006091636,0.000074072515,0.0002803306,0.0027248405,0.000072562434,0.01133045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9941201,0.0014342522,0.0015330432,0.00094515365,0.0009090386,0.0010584153],"domain_scores_gemma":[0.99595284,0.0006267073,0.001248967,0.0012177177,0.00045603252,0.00049770606],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003917847,0.0007852112,0.0006713812,0.00037288506,0.0015455972,0.004386697,0.0025158715,0.0005385231,0.0013341393],"category_scores_gemma":[0.0006873199,0.0009214738,0.00028422996,0.0007776331,0.0003130621,0.0026230942,0.000929938,0.001055913,0.0003885932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010598257,0.00083255407,0.0043592923,0.0002388114,0.00032941275,0.0003990434,0.13450369,0.79058605,0.0015841022,0.023135584,0.006944339,0.03698114],"study_design_scores_gemma":[0.003812112,0.0006441172,0.121197194,0.0020784722,0.00043266657,0.00041079454,0.014474236,0.80662143,0.014179384,0.0016048426,0.03264481,0.0018999644],"about_ca_topic_score_codex":0.0018725777,"about_ca_topic_score_gemma":0.0030711328,"teacher_disagreement_score":0.5572292,"about_ca_system_score_codex":0.00067556713,"about_ca_system_score_gemma":0.0032530962,"threshold_uncertainty_score":0.99975425},"labels":[],"label_agreement":null},{"id":"W64134055","doi":"","title":"Bayesian Learning of Recursively Factored Environments","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Factoring; Computer science; Reinforcement learning; Factorization; Inference; Class (philosophy); Artificial intelligence; Bayesian probability; Task (project management); Machine learning; Scaling; Bayesian inference; Theoretical computer science; Algorithm; Mathematics","score_opus":0.00994807483159242,"score_gpt":0.20887989202429472,"score_spread":0.1989318171927023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W64134055","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":[0.0051166364,0.000006440732,0.97535664,0.00018710099,0.00008675558,0.0001250158,4.8438416e-8,0.00006422593,0.01905712],"genre_scores_gemma":[0.93494123,0.000007367906,0.056413848,0.00007176708,0.000009199557,0.000004972843,0.0000013024891,0.000006562921,0.00854377],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990883,0.000046239475,0.00020591395,0.00018492706,0.00026966148,0.00020496071],"domain_scores_gemma":[0.999413,0.000058230493,0.00012890648,0.00031038205,0.000020300162,0.000069156704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000084258056,0.00009130381,0.000111702495,0.00006313683,0.000051881172,0.00005920289,0.0005508716,0.00004287671,0.00042786362],"category_scores_gemma":[0.000054325945,0.0000802276,0.00004106392,0.00011828323,0.00003760568,0.00045980062,0.00019709484,0.00012709908,0.0004260575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000031274863,0.00007761744,0.055720147,0.00002889377,0.00008704161,0.0000042595398,0.0025364049,0.8177065,0.026610708,0.051916774,0.0024256152,0.042882863],"study_design_scores_gemma":[0.00026860475,0.00021285913,0.03439582,0.000015741429,0.0000036626914,0.0000021642325,0.000103280734,0.9478611,0.010771538,0.0005426625,0.0056118956,0.00021068567],"about_ca_topic_score_codex":0.000044847424,"about_ca_topic_score_gemma":1.2996153e-7,"teacher_disagreement_score":0.9298246,"about_ca_system_score_codex":0.000025668556,"about_ca_system_score_gemma":0.000012988737,"threshold_uncertainty_score":0.5476249},"labels":[],"label_agreement":null},{"id":"W6888783548","doi":"10.22067/econg.2023.80748.1066","title":"REE-Y-Ti-Th mineralization in the albite bearing metasomatite and metasomatized rhyolite hosted in Choghart magnetite-apatite deposit, Central Iran: Interplay of evaporitic brines, hydrothermal-magmatic fluids","year":2023,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Reinforcement Learning in Robotics","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":"Metasomatism; Mineralization (soil science); Hydrothermal circulation; Albite; Calcite; Rhyolite; Fluid inclusions; Isotope geochemistry; δ34S","score_opus":0.11849839901669237,"score_gpt":0.47022455640057076,"score_spread":0.35172615738387836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6888783548","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":[0.96061486,0.0041409484,0.032576405,0.0002375435,0.00032703698,0.0011491384,0.000009259014,0.000072559844,0.000872262],"genre_scores_gemma":[0.99329454,0.0029080284,0.0031640083,0.00024765808,0.000040173472,0.000068756075,0.000030597676,0.00004521053,0.00020105368],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99537134,0.00088032417,0.0016557622,0.00050273247,0.0009820272,0.00060780765],"domain_scores_gemma":[0.997281,0.00074292003,0.000873672,0.0007963317,0.00015960426,0.00014644352],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002630996,0.00038212785,0.0009239625,0.001672629,0.0001354344,0.0014599351,0.0033026882,0.000097672484,0.00024186923],"category_scores_gemma":[0.00060301134,0.00031871733,0.000144,0.0034621442,0.0001262786,0.003393601,0.0011711115,0.00040012266,0.000008976205],"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":[0.00006666074,0.00013788839,0.8213212,0.00067679875,0.00017790539,0.0000982198,0.0037543734,0.09293371,0.07577463,0.0008561193,0.000752512,0.0034499858],"study_design_scores_gemma":[0.00093306863,0.000023347224,0.7005178,0.001085023,0.000053956213,0.000025918062,0.000049419657,0.29360586,0.0028441472,0.0004188845,0.00015977265,0.00028280387],"about_ca_topic_score_codex":0.0020981329,"about_ca_topic_score_gemma":0.00031222805,"teacher_disagreement_score":0.20067215,"about_ca_system_score_codex":0.000098377284,"about_ca_system_score_gemma":0.00006586063,"threshold_uncertainty_score":0.9999265},"labels":[],"label_agreement":null},{"id":"W6892327132","doi":"10.5065/d6f47m5p","title":"SWL11 Bottle data. Version 1.0","year":2015,"lang":"en","type":"dataset","venue":"Earth Observing Laboratory","topic":"Reinforcement Learning in Robotics","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":true,"ca_institutions":"Fisheries and Oceans Canada","funders":"","keywords":"Coast guard; Cruise; Hydrography; Water bottle; Longitude; Bottle; Latitude; Colored dissolved organic matter","score_opus":0.05144617681186247,"score_gpt":0.2781954881882576,"score_spread":0.22674931137639515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6892327132","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":[0.000013497707,0.0009352803,0.016128322,0.00019803845,0.0041345134,0.00023585605,0.9777297,0.00037982682,0.00024497465],"genre_scores_gemma":[0.000007653869,0.00017092445,0.014056599,0.0009528129,0.0005251975,0.000005715572,0.98352724,0.000035653124,0.00071822334],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99642634,0.00026538686,0.0004717934,0.0010367396,0.0012168001,0.0005829415],"domain_scores_gemma":[0.99203587,0.00015544087,0.00044753661,0.0065872935,0.00046328863,0.00031055073],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012904,0.00044850557,0.00045071976,0.00021380407,0.00021256415,0.00052795047,0.0077582584,0.00041877633,0.00021302352],"category_scores_gemma":[0.00075498095,0.0004667648,0.00005209352,0.0008700198,0.00007032823,0.0013569959,0.0052829394,0.00094804686,0.004799472],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027927147,0.000020318623,0.00003178467,0.000098446726,0.000034158835,0.00006874364,0.000025331447,0.007094455,0.000008244554,0.000027881093,0.9924624,0.00012543051],"study_design_scores_gemma":[0.00027009335,0.00007780117,0.00010688132,0.00013753535,0.000032375425,0.000002703955,0.000009401089,0.017428966,0.000015779757,0.000010852503,0.98141164,0.00049595407],"about_ca_topic_score_codex":0.00010684311,"about_ca_topic_score_gemma":0.000051256768,"teacher_disagreement_score":0.011050757,"about_ca_system_score_codex":0.000098637545,"about_ca_system_score_gemma":0.0012207141,"threshold_uncertainty_score":0.9997784},"labels":[],"label_agreement":null},{"id":"W6893087174","doi":"10.5281/zenodo.14162773","title":"Hydrolysate Untargeted Metabolomics Mass Spectrometry Data","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Reinforcement Learning in Robotics","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":"Dalhousie University","funders":"","keywords":"Hydrolysate; Mass spectrometry; Metabolomics; Liquid chromatography–mass spectrometry; Analyte","score_opus":0.0442405478327345,"score_gpt":0.2672488440427971,"score_spread":0.22300829621006257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893087174","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":[0.000002653981,0.00032963086,0.23164515,0.0006128074,0.0010582233,0.0004519666,0.75829417,0.0016871636,0.005918239],"genre_scores_gemma":[0.000069872156,0.0007846143,0.007153991,0.0002279281,0.0003647906,3.247653e-8,0.9893285,0.001343654,0.0007265894],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956742,0.00049670535,0.00057758926,0.001451771,0.0010510995,0.0007486247],"domain_scores_gemma":[0.9943136,0.00006087727,0.00031095205,0.004699046,0.00034338268,0.0002721518],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0016177376,0.00042757374,0.00041649156,0.00090491516,0.0014084894,0.004499148,0.013943963,0.00024705403,0.0061978525],"category_scores_gemma":[0.00094025896,0.00044776528,0.0001002607,0.0018142967,0.0001682289,0.0008396369,0.015853621,0.0014706621,0.10391722],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009356946,0.00003640915,4.9645305e-8,0.00017121564,0.00019444864,0.0000859949,0.000055688033,0.0019073943,0.00025553978,0.00085682987,0.9941087,0.0023183974],"study_design_scores_gemma":[0.0002204442,0.00015281668,0.0000023131713,0.00006053545,0.0000906247,0.00010670923,0.000017291768,0.039713647,0.00005916247,0.00023001371,0.9589133,0.00043313316],"about_ca_topic_score_codex":0.000022088103,"about_ca_topic_score_gemma":2.956027e-7,"teacher_disagreement_score":0.23103437,"about_ca_system_score_codex":0.00028118203,"about_ca_system_score_gemma":0.000021557065,"threshold_uncertainty_score":0.9998915},"labels":[],"label_agreement":null},{"id":"W6894416521","doi":"10.5555/3635637.3662926","title":"MaDi:Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","year":2024,"lang":"en","type":"article","venue":"TU/e Research Portal","topic":"Reinforcement Learning in Robotics","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":"Generalization; Reinforcement learning; Focus (optics); Artificial neural network; Contrast (vision); Control (management); Deep learning","score_opus":0.05700158475965024,"score_gpt":0.4050078222895636,"score_spread":0.3480062375299134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894416521","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":[0.011288566,0.00008662503,0.9811563,0.0007544584,0.00037137605,0.00075233995,4.551039e-7,0.00031568107,0.005274216],"genre_scores_gemma":[0.9791394,0.00004650291,0.0069133034,0.0000407251,0.00022505088,0.00023314895,0.000089850444,0.000039723785,0.013272316],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99670154,0.00021880263,0.0004894247,0.0006034991,0.001072029,0.0009147025],"domain_scores_gemma":[0.99875796,0.00042520065,0.000060089664,0.00030104202,0.00021367795,0.00024201917],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002269394,0.00018221367,0.00017949339,0.00086537225,0.00053832436,0.0011194646,0.00056357164,0.00010083234,0.00018410974],"category_scores_gemma":[0.00081302016,0.00018957538,0.000092996284,0.0015546634,0.0000641526,0.0007279777,0.0003851005,0.0009666692,0.00030015263],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012286651,0.000020116593,0.0009168321,0.0000785305,0.000022235363,0.000075376745,0.0016578328,0.96355426,0.0009908989,0.024794731,0.00088731357,0.006989558],"study_design_scores_gemma":[0.00019861464,0.00049897144,0.0005668554,0.000102905455,0.0000041586454,0.000014630624,0.00043727786,0.9536602,0.00037174154,0.00014621756,0.043792058,0.00020639632],"about_ca_topic_score_codex":0.00011052087,"about_ca_topic_score_gemma":0.00004412564,"teacher_disagreement_score":0.974243,"about_ca_system_score_codex":0.00025182494,"about_ca_system_score_gemma":0.00031284764,"threshold_uncertainty_score":0.99991745},"labels":[],"label_agreement":null},{"id":"W6901636194","doi":"10.60692/16y90-1d376","title":"Editorial: Advances in Robots Trajectories Learning via Fast Neural Networks","year":2021,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Reinforcement Learning in Robotics","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 Calgary","funders":"","keywords":"Artificial neural network; Robot; Trajectory; Feature (linguistics); Key (lock)","score_opus":0.01361408417350617,"score_gpt":0.21204383618730055,"score_spread":0.19842975201379437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901636194","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":[0.0030824034,0.000024613479,0.9601664,0.000028504699,0.034703106,0.00015333357,8.689197e-7,0.0003802205,0.0014605642],"genre_scores_gemma":[0.9940249,0.0000013620735,0.002089263,0.00005694056,0.0036460373,0.000026473383,0.000014933002,0.00000980831,0.00013031857],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979634,0.00016675235,0.0007106042,0.0002260175,0.0005336205,0.00039956038],"domain_scores_gemma":[0.99884695,0.000023667846,0.00035485055,0.00041507138,0.00027446877,0.00008497128],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039661865,0.00020833994,0.00026816048,0.0001967722,0.00017896849,0.00063331355,0.00044572004,0.00014000299,0.0000058205487],"category_scores_gemma":[0.00006429922,0.00019701799,0.000069941816,0.0007083185,0.000023000806,0.0036764138,0.00020329024,0.00035713747,0.00010953284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000066358857,6.95043e-7,0.032400936,0.000078780664,0.000006587677,0.000005541007,0.014838066,0.95054436,4.42862e-7,0.00027046073,0.000079559024,0.001767923],"study_design_scores_gemma":[0.0005249233,0.00004115186,0.0052404515,0.00009383376,0.0000043738864,0.000031319494,0.0026369025,0.9884439,0.000050019036,9.4038495e-7,0.0027004827,0.00023169401],"about_ca_topic_score_codex":0.0000053242566,"about_ca_topic_score_gemma":5.6826053e-7,"teacher_disagreement_score":0.9909425,"about_ca_system_score_codex":0.00013980776,"about_ca_system_score_gemma":0.00005029972,"threshold_uncertainty_score":0.803416},"labels":[],"label_agreement":null},{"id":"W6908170018","doi":"10.25573/serc.c.6100506.v5","title":"MarineGEO Bocas del Toro Observatory Data","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Reinforcement Learning in Robotics","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":"Observatory; Nova scotia; Context (archaeology)","score_opus":0.11380987495605834,"score_gpt":0.2849537580977909,"score_spread":0.17114388314173257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6908170018","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":[1.614142e-8,0.0011179247,0.0031632157,0.00008234018,0.0006378243,0.00037951357,0.13530394,0.0011654203,0.8581498],"genre_scores_gemma":[0.0000019415097,0.000012155791,0.0055905487,0.00070006633,0.00032526534,0.00008021785,0.31186453,0.00026704557,0.68115824],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979802,0.00006296916,0.00021414194,0.0007714329,0.0006146286,0.00035663505],"domain_scores_gemma":[0.995463,0.000090075395,0.00031065216,0.004003095,0.000029931018,0.00010324747],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.00007669699,0.000292504,0.00024915402,0.0001290773,0.00009557542,0.00019709095,0.007082136,0.00018390323,0.76029575],"category_scores_gemma":[0.000518182,0.000316177,0.00006103788,0.00027498245,0.000005371871,0.0002793534,0.00975649,0.0004884122,0.008930253],"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":[3.4356168e-7,0.0000071431796,0.000028521843,0.0001409466,0.00003213913,0.000061662184,0.000014752453,0.0016268162,8.2358966e-8,0.00010703345,0.9962536,0.0017269665],"study_design_scores_gemma":[0.00009639719,0.000022821478,0.00011639466,0.00037025826,0.0000059997647,0.000007103493,0.0000034026916,0.04504327,4.3576853e-7,0.0000043062764,0.95398766,0.00034195505],"about_ca_topic_score_codex":0.000056369747,"about_ca_topic_score_gemma":0.000023773882,"teacher_disagreement_score":0.7513655,"about_ca_system_score_codex":0.000102237485,"about_ca_system_score_gemma":0.0002299898,"threshold_uncertainty_score":0.999929},"labels":[],"label_agreement":null},{"id":"W6913045718","doi":"10.5555/3545946.3598862","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Open Repository and Bibliography (University of Luxembourg)","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; University of Alberta; Alberta Machine Intelligence Institute; Compute Canada; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Noise (video); Focus (optics); Robot; Code (set theory); Training (meteorology); Transfer of learning; Deep learning","score_opus":0.018197541683775263,"score_gpt":0.22543555722018838,"score_spread":0.2072380155364131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6913045718","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":[0.45723775,0.000058361005,0.5303624,0.00011746249,0.0001267402,0.0005779728,2.946207e-7,0.00026849346,0.011250499],"genre_scores_gemma":[0.98607385,0.00026270005,0.012931973,0.000014399798,0.0000062631816,0.0000022908807,0.0000050768895,0.0000096298345,0.0006937985],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864995,0.00010857295,0.00020862411,0.00037467844,0.0003224785,0.0003356949],"domain_scores_gemma":[0.999146,0.00009763281,0.0002492249,0.00033613012,0.000056252436,0.000114785005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005048583,0.00016047152,0.0002858777,0.00621262,0.00043263863,0.0003055272,0.0009913952,0.00006565405,0.0000177558],"category_scores_gemma":[0.0000019551428,0.00017458564,0.00007592766,0.011291175,0.00013101648,0.0013300441,0.0007567343,0.00022602876,0.000005615483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006647701,0.00003004756,0.087817915,0.00022174223,0.00015409358,0.00062467676,0.008967955,0.892328,0.0013690534,0.0007933839,0.0001142991,0.007512337],"study_design_scores_gemma":[0.0009284406,0.00034038373,0.0852458,0.00030213056,0.000025562693,0.000041193824,0.0044222656,0.9079936,0.00006557807,0.000054466884,0.00029985432,0.00028069463],"about_ca_topic_score_codex":0.0002393538,"about_ca_topic_score_gemma":0.000025976226,"teacher_disagreement_score":0.52883613,"about_ca_system_score_codex":0.000018588456,"about_ca_system_score_gemma":0.000054576165,"threshold_uncertainty_score":0.71193963},"labels":[],"label_agreement":null},{"id":"W6918060949","doi":"10.58079/sgu","title":"Journée des doctorants de l’Association française d’études canadiennes","year":2015,"lang":"fr","type":"other","venue":"OpenEdition (OpenEdition)","topic":"Reinforcement Learning in Robotics","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":"Context (archaeology); Perspective (graphical); Subject (documents)","score_opus":0.03010377845884565,"score_gpt":0.2518991097946293,"score_spread":0.22179533133578366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6918060949","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018146589,0.002623513,0.20073558,0.022295864,0.013227215,0.0020558988,0.00064568705,0.00064760796,0.75595397],"genre_scores_gemma":[0.06988469,0.00111257,0.021255532,0.014766429,0.004834881,0.00038483756,0.0018250508,0.00048773218,0.8854483],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99275285,0.0008350853,0.0012503088,0.001199923,0.0019423608,0.0020194526],"domain_scores_gemma":[0.99358124,0.0004986645,0.0016731278,0.0011277561,0.0018160618,0.0013031272],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication","insufficient_payload"],"category_scores_codex":[0.0026843743,0.0010200483,0.001013184,0.00064394507,0.0010553364,0.0016130982,0.0020887326,0.001113474,0.02502671],"category_scores_gemma":[0.0019215253,0.0011365669,0.00031304287,0.0011553849,0.00039119137,0.014629437,0.00055950164,0.0011206502,0.008098502],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007668945,0.00048108457,0.0030469745,0.00058742624,0.00080020487,0.00042633587,0.0029903126,0.110180855,0.00019290418,0.38585484,0.48434067,0.011021694],"study_design_scores_gemma":[0.0017208016,0.000449465,0.012461194,0.0014849798,0.00026844052,0.00014216283,0.00023508615,0.017318022,0.00020187879,0.0018956587,0.96240693,0.0014153809],"about_ca_topic_score_codex":0.004840941,"about_ca_topic_score_gemma":0.08379552,"teacher_disagreement_score":0.47806627,"about_ca_system_score_codex":0.0045997617,"about_ca_system_score_gemma":0.0025840534,"threshold_uncertainty_score":0.9994233},"labels":[],"label_agreement":null},{"id":"W6930229253","doi":"10.5281/zenodo.11094777","title":"Signals and Systems OER Labs","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Set (abstract data type); Key (lock); Data collection; Identification (biology)","score_opus":0.03538107557583014,"score_gpt":0.24977624318281305,"score_spread":0.2143951676069829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930229253","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000017661052,0.0011648077,0.21646068,0.00023143546,0.0003914601,0.0003685594,0.000043154658,0.0023638636,0.7789743],"genre_scores_gemma":[0.0025917387,0.00041051485,0.0012527863,0.00012468781,0.00042662185,6.065187e-8,0.00035053404,0.008988024,0.98585504],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981052,0.00024407223,0.00023201013,0.00059505436,0.00048269957,0.00034091718],"domain_scores_gemma":[0.9987928,0.000018095778,0.00014805401,0.00072038005,0.00016256748,0.00015810013],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005572392,0.00021555308,0.000211094,0.00045836758,0.00044825676,0.0030155336,0.0016238609,0.00014704645,0.0061544687],"category_scores_gemma":[0.00017303009,0.00021402618,0.000039918734,0.0004679544,0.00011003063,0.00015998831,0.0026052992,0.00037752715,0.035944104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016861873,0.000009596692,1.2732013e-7,0.00028228914,0.00006366103,0.000026423915,0.00030193257,0.0008051531,0.0000768346,0.017607916,0.9744269,0.006397458],"study_design_scores_gemma":[0.00013696445,0.00009845862,0.0000022603735,0.00024559573,0.000014335719,0.000085259635,0.000037121652,0.015487508,0.000008476343,0.00006708474,0.98359287,0.0002240867],"about_ca_topic_score_codex":0.000017697923,"about_ca_topic_score_gemma":6.9892884e-8,"teacher_disagreement_score":0.21520789,"about_ca_system_score_codex":0.00007763277,"about_ca_system_score_gemma":0.0000039569563,"threshold_uncertainty_score":0.99801946},"labels":[],"label_agreement":null},{"id":"W6949081508","doi":"10.5281/zenodo.12124482","title":"Iso 9110 pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Reinforcement Learning in Robotics","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":"Certification; Quality management system; Process (computing); Quality (philosophy); Quality of analytical results; Control (management); Risk management; Quality assurance","score_opus":0.027056946696764745,"score_gpt":0.2462997047227309,"score_spread":0.21924275802596616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949081508","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.2270583e-7,0.00020384973,0.2924877,0.0003903511,0.00041735734,0.00025009736,0.000023797571,0.002592333,0.7036342],"genre_scores_gemma":[0.00029723143,0.0001616094,0.0033193477,0.00019153721,0.00039402643,2.875355e-8,0.00051014015,0.0080748275,0.98705125],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977613,0.00020479562,0.00026031723,0.00070856675,0.0006091216,0.0004558619],"domain_scores_gemma":[0.99832636,0.0000134412785,0.00016513304,0.001139348,0.00017818093,0.00017753153],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004474027,0.00025907037,0.00021401489,0.00059085677,0.00057617883,0.0023504833,0.003259651,0.0001785484,0.08323519],"category_scores_gemma":[0.00025112947,0.000271296,0.00008785285,0.00075809675,0.00012342457,0.00018584692,0.003406595,0.000578499,0.44385627],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000018735466,0.000018301593,6.643666e-8,0.00013764309,0.000060143433,0.000032860255,0.00026052468,0.0003828871,0.000038471626,0.016828746,0.96661735,0.015621128],"study_design_scores_gemma":[0.0001469151,0.000118092124,0.0000025816703,0.00016029595,0.0000147311375,0.0000665228,0.000021182073,0.0060703,0.000015927322,0.00019649872,0.9929053,0.0002816452],"about_ca_topic_score_codex":0.000013110982,"about_ca_topic_score_gemma":1.4331181e-7,"teacher_disagreement_score":0.3606211,"about_ca_system_score_codex":0.0001377628,"about_ca_system_score_gemma":0.0000061993014,"threshold_uncertainty_score":0.9999739},"labels":[],"label_agreement":null},{"id":"W6979290938","doi":"","title":"A Smooth Sea Never Made a Skilled $\\texttt{SAILOR}$: Robust Imitation via Learning to Search","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Office of Naval Research; Canada Excellence Research Chairs, Government of Canada; National Science Foundation","keywords":"Mistake; Set (abstract data type); Imitation; Outcome (game theory); Code (set theory); Task (project management); Plan (archaeology); Process (computing); Test (biology); Component (thermodynamics); Expert system","score_opus":0.04761884207748829,"score_gpt":0.2007396210769313,"score_spread":0.153120778999443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979290938","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":[0.06975389,0.0000076597435,0.92218715,0.0005658383,0.00024594998,0.00028237532,3.8573492e-7,0.000294072,0.0066627073],"genre_scores_gemma":[0.96048117,0.000015018953,0.008086095,0.0005202331,0.000025928946,0.0000011319139,0.000005499411,0.000014568387,0.030850353],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981884,0.00020938055,0.00020180785,0.00071823166,0.00017188051,0.0005103448],"domain_scores_gemma":[0.9986463,0.00021488772,0.000089372006,0.00065112236,0.000213669,0.0001846478],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003728325,0.0002147989,0.00021235306,0.0005474041,0.00036435053,0.0001812966,0.0011428444,0.000111952664,0.00006622619],"category_scores_gemma":[0.00013488054,0.0002535292,0.000111260284,0.002239492,0.000061165214,0.00090739765,0.0007253897,0.00041968355,0.0006038981],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028552671,0.00002766323,0.0055738296,0.000019958805,0.00003730936,0.00005678019,0.0006135878,0.95771635,0.0002146958,0.033871774,0.0004603737,0.0013791303],"study_design_scores_gemma":[0.000657777,0.00012499066,0.0072332127,0.00005052233,0.000023617262,0.0000016988769,0.0002554233,0.9878001,0.0002265385,0.00049684505,0.0028607778,0.00026845888],"about_ca_topic_score_codex":0.00010273601,"about_ca_topic_score_gemma":0.000012489867,"teacher_disagreement_score":0.914101,"about_ca_system_score_codex":0.00029639484,"about_ca_system_score_gemma":0.00015169592,"threshold_uncertainty_score":0.9999917},"labels":[],"label_agreement":null},{"id":"W6982999955","doi":"","title":"Legion of French Volunteers Against Bolshevism","year":2016,"lang":"en","type":"article","venue":"Digital Kenyon (Kenyon College)","topic":"Reinforcement Learning in Robotics","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":"Infantry; State (computer science); German; Government (linguistics); Head (geology); First world war","score_opus":0.009506763513425517,"score_gpt":0.20875069457741818,"score_spread":0.19924393106399266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6982999955","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":[0.06584695,0.00012278908,0.8248762,0.0011275116,0.0012835949,0.0005307543,0.00006322336,0.00046275478,0.10568624],"genre_scores_gemma":[0.9775534,0.000051063074,0.0024708158,0.00021381085,0.000099149845,0.000012004249,0.00001180384,0.000034800058,0.019553138],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99713653,0.00005469441,0.0007189928,0.0006257506,0.0008450824,0.000618952],"domain_scores_gemma":[0.99779254,0.0002713207,0.0003210222,0.0011137733,0.00027519438,0.00022612857],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00025730729,0.00034959937,0.00042466924,0.00029921363,0.00011240822,0.0002563516,0.0015180256,0.00016178236,0.000040760988],"category_scores_gemma":[0.00027786157,0.00026739418,0.00023501615,0.0007442813,0.00020778856,0.0020092665,0.0005526648,0.00016655479,0.00049766543],"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":[0.00019414678,0.0011424174,0.06447812,0.0005601824,0.0007376616,0.0004653476,0.0029147763,0.063879006,0.025373923,0.34498474,0.17346908,0.3218006],"study_design_scores_gemma":[0.011161731,0.0033022712,0.029353356,0.002550448,0.000085047825,0.00014395977,0.00044179044,0.23144539,0.03321521,0.0063482574,0.6771553,0.0047972566],"about_ca_topic_score_codex":0.000015887308,"about_ca_topic_score_gemma":0.0000034557386,"teacher_disagreement_score":0.91170645,"about_ca_system_score_codex":0.00016221256,"about_ca_system_score_gemma":0.00018351976,"threshold_uncertainty_score":0.9999778},"labels":[],"label_agreement":null},{"id":"W6987579751","doi":"","title":"Temporal credit assignment via traces in reinforcement learning","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Function (biology); Q-learning; Reinforcement; Bellman equation; Temporal difference learning; Variance (accounting); Value (mathematics)","score_opus":0.018578035697775906,"score_gpt":0.24307545516194132,"score_spread":0.2244974194641654,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987579751","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23463126,0.0012316832,0.032721065,0.000738133,0.020133367,0.009253732,0.00010813516,0.006082939,0.6950997],"genre_scores_gemma":[0.97545713,0.00017070162,0.006785064,0.00033995576,0.000101149235,0.00020584758,0.0008581937,0.00019025494,0.015891712],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99204576,0.0005918996,0.0019140624,0.00186023,0.0022896077,0.0012984297],"domain_scores_gemma":[0.9962502,0.00030113026,0.00143761,0.0011792068,0.00027976208,0.0005520587],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0013923466,0.0011698684,0.001133865,0.00075824454,0.000982419,0.00046544924,0.0028235123,0.00087592826,0.00024226894],"category_scores_gemma":[0.0007857525,0.0013067061,0.0003665211,0.0013425505,0.000055157565,0.0019292759,0.00063251104,0.0038736144,0.0007609089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022803902,0.00021005538,0.00031166954,0.00082250725,0.00037572705,0.00062839966,0.0002295241,0.7812454,0.014560451,0.08658453,0.00003794598,0.114765726],"study_design_scores_gemma":[0.0058261584,0.003977322,0.0026450837,0.0028558248,0.00036834858,0.000078361285,0.0012069729,0.45910367,0.07276021,0.009492977,0.43391255,0.0077725174],"about_ca_topic_score_codex":0.00024748524,"about_ca_topic_score_gemma":0.00018431069,"teacher_disagreement_score":0.7408259,"about_ca_system_score_codex":0.0014538696,"about_ca_system_score_gemma":0.00016322389,"threshold_uncertainty_score":0.99893826},"labels":[],"label_agreement":null},{"id":"W6991803794","doi":"","title":"Inductive biases and generalisation for deep reinforcement learning","year":2021,"lang":"en","type":"dissertation","venue":"Oxford University Research Archive (ORA) (University of Oxford)","topic":"Reinforcement Learning in Robotics","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":"Kellogg's (Canada)","funders":"","keywords":"Reinforcement learning; Focus (optics); Scope (computer science); Transfer of learning; Artificial neural network; Deep learning; Moment (physics); Inductive bias","score_opus":0.04855249049508199,"score_gpt":0.28390067756952664,"score_spread":0.23534818707444466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991803794","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":[0.055867206,0.0001181639,0.91438806,0.00030634375,0.00026757005,0.001193986,0.000028418577,0.00012446167,0.027705789],"genre_scores_gemma":[0.5721554,0.014333644,0.23443691,0.00006681485,0.00029353183,0.0000057973416,0.00936716,0.000168576,0.16917215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962018,0.0005820633,0.000271396,0.0010038874,0.0011214681,0.0008193701],"domain_scores_gemma":[0.9962498,0.0009527518,0.00053089135,0.00068304304,0.0012557957,0.00032769627],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00083295186,0.0003855276,0.00059777166,0.0015239364,0.001684018,0.00016637213,0.0018260891,0.00033430304,0.000084030056],"category_scores_gemma":[0.0003791498,0.0005359598,0.0002973947,0.0010884488,0.00042192588,0.001198034,0.0012316345,0.0012131337,0.0000036382748],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003573203,0.0004312619,0.005260586,0.0030479797,0.0023916226,0.0007085487,0.09185699,0.5746467,0.0060044657,0.2264147,0.0057098004,0.07995414],"study_design_scores_gemma":[0.003552161,0.0021505416,0.0058150855,0.00084402756,0.00024123497,0.000012425087,0.10946187,0.6918239,0.00058133394,0.001805508,0.18243864,0.0012732529],"about_ca_topic_score_codex":0.0006397894,"about_ca_topic_score_gemma":0.0010380046,"teacher_disagreement_score":0.67995113,"about_ca_system_score_codex":0.0004153235,"about_ca_system_score_gemma":0.0007546219,"threshold_uncertainty_score":0.9997092},"labels":[],"label_agreement":null},{"id":"W7000794688","doi":"","title":"Hard attention finding using reinforcement learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Matching (statistics)","score_opus":0.034519857057459157,"score_gpt":0.27209616070439535,"score_spread":0.2375763036469362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000794688","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":[0.6035037,0.00040432613,0.028266765,0.000047663158,0.014931966,0.003026956,0.000057249425,0.0030118339,0.34674954],"genre_scores_gemma":[0.8417531,0.00019005637,0.02256227,0.00032236864,0.00010381923,0.00010887688,0.0010094877,0.00020915092,0.13374083],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993311,0.00047916127,0.0015662705,0.0016891415,0.0016956074,0.0012588243],"domain_scores_gemma":[0.99586815,0.00028620794,0.0014949747,0.0014411492,0.00062274566,0.00028679395],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014864291,0.0010526982,0.0009164923,0.001216549,0.0026454774,0.0006824323,0.0023268755,0.000930975,0.0001145757],"category_scores_gemma":[0.0010914546,0.0012444155,0.00058921153,0.0014821822,0.000036535002,0.002105516,0.000767574,0.0029281138,0.0003597341],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006540462,0.000060289127,0.000118708434,0.00085021474,0.0004297352,0.000079518264,0.000030346055,0.72220874,0.039004378,0.16809805,0.000009460721,0.06904513],"study_design_scores_gemma":[0.0036371262,0.00085669925,0.0025658447,0.0080944775,0.0010380475,0.000083842984,0.00067324383,0.7920033,0.058591284,0.007394649,0.11864997,0.0064115403],"about_ca_topic_score_codex":0.00017069372,"about_ca_topic_score_gemma":0.000037500835,"teacher_disagreement_score":0.23824945,"about_ca_system_score_codex":0.0018028478,"about_ca_system_score_gemma":0.00019999593,"threshold_uncertainty_score":0.9993722},"labels":[],"label_agreement":null},{"id":"W7006393979","doi":"","title":"Towards building model-based reinforcement learning agents that effectively adapt and generalize","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Control (management); Key (lock); Action (physics); Feature (linguistics); Stability (learning theory)","score_opus":0.029598980048585154,"score_gpt":0.268028614514628,"score_spread":0.23842963446604284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006393979","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":[0.45342126,0.001235023,0.23812857,0.0002152024,0.007991128,0.0061736037,0.00015646803,0.0038301134,0.2888486],"genre_scores_gemma":[0.951793,0.00025460153,0.022978121,0.0005345563,0.000034069377,0.00015341442,0.00039017605,0.00015715424,0.02370489],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99360406,0.0005729567,0.001039509,0.0018804057,0.0017174269,0.0011856625],"domain_scores_gemma":[0.99646723,0.00035228507,0.0010217103,0.0012442525,0.00047704333,0.0004374938],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0014508609,0.0012231991,0.0010793471,0.000941956,0.0019089064,0.0006146842,0.002017444,0.00087628665,0.000041768762],"category_scores_gemma":[0.00086194405,0.0013466012,0.00042971878,0.00086569827,0.00005860224,0.0013759366,0.00064117357,0.0023868072,0.00004327658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000766417,0.00003451355,0.00003098045,0.0005573319,0.00021457879,0.000037558133,0.00002330091,0.8642599,0.003306813,0.08203117,0.000011301092,0.049415894],"study_design_scores_gemma":[0.0016279047,0.00034727622,0.00040937282,0.0013312263,0.00024071692,0.0000079475785,0.00004528716,0.9281761,0.04849283,0.0033610808,0.014333918,0.0016263078],"about_ca_topic_score_codex":0.00025426465,"about_ca_topic_score_gemma":0.0000437871,"teacher_disagreement_score":0.49837175,"about_ca_system_score_codex":0.0011849026,"about_ca_system_score_gemma":0.00027568842,"threshold_uncertainty_score":0.9999147},"labels":[],"label_agreement":null},{"id":"W7008828355","doi":"","title":"Continuous coordination as a realistic scenario for lifelong learning","year":2021,"lang":"en","type":"other","venue":"Open MIND","topic":"Reinforcement Learning in Robotics","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":"Université de Montréal","keywords":"Forge; Context (archaeology); ESPACE","score_opus":0.040751536259580244,"score_gpt":0.32624474546161075,"score_spread":0.28549320920203053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008828355","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000004272868,0.000104723105,0.5056714,0.00021666821,0.00041082923,0.0006275464,0.000002318057,0.0000147838655,0.49294746],"genre_scores_gemma":[0.00036129885,0.000014503429,0.1481629,0.000071790644,0.00019844639,0.000043164924,0.00020502286,0.00013301677,0.8508099],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998396,0.000100858386,0.0002796133,0.00061941764,0.00028907383,0.00031505086],"domain_scores_gemma":[0.99859434,0.00016675844,0.00045511778,0.0005774417,0.0001194959,0.00008682276],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000431833,0.00024032519,0.00039562988,0.00015807299,0.0001320407,0.0011570627,0.0015096915,0.00023648821,0.002919803],"category_scores_gemma":[0.000601487,0.00025602544,0.00008028145,0.00023058617,0.000033879845,0.00014100526,0.0006888964,0.00028888855,0.00041041718],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024172346,0.00008976654,0.00022750291,0.00022062576,0.0003679867,0.00020051244,0.0015064168,0.05492034,0.00010095044,0.0077572395,0.5515058,0.3830787],"study_design_scores_gemma":[0.00044839235,0.00013174528,0.000012228507,0.00044672706,0.00002742488,0.000014105709,0.000034062334,0.07597665,0.000038624017,0.000026450212,0.922541,0.00030259026],"about_ca_topic_score_codex":0.00025253417,"about_ca_topic_score_gemma":0.00006760378,"teacher_disagreement_score":0.3827761,"about_ca_system_score_codex":0.0000780944,"about_ca_system_score_gemma":0.0003195423,"threshold_uncertainty_score":0.9999892},"labels":[],"label_agreement":null},{"id":"W7015310510","doi":"","title":"A Study of Augmentation-Sensitivity in Reinforcement Learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Stability (learning theory)","score_opus":0.02194920132953579,"score_gpt":0.26966483510707484,"score_spread":0.24771563377753905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015310510","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":[0.9224552,0.0000406618,0.0005174701,0.000008805034,0.001483915,0.0019123326,0.000012614132,0.000310786,0.073258236],"genre_scores_gemma":[0.98431283,0.000056251305,0.0013559235,0.0000635806,0.000012702472,0.00014081263,0.00024544404,0.000060474973,0.013751964],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940846,0.00081456,0.0016698526,0.0012284209,0.0014980101,0.0007045666],"domain_scores_gemma":[0.99632674,0.0005289588,0.001281719,0.0011985861,0.0005077161,0.00015629237],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0018902658,0.0007169135,0.0009746144,0.0012405672,0.000637272,0.00015194643,0.0012405352,0.00045398044,0.000039186205],"category_scores_gemma":[0.00095163926,0.0008367227,0.00020278172,0.0017051038,0.00002664456,0.0010948863,0.0005487204,0.0019972161,0.00006048896],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013666823,0.0005144273,0.00081507844,0.0004887236,0.00029674036,0.00018647588,0.00032342438,0.8944274,0.004011381,0.05731658,0.000002226423,0.041480828],"study_design_scores_gemma":[0.045302983,0.018742075,0.124128744,0.016162092,0.0023566762,0.000113008355,0.038979225,0.48084095,0.21791358,0.016327677,0.021590212,0.017542778],"about_ca_topic_score_codex":0.00095666235,"about_ca_topic_score_gemma":0.0024956705,"teacher_disagreement_score":0.4135865,"about_ca_system_score_codex":0.00088895933,"about_ca_system_score_gemma":0.00015303354,"threshold_uncertainty_score":0.99940836},"labels":[],"label_agreement":null},{"id":"W7015655229","doi":"","title":"Towards alignment of Reinforcement Learning agents; for consideration of safety, robustness and fairness.","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Robustness (evolution); Reinforcement learning; Control theory (sociology); Control (management)","score_opus":0.02355615140994175,"score_gpt":0.2650591302153393,"score_spread":0.24150297880539753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015655229","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":[0.57345617,0.00275838,0.20849022,0.00040730188,0.015800001,0.014329212,0.0006869858,0.0019216234,0.18215008],"genre_scores_gemma":[0.9772069,0.00045125306,0.0115899695,0.000054593907,0.000029081966,0.00015143202,0.00067692454,0.00011717467,0.009722662],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99539083,0.0002133494,0.0016796199,0.000985781,0.0011888349,0.000541579],"domain_scores_gemma":[0.99668926,0.0003384304,0.0013292825,0.0007312399,0.00073086575,0.00018091238],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014141756,0.0006448035,0.00093662203,0.00054075423,0.0005372026,0.00017244667,0.00082868285,0.00051481044,0.000053514952],"category_scores_gemma":[0.00070743036,0.0006809856,0.00032720962,0.00049063354,0.00008136617,0.00078757596,0.0004351816,0.0007894693,0.000011716152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011339646,0.000042757503,0.000008364585,0.002418007,0.00034409954,0.000010063758,0.000108145345,0.57611537,0.004505429,0.37809336,0.000011059113,0.038229916],"study_design_scores_gemma":[0.004378482,0.0026857462,0.0005490477,0.0053474777,0.0011905428,0.00004973425,0.0016583465,0.60620224,0.3014296,0.022669064,0.05074287,0.0030968552],"about_ca_topic_score_codex":0.00009948739,"about_ca_topic_score_gemma":0.000048941485,"teacher_disagreement_score":0.40375072,"about_ca_system_score_codex":0.00043141088,"about_ca_system_score_gemma":0.00015885221,"threshold_uncertainty_score":0.9995641},"labels":[],"label_agreement":null},{"id":"W7015986514","doi":"","title":"Towards better generalization capabilities of reinforcement learning agents via self-supervision","year":2023,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Generalization; Reinforcement learning; Control (management); Feature (linguistics); Stability (learning theory)","score_opus":0.019249336379743232,"score_gpt":0.25199970022537843,"score_spread":0.2327503638456352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015986514","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":[0.91226214,0.00024614402,0.008958535,0.00008071905,0.008928328,0.0028916772,0.0000842281,0.0036109409,0.0629373],"genre_scores_gemma":[0.9571602,0.00047925784,0.012477342,0.00027392124,0.00009525456,0.00016057007,0.0018696684,0.00029800533,0.027185805],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9931929,0.000549521,0.001775768,0.0013296313,0.0022081374,0.0009440547],"domain_scores_gemma":[0.99590683,0.00020402076,0.0012857579,0.0014467028,0.0008794699,0.00027724617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013800601,0.0009106017,0.0009255773,0.00088260905,0.0010155828,0.00023776387,0.002058853,0.0008119142,0.00021882879],"category_scores_gemma":[0.0006752349,0.0009868466,0.00047360524,0.0012834894,0.000052451076,0.0014940342,0.0006939099,0.001439742,0.0004216849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006351413,0.00012754019,0.00017914928,0.0021998216,0.00070799,0.000041170206,0.0005390967,0.83254254,0.011371461,0.055909753,0.000040340627,0.09627764],"study_design_scores_gemma":[0.0028519414,0.0017278726,0.004568593,0.0022666662,0.00079355814,0.00002928037,0.00094272854,0.76945543,0.12635405,0.012593812,0.073850915,0.0045651295],"about_ca_topic_score_codex":0.0005429303,"about_ca_topic_score_gemma":0.0000668116,"teacher_disagreement_score":0.1149826,"about_ca_system_score_codex":0.00070579175,"about_ca_system_score_gemma":0.00011864261,"threshold_uncertainty_score":0.9992582},"labels":[],"label_agreement":null},{"id":"W7021226743","doi":"","title":"North American Energy Partners Inc. Announces Results for the Fourth Quarter Ended December 31, 2017","year":2018,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Energy (signal processing); Fourth World","score_opus":0.027513206543679274,"score_gpt":0.28858685765101116,"score_spread":0.2610736511073319,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7021226743","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.24439e-7,0.000025634019,0.5137684,0.00048381565,0.0006183531,0.00021147981,0.000012044522,0.00023902918,0.48464042],"genre_scores_gemma":[0.00042815114,0.00017873052,0.054395292,0.0011746892,0.0008448732,0.000101159225,0.00011033195,0.000109200286,0.9426576],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975761,0.00008056212,0.00042252825,0.0007396166,0.0005645999,0.0006165839],"domain_scores_gemma":[0.9968251,0.0004392378,0.00074313104,0.0017217785,0.00014388449,0.00012686655],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028563294,0.00043257998,0.00040083588,0.00018949025,0.00022050028,0.0003590777,0.002310064,0.00013139009,0.000050572864],"category_scores_gemma":[0.00009104952,0.00027242463,0.00014339181,0.00036962106,0.0004055247,0.00015153324,0.00032012624,0.00015424975,0.00028823048],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019985597,0.000011332593,0.000063401516,0.000008499033,0.00014116104,0.000002642328,0.00013864289,0.0063637304,1.7927232e-7,0.0028037976,0.9888871,0.0015595636],"study_design_scores_gemma":[0.00034794924,0.00028122967,0.00007815427,0.000020546691,0.000025078165,0.0000031455736,0.000034900342,0.15212122,0.0000034274792,0.000030621155,0.84669757,0.00035618083],"about_ca_topic_score_codex":0.00076870574,"about_ca_topic_score_gemma":0.008427753,"teacher_disagreement_score":0.4593731,"about_ca_system_score_codex":0.00004790047,"about_ca_system_score_gemma":0.00020262029,"threshold_uncertainty_score":0.9999728},"labels":[],"label_agreement":null},{"id":"W7023516600","doi":"","title":"Ontario's vaccine rollout plan and charges in Beirut blast: In The News for Dec. 11","year":2020,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Government (linguistics); Action plan; Work (physics)","score_opus":0.02289565758732529,"score_gpt":0.2388574012022127,"score_spread":0.2159617436148874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023516600","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015025937,0.0001877745,0.60718954,0.004842077,0.00038562898,0.0016244344,0.000004070921,0.00016724902,0.38544896],"genre_scores_gemma":[0.004503605,0.00013497894,0.051692072,0.0047298437,0.00036694953,0.00013982551,0.00004931246,0.00019893018,0.9381845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99877965,0.000044810506,0.0002666199,0.0004103748,0.00021329278,0.00028526748],"domain_scores_gemma":[0.9992397,0.00014635544,0.00013135033,0.0004242935,0.00000757077,0.000050756393],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019748374,0.00023780891,0.00032310782,0.00021361836,0.000026186926,0.00016041056,0.0009992024,0.00015435317,0.0003275516],"category_scores_gemma":[0.000041096075,0.00016476905,0.000043646647,0.0001992379,0.00001176312,0.00008242873,0.00020598005,0.00022566158,0.000021027086],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028034648,0.00005468037,0.07865951,0.0001655927,0.000056313558,0.00005095509,0.009571046,0.008933987,0.000006090964,0.020737547,0.87709856,0.004637676],"study_design_scores_gemma":[0.00090527424,0.0001327905,0.0023496607,0.0000936089,0.0000073667393,0.0000040452733,0.00007552345,0.045706905,0.0000036394815,0.00009842273,0.9503767,0.0002460709],"about_ca_topic_score_codex":0.015179709,"about_ca_topic_score_gemma":0.42621782,"teacher_disagreement_score":0.55549747,"about_ca_system_score_codex":0.00004793103,"about_ca_system_score_gemma":0.00009198473,"threshold_uncertainty_score":0.9913783},"labels":[],"label_agreement":null},{"id":"W7023517986","doi":"","title":"O’Reilly Automotive, Inc. Reports Fourth Quarter and Full-Year 2017 Results and Announces Additional $1.0 Billion Share Repurchase Authorization","year":2018,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Authorization; Payment; Government (linguistics)","score_opus":0.01473504582704913,"score_gpt":0.24412804123024037,"score_spread":0.22939299540319125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023517986","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000013920248,0.00009955414,0.4916642,0.00076510326,0.001167024,0.0005840435,0.00058926304,0.00085253065,0.50426435],"genre_scores_gemma":[0.00082835933,0.00024493516,0.12965417,0.00026374697,0.0010405077,0.00004358547,0.004863792,0.0001792814,0.8628816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997331,0.000100281395,0.000535835,0.0010498781,0.0006691274,0.00031383353],"domain_scores_gemma":[0.997759,0.000117090945,0.0008388253,0.0008379739,0.0002789689,0.00016816103],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00047424642,0.00036367238,0.00031615078,0.0004372741,0.00020445122,0.00045405838,0.00034243223,0.00036253882,0.0024114174],"category_scores_gemma":[0.00043126414,0.00030832575,0.000040274324,0.00025245966,0.00020278744,0.0004642082,0.00037262723,0.00020623069,0.00015369341],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000126166,0.000014152257,0.000055197703,0.00004201233,0.000039038205,0.000071767136,0.00018582134,0.00028211225,0.0000035582555,0.0017810611,0.9970052,0.00050741405],"study_design_scores_gemma":[0.00050823775,0.0006013667,0.0007272965,0.00049851404,0.000021120792,0.00025218233,0.000045325618,0.072917804,0.000004190487,0.00032813416,0.9235066,0.00058922765],"about_ca_topic_score_codex":0.000041280444,"about_ca_topic_score_gemma":0.000041390074,"teacher_disagreement_score":0.36201003,"about_ca_system_score_codex":0.000039971634,"about_ca_system_score_gemma":0.00013432984,"threshold_uncertainty_score":0.9999369},"labels":[],"label_agreement":null},{"id":"W7024241891","doi":"","title":"Responsible, Sustainable Production and Consumption through the lens of Inclusion and Diversity.","year":2025,"lang":"en","type":"other","venue":"OCAD University Open Research Repository (OCAD University)","topic":"Reinforcement Learning in Robotics","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":"Sustainability; Inclusion (mineral); Consumption (sociology); Production (economics); Sustainable consumption; Immigration; Sustainable development; Product (mathematics); Social exclusion","score_opus":0.05194559815452137,"score_gpt":0.2956143282971589,"score_spread":0.2436687301426375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024241891","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008969006,0.0003129159,0.022129761,0.0012585579,0.00019206725,0.0013313239,0.000006804983,0.00010996185,0.9737617],"genre_scores_gemma":[0.014606623,0.002430112,0.0017814607,0.00001940266,0.000031989024,2.679346e-7,0.0000056738013,0.000029877847,0.9810946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964102,0.001302269,0.0001604567,0.0008388923,0.0008050936,0.0004831219],"domain_scores_gemma":[0.99770975,0.00029195938,0.00031138794,0.0010285337,0.000545567,0.00011278443],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.0011456744,0.00025743322,0.0003647796,0.0010804378,0.00409065,0.00024176476,0.0027882224,0.00035190186,0.0000028307313],"category_scores_gemma":[0.00016808302,0.00026296274,0.00006581422,0.0013164561,0.0011919698,0.0014561088,0.020568762,0.0007806234,0.0000052339965],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020569703,0.000039746537,0.00096889155,0.00029020564,0.00013676574,0.00022140626,0.0014748186,0.00041468,0.00011123076,0.98276466,0.013218328,0.00015356492],"study_design_scores_gemma":[0.0009857275,0.00031143322,0.0011357482,0.0006943286,0.00013162887,0.000019872163,0.00314211,0.0010778251,0.0003173285,0.00039395128,0.99138296,0.00040706017],"about_ca_topic_score_codex":0.007832423,"about_ca_topic_score_gemma":0.000313982,"teacher_disagreement_score":0.98237073,"about_ca_system_score_codex":0.0005100877,"about_ca_system_score_gemma":0.00084014214,"threshold_uncertainty_score":0.99998224},"labels":[],"label_agreement":null},{"id":"W7024873855","doi":"","title":"Summary of the Functional Foods and Nutraceuticals Survey","year":2017,"lang":"en","type":"article","venue":"AgEcon Search (University of Minnesota, USA)","topic":"Reinforcement Learning in Robotics","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":"Nutraceutical; Baseline (sea); Food sector; Agriculture; Intellectual property; Functional food","score_opus":0.07801678161677084,"score_gpt":0.27041173991398765,"score_spread":0.1923949582972168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7024873855","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":[0.8080954,0.000044689565,0.18380533,0.0019732113,0.00021723312,0.00017470929,0.000013413831,0.000014441657,0.0056615984],"genre_scores_gemma":[0.9914659,0.00007644543,0.0035378954,0.000025866086,0.0000111264635,7.1647186e-8,0.000002384,0.0000035281087,0.004876773],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989073,0.00018028318,0.000106295556,0.0002182111,0.00039024046,0.00019767116],"domain_scores_gemma":[0.99839765,0.0003342898,0.00017728585,0.0008275948,0.00018126277,0.0000819073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009357962,0.00007946714,0.00016283497,0.000057335077,0.00052602997,0.00005907305,0.001396661,0.000067180415,0.00008731741],"category_scores_gemma":[0.00016683935,0.00007652998,0.00006695827,0.00011451318,0.0006098706,0.000581025,0.0011596553,0.00018050891,0.000017175475],"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":[0.0000939147,0.00011500653,0.92991436,0.00017416767,0.00018372358,0.000025821779,0.0018432459,0.005830693,0.0019017905,0.033406664,0.006137717,0.020372879],"study_design_scores_gemma":[0.0003868951,0.00007991753,0.96508116,0.000028192291,0.0000078599915,0.0000033578824,0.00011904786,0.032300185,0.0003420799,0.00009004261,0.001482274,0.00007898015],"about_ca_topic_score_codex":0.0006560983,"about_ca_topic_score_gemma":0.00031538584,"teacher_disagreement_score":0.18337055,"about_ca_system_score_codex":0.000020551204,"about_ca_system_score_gemma":0.00009538188,"threshold_uncertainty_score":0.40458506},"labels":[],"label_agreement":null},{"id":"W7030246915","doi":"","title":"Network architecture enforced symmetry","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Gait; Variety (cybernetics); Symmetry (geometry); Work (physics); Task (project management); Space (punctuation); Motion (physics); Action (physics)","score_opus":0.012529671805740791,"score_gpt":0.23157169526475793,"score_spread":0.21904202345901713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030246915","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10144763,0.00091753324,0.00553313,0.0000985884,0.022349786,0.0036226776,0.00023407434,0.0032192743,0.8625773],"genre_scores_gemma":[0.8503819,0.0001755775,0.031119933,0.0019229855,0.00036012533,0.00015218667,0.0015416675,0.0004936853,0.11385195],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99276704,0.0004735135,0.001307989,0.0019300669,0.0018336938,0.0016877232],"domain_scores_gemma":[0.9945128,0.0004742817,0.0012423963,0.002851026,0.00044556585,0.00047395876],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.0011805878,0.0012945478,0.0011803042,0.0006390087,0.0012611584,0.0005055868,0.0042895437,0.0014180585,0.00017926634],"category_scores_gemma":[0.00069256005,0.0013506741,0.0006188547,0.0016103769,0.000055062876,0.0011701188,0.00075536594,0.0038557828,0.0020931058],"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":[0.00007889025,0.000053928547,0.000027291557,0.0005662564,0.0003447938,0.00009127329,0.00002742532,0.266909,0.0023486929,0.60039645,0.00008036282,0.12907562],"study_design_scores_gemma":[0.006275674,0.0023893276,0.002911456,0.005599767,0.0010254903,0.00033745807,0.0004216601,0.06099081,0.032763578,0.15903784,0.71409833,0.014148595],"about_ca_topic_score_codex":0.00007874093,"about_ca_topic_score_gemma":0.000059406848,"teacher_disagreement_score":0.74893427,"about_ca_system_score_codex":0.0006787803,"about_ca_system_score_gemma":0.00016343797,"threshold_uncertainty_score":0.9999806},"labels":[],"label_agreement":null},{"id":"W7033768098","doi":"","title":"Sand Filling Activities-Salinity Monitoring Matang Federal Administrative Centre (FAC) Access Road, Kuching Division, Sarawak (2rd Quarter 2004)","year":2004,"lang":"en","type":"report","venue":"Unimas Institutional Repository (Universiti Malaysia Sarawak)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Work (physics)","score_opus":0.04250607032389964,"score_gpt":0.29324271924765444,"score_spread":0.2507366489237548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033768098","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":[0.10294713,0.0008910669,0.6950313,0.0004636462,0.012361742,0.0013169586,0.00015091995,0.0010999196,0.18573734],"genre_scores_gemma":[0.98016053,0.00018022122,0.008239694,0.00006675645,0.0015083138,0.000014380279,0.00035473745,0.00008803549,0.009387321],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.991823,0.00036453377,0.0012291531,0.0019198363,0.0033688066,0.0012946523],"domain_scores_gemma":[0.9948209,0.0003490398,0.0016114551,0.0015318239,0.0010995567,0.00058721646],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00073168625,0.0012553259,0.0011775576,0.001015537,0.003308915,0.0023916052,0.0031790847,0.000914217,0.00009682188],"category_scores_gemma":[0.00020118471,0.0014389653,0.0006100294,0.0009489184,0.0006014701,0.005641499,0.001530405,0.002234554,0.00006508546],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00008590009,0.00020640131,0.015169058,0.00045210472,0.00070548174,0.0041684806,0.0016815665,0.9694335,0.00039923398,0.0045247073,0.0021430836,0.0010305089],"study_design_scores_gemma":[0.012545183,0.0023237288,0.07672017,0.027191672,0.0017994737,0.013113585,0.011577934,0.7113732,0.01367243,0.0019136051,0.109182514,0.018586509],"about_ca_topic_score_codex":0.00091016723,"about_ca_topic_score_gemma":0.000008275254,"teacher_disagreement_score":0.8772134,"about_ca_system_score_codex":0.005844949,"about_ca_system_score_gemma":0.008499012,"threshold_uncertainty_score":0.99880594},"labels":[],"label_agreement":null},{"id":"W7033872038","doi":"","title":"Santander Consumer USA Holdings Inc. Reports First Quarter 2017 Results","year":2017,"lang":"en","type":"other","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Consumption (sociology); Consumer behaviour; Work (physics)","score_opus":0.02679481426724293,"score_gpt":0.2738101485653214,"score_spread":0.24701533429807845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7033872038","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":[9.965191e-7,0.00020263964,0.2131605,0.00035635335,0.0020065045,0.00029714874,0.0000050713397,0.00042562716,0.78354514],"genre_scores_gemma":[0.0015082052,0.00040185434,0.017176976,0.00031716633,0.0002848643,0.000013347487,0.00003575577,0.00016528537,0.9800965],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9971617,0.000038637256,0.0005458446,0.0010135119,0.00069787994,0.00054245524],"domain_scores_gemma":[0.9943753,0.00009275101,0.0014394553,0.003829687,0.000088113346,0.00017467835],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004902795,0.00047212074,0.0005012559,0.00029329117,0.0003028113,0.00078110676,0.0018024901,0.00048507657,0.0012256814],"category_scores_gemma":[0.00021630798,0.00039937382,0.00012434178,0.000081943894,0.00018582422,0.00035672507,0.00065380643,0.00041929874,0.0016964226],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000032987011,0.000011051472,0.00040714702,0.00003490193,0.000073197785,0.00037862707,0.000095583615,0.00036856235,0.0000017622308,0.0006712662,0.99763453,0.0003200787],"study_design_scores_gemma":[0.00039202298,0.00005237285,0.00024472678,0.00031714496,0.000021472057,0.0001564437,0.0000033100039,0.0049192435,0.0000132812675,0.000033670167,0.9932847,0.0005616151],"about_ca_topic_score_codex":0.00090390653,"about_ca_topic_score_gemma":0.00041229968,"teacher_disagreement_score":0.1965514,"about_ca_system_score_codex":0.000062290506,"about_ca_system_score_gemma":0.00013580377,"threshold_uncertainty_score":0.9998458},"labels":[],"label_agreement":null},{"id":"W7037446629","doi":"","title":"Être parent d’un adulte atteint de schizophrénie en Mauricie–Centre-du-Québec : stratégies de coping et représentations sociales de la maladie","year":2023,"lang":"fr","type":"other","venue":"Le dépôt institutionnel (Université du Québec à Trois-Rivières)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Coping (psychology); Disease; Qualitative research; Distress","score_opus":0.01668348037815944,"score_gpt":0.2387424358042205,"score_spread":0.22205895542606105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037446629","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":[0.05364265,0.0005742498,0.8887546,0.037775043,0.0010349434,0.00073019444,0.00007828437,0.0011330773,0.016276922],"genre_scores_gemma":[0.8819717,0.0014771175,0.026003635,0.0011283731,0.0013083656,0.00004351759,0.000102616614,0.0004575241,0.08750714],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99440265,0.001391906,0.000768919,0.001239323,0.0007558618,0.0014413433],"domain_scores_gemma":[0.995709,0.0015254967,0.00083330617,0.0010863519,0.00031562475,0.0005302145],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009917363,0.000940176,0.00080646755,0.00068918173,0.0017417136,0.0007331835,0.0021083343,0.00072498876,0.0015355885],"category_scores_gemma":[0.0009917627,0.001121377,0.00059893663,0.000990812,0.0016038582,0.0011460743,0.0010831493,0.0013397873,0.0011852604],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000053460488,0.00022697904,0.049415536,0.00022374262,0.0005482318,0.0010231466,0.06460696,0.6786452,0.00009002716,0.19766904,0.0056375246,0.001860137],"study_design_scores_gemma":[0.004490504,0.0002615739,0.18349375,0.0024597442,0.00082397513,0.0006264697,0.023614084,0.7107589,0.00014014145,0.00101104,0.06982171,0.0024980942],"about_ca_topic_score_codex":0.58752775,"about_ca_topic_score_gemma":0.6815587,"teacher_disagreement_score":0.862751,"about_ca_system_score_codex":0.0056840437,"about_ca_system_score_gemma":0.012203193,"threshold_uncertainty_score":0.9995924},"labels":[],"label_agreement":null},{"id":"W7037450537","doi":"","title":"The effects of cyclic mechanical stretch on nuclear protein import in vascular smooth muscle cells","year":2005,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Vascular smooth muscle; Myocyte; Smooth muscle; Nuclear protein; Cell nucleus; Blood vessel","score_opus":0.005845724919362133,"score_gpt":0.18896707761745965,"score_spread":0.1831213526980975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037450537","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":[0.99323004,0.00005452093,0.0032968225,0.00023326247,0.00040129718,0.00086172204,0.0000011834387,0.000066939356,0.0018541977],"genre_scores_gemma":[0.9948866,0.00023359177,0.003955494,0.000017781527,0.00003349155,0.000001161195,0.000014750508,0.00003339568,0.0008237292],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.99826634,0.00015369189,0.00019496893,0.0003928508,0.0006945039,0.00029765753],"domain_scores_gemma":[0.9983921,0.00016702812,0.00049023,0.00079674926,0.00008734216,0.000066540095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003277634,0.00022674879,0.0003559779,0.0002216651,0.00017986893,0.00004064179,0.0015653854,0.0002681483,0.000004763216],"category_scores_gemma":[0.00005985605,0.00024101582,0.00020872963,0.0003432615,0.000060583392,0.000198255,0.0002152677,0.00049516157,0.00003806052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015397903,0.0033481189,0.0030047083,0.011046502,0.0020357776,0.0014103174,0.025679024,0.2838224,0.26960015,0.20434162,0.009442362,0.18472925],"study_design_scores_gemma":[0.0067634885,0.004466227,0.51234686,0.0054053687,0.00044169644,0.0000013737523,0.03443912,0.37005323,0.023375582,0.000740675,0.0392206,0.002745806],"about_ca_topic_score_codex":0.0005234283,"about_ca_topic_score_gemma":0.019321458,"teacher_disagreement_score":0.50934213,"about_ca_system_score_codex":0.00016018967,"about_ca_system_score_gemma":0.00009325469,"threshold_uncertainty_score":0.99857336},"labels":[],"label_agreement":null},{"id":"W7042992782","doi":"","title":"Reproducibility and reusability in deep reinforcement learning","year":2018,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Reproducibility; Reinforcement learning; Reusability; Reinforcement; Reliability (semiconductor)","score_opus":0.018471971676706552,"score_gpt":0.2572029638222421,"score_spread":0.23873099214553556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042992782","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":[0.8851706,0.00027819775,0.0008874748,0.000054605563,0.0025451707,0.001958278,0.000010147156,0.00085180765,0.10824375],"genre_scores_gemma":[0.9775847,0.00020335893,0.0114465,0.00014974774,0.00006298332,0.00012199936,0.0002472016,0.00011314343,0.010070321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906481,0.0008425698,0.0017956693,0.0043146205,0.0012930112,0.0011060645],"domain_scores_gemma":[0.99274725,0.00040354003,0.0010341615,0.004861493,0.0005863112,0.00036725763],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007616085,0.0009055281,0.0009799987,0.000555579,0.001095237,0.00032227204,0.0019768719,0.0008361319,0.00014201681],"category_scores_gemma":[0.0090461485,0.0009969268,0.00024401132,0.0011075235,0.00015908171,0.0016628506,0.0010245937,0.0027645282,0.00022784717],"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":[0.0006628223,0.000527547,0.0056099244,0.0029217736,0.00045316084,0.00020701248,0.0006307872,0.22012472,0.008590429,0.17123045,0.000017205626,0.5890242],"study_design_scores_gemma":[0.009990582,0.006348495,0.10788882,0.00519819,0.00065808214,0.00022170886,0.002252697,0.35095987,0.117311716,0.12331596,0.26056692,0.015286949],"about_ca_topic_score_codex":0.00035348,"about_ca_topic_score_gemma":0.00072791934,"teacher_disagreement_score":0.5737372,"about_ca_system_score_codex":0.0011847185,"about_ca_system_score_gemma":0.00010659934,"threshold_uncertainty_score":0.99953616},"labels":[],"label_agreement":null},{"id":"W7045640502","doi":"","title":"Artificial intelligence driven decision-making under uncertainty","year":2024,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; McGill University","keywords":"Expert system; Applications of artificial intelligence; Key (lock); Artificial neural network; Feature (linguistics)","score_opus":0.027112096147988998,"score_gpt":0.29207114915231774,"score_spread":0.26495905300432876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7045640502","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":[0.46781442,0.0018953138,0.15038857,0.00038478206,0.06293578,0.0057796338,0.0006102475,0.008655013,0.30153626],"genre_scores_gemma":[0.96839535,0.00013572039,0.02611209,0.0003852969,0.00014282046,0.00008778344,0.00022571407,0.00022983942,0.0042854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99262464,0.0003063882,0.0017149352,0.0021514744,0.0020143162,0.0011882671],"domain_scores_gemma":[0.9950962,0.0012448796,0.0007669141,0.001950908,0.0005807528,0.00036035385],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012150691,0.0010939694,0.0008686859,0.00096604414,0.0013140632,0.0010516897,0.003728177,0.0010206244,0.00027542363],"category_scores_gemma":[0.0014144371,0.0011305847,0.0006010107,0.0018541501,0.00009266751,0.0013574985,0.00093685207,0.0030508847,0.0033135535],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036421603,0.000037453385,0.0000010900935,0.00012208626,0.00011832918,0.00010630506,0.000026630747,0.32499507,0.0005994585,0.38899368,0.000008013956,0.28495547],"study_design_scores_gemma":[0.00012259022,0.00030508434,0.00008333434,0.00342602,0.00025466448,0.0000609525,0.00059566414,0.29158795,0.0063153626,0.67669344,0.018064098,0.00249085],"about_ca_topic_score_codex":0.00007168253,"about_ca_topic_score_gemma":0.0005075585,"teacher_disagreement_score":0.5005809,"about_ca_system_score_codex":0.0013236861,"about_ca_system_score_gemma":0.00022094675,"threshold_uncertainty_score":0.9999861},"labels":[],"label_agreement":null},{"id":"W7071380059","doi":"","title":"Risk-directed exploration in reinforcement learning","year":2005,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Entropy (arrow of time); Measure (data warehouse); Action (physics); Reinforcement; Action selection; Class (philosophy)","score_opus":0.01879923180380377,"score_gpt":0.24857631707950886,"score_spread":0.2297770852757051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071380059","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4276886,0.0005948108,0.005004959,0.00011144217,0.0076561472,0.0045075538,0.00006420284,0.006283541,0.5480887],"genre_scores_gemma":[0.9556458,0.0010379037,0.010734794,0.00015703627,0.00010263161,0.00027476257,0.0011647284,0.00020714186,0.030675204],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99302846,0.0008335284,0.0017417327,0.0015732162,0.0016569812,0.001166061],"domain_scores_gemma":[0.9957059,0.00034876383,0.0017491083,0.0013678927,0.00050550635,0.00032281957],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017735513,0.0010025095,0.0008700825,0.001217411,0.0012315293,0.00041435042,0.0020138128,0.00092295185,0.00017857333],"category_scores_gemma":[0.0018415024,0.0011619863,0.0002809724,0.0016914578,0.00003715168,0.0035692432,0.00039187443,0.0037779233,0.00093792146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007935349,0.000081759914,0.000099750185,0.00013375522,0.00011306098,0.000052766485,0.00009766249,0.8261395,0.0020220943,0.049423493,0.000008722116,0.12174806],"study_design_scores_gemma":[0.00585928,0.0017254784,0.0066044717,0.0025955592,0.00038219435,0.000040805855,0.001196282,0.71707886,0.047191042,0.011402019,0.198804,0.007120008],"about_ca_topic_score_codex":0.00030247465,"about_ca_topic_score_gemma":0.0010801768,"teacher_disagreement_score":0.5279572,"about_ca_system_score_codex":0.0015845412,"about_ca_system_score_gemma":0.00012489612,"threshold_uncertainty_score":0.99983996},"labels":[],"label_agreement":null},{"id":"W7072003558","doi":"","title":"Uncertainty aware behavioral cloning using Bayesian Neural Networks","year":2019,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","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":"Consistency (knowledge bases); Probabilistic logic; Artificial neural network; Scalability; Robot; Reinforcement learning","score_opus":0.02643474342105103,"score_gpt":0.2769272709484118,"score_spread":0.2504925275273608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7072003558","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":[0.94291174,0.00034388903,0.017799329,0.00002604062,0.017709943,0.002561912,0.0001866993,0.0020059461,0.016454505],"genre_scores_gemma":[0.9866047,0.0000365972,0.0069811307,0.00026487026,0.00012781238,0.000045656212,0.0009580344,0.0002808787,0.0047003557],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99282193,0.00054259354,0.001423696,0.0019728432,0.0015556847,0.0016832399],"domain_scores_gemma":[0.9950858,0.00026656062,0.0013831733,0.0021616865,0.000599108,0.0005036982],"candidate_categories":["metaepi_narrow","sts","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.00091353955,0.0013050807,0.001144676,0.00062219653,0.0017891318,0.00075439934,0.0032734862,0.001335401,0.000111142595],"category_scores_gemma":[0.00020083452,0.00146206,0.0006392135,0.0012151934,0.00006953044,0.002202336,0.00072620186,0.003587329,0.00013762839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050608367,0.00006672925,0.00020229572,0.00015444706,0.00010148794,0.00012705913,0.000021736802,0.9352117,0.00094127393,0.014038847,0.0000024639608,0.049081318],"study_design_scores_gemma":[0.00077747315,0.00030411014,0.0003076151,0.0005877611,0.00021746656,0.00006288242,0.00018025571,0.99215317,0.0010388669,0.0005618219,0.001959744,0.0018488598],"about_ca_topic_score_codex":0.00063987257,"about_ca_topic_score_gemma":0.00023948908,"teacher_disagreement_score":0.05694141,"about_ca_system_score_codex":0.001350595,"about_ca_system_score_gemma":0.0001553429,"threshold_uncertainty_score":0.9999701},"labels":[],"label_agreement":null},{"id":"W7093331850","doi":"10.1016/j.engappai.2025.112779","title":"Shaping <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si159.svg\" display=\"inline\" id=\"d1e703\"> <mml:mi>Q</mml:mi> </mml:math> -values right: A distributional normalized actor–critic approach","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; National Fire Agency; Busan Metropolitan City; Information Technology Research Centre; Korea Institute for Advancement of Technology; Ministry of Science and ICT, South Korea; Ministry of Trade, Industry and Energy; Ministry of Education","keywords":"Reinforcement learning; Key (lock); Upper and lower bounds; Stability (learning theory); Range (aeronautics); Value (mathematics); Q-learning","score_opus":0.022669345411759204,"score_gpt":0.2668609660288699,"score_spread":0.2441916206171107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7093331850","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":[0.1275769,0.00011954739,0.87108314,0.00016039773,0.00028293784,0.00011045327,0.000023736444,0.0002298079,0.00041309692],"genre_scores_gemma":[0.936542,0.000038363967,0.06262662,0.000062748884,0.00016453267,0.00035651063,0.00013676925,0.00003070545,0.00004179292],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978044,0.000027476064,0.00071660016,0.0005052943,0.0005010931,0.00044512673],"domain_scores_gemma":[0.99827,0.00036452277,0.00024464773,0.0008731349,0.00012769058,0.000120009245],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046586856,0.00024238027,0.00018186227,0.00017453145,0.00037338713,0.00026447832,0.0011816852,0.00019636337,0.000011108757],"category_scores_gemma":[0.00031754604,0.00030059644,0.00018999528,0.00073740055,0.00018970598,0.0003771323,0.00044841442,0.00038409553,0.00019981274],"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":[0.0000074914933,0.000057897272,0.0000027548224,0.00012086498,0.000047829224,0.0000023984128,0.00020200678,0.3401814,0.001229765,0.6570319,0.000027263808,0.0010884462],"study_design_scores_gemma":[0.000042540134,0.000049068523,0.000026703114,0.00013777704,0.000045155655,0.000014255607,0.000100733705,0.9730271,0.023514299,0.0015091728,0.0013069721,0.00022622796],"about_ca_topic_score_codex":0.00005795454,"about_ca_topic_score_gemma":0.000003562082,"teacher_disagreement_score":0.808965,"about_ca_system_score_codex":0.000037273003,"about_ca_system_score_gemma":0.0001814017,"threshold_uncertainty_score":0.9999446},"labels":[],"label_agreement":null},{"id":"W7095254530","doi":"","title":"Regularized Reinforcement Learning with Performance Guarantees","year":2014,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Control (management); Reinforcement; Active learning (machine learning)","score_opus":0.0067977949779677894,"score_gpt":0.19196615697294636,"score_spread":0.18516836199497858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095254530","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":[0.010640195,0.0000035799628,0.91631085,0.00025886347,0.00009315069,0.000121846315,5.0866076e-9,0.0004198,0.07215171],"genre_scores_gemma":[0.88900816,0.000010472814,0.09009469,0.00032294737,0.000036977497,0.000009941005,0.0000020968328,0.000012008044,0.020502724],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985336,0.000059650076,0.00024122794,0.00030526702,0.00048765805,0.00037258552],"domain_scores_gemma":[0.99902433,0.00007271138,0.00013029423,0.00060781237,0.000090308815,0.000074543124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004610521,0.00016921436,0.0001699636,0.00009679748,0.00023476047,0.00020161804,0.0007367309,0.000044341592,0.00006976554],"category_scores_gemma":[0.000053387776,0.00012365992,0.000036146303,0.00028568678,0.000051949904,0.0005874309,0.00020978581,0.00022515359,0.00020935229],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000113579135,0.0000044282688,0.0021060924,0.000016075197,0.000014154565,0.0000010933475,0.00020013051,0.94849616,0.00021591503,0.043729927,0.00010174226,0.0051029497],"study_design_scores_gemma":[0.00061766495,0.00059634424,0.001242701,0.00003869194,0.000004883491,0.000012907579,0.000015544138,0.98072153,0.0018263498,0.000033035318,0.014674168,0.00021616563],"about_ca_topic_score_codex":0.000009105795,"about_ca_topic_score_gemma":8.4587936e-7,"teacher_disagreement_score":0.87836796,"about_ca_system_score_codex":0.000033557346,"about_ca_system_score_gemma":0.000034756482,"threshold_uncertainty_score":0.5042705},"labels":[],"label_agreement":null},{"id":"W7096680464","doi":"","title":"Reinforcement Learning for Factored Markov Decision Processes","year":2002,"lang":"en","type":"article","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Markov decision process; Inference; Partially observable Markov decision process; Representation (politics); Core (optical fiber); Action (physics); State (computer science); Markov process; Q-learning","score_opus":0.03809663181555732,"score_gpt":0.3046626435827796,"score_spread":0.2665660117672223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096680464","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":[0.001653728,0.00012793805,0.9866105,0.00053685973,0.00024991302,0.0003432728,7.1038535e-8,0.00030452225,0.01017322],"genre_scores_gemma":[0.8537262,0.00010786244,0.10654658,0.00019841809,0.00008122523,0.00004750776,0.0000045547918,0.00002357474,0.039264075],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857694,0.000024039606,0.0002435298,0.00033801858,0.00041518192,0.0004023162],"domain_scores_gemma":[0.9987299,0.0003967187,0.00016065518,0.00043593958,0.00017582354,0.00010098026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002135144,0.00017116911,0.00016226727,0.00010689044,0.00024448428,0.00023617868,0.000698605,0.00006694366,0.00020041698],"category_scores_gemma":[0.0007816636,0.00015731728,0.00006133372,0.00037290377,0.000025325597,0.00038510037,0.0002096227,0.00015989866,0.00017568022],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012549602,0.000017047032,0.00037011385,0.00008018394,0.000018002298,0.0000031567374,0.0035933757,0.96429867,0.00018733325,0.0015265642,0.007094809,0.022798216],"study_design_scores_gemma":[0.0005057729,0.00026967272,0.000108720626,0.000053237713,0.0000063572625,0.000004283254,0.00012618708,0.9058011,0.0011554935,0.000087292225,0.09165591,0.00022597631],"about_ca_topic_score_codex":0.0000072451003,"about_ca_topic_score_gemma":0.0000012129523,"teacher_disagreement_score":0.8800639,"about_ca_system_score_codex":0.00006986528,"about_ca_system_score_gemma":0.000032413613,"threshold_uncertainty_score":0.6415212},"labels":[],"label_agreement":null},{"id":"W7097981727","doi":"","title":"Author manuscript, published in &amp;quot;Advances in Neural Information Processing Systems, Canada (2008)&amp;quot; Particle Filter-based Policy Gradient in POMDPs","year":2013,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Parameterized complexity; Resampling; Particle filter; Measure (data warehouse); Markov decision process; Variance (accounting); Process (computing); Markov process; Filter (signal processing)","score_opus":0.023871227454056985,"score_gpt":0.2540971173766306,"score_spread":0.23022588992257362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097981727","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":[0.5486812,0.00048241482,0.42929754,0.013639353,0.0014773997,0.0022256656,0.0000043948135,0.00047542067,0.003716607],"genre_scores_gemma":[0.9878728,0.000005287136,0.009861339,0.0010575013,0.000038886774,0.00016291729,0.00002966894,0.000013445601,0.0009581674],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965711,0.00018895422,0.0011636212,0.00039664257,0.00072494795,0.00095472904],"domain_scores_gemma":[0.99853307,0.00011133445,0.0003393606,0.00062332005,0.00018211668,0.00021080054],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00064503384,0.00029097332,0.00034196864,0.0007135311,0.00010244959,0.0012281352,0.0009496767,0.00009490107,0.000041277435],"category_scores_gemma":[0.00043416422,0.00026537306,0.00003261889,0.002019324,0.00003896243,0.007886042,0.00019577112,0.00037988773,0.000054053777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007670424,0.000058866925,0.04348889,0.00019432671,0.0000025984036,0.0000069230146,0.0017675867,0.9432087,0.00003245164,0.0021738638,0.0029013029,0.0061568143],"study_design_scores_gemma":[0.0007893894,0.000041408835,0.028587744,0.000118671436,0.0000014217632,0.0000068546547,0.00028332553,0.9523408,0.000054592947,0.00007161039,0.01737696,0.00032722286],"about_ca_topic_score_codex":0.37793577,"about_ca_topic_score_gemma":0.35233256,"teacher_disagreement_score":0.43919158,"about_ca_system_score_codex":0.0010295323,"about_ca_system_score_gemma":0.0009689515,"threshold_uncertainty_score":0.99997985},"labels":[],"label_agreement":null},{"id":"W7102328828","doi":"","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Perspective (graphical); Simple (philosophy); Surrogate model; Verifiable secret sharing; Optimization problem","score_opus":0.06663284614697988,"score_gpt":0.2247884175724866,"score_spread":0.15815557142550674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7102328828","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":[0.027825153,0.00012393494,0.92736405,0.0009494956,0.00167948,0.00051094143,0.000004729343,0.00036441648,0.04117778],"genre_scores_gemma":[0.9511844,0.001009108,0.0014303898,0.00095078314,0.0001271695,6.940109e-7,0.0000149817415,0.00003828672,0.04524422],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.995652,0.0004265032,0.000656279,0.0016877012,0.00030194825,0.0012755285],"domain_scores_gemma":[0.99648535,0.00027899226,0.0005742156,0.001790304,0.00045652877,0.00041461637],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00058381236,0.0006414635,0.0005692295,0.0014368895,0.001170649,0.00058115285,0.0028246439,0.00033403243,0.0001548899],"category_scores_gemma":[0.00044390163,0.0008548881,0.00033637937,0.0063475035,0.00037871176,0.0019647046,0.0020965654,0.00074793166,0.0005980755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045899444,0.000053959928,0.0126334755,0.000109342756,0.00013758626,0.00034209964,0.00041430985,0.63754994,0.000021064865,0.34742162,0.000120691315,0.0011500318],"study_design_scores_gemma":[0.0018237297,0.0001866098,0.0023665472,0.0005783951,0.0001641368,0.000013181934,0.00048061117,0.9808972,0.00013144081,0.0065331836,0.0060594557,0.00076549745],"about_ca_topic_score_codex":0.00030829385,"about_ca_topic_score_gemma":0.000016331056,"teacher_disagreement_score":0.92593366,"about_ca_system_score_codex":0.0010793395,"about_ca_system_score_gemma":0.0010430551,"threshold_uncertainty_score":0.9993902},"labels":[],"label_agreement":null},{"id":"W7102329548","doi":"","title":"Causal Deep Q Network","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Mitacs","keywords":"Spurious relationship; Reinforcement learning; Causal model; Causal reasoning; Benchmark (surveying); Associative property; Causal structure","score_opus":0.026820504218234478,"score_gpt":0.27053520882870463,"score_spread":0.24371470461047015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7102329548","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":[0.039316777,0.0014485135,0.91912645,0.002445072,0.008450106,0.0003920354,4.5513696e-7,0.00027132675,0.028549265],"genre_scores_gemma":[0.95511687,0.00026723795,0.007031834,0.0034977251,0.00082309084,0.00001771351,0.0000053409967,0.00003310415,0.033207078],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958656,0.00026307715,0.00090553064,0.0010207612,0.0005562184,0.0013888556],"domain_scores_gemma":[0.9969379,0.00036272933,0.00033603638,0.0018801047,0.00024152067,0.00024171594],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007595739,0.000504122,0.0005102527,0.0001898978,0.000754233,0.00047323873,0.0022892267,0.00031519003,0.00033773974],"category_scores_gemma":[0.00031627846,0.00055015716,0.0002282666,0.0020308222,0.00026443717,0.00062419387,0.0017505486,0.0009046151,0.002298425],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011405034,0.000034699093,0.38347617,0.00005131813,0.00012873881,0.000042030264,0.00032957736,0.58783394,0.00003184624,0.015949128,0.006310136,0.0058010477],"study_design_scores_gemma":[0.0006011988,0.00018911931,0.21907353,0.00028479443,0.00009304851,0.0000064116134,0.000034987435,0.7208797,0.00018191333,0.0004246139,0.057701297,0.0005294337],"about_ca_topic_score_codex":0.000047366553,"about_ca_topic_score_gemma":0.000016806967,"teacher_disagreement_score":0.9158001,"about_ca_system_score_codex":0.00021068795,"about_ca_system_score_gemma":0.00043772755,"threshold_uncertainty_score":0.999695},"labels":[],"label_agreement":null},{"id":"W7107957261","doi":"10.71781/32566","title":"Modeling the world to reason and plan","year":2025,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Reinforcement Learning in Robotics","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":"Mitacs; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Canadian Institute for Advanced Research; Nvidia","keywords":"Context (archaeology); Gloom; Demise","score_opus":0.051368406102648166,"score_gpt":0.32856710235170883,"score_spread":0.2771986962490607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7107957261","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018753134,0.00018699818,0.47350073,0.001296518,0.0012877688,0.0013380356,0.0000035898377,0.0000096163485,0.5036236],"genre_scores_gemma":[0.07648636,0.000029920018,0.121412195,0.00035040904,0.00009604409,0.000056146317,0.00018930822,0.000021721335,0.8013579],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990894,0.000032853666,0.00018046435,0.0003492021,0.0001933354,0.0001547505],"domain_scores_gemma":[0.9992578,0.00007435133,0.00006622535,0.00050460745,0.000048410802,0.00004861627],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00027731204,0.0001346073,0.00014913807,0.00011389316,0.000166674,0.0010389341,0.0016989377,0.00006110569,0.00006165232],"category_scores_gemma":[0.000057263565,0.00010340708,0.000021912103,0.00028308723,0.0000041961935,0.00018037642,0.00043137133,0.0002243588,0.00009621559],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018957246,0.0000051626107,0.000018244335,0.000018588964,0.000028814256,0.0000044843114,0.0034695442,0.78547823,0.000017201233,0.0019739657,0.0013490638,0.20761772],"study_design_scores_gemma":[0.000089444286,0.000023858645,0.000061158105,0.00032703174,0.00001840744,9.1150247e-7,0.0002542696,0.94869065,0.00018707429,0.00007154686,0.050102487,0.00017317015],"about_ca_topic_score_codex":0.00007723374,"about_ca_topic_score_gemma":0.00084970414,"teacher_disagreement_score":0.35208854,"about_ca_system_score_codex":0.000024652132,"about_ca_system_score_gemma":0.00012708998,"threshold_uncertainty_score":0.9999981},"labels":[],"label_agreement":null},{"id":"W7110060432","doi":"10.1162/isal.a.888","title":"Energy Costs and Neural Complexity Evolution in Changing Environments","year":2025,"lang":"","type":"article","venue":"ALIFE","topic":"Reinforcement Learning in Robotics","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":"Institut National de la Recherche Scientifique","funders":"University of Cape Town","keywords":"Artificial neural network; Energy (signal processing); Cognition; Reinforcement learning; Key (lock); Efficient energy use","score_opus":0.020688039422258175,"score_gpt":0.2517305875269306,"score_spread":0.23104254810467245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7110060432","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":[0.02382361,0.00085715554,0.9703449,0.0012408696,0.0010247268,0.00017110219,0.0000014628637,0.00003163598,0.0025045401],"genre_scores_gemma":[0.99397135,0.00015931528,0.0012235795,0.0012873154,0.000052931402,0.000009178359,0.000006158745,0.000009076505,0.0032810979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99782467,0.0002267799,0.00044613495,0.00054251234,0.00034587784,0.0006140285],"domain_scores_gemma":[0.9991269,0.00011060078,0.0001552271,0.00048814836,0.000015620592,0.00010350139],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039224944,0.00023762659,0.00026001717,0.0005978809,0.0002547374,0.00019294837,0.00050355453,0.0001154678,0.000021789463],"category_scores_gemma":[0.00005593817,0.00028271074,0.000045989265,0.0009890461,0.00022942685,0.00042654097,0.0010489253,0.00023567518,0.000016007698],"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":[0.00003580889,0.00012656873,0.09956957,0.00008988719,0.000084054314,0.000039639603,0.0014559039,0.39354736,0.0004922404,0.45759767,0.00035133166,0.046609957],"study_design_scores_gemma":[0.00060974545,0.00006533593,0.05749254,0.0001464529,0.000013305365,0.0000037648092,0.0000735214,0.9381367,0.000113603666,0.0005860642,0.0025489088,0.00021004118],"about_ca_topic_score_codex":0.0003506516,"about_ca_topic_score_gemma":0.000036448386,"teacher_disagreement_score":0.9701477,"about_ca_system_score_codex":0.000458457,"about_ca_system_score_gemma":0.00006380338,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W7113916458","doi":"","title":"A-3PO: Accelerating Asynchronous LLM Training with Staleness-aware Proximal Policy Approximation","year":2025,"lang":"","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada)","funders":"","keywords":"Asynchronous communication; Reinforcement learning; Overhead (engineering); Interpolation (computer graphics); Stability (learning theory); Speedup; Constraint (computer-aided design); Code (set theory)","score_opus":0.0748734437683085,"score_gpt":0.2104304695268579,"score_spread":0.1355570257585494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7113916458","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":[0.08282388,0.000036660975,0.89957446,0.00033761482,0.00037024365,0.00083160115,0.000004828847,0.00033988353,0.015680842],"genre_scores_gemma":[0.9867979,0.000057381196,0.0069711446,0.00026587566,0.00017583297,0.0000031972274,0.000017576496,0.000042909243,0.0056681624],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959789,0.00031213692,0.00058752025,0.001600939,0.00030989797,0.0012105948],"domain_scores_gemma":[0.9970279,0.0002409652,0.00064210995,0.0013212269,0.00048817685,0.0002796207],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054637104,0.0006704957,0.0006036521,0.0009490101,0.001197201,0.000827125,0.0019330501,0.000316853,0.000055292072],"category_scores_gemma":[0.00015799445,0.00076089887,0.00019062376,0.004375091,0.00042854933,0.002439955,0.0009425215,0.0007999298,0.000069288326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089539855,0.00011321701,0.0053073135,0.00024562047,0.00016983016,0.00014677098,0.0019148025,0.7820057,0.000055410906,0.20258868,0.000020587691,0.007342479],"study_design_scores_gemma":[0.001980114,0.00060841127,0.0018816974,0.00060147356,0.00014337932,0.000016375798,0.0017984301,0.9906721,0.00030976135,0.000998419,0.00023359619,0.0007562589],"about_ca_topic_score_codex":0.00014918014,"about_ca_topic_score_gemma":0.000053222735,"teacher_disagreement_score":0.90397406,"about_ca_system_score_codex":0.000996617,"about_ca_system_score_gemma":0.0025379362,"threshold_uncertainty_score":0.9994842},"labels":[],"label_agreement":null},{"id":"W7117850973","doi":"","title":"The World Is Bigger! A Computationally-Embedded Perspective on the Big World Hypothesis","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Reinforcement Learning in Robotics","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":"Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Perspective (graphical); Construct (python library); Markov decision process; Automaton; Process (computing); Learning automata; Variety (cybernetics)","score_opus":0.057509890548072894,"score_gpt":0.29628165420160074,"score_spread":0.23877176365352784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117850973","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":[0.067131825,0.0017701077,0.33815292,0.32936805,0.009330819,0.002938517,0.000015597368,0.0005393426,0.2507528],"genre_scores_gemma":[0.81896156,0.00012926201,0.001245822,0.016942717,0.00042162632,0.000076636345,0.0000014224129,0.000045111785,0.16217583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99456245,0.00077791174,0.0010030802,0.0012760832,0.0012661607,0.0011143154],"domain_scores_gemma":[0.9866103,0.009471014,0.00063874177,0.0023149888,0.0007940178,0.00017095909],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015014824,0.0007009228,0.00051085587,0.00071158,0.0028858327,0.0013693053,0.003766493,0.00012550714,0.00032245085],"category_scores_gemma":[0.0013434644,0.0004625607,0.00047732762,0.0053217653,0.000894939,0.00030112462,0.0011336878,0.0013774757,0.0019795676],"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":[0.00018785908,0.00031087897,0.034740172,0.000047346908,0.0013673407,0.00003286158,0.00896888,0.2966577,0.00009965864,0.5691683,0.06371112,0.02470785],"study_design_scores_gemma":[0.0014257467,0.00033032292,0.20089528,0.000865863,0.0002675878,0.000005203956,0.0023252706,0.67629653,0.0028570013,0.01229893,0.10120826,0.0012240038],"about_ca_topic_score_codex":0.00008196972,"about_ca_topic_score_gemma":0.0002210202,"teacher_disagreement_score":0.75182974,"about_ca_system_score_codex":0.00076939334,"about_ca_system_score_gemma":0.00088034465,"threshold_uncertainty_score":0.9997826},"labels":[],"label_agreement":null},{"id":"W7118190000","doi":"10.1145/3765766.3787117","title":"10.1145/3765766.3787117","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Adaptation (eye); Component (thermodynamics); Key (lock)","score_opus":0.006354011713904454,"score_gpt":0.180076401831819,"score_spread":0.17372239011791454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118190000","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006198874,0.000012699001,0.014489757,0.0005584924,0.0000074024374,0.0001365423,5.1281705e-7,0.0003592905,0.98437333],"genre_scores_gemma":[0.00027685345,2.612746e-7,0.007402023,0.00021190727,0.0000706229,0.000008185523,0.0000030365188,0.000013579643,0.9920135],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988488,0.000037006612,0.00018503188,0.00028765225,0.00030415086,0.0003373497],"domain_scores_gemma":[0.9990151,0.000052825766,0.0000352853,0.0007015325,0.000042133554,0.00015313571],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00016610956,0.00013255062,0.00013046635,0.0000791307,0.00009856972,0.00018217652,0.0010298827,0.000049001224,0.95131344],"category_scores_gemma":[0.0000357843,0.00013229335,0.000050649913,0.0003484708,0.00002195505,0.00029000442,0.00016531178,0.0001127865,0.9870384],"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":[0.000008583986,0.000018170265,4.4393332e-7,0.0000036418867,0.000012350542,0.000009581067,0.000060015198,0.214242,0.000029181829,0.00008099395,0.14135782,0.6441772],"study_design_scores_gemma":[0.0001143265,0.00013001641,0.000034312383,0.000008762766,0.0000029337803,0.000006873901,1.837288e-7,0.11793243,0.0000462716,0.000007646817,0.88156235,0.0001538901],"about_ca_topic_score_codex":0.000008399151,"about_ca_topic_score_gemma":1.8444595e-8,"teacher_disagreement_score":0.7402045,"about_ca_system_score_codex":0.000037093854,"about_ca_system_score_gemma":0.00003284967,"threshold_uncertainty_score":0.53947663},"labels":[],"label_agreement":null},{"id":"W7118628814","doi":"10.1214/25-sts1001","title":"Sample-Based Planning and Learning with Function Approximation","year":2025,"lang":"","type":"article","venue":"Statistical Science","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Function approximation; Core (optical fiber); Focus (optics); Dimension (graph theory); Function (biology); Approximation algorithm; Optimism","score_opus":0.015498831904994551,"score_gpt":0.28179290718513256,"score_spread":0.266294075280138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118628814","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":[0.0013297846,0.000072296214,0.9928828,0.00045910885,0.00044050792,0.00032318648,0.0000039596075,0.000121520774,0.0043668724],"genre_scores_gemma":[0.7320212,0.0000024992833,0.26737165,0.00028809754,0.000020310474,0.000010032485,0.000006760847,0.0000065697336,0.00027285056],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99647367,0.0001989344,0.0004132342,0.0010342652,0.0011118393,0.00076803257],"domain_scores_gemma":[0.99692476,0.0019072565,0.00020618885,0.00039243855,0.00031259458,0.00025678796],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019359196,0.00026813048,0.00024887736,0.00039277851,0.001826012,0.0015378342,0.0006532875,0.00007795977,0.000050811326],"category_scores_gemma":[0.003144329,0.00023584187,0.000018329683,0.002424832,0.0020007084,0.00090622547,0.0003574946,0.00067556737,0.000016907507],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063680876,0.000019627114,0.009864411,0.0001081234,0.00000934935,0.0000060089183,0.00035642614,0.59633327,0.00016118168,0.33646446,0.000028894061,0.056584567],"study_design_scores_gemma":[0.00052511785,0.0007725439,0.04181777,0.0003134123,0.000042031203,0.0000030356907,0.00013678722,0.9528265,0.00012463689,0.0024142545,0.000758955,0.0002649639],"about_ca_topic_score_codex":0.00006124946,"about_ca_topic_score_gemma":0.000001518596,"teacher_disagreement_score":0.73069143,"about_ca_system_score_codex":0.00019113126,"about_ca_system_score_gemma":0.0009823946,"threshold_uncertainty_score":0.99949867},"labels":[],"label_agreement":null},{"id":"W7123349578","doi":"10.1109/cdc57313.2025.11312137","title":"Kernel Mean Embedding Topology: Weak and Strong Forms for Stochastic Kernels and Implications for Model Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Queen's University","funders":"","keywords":"Embedding; Kernel (algebra); Robustness (evolution); Stochastic process; Network topology; Topology (electrical circuits); Weak topology (polar topology); Reproducing kernel Hilbert space","score_opus":0.03230569072649504,"score_gpt":0.3301698920966929,"score_spread":0.29786420137019787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7123349578","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":[0.002716115,0.0003871804,0.98838425,0.0031742237,0.00029875457,0.0021006628,0.00001313885,0.00014333171,0.0027823676],"genre_scores_gemma":[0.8388183,0.000078272074,0.14496928,0.0002576493,0.000054892964,0.00030196682,0.000019726023,0.00003361632,0.015466281],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970034,0.00004367444,0.00076464046,0.0010754332,0.00016007571,0.00095279166],"domain_scores_gemma":[0.99731123,0.0012333199,0.00033399742,0.000587118,0.00031763624,0.00021672224],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000800368,0.0004417042,0.0005329917,0.00032250563,0.0014385509,0.0007234574,0.00065785385,0.00025962008,0.000008972566],"category_scores_gemma":[0.0005495814,0.00044071954,0.00014396569,0.000302346,0.0003010095,0.00075734715,0.00085489976,0.0003868061,0.0000015284133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020476162,0.000013170332,0.00038458136,0.00013805025,0.00007498082,3.6534267e-8,0.0006519339,0.58610684,0.00010947181,0.40228805,0.000140631,0.010071749],"study_design_scores_gemma":[0.0014992806,0.0003928066,0.00039387838,0.00013768363,0.00016242944,0.0000069384946,0.0007934081,0.96682614,0.00004890207,0.02897738,0.00034527227,0.0004158656],"about_ca_topic_score_codex":0.00001560787,"about_ca_topic_score_gemma":0.000013870524,"teacher_disagreement_score":0.84341496,"about_ca_system_score_codex":0.00013425792,"about_ca_system_score_gemma":0.00028575162,"threshold_uncertainty_score":0.9998614},"labels":[],"label_agreement":null},{"id":"W7124135461","doi":"10.65109/gnlj3027","title":"POMDP planning and execution in an augmented space","year":2014,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Upper and lower bounds; Markov decision process; Partially observable Markov decision process; Suite; Linear programming; Action (physics); Space (punctuation); Branch and bound","score_opus":0.022786742106857858,"score_gpt":0.27798784173079166,"score_spread":0.2552010996239338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124135461","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":[0.07486417,0.00008416669,0.9127872,0.0006742692,0.0004414955,0.00020167932,1.1792982e-7,0.00009930935,0.010847588],"genre_scores_gemma":[0.97300965,0.000016617883,0.024219634,0.00036337064,0.00007742084,0.0000032004045,0.0000033652873,0.000013544109,0.0022931786],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978034,0.00025842877,0.0004174346,0.00060956256,0.00038073168,0.0005304469],"domain_scores_gemma":[0.99885035,0.00011976295,0.00016929112,0.00059003313,0.0000631565,0.00020742737],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00087812264,0.00024540763,0.0002429104,0.0002605147,0.00017292413,0.0005725329,0.0005030591,0.00013762053,0.00005552824],"category_scores_gemma":[0.00011326976,0.00025445,0.00002688152,0.00043311124,0.000095681426,0.0011446669,0.0003996471,0.00032392697,0.000048448925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017403636,0.00004292482,0.04744987,0.00003531878,0.00000830401,0.000009862194,0.0032770683,0.89481777,0.00054837775,0.042809054,0.00015488472,0.010829155],"study_design_scores_gemma":[0.00070989126,0.00057307014,0.03853338,0.00014530735,0.000006656033,0.000008830716,0.00020728457,0.95779985,0.000293186,0.00018848017,0.0012412056,0.00029288474],"about_ca_topic_score_codex":0.00009158142,"about_ca_topic_score_gemma":0.000013553053,"teacher_disagreement_score":0.8981455,"about_ca_system_score_codex":0.000080569785,"about_ca_system_score_gemma":0.000045833964,"threshold_uncertainty_score":0.99999076},"labels":[],"label_agreement":null},{"id":"W7124138561","doi":"10.65109/kjtg4247","title":"Efficient planning in R-max","year":2011,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Value (mathematics); Automated planning and scheduling; Markov decision process; Order (exchange); Active learning (machine learning)","score_opus":0.06178843939825616,"score_gpt":0.26707263148114885,"score_spread":0.2052841920828927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124138561","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":[0.017820856,0.00011987408,0.76419663,0.000059196005,0.0010686213,0.00020302078,1.01991155e-7,0.00009533282,0.21643634],"genre_scores_gemma":[0.9461052,0.0000059045483,0.04922187,0.00027882357,0.00004125298,0.00000503351,3.6430362e-7,0.000015712558,0.0043258467],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730176,0.00011175107,0.00066482526,0.0006063232,0.00050753116,0.0008077828],"domain_scores_gemma":[0.99865365,0.000087747336,0.00018543264,0.00083443424,0.00006639146,0.00017236834],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00072324433,0.0002755773,0.00027034726,0.00034764665,0.00011997119,0.00016953991,0.0013391714,0.00013946184,0.0009963934],"category_scores_gemma":[0.00009327609,0.00027185632,0.00008177425,0.00085502455,0.00010412564,0.00017020528,0.0007671166,0.00045628738,0.0010516742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010305379,0.00008651018,0.013079691,0.000018704926,0.000010578589,0.00011104906,0.014510145,0.9448639,0.000016707569,0.024152068,0.0001160221,0.0030243257],"study_design_scores_gemma":[0.00042533164,0.00021084925,0.02226367,0.00015151345,0.0000053951276,0.000009672669,0.00024745316,0.9755291,0.0003305519,0.00008222301,0.00040985667,0.00033442202],"about_ca_topic_score_codex":0.00013254373,"about_ca_topic_score_gemma":0.000002667679,"teacher_disagreement_score":0.92828435,"about_ca_system_score_codex":0.00011814134,"about_ca_system_score_gemma":0.00013343753,"threshold_uncertainty_score":0.99997336},"labels":[],"label_agreement":null},{"id":"W7124143215","doi":"10.65109/vuye5463","title":"Optimal policy switching algorithms for reinforcement learning","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Task (project management); Q-learning; Function (biology); Markov decision process; Function approximation; Control (management); Optimal control","score_opus":0.023923541871614384,"score_gpt":0.30137341905869686,"score_spread":0.27744987718708247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124143215","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":[0.0017373931,0.000027568378,0.96788883,0.0028699737,0.0039373133,0.0013035646,8.0533454e-7,0.0004803246,0.021754233],"genre_scores_gemma":[0.56918913,0.000046680147,0.38575864,0.0007348288,0.001937439,0.00007155426,0.00001398142,0.0000816107,0.04216613],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940652,0.0001012394,0.001403186,0.0012679211,0.0011483817,0.0020140193],"domain_scores_gemma":[0.99601966,0.00055256573,0.00076694693,0.0014844126,0.0005448512,0.00063155557],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001988269,0.0007767571,0.0006341972,0.0006649547,0.0015356826,0.0019110753,0.0025493228,0.00046788546,0.00054453703],"category_scores_gemma":[0.0015346955,0.0007899889,0.00047695747,0.0009877414,0.00016137236,0.0015347295,0.0015093826,0.0022878638,0.00041396922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002262927,0.000033892837,0.0001235614,0.00007517273,0.00009356697,0.0000054762613,0.0018879848,0.8313979,0.0031241558,0.1019223,0.0003588872,0.060954466],"study_design_scores_gemma":[0.0014135276,0.0010176012,0.000083147206,0.000060400445,0.00004467571,0.000039158505,0.0001698113,0.92630875,0.002617862,0.0001655494,0.06718995,0.00088954065],"about_ca_topic_score_codex":0.0002960952,"about_ca_topic_score_gemma":0.000008868184,"teacher_disagreement_score":0.5821302,"about_ca_system_score_codex":0.00021283884,"about_ca_system_score_gemma":0.0010512868,"threshold_uncertainty_score":0.9997642},"labels":[],"label_agreement":null},{"id":"W7124145910","doi":"10.65109/dwjt8467","title":"Basis function discovery using spectral clustering and bisimulation metrics","year":2011,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Set (abstract data type); Feature (linguistics); Function (biology); Basis (linear algebra); Cluster analysis; Focus (optics); State (computer science)","score_opus":0.08381540224386577,"score_gpt":0.2621151350149372,"score_spread":0.17829973277107145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124145910","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":[0.06555986,0.00012820931,0.9262528,0.00002517836,0.0018524455,0.0002418913,4.7909646e-7,0.000099176534,0.00583999],"genre_scores_gemma":[0.8845871,0.00007551889,0.11373541,0.000112478745,0.00014367104,8.8043987e-7,0.0000012970413,0.000022174721,0.0013214605],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976739,0.000106019215,0.00057235605,0.00062570494,0.0005055725,0.00051644375],"domain_scores_gemma":[0.99877316,0.000114673945,0.0003048335,0.0005483082,0.000110860994,0.0001481692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000531334,0.00030535227,0.00026120598,0.00055850745,0.00035975152,0.0009184472,0.0003518678,0.00015407926,0.00017186109],"category_scores_gemma":[0.00010749745,0.00030828422,0.00009512083,0.0012410022,0.000093042225,0.0037612994,0.0006459806,0.00026205555,0.00002700185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004580924,0.0000356157,0.024307355,0.00006540513,0.00007184864,0.0000067749615,0.0013297293,0.95044285,0.00030800505,0.0068050874,0.000009169995,0.016572358],"study_design_scores_gemma":[0.00037611247,0.00035105846,0.028934836,0.00005363692,0.00009981179,0.0000152316725,0.00011371672,0.9687819,0.0006303762,0.00022702198,0.000055261655,0.0003610756],"about_ca_topic_score_codex":0.0002825591,"about_ca_topic_score_gemma":0.000011726503,"teacher_disagreement_score":0.81902725,"about_ca_system_score_codex":0.00017306111,"about_ca_system_score_gemma":0.00007607293,"threshold_uncertainty_score":0.99993694},"labels":[],"label_agreement":null},{"id":"W7124153011","doi":"10.65109/actd7997","title":"Escaping local optima in POMDP planning as inference","year":2011,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Partially observable Markov decision process; Inference; Reinforcement learning; Controller (irrigation); Greedy algorithm; Local planning; Control (management)","score_opus":0.08219326181887587,"score_gpt":0.30553004872109796,"score_spread":0.22333678690222208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124153011","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":[0.0045589274,0.00017301997,0.8062892,0.000077829194,0.0007777359,0.00024234684,1.3511475e-7,0.00015185936,0.18772893],"genre_scores_gemma":[0.9057856,0.000046622317,0.09102084,0.00056825683,0.00005630322,0.000008603432,0.0000011328937,0.000025644533,0.002486969],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960026,0.0001901962,0.0010006708,0.0009186116,0.0007092562,0.0011786225],"domain_scores_gemma":[0.99792653,0.00026712936,0.00031151754,0.0010531567,0.00014183298,0.000299813],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085448084,0.0004705765,0.00045347013,0.00047385786,0.00020209214,0.00042624885,0.0021520401,0.00027404097,0.0016456112],"category_scores_gemma":[0.00030543123,0.0004943494,0.00011001545,0.0010181175,0.00028420772,0.0015361485,0.0014803023,0.00091601856,0.0016544978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002382197,0.00006633281,0.014107218,0.000038817878,0.000023957233,0.00022986514,0.014164768,0.89965487,0.00001998913,0.048185796,0.000062208,0.023422386],"study_design_scores_gemma":[0.0005715272,0.000506232,0.010308852,0.0005069008,0.00000970447,0.000030107554,0.00088449544,0.98469514,0.0008028223,0.00082676887,0.00023668018,0.00062079186],"about_ca_topic_score_codex":0.00078548474,"about_ca_topic_score_gemma":0.000011322319,"teacher_disagreement_score":0.9012267,"about_ca_system_score_codex":0.00020627234,"about_ca_system_score_gemma":0.00042719903,"threshold_uncertainty_score":0.9997508},"labels":[],"label_agreement":null},{"id":"W7124156211","doi":"10.65109/qppa8970","title":"Using spatial hints to improve policy reuse in a reinforcement learning agent","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 British Columbia","funders":"","keywords":"Reinforcement learning; Reuse; Exploit; Robustness (evolution); Task (project management); Domain (mathematical analysis); Policy learning","score_opus":0.031227505286058152,"score_gpt":0.3106378969221901,"score_spread":0.27941039163613196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124156211","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":[0.084905386,0.0000072194616,0.8982509,0.0017817492,0.0037847986,0.0012630558,5.7481776e-7,0.00017018557,0.009836136],"genre_scores_gemma":[0.89617765,0.000020058496,0.08829288,0.0013521446,0.0008389019,0.000025342217,0.0000034200382,0.00006648761,0.013223089],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9933829,0.00023371849,0.001679377,0.0013985075,0.001394897,0.0019106114],"domain_scores_gemma":[0.99524766,0.00015805096,0.000608097,0.0028464806,0.00031478025,0.00082493166],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016711211,0.0007334338,0.00065256987,0.0013838101,0.00047546782,0.0011265093,0.0033634233,0.00040116053,0.00087673945],"category_scores_gemma":[0.0033984282,0.0007789025,0.0001826801,0.0019304625,0.00014478389,0.0009934554,0.0053934483,0.002303683,0.0011141986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041786563,0.00006127624,0.0019096676,0.000046865985,0.000034921555,0.000048578044,0.004686185,0.9257485,0.043534286,0.004782466,0.00011144598,0.018993972],"study_design_scores_gemma":[0.0011817666,0.0008927755,0.0015674159,0.00014892325,0.000019600153,0.000019555257,0.0000989019,0.9809281,0.006056323,0.00009443454,0.008107757,0.00088439835],"about_ca_topic_score_codex":0.012297003,"about_ca_topic_score_gemma":0.00048068055,"teacher_disagreement_score":0.81127226,"about_ca_system_score_codex":0.0008976587,"about_ca_system_score_gemma":0.0012455062,"threshold_uncertainty_score":0.99999803},"labels":[],"label_agreement":null},{"id":"W7124164391","doi":"10.65109/pwam3332","title":"Smart exploration in reinforcement learning using absolute temporal difference errors","year":2013,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"McGill University","funders":"","keywords":"Reinforcement learning; State (computer science); Temporal difference learning; Function (biology); Control (management); Function approximation","score_opus":0.060067349247302546,"score_gpt":0.2738622850019143,"score_spread":0.21379493575461173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124164391","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":[0.09957088,0.00005572442,0.89180785,0.0007117892,0.0011654324,0.0011815553,1.0581651e-7,0.00020393227,0.0053027384],"genre_scores_gemma":[0.95098585,0.00009685748,0.029137414,0.00031426543,0.00010585717,0.00006285047,0.000015158063,0.000048636048,0.01923314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940043,0.00041288923,0.0018009938,0.0010892301,0.0012534672,0.001439123],"domain_scores_gemma":[0.99725306,0.00015423825,0.0008304356,0.0010617893,0.0003482307,0.00035225193],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009309756,0.00069024554,0.00062553317,0.000671872,0.00053089345,0.0014359702,0.0013688036,0.00030366005,0.0012592255],"category_scores_gemma":[0.0002511245,0.00070508267,0.00014193439,0.001398788,0.0001875909,0.0044834106,0.0011810286,0.0011551608,0.001181996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008978982,0.000043933247,0.016848797,0.00006179991,0.000027377113,0.000011679194,0.0034484146,0.9707837,0.0010770195,0.0020901721,0.00009309603,0.0055050403],"study_design_scores_gemma":[0.00081234967,0.00050946395,0.012823091,0.0003244049,0.000016891401,0.000007780441,0.00066882337,0.9831087,0.00027225417,0.0002489056,0.0004014064,0.0008059216],"about_ca_topic_score_codex":0.0044012857,"about_ca_topic_score_gemma":0.00009788236,"teacher_disagreement_score":0.8626704,"about_ca_system_score_codex":0.00061102584,"about_ca_system_score_gemma":0.00036585378,"threshold_uncertainty_score":0.99965376},"labels":[],"label_agreement":null},{"id":"W7124164408","doi":"10.65109/ycuv1950","title":"Policy optimization by marginal-map probabilistic inference in generative models","year":2014,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Partially observable Markov decision process; Inference; Benchmark (surveying); Bounded function; Generative model; Probabilistic logic; Bayesian inference; Scalability","score_opus":0.022099080594102625,"score_gpt":0.26834929519673417,"score_spread":0.24625021460263155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124164408","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":[0.00009318266,0.00004795135,0.97784084,0.0031879137,0.0003621855,0.0007196611,0.0000023611692,0.000117406686,0.017628467],"genre_scores_gemma":[0.7550333,0.000119032695,0.23405012,0.0011020296,0.00016630141,0.000050931998,0.000027228745,0.000033117343,0.009417899],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959023,0.00054984953,0.00094120967,0.0009891365,0.0007207196,0.00089677883],"domain_scores_gemma":[0.99745405,0.0005033223,0.00038060438,0.0010402461,0.00036508677,0.00025667663],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008296253,0.0004943482,0.0004724468,0.00044502862,0.00022164131,0.0008182838,0.0013880824,0.00024044691,0.00017692728],"category_scores_gemma":[0.0010910598,0.000497642,0.000076977005,0.0013438228,0.00022052848,0.0017438503,0.0006782765,0.00047997545,0.00013788888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006249094,0.00006331729,0.00011535331,0.000050971863,0.000009822608,0.0000010462264,0.00094173884,0.75473887,0.000019652909,0.24147561,0.00032122555,0.0022561606],"study_design_scores_gemma":[0.00065185543,0.00035345188,0.000024783934,0.00011512861,0.0000100955,0.0000013276541,0.000020485293,0.9897929,0.00008284805,0.008114412,0.00028239595,0.0005503039],"about_ca_topic_score_codex":0.00033294258,"about_ca_topic_score_gemma":0.00002298339,"teacher_disagreement_score":0.75494015,"about_ca_system_score_codex":0.00042157987,"about_ca_system_score_gemma":0.000620595,"threshold_uncertainty_score":0.9997475},"labels":[],"label_agreement":null},{"id":"W7124165107","doi":"10.65109/twxw5772","title":"Sigma point policy iteration","year":2008,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Iterated function; Sigma; Function (biology); Fixed point; Point (geometry); Order (exchange); Markov decision process; Bellman equation","score_opus":0.028661473987990967,"score_gpt":0.2603251415755973,"score_spread":0.23166366758760631,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124165107","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":[0.0014588987,0.000045314824,0.8987091,0.006011042,0.00079542777,0.00025038657,3.2196533e-7,0.00020665264,0.09252281],"genre_scores_gemma":[0.90334165,0.00015510997,0.029749295,0.002946604,0.0006237041,0.000004859364,0.0000040097675,0.000019413174,0.06315535],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99729,0.00013040466,0.000642523,0.0005712673,0.0007169962,0.00064877974],"domain_scores_gemma":[0.99815756,0.000098020006,0.00022494365,0.0010553268,0.00022237748,0.00024177175],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028578084,0.00030130093,0.00024737857,0.00035240682,0.0006094653,0.00044123008,0.00097496586,0.00014535208,0.00069811434],"category_scores_gemma":[0.000261735,0.0002974318,0.00014331561,0.001029316,0.00016821604,0.0014341451,0.0005279158,0.0003096745,0.0016619081],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052046294,0.0000532515,0.00092706655,0.000018823146,0.000027803902,0.000057297428,0.0044560977,0.8276007,0.00030442493,0.15259059,0.006453012,0.007505709],"study_design_scores_gemma":[0.000408084,0.00032669344,0.0027663321,0.00002220643,0.0000056496424,0.00016430665,0.000025576466,0.9860527,0.0007177355,0.0002160518,0.008936278,0.00035838026],"about_ca_topic_score_codex":0.00013753866,"about_ca_topic_score_gemma":0.0000022483975,"teacher_disagreement_score":0.90188277,"about_ca_system_score_codex":0.00021139767,"about_ca_system_score_gemma":0.00061299047,"threshold_uncertainty_score":0.9999478},"labels":[],"label_agreement":null},{"id":"W7124167367","doi":"10.65109/hsjq2262","title":"Distributed multiagent resource allocation with adaptive preemption for dynamic tasks","year":2014,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Preemption; Resource allocation; Task (project management); Resource (disambiguation); Multi-agent system","score_opus":0.01697424960136613,"score_gpt":0.24673887685720808,"score_spread":0.22976462725584196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124167367","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":[0.0012759164,0.000029407998,0.99383897,0.0012905528,0.00031526986,0.0018108453,0.000015330817,0.00024119236,0.0011825144],"genre_scores_gemma":[0.8560102,0.000009610684,0.139248,0.0002404383,0.000086450236,0.000112357026,0.00025413005,0.00003788455,0.004000965],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966896,0.0002534714,0.0006386048,0.0009708439,0.0007199984,0.00072744756],"domain_scores_gemma":[0.99716103,0.0004221606,0.0005730395,0.001157816,0.00045553606,0.00023043639],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008984173,0.0004432505,0.0003502875,0.00014548124,0.00046071093,0.00043772996,0.00097140024,0.00021420585,0.000040741103],"category_scores_gemma":[0.0002362865,0.0003895805,0.00012560222,0.0004959319,0.00017486635,0.000634562,0.00028291348,0.00030196857,0.0000937599],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019078546,0.00008387459,0.00014538055,0.0000678788,0.00008955325,7.093366e-7,0.00082965556,0.955107,0.00014559524,0.016029581,0.0005319105,0.026778089],"study_design_scores_gemma":[0.001747791,0.0026043893,0.002654212,0.00016651972,0.000093851435,0.0000066603116,0.0001838722,0.980834,0.00041093698,0.00010279309,0.010661037,0.00053392234],"about_ca_topic_score_codex":0.000041086616,"about_ca_topic_score_gemma":0.000040801384,"teacher_disagreement_score":0.85473424,"about_ca_system_score_codex":0.00037312848,"about_ca_system_score_gemma":0.00013615706,"threshold_uncertainty_score":0.99985564},"labels":[],"label_agreement":null},{"id":"W7124174011","doi":"10.65109/zzer3937","title":"Using bisimulation for policy transfer in MDPs","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Markov decision process; Markov process; Work (physics); Bisimulation; Transfer (computing); Partially observable Markov decision process","score_opus":0.06793892293769213,"score_gpt":0.355023856049797,"score_spread":0.2870849331121049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124174011","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":[0.0717522,0.0000052785076,0.9226857,0.0012056484,0.001205465,0.00070545136,0.0000010692082,0.00005702179,0.0023821946],"genre_scores_gemma":[0.87882316,0.0000046597816,0.11943829,0.00034027305,0.00034823825,0.0000057701363,0.0000020800621,0.000021713184,0.0010158197],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99790454,0.00004878363,0.00061522727,0.00047593008,0.00033095398,0.00062459323],"domain_scores_gemma":[0.99883497,0.0002206119,0.00006610185,0.0005987551,0.00015364177,0.00012589253],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006052939,0.00023667677,0.00023836299,0.00055089843,0.00017465712,0.00038242925,0.0006723026,0.0002441503,0.00010173697],"category_scores_gemma":[0.00023546783,0.0002463349,0.00012461061,0.0009692607,0.000089733396,0.00085758674,0.00010562273,0.00042773297,0.000029336736],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010849458,0.000028610013,0.0014283567,0.00003180176,0.000007214819,8.878719e-7,0.00077926717,0.82478476,0.007016806,0.15626542,0.000006887024,0.009639118],"study_design_scores_gemma":[0.0010274199,0.00014926029,0.001480308,0.0000302634,0.000009664931,0.000003961657,0.000009647577,0.99202937,0.0023360942,0.0010091423,0.0016255364,0.0002893211],"about_ca_topic_score_codex":0.00050062087,"about_ca_topic_score_gemma":0.00014465896,"teacher_disagreement_score":0.807071,"about_ca_system_score_codex":0.000111982736,"about_ca_system_score_gemma":0.0004761103,"threshold_uncertainty_score":0.99999887},"labels":[],"label_agreement":null},{"id":"W7124176698","doi":"10.65109/anfh7318","title":"Incremental Policy Iteration with Guaranteed Escape from Local Optima in POMDP Planning","year":2015,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Partially observable Markov decision process; Bounded function; Controller (irrigation); Markov decision process; Scale (ratio); Energy consumption; Property (philosophy); Local search (optimization)","score_opus":0.0358786020138582,"score_gpt":0.28255704684655975,"score_spread":0.24667844483270154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124176698","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":[0.068361856,0.00012893943,0.9145938,0.0010536251,0.00041111535,0.00043727973,0.0000031468503,0.00013123913,0.014879008],"genre_scores_gemma":[0.9238613,0.000004835287,0.073853076,0.001215439,0.00030434818,0.000010303933,0.000033746634,0.000033414926,0.000683505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99596727,0.00025095898,0.0008794828,0.0008498399,0.001205747,0.00084670156],"domain_scores_gemma":[0.99824154,0.00012230041,0.00032512503,0.00077275163,0.00018502612,0.0003532355],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006830819,0.00049053686,0.00045464563,0.0005732458,0.00015859732,0.0010348879,0.0010999774,0.00020435052,0.00013091031],"category_scores_gemma":[0.000108286134,0.00044725815,0.000061782266,0.0012515839,0.00020729213,0.0016977491,0.00065269804,0.00056599296,0.00027977605],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021039355,0.00008189218,0.021328213,0.000010479976,0.00004921723,0.00011843779,0.009774159,0.96039927,0.0001560343,0.0033334112,0.00039129847,0.004147165],"study_design_scores_gemma":[0.0034850729,0.0010611517,0.003877513,0.0003334992,0.000017176499,0.00003308674,0.0015109307,0.98765785,0.0008588788,0.00012400011,0.00047251326,0.00056834775],"about_ca_topic_score_codex":0.0046790307,"about_ca_topic_score_gemma":0.00009694521,"teacher_disagreement_score":0.8554995,"about_ca_system_score_codex":0.0007466091,"about_ca_system_score_gemma":0.0008855658,"threshold_uncertainty_score":0.99979794},"labels":[],"label_agreement":null},{"id":"W7124178739","doi":"10.65109/muso7637","title":"Quasi deterministic POMDPs and DecPOMDPs","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Laval","funders":"","keywords":"Observability; Observable; Extension (predicate logic); Class (philosophy); Markov decision process; Markov chain; Markov process","score_opus":0.012205200261922752,"score_gpt":0.25202832314467016,"score_spread":0.2398231228827474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124178739","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":[0.031407923,0.00007253057,0.9293935,0.0008704349,0.003693939,0.0003361209,7.499483e-7,0.00032270068,0.033902157],"genre_scores_gemma":[0.87482154,0.00008198733,0.116817206,0.0006497087,0.00024352517,0.0000063839166,9.3361035e-7,0.000028907205,0.007349806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99698573,0.00008983154,0.00065669353,0.0008640041,0.0005876025,0.0008161513],"domain_scores_gemma":[0.99723315,0.0004360627,0.00025279468,0.0014023077,0.00016389287,0.00051181944],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00064479123,0.00042942786,0.0003702588,0.00018759242,0.00045046792,0.0012908006,0.0013512991,0.00029833763,0.0005197821],"category_scores_gemma":[0.00041493826,0.00041422222,0.00009690086,0.00037316795,0.000330649,0.00069449726,0.0010910359,0.0009661977,0.0007238974],"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":[0.00003273788,0.0008266102,0.01923723,0.00040135204,0.000234074,0.00034635016,0.0070779133,0.009438531,0.0049294755,0.67508066,0.002215619,0.28017944],"study_design_scores_gemma":[0.0005129144,0.00077463716,0.0042494247,0.000030041434,0.000045341483,0.00021521372,0.000036477446,0.9714074,0.0004020917,0.000624135,0.021126559,0.0005757668],"about_ca_topic_score_codex":0.000033135315,"about_ca_topic_score_gemma":0.000029589024,"teacher_disagreement_score":0.96196884,"about_ca_system_score_codex":0.000026470438,"about_ca_system_score_gemma":0.0002592227,"threshold_uncertainty_score":0.99983096},"labels":[],"label_agreement":null},{"id":"W7124181186","doi":"10.65109/apft3995","title":"Expectation-Maximization for Inverse Reinforcement Learning with Hidden Data","year":2016,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Missing data; Reinforcement learning; Task (project management); Trajectory; Feature (linguistics); Key (lock); State space; State (computer science); Sorting","score_opus":0.049844816202744585,"score_gpt":0.27516061794495544,"score_spread":0.22531580174221086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124181186","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":[0.00031149687,0.00002209763,0.99002016,0.002260161,0.00059371366,0.0012368528,0.0000039468814,0.00027384958,0.00527773],"genre_scores_gemma":[0.63451964,0.00021447829,0.29127067,0.0004201512,0.0003238992,0.000086031585,0.00019230168,0.000081144426,0.07289169],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99602,0.0001393527,0.0008384814,0.0012532679,0.0009402005,0.0008086726],"domain_scores_gemma":[0.9954033,0.0006693319,0.0007406207,0.002356217,0.0005818061,0.0002487462],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007865781,0.00044757884,0.00035484528,0.00026376444,0.00059289817,0.0005512045,0.0025006223,0.00015195043,0.00071092736],"category_scores_gemma":[0.0009349517,0.00030264212,0.000071020884,0.0005889045,0.00018324085,0.0037162928,0.0012954148,0.00019022053,0.00031119992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012879563,0.000028864297,0.0018837941,0.00007597026,0.00015780391,0.0000048996108,0.0016239433,0.93789184,0.00020803232,0.01576092,0.00363481,0.038600344],"study_design_scores_gemma":[0.0026808553,0.0012105538,0.00013583405,0.000306339,0.00008057061,0.000007505416,0.0004103833,0.97919494,0.0005339357,0.00008309206,0.014761535,0.00059447385],"about_ca_topic_score_codex":0.000033167693,"about_ca_topic_score_gemma":0.000022390162,"teacher_disagreement_score":0.6987495,"about_ca_system_score_codex":0.0002462042,"about_ca_system_score_gemma":0.00050163636,"threshold_uncertainty_score":0.99994254},"labels":[],"label_agreement":null},{"id":"W7124207829","doi":"10.65109/ccmg9392","title":"From Global Selective Perception to Local Selective Perception","year":2004,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Laval","funders":"","keywords":"Reinforcement learning; Perception; Active perception; Reinforcement; Work (physics); Control (management)","score_opus":0.012729836536510363,"score_gpt":0.26972374028830953,"score_spread":0.25699390375179915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124207829","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":[0.07214452,0.000014967926,0.9088469,0.001835187,0.0016070951,0.0010566221,0.000015044813,0.00045464627,0.01402501],"genre_scores_gemma":[0.88250434,0.000022750291,0.11347971,0.0019415568,0.00076092995,0.000031656866,0.000031317006,0.000037466605,0.0011902652],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940504,0.00031951017,0.0008840581,0.0019531026,0.0014647798,0.001328175],"domain_scores_gemma":[0.9970747,0.00008797872,0.00028002038,0.0009960168,0.00088624796,0.0006750195],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042875335,0.00077807053,0.00059778395,0.00022995698,0.00067295204,0.00087270554,0.0014318436,0.0005198641,0.00095754315],"category_scores_gemma":[0.00016324315,0.00083481456,0.00029653186,0.002588486,0.00026748527,0.0016432471,0.00079958513,0.00080329936,0.008312101],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000119440294,0.0001741614,0.0010494189,0.000010747497,0.00012605556,0.000013798459,0.018591132,0.9233431,0.0016803914,0.0028254627,0.0013189828,0.050747287],"study_design_scores_gemma":[0.0022044266,0.0031951687,0.15653536,0.00021148665,0.00013677705,0.0000531681,0.006614854,0.8230998,0.00076734764,0.0051947436,0.00048043657,0.00150641],"about_ca_topic_score_codex":0.005405659,"about_ca_topic_score_gemma":0.0003444888,"teacher_disagreement_score":0.81035984,"about_ca_system_score_codex":0.007465054,"about_ca_system_score_gemma":0.0009124635,"threshold_uncertainty_score":0.9999557},"labels":[],"label_agreement":null},{"id":"W7124240193","doi":"10.65109/jsvi2318","title":"FedFormer: Contextual Federation with Attention in Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Waterloo","funders":"","keywords":"Reinforcement learning; Aggregate (composite); Reinforcement; Transformer","score_opus":0.02335311171161477,"score_gpt":0.2575649258979304,"score_spread":0.23421181418631562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124240193","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":[0.03056482,0.000020988158,0.9366148,0.0012417262,0.0006001518,0.0008340199,1.5386267e-7,0.000515341,0.029607985],"genre_scores_gemma":[0.9291329,0.00016522409,0.0017337092,0.00022159268,0.00009178789,0.00004634804,0.00006714655,0.000037127065,0.06850416],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99550664,0.00023325883,0.0010595315,0.00083730987,0.0012576298,0.0011056426],"domain_scores_gemma":[0.9983868,0.00017969101,0.00044632496,0.0005655784,0.00024296467,0.0001786522],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014177846,0.0004532164,0.00041635186,0.0007215359,0.000736035,0.0013514422,0.00062982144,0.00019600852,0.0003171446],"category_scores_gemma":[0.00016751056,0.0004179366,0.00008763638,0.0023918487,0.00012086405,0.0018155904,0.00048681407,0.0007863611,0.002180716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058656857,0.000023701945,0.013132091,0.00006378045,0.000046079484,0.00004981085,0.0017243263,0.9568469,0.00027661215,0.014620667,0.00046840624,0.012688993],"study_design_scores_gemma":[0.0019303736,0.0016779039,0.014989796,0.00030356157,0.000016671389,0.000013708807,0.0013342568,0.97646606,0.0001601909,0.000024267876,0.0025378999,0.0005453063],"about_ca_topic_score_codex":0.00020543601,"about_ca_topic_score_gemma":0.00014093675,"teacher_disagreement_score":0.9348811,"about_ca_system_score_codex":0.0003669576,"about_ca_system_score_gemma":0.00028019134,"threshold_uncertainty_score":0.99982727},"labels":[],"label_agreement":null},{"id":"W7124241411","doi":"10.65109/ldqz4728","title":"Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; University of Alberta; Vector Institute","funders":"","keywords":"Reinforcement learning; Sample complexity; Set (abstract data type); Sample (material); Convergence (economics); Action (physics); Error-driven learning; State (computer science)","score_opus":0.05499245184937777,"score_gpt":0.27924540457871294,"score_spread":0.22425295272933518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124241411","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":[0.08978131,0.00016407849,0.9008216,0.00049024646,0.0025781582,0.0012939187,0.0000011750104,0.0014111163,0.0034583982],"genre_scores_gemma":[0.92446214,0.0010413916,0.008062466,0.00024180269,0.00017076716,0.00009970058,0.00015362693,0.00013373514,0.06563434],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9889557,0.001084068,0.0025201486,0.002262042,0.0025155253,0.002662559],"domain_scores_gemma":[0.99531853,0.0013004061,0.0010051324,0.0014668647,0.00026675826,0.0006423268],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0027826098,0.0011238436,0.0010713831,0.001578277,0.0009669736,0.0011828291,0.0026348485,0.000617789,0.001462646],"category_scores_gemma":[0.0022299595,0.0012390806,0.00043814507,0.0036842497,0.00018918213,0.0014340106,0.0041078688,0.0036907033,0.009335685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043465145,0.000096098745,0.14069223,0.000060585175,0.00012871038,0.00024800992,0.012255914,0.83450764,0.00054906355,0.00026805708,0.00020532354,0.010944868],"study_design_scores_gemma":[0.0041517904,0.0006597966,0.05610912,0.00040725,0.000035929857,0.0000040830773,0.0041367235,0.9243468,0.0005833302,0.000019451492,0.008279756,0.0012659461],"about_ca_topic_score_codex":0.0032248346,"about_ca_topic_score_gemma":0.00031534312,"teacher_disagreement_score":0.89275914,"about_ca_system_score_codex":0.00094808254,"about_ca_system_score_gemma":0.00040844348,"threshold_uncertainty_score":0.999854},"labels":[],"label_agreement":null},{"id":"W7124241732","doi":"10.65109/xgyf2237","title":"Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Thales (Canada)","funders":"","keywords":"Interpretability; Reinforcement learning; Robustness (evolution); Function (biology); Heuristic; Preference","score_opus":0.028391592682051756,"score_gpt":0.21991690947366765,"score_spread":0.19152531679161588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124241732","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":[0.0013478547,0.00008084009,0.9207791,0.0008600441,0.0017807333,0.0010388069,0.0000037013813,0.0005877181,0.073521174],"genre_scores_gemma":[0.84235144,0.000011306936,0.014613089,0.0008313879,0.0000876833,0.00024538927,0.000093463226,0.00006619223,0.14170004],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9928274,0.00066130474,0.0011739606,0.0014884509,0.002399022,0.0014498567],"domain_scores_gemma":[0.9962199,0.00026381266,0.00088694156,0.0018613378,0.00035048186,0.00041756555],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000968532,0.0008055867,0.00067698036,0.0006345236,0.0029826127,0.0009948167,0.0024350411,0.00014132145,0.01569544],"category_scores_gemma":[0.00013764194,0.0007470221,0.000276205,0.002222819,0.0002536535,0.0009144087,0.002136319,0.002443864,0.00018234155],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003556256,0.00007184241,0.0027641447,0.000059845464,0.00021653312,0.000028758015,0.0018162364,0.9808074,0.00012639562,0.0022139938,0.002541288,0.008997927],"study_design_scores_gemma":[0.0019840444,0.0054685483,0.00033518014,0.000099188124,0.00014012054,0.000042981894,0.0010662029,0.91934186,0.00033573818,0.000028429846,0.07024059,0.00091709435],"about_ca_topic_score_codex":0.00021265504,"about_ca_topic_score_gemma":0.000039984447,"teacher_disagreement_score":0.906166,"about_ca_system_score_codex":0.0010094537,"about_ca_system_score_gemma":0.0014253232,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W7124242323","doi":"10.65109/kkdn1922","title":"Dynamic Reward Sharing to Enhance Learning in the Context of Multiagent Teams","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Process (computing); Context (archaeology); Function (biology); Social learning; Hyperparameter; Policy learning","score_opus":0.01162814992993511,"score_gpt":0.30194284473227656,"score_spread":0.29031469480234146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124242323","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":[0.05735659,0.00023266174,0.92397743,0.003932325,0.0007388925,0.0008483838,3.1079477e-7,0.00007052319,0.0128429],"genre_scores_gemma":[0.9628615,0.00009542006,0.011640325,0.001935419,0.000012328318,0.000030437102,0.0000012934302,0.000013254403,0.023410022],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962425,0.000403359,0.0011253736,0.0008530189,0.0006706087,0.0007051038],"domain_scores_gemma":[0.9973983,0.00070666295,0.00031182694,0.001321404,0.00017880985,0.000082980674],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002532797,0.00033004745,0.00046140098,0.00043993228,0.00029413568,0.00035891894,0.0033015576,0.0001327624,0.00008380367],"category_scores_gemma":[0.001059471,0.00027190603,0.00015014099,0.0019409071,0.00011693859,0.00032317158,0.0016667218,0.0011298856,0.00014307206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021243655,0.00006916041,0.0070858486,0.00012573076,0.000039961,0.0000090344265,0.02258767,0.8860733,0.0009862054,0.008660826,0.00016580398,0.07417521],"study_design_scores_gemma":[0.00032169672,0.00026953506,0.0052880147,0.0007253216,0.000016834654,0.0000016808178,0.005759508,0.98168945,0.0024038544,0.000056105902,0.0032026463,0.0002653555],"about_ca_topic_score_codex":0.0005445102,"about_ca_topic_score_gemma":0.00021366781,"teacher_disagreement_score":0.91233706,"about_ca_system_score_codex":0.00029660674,"about_ca_system_score_gemma":0.00023483366,"threshold_uncertainty_score":0.9999733},"labels":[],"label_agreement":null},{"id":"W7124247083","doi":"10.65109/egea9379","title":"β-DQN: Improving Deep Q-Learning By Evolving the Behavior","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada); University of Alberta","funders":"","keywords":"Generality; Simple (philosophy); Function (biology); Range (aeronautics); Population; Overhead (engineering)","score_opus":0.0075758198450625105,"score_gpt":0.24484235876922628,"score_spread":0.23726653892416377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124247083","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":[0.0008879095,0.0024447485,0.9480663,0.0016821596,0.002545188,0.0010013158,4.4347726e-7,0.00038631566,0.04298565],"genre_scores_gemma":[0.87906915,0.00014848914,0.012999378,0.0013994604,0.00012634406,0.00013697999,0.000004787595,0.00004053857,0.10607486],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952721,0.0004543608,0.0010235811,0.001077138,0.00090582494,0.0012669701],"domain_scores_gemma":[0.9965963,0.0007813605,0.00047920275,0.0016042449,0.00036152184,0.00017741807],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015135867,0.0005670319,0.00042771106,0.0002417751,0.0021499784,0.0028951906,0.003438134,0.00028138026,0.0008135707],"category_scores_gemma":[0.00087661366,0.0004492976,0.00027199605,0.0015584562,0.0002971606,0.0011107911,0.002657391,0.0017816115,0.0003149953],"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":[0.000010033022,0.00012644035,0.017169178,0.00015647543,0.00015822667,0.000025519188,0.0021933466,0.37507895,0.004119974,0.021174528,0.007926283,0.571861],"study_design_scores_gemma":[0.00042346428,0.00021175586,0.0022761964,0.000120517754,0.00015812335,0.00000830289,0.0006318919,0.9762239,0.0009711293,0.000035995057,0.018451804,0.00048696183],"about_ca_topic_score_codex":0.0002835602,"about_ca_topic_score_gemma":0.000012353652,"teacher_disagreement_score":0.9350669,"about_ca_system_score_codex":0.00032490495,"about_ca_system_score_gemma":0.00032311716,"threshold_uncertainty_score":0.99979585},"labels":[],"label_agreement":null},{"id":"W7124247225","doi":"10.65109/vzsi9543","title":"Hiking up that HILL with Cogment-Verse: Train &amp; Operate Multi-agent Systems Learning from Humans","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Network for Business Sustainability; Institut national de psychiatrie légale Philippe-Pinel","funders":"","keywords":"Variety (cybernetics); Reinforcement learning; Generalization; Context (archaeology); Formalism (music); Applications of artificial intelligence","score_opus":0.12597040934911097,"score_gpt":0.290253081006849,"score_spread":0.16428267165773802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124247225","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":[0.03314126,0.00030134173,0.95457476,0.00050503516,0.005172735,0.0013462587,0.000010713275,0.001393334,0.0035545672],"genre_scores_gemma":[0.8242202,0.00037996727,0.009934323,0.00026199996,0.0002988325,0.000069497226,0.0001639864,0.00014263348,0.16452856],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9915737,0.0011699537,0.0012692744,0.001993096,0.002062128,0.0019318323],"domain_scores_gemma":[0.9960607,0.00058793306,0.0007908814,0.0016789798,0.00031403257,0.00056743354],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0023978576,0.001014537,0.00097423804,0.0005380178,0.0015897141,0.0033704524,0.0022144972,0.00035451472,0.00096209336],"category_scores_gemma":[0.00018573624,0.0008986808,0.000256745,0.0016847576,0.00027412237,0.0014295859,0.0013686243,0.001482212,0.004668406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028604005,0.000051334595,0.0068794247,0.00012611802,0.0003982585,0.00015088888,0.024155827,0.963138,0.00082525925,0.0012678595,0.0014147818,0.0015636667],"study_design_scores_gemma":[0.0026026883,0.0003222971,0.0019730644,0.0008670073,0.0001068299,0.000014923444,0.009011345,0.9501884,0.0001941471,0.0000027147632,0.03353098,0.001185597],"about_ca_topic_score_codex":0.0015017997,"about_ca_topic_score_gemma":0.00016335856,"teacher_disagreement_score":0.94464046,"about_ca_system_score_codex":0.00052888045,"about_ca_system_score_gemma":0.00031313847,"threshold_uncertainty_score":0.9999512},"labels":[],"label_agreement":null},{"id":"W7124253663","doi":"10.65109/rjqi2619","title":"Off-Policy Evolutionary Reinforcement Learning with Maximum Mutations","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Toronto","funders":"","keywords":"Reinforcement learning; Scalability; Hyperparameter; Learning classifier system; Population; Evolutionary algorithm; Evolutionary computation; Sensitivity (control systems)","score_opus":0.015079677678669174,"score_gpt":0.24667902275559514,"score_spread":0.23159934507692598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124253663","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":[0.0005559473,0.00026116622,0.90156734,0.0049295016,0.00068089,0.00079047616,0.000002583411,0.00042246035,0.09078965],"genre_scores_gemma":[0.84849405,0.00009650531,0.020382723,0.0012545339,0.00023401607,0.0002064291,0.00009588975,0.00006381336,0.12917203],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99373734,0.0005364125,0.0009841991,0.0010239545,0.002446992,0.001271078],"domain_scores_gemma":[0.99717396,0.0002467129,0.000680267,0.0012056722,0.00033824894,0.0003551089],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000780804,0.00055223063,0.00041352163,0.0008892949,0.004067635,0.00049117254,0.001904883,0.000085823645,0.0058267354],"category_scores_gemma":[0.00018243435,0.0005727425,0.00019094693,0.003208334,0.00031085816,0.0010543239,0.0030098802,0.0016213249,0.0004941973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051709983,0.000086299806,0.0011350521,0.000031740892,0.0001444007,0.00006548025,0.0026792197,0.90895796,0.0000188994,0.07566661,0.0019622857,0.009200373],"study_design_scores_gemma":[0.0010712205,0.0024129888,0.0007843952,0.000031075546,0.00005098668,0.00020532586,0.0013999441,0.8621307,0.000020855128,0.00038961627,0.13083959,0.0006633317],"about_ca_topic_score_codex":0.00032419426,"about_ca_topic_score_gemma":0.000003954885,"teacher_disagreement_score":0.8811846,"about_ca_system_score_codex":0.0015486489,"about_ca_system_score_gemma":0.0023550272,"threshold_uncertainty_score":0.9996724},"labels":[],"label_agreement":null},{"id":"W7124257082","doi":"10.65109/ehmm3042","title":"Search-Improved Game-Theoretic Multiagent Reinforcement Learning in General and Negotiation Games","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Negotiation; Generative grammar; Bayesian probability; Test (biology); Representation (politics); Bayesian inference; Social learning; Reinforcement","score_opus":0.0221885923684442,"score_gpt":0.27029056563293824,"score_spread":0.24810197326449404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124257082","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":[0.14424376,0.00015594067,0.84874344,0.001554032,0.00080188666,0.0011330803,4.0195036e-7,0.0005214381,0.0028459982],"genre_scores_gemma":[0.95891446,0.0017685116,0.0054568932,0.00035146656,0.00014580146,0.000044962737,0.00003033894,0.000056134097,0.033231452],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994535,0.0005400681,0.001218497,0.0011686721,0.0010310414,0.0015066711],"domain_scores_gemma":[0.9979499,0.00037067794,0.00032680578,0.0008024621,0.00018364195,0.0003665302],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021959126,0.00055531395,0.00052223774,0.0009685073,0.00033231502,0.00094777026,0.0008451207,0.00025375094,0.00035176228],"category_scores_gemma":[0.00051309745,0.0005722512,0.00013399961,0.001950742,0.000317597,0.00091052667,0.0016933341,0.0009973377,0.0005240455],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028981854,0.000024950292,0.006432579,0.00016138334,0.00004275226,0.000035939665,0.008074931,0.94010484,0.0014399685,0.015721068,0.00011686222,0.027815735],"study_design_scores_gemma":[0.0016920725,0.00063773606,0.017336912,0.00015771958,0.000021400341,0.0000081179405,0.0006922274,0.97626597,0.001381125,0.0001345475,0.001059061,0.00061310775],"about_ca_topic_score_codex":0.0003337971,"about_ca_topic_score_gemma":0.0000174427,"teacher_disagreement_score":0.8432866,"about_ca_system_score_codex":0.00033189144,"about_ca_system_score_gemma":0.000262111,"threshold_uncertainty_score":0.9996729},"labels":[],"label_agreement":null},{"id":"W7124264120","doi":"10.65109/zliw2815","title":"Mastering Robot Control through Point-based Reinforcement Learning with Pre-training","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Robot; Leverage (statistics); Robotics; Limiting; Rendering (computer graphics)","score_opus":0.026406348197170807,"score_gpt":0.2616624150467427,"score_spread":0.2352560668495719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124264120","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":[0.00033014585,0.00066992507,0.9552434,0.002921948,0.0018650291,0.0012195226,9.762961e-7,0.0016077728,0.036141284],"genre_scores_gemma":[0.87879205,0.000045687146,0.095468834,0.0013932004,0.00035975582,0.0000771665,0.000011740433,0.00014899012,0.023702566],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99227446,0.00034852084,0.0015692313,0.0018340074,0.0019179069,0.0020558783],"domain_scores_gemma":[0.9966751,0.00080003415,0.0004747813,0.0013743163,0.0002794819,0.0003962922],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0015676877,0.0011108106,0.00091860397,0.00043403707,0.00079838285,0.0040677665,0.0016146618,0.00029849814,0.0014634335],"category_scores_gemma":[0.00016720033,0.00095366326,0.00036167746,0.0014980313,0.00033612782,0.0021421867,0.00058229093,0.0018520827,0.00061130145],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013623468,0.000024880414,0.00024371243,0.00062073977,0.0004419515,0.00029108685,0.008985128,0.95606226,0.00049887097,0.01428635,0.00016604966,0.018242722],"study_design_scores_gemma":[0.00221499,0.0027663533,0.000097717886,0.0028630302,0.000210721,0.00009695398,0.00073229044,0.9749413,0.00065431924,0.000052123196,0.014129009,0.0012411812],"about_ca_topic_score_codex":0.000120344266,"about_ca_topic_score_gemma":0.000008436053,"teacher_disagreement_score":0.8784619,"about_ca_system_score_codex":0.00048214456,"about_ca_system_score_gemma":0.0011533058,"threshold_uncertainty_score":0.9994494},"labels":[],"label_agreement":null},{"id":"W7124267618","doi":"10.65109/odcq7385","title":"Centralized Model and Exploration Policy for Multi-Agent RL","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Vector Institute","funders":"","keywords":"Sample (material); Key (lock); Polynomial; Sample complexity; Robot; Swarm behaviour","score_opus":0.12786196221678384,"score_gpt":0.33449133675714904,"score_spread":0.2066293745403652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124267618","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":[0.0006247833,0.00010637038,0.9919884,0.0047568623,0.000632472,0.0012224228,0.000012322837,0.00011940128,0.0005369191],"genre_scores_gemma":[0.56239927,0.00026631713,0.40200695,0.0020706146,0.00012804985,0.00031056692,0.000030459862,0.000039266277,0.0327485],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99750453,0.00014620919,0.0005353432,0.0006277533,0.00054307823,0.0006430954],"domain_scores_gemma":[0.99879915,0.00007342192,0.00024528799,0.0005596981,0.00011543964,0.00020699362],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005541653,0.00026190118,0.00025042018,0.00023760312,0.0010620444,0.00043936825,0.0007026567,0.000055023298,0.00011460966],"category_scores_gemma":[0.00012416873,0.00028851224,0.00011590952,0.00046190922,0.000062751904,0.0008850948,0.0012579088,0.00022930634,0.0000134039665],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028366647,0.00007602939,0.000035214667,0.00003620883,0.000025847145,0.0000010706101,0.0047446894,0.8765028,0.0002000749,0.111619174,0.0010472671,0.0056832265],"study_design_scores_gemma":[0.002103404,0.0003524584,0.000030469131,0.0000069374455,0.000022163274,0.00000465685,0.00036894114,0.9884215,0.00014167359,0.00091374357,0.0073099122,0.0003241183],"about_ca_topic_score_codex":0.00007028197,"about_ca_topic_score_gemma":0.000004199866,"teacher_disagreement_score":0.5899815,"about_ca_system_score_codex":0.00032033003,"about_ca_system_score_gemma":0.0004191022,"threshold_uncertainty_score":0.9999567},"labels":[],"label_agreement":null},{"id":"W7124272070","doi":"10.65109/emmn5327","title":"Neural Population Learning beyond Symmetric Zero-Sum Games","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Google (Canada)","funders":"","keywords":"Convergence (economics); Suite; Population; Domain (mathematical analysis); Transfer of learning; Scale (ratio); Control (management); Stability (learning theory)","score_opus":0.017970437138648165,"score_gpt":0.26461794517087306,"score_spread":0.2466475080322249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124272070","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":[0.0068538315,0.0030812516,0.9439968,0.001634205,0.007001653,0.00036295663,7.0068023e-7,0.0011589734,0.035909638],"genre_scores_gemma":[0.9225474,0.0002894872,0.008840471,0.0002940575,0.00038517712,0.000007581276,0.000025346408,0.000063551095,0.067546934],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952658,0.000318202,0.00096227427,0.0012016947,0.0012366866,0.0010153545],"domain_scores_gemma":[0.9979848,0.00055302674,0.00022161515,0.00076222036,0.0002014023,0.00027690013],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008947849,0.0005344134,0.00042813589,0.0012663779,0.0005040785,0.0037632508,0.0011154115,0.00026513272,0.0005804429],"category_scores_gemma":[0.00054522627,0.0005168289,0.0002696432,0.0053992714,0.000091910624,0.0022193003,0.0008548439,0.0013051338,0.0016921717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003464052,0.000015106811,0.0043876986,0.00018600562,0.000063740765,0.000055064895,0.00058022275,0.7498056,0.00004679531,0.077511646,0.0013931026,0.16595149],"study_design_scores_gemma":[0.00018302292,0.00034031077,0.0147007555,0.00018261558,0.00006954132,0.00004969902,0.00004655531,0.97069615,0.000058688653,0.000770924,0.012322743,0.00057901884],"about_ca_topic_score_codex":0.00021890886,"about_ca_topic_score_gemma":0.0000028209163,"teacher_disagreement_score":0.93515635,"about_ca_system_score_codex":0.00027384065,"about_ca_system_score_gemma":0.00015251775,"threshold_uncertainty_score":0.9997283},"labels":[],"label_agreement":null},{"id":"W7124275932","doi":"10.65109/dxvr3975","title":"Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning","year":2017,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Function approximation; Nonlinear system; Function (biology); Class (philosophy); Q-learning; Control theory (sociology)","score_opus":0.034713047450533524,"score_gpt":0.2929229350638085,"score_spread":0.258209887613275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124275932","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":[0.0018880955,0.000037024427,0.979401,0.0010639624,0.0024944562,0.002359064,0.0000010290079,0.00015170797,0.012603654],"genre_scores_gemma":[0.9284223,0.00007836046,0.05122981,0.00025847816,0.000461966,0.00020363177,0.000056319015,0.00005305648,0.019236129],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956833,0.00012625406,0.0012496028,0.0009512988,0.00088208646,0.0011074465],"domain_scores_gemma":[0.99618906,0.00027401137,0.00106894,0.0018154169,0.00043698144,0.00021561107],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001951365,0.00050776213,0.00053931517,0.0003838396,0.0017956564,0.0025117155,0.0018133932,0.00032676954,0.00017996105],"category_scores_gemma":[0.0018256021,0.00054186094,0.00022558733,0.00022259093,0.00017736726,0.0033262218,0.00085690996,0.0007131349,0.00021362676],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013429434,0.00005886154,0.0022352724,0.00039947903,0.000057131754,0.0000032035075,0.00088098535,0.94535226,0.00025647893,0.022923907,0.00019227956,0.027505867],"study_design_scores_gemma":[0.0024019757,0.0015123276,0.0024720218,0.00031643655,0.000056794517,0.0000029573387,0.00017726822,0.97982323,0.0006263904,0.00047156532,0.011544028,0.0005950001],"about_ca_topic_score_codex":0.00009997684,"about_ca_topic_score_gemma":0.000028913082,"teacher_disagreement_score":0.9281712,"about_ca_system_score_codex":0.00040466405,"about_ca_system_score_gemma":0.00027851088,"threshold_uncertainty_score":0.9997033},"labels":[],"label_agreement":null},{"id":"W7124283399","doi":"10.65109/cwyu2303","title":"Two-Level Actor-Critic Using Multiple Teachers","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Vector Institute; University of Alberta","funders":"","keywords":"Inefficiency; Variety (cybernetics); Sample (material); Domain (mathematical analysis); Action (physics); Forcing (mathematics)","score_opus":0.1396883853120315,"score_gpt":0.336168527520682,"score_spread":0.19648014220865048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124283399","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":[0.035599906,0.000049439634,0.95204145,0.0006074743,0.0033573853,0.00042229262,0.0000040144464,0.00087377924,0.0070442874],"genre_scores_gemma":[0.8687646,0.000033064913,0.10674201,0.00043276255,0.00030776308,0.0000062417907,0.000008460751,0.000064756394,0.02364037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99519455,0.00026329677,0.00083877926,0.0010133685,0.0011267738,0.0015632214],"domain_scores_gemma":[0.9970341,0.00067142176,0.00023363736,0.0014364003,0.00021346299,0.00041098945],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010913115,0.00052277464,0.00045218912,0.00051313976,0.0006617896,0.0010287107,0.0019410391,0.00021011528,0.00045483472],"category_scores_gemma":[0.00087047025,0.0005549085,0.00025626904,0.0023521334,0.0002436636,0.0012509502,0.001558352,0.000710086,0.0033394778],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042559145,0.000034796496,0.0071726744,0.000053395393,0.000080553364,0.00006996172,0.0035873647,0.96877843,0.0027482377,0.0038530405,0.0009379444,0.012679362],"study_design_scores_gemma":[0.0010388454,0.00010299323,0.0030588207,0.0001279911,0.00004255468,0.000018882913,0.00075649313,0.99174637,0.00076154026,0.000096945485,0.0015676795,0.000680873],"about_ca_topic_score_codex":0.00048009242,"about_ca_topic_score_gemma":0.000021210702,"teacher_disagreement_score":0.8452994,"about_ca_system_score_codex":0.0003396288,"about_ca_system_score_gemma":0.00042586555,"threshold_uncertainty_score":0.99969023},"labels":[],"label_agreement":null},{"id":"W7124285129","doi":"10.65109/vyhj2561","title":"Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Montréal","funders":"","keywords":"Dual (grammatical number); Process (computing); Reinforcement learning; Computation; Multi-agent system","score_opus":0.009116201324229783,"score_gpt":0.2322789746532104,"score_spread":0.22316277332898063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124285129","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":[0.005304886,0.0002152031,0.8964873,0.0018623286,0.0010934706,0.00061742216,3.0410385e-7,0.0004162312,0.094002835],"genre_scores_gemma":[0.65534073,0.0000738999,0.06336686,0.0009864426,0.000090038906,0.000018399667,0.0000056234635,0.000034074706,0.28008395],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952829,0.00041191827,0.00085294514,0.001271421,0.0010411912,0.0011396189],"domain_scores_gemma":[0.9971499,0.0003664434,0.00035343872,0.0014528666,0.00041614083,0.0002612225],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008309105,0.0006364456,0.0006054567,0.00041781794,0.00069434114,0.0011439628,0.0012312235,0.00028993428,0.0007494005],"category_scores_gemma":[0.0002694027,0.00054276135,0.00017515139,0.001560131,0.00025420866,0.00063025544,0.0012977986,0.0011274139,0.00058050355],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009001272,0.000099954996,0.0041235127,0.00011003796,0.00034566343,0.00012886469,0.0012556505,0.9280711,0.0007019554,0.047682505,0.0023308306,0.015059944],"study_design_scores_gemma":[0.002079721,0.00065340364,0.0029025404,0.0003608824,0.00012962424,0.000035948156,0.00026128368,0.9455129,0.0026089347,0.000059823935,0.044736464,0.0006585016],"about_ca_topic_score_codex":0.00011413303,"about_ca_topic_score_gemma":0.0000126270315,"teacher_disagreement_score":0.83312047,"about_ca_system_score_codex":0.00022119409,"about_ca_system_score_gemma":0.0006460168,"threshold_uncertainty_score":0.99989295},"labels":[],"label_agreement":null},{"id":"W7124289677","doi":"10.65109/ldoy7418","title":"Leveraging Sub-Optimal Data for Human-in-the-Loop Reinforcement Learning","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Function (biology); Data collection; Human-in-the-loop; Temporal difference learning; Work (physics)","score_opus":0.09075955790988156,"score_gpt":0.3330438801573506,"score_spread":0.24228432224746904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124289677","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":[0.002041674,0.001000104,0.9806329,0.0026117994,0.0020884252,0.0014765403,0.000002783711,0.00038680056,0.009758984],"genre_scores_gemma":[0.95408684,0.00022598193,0.013899356,0.00082129304,0.00065643206,0.00008154121,0.0002465471,0.000083710125,0.029898321],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99341965,0.0003130046,0.0014621875,0.0018900465,0.001354915,0.0015601778],"domain_scores_gemma":[0.99502295,0.0012008038,0.0002554472,0.003214493,0.00014493037,0.00016135648],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0055081327,0.00065640226,0.0005088851,0.00053341396,0.0010451551,0.0045266245,0.0065783174,0.00020736422,0.00028066838],"category_scores_gemma":[0.00037876717,0.00055664516,0.00024061339,0.0013446476,0.00017873212,0.0023753543,0.0030100362,0.0015337579,0.00039077838],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013092526,0.00003049724,0.00009491605,0.00042928656,0.000111706424,0.000092376846,0.0044741933,0.9277676,0.00030471117,0.045981348,0.0069664745,0.013733806],"study_design_scores_gemma":[0.00065229245,0.00053553534,0.00004384608,0.0005029039,0.000090375426,0.00003977345,0.0007466826,0.90240216,0.00027382118,0.00014178867,0.093926296,0.00064451265],"about_ca_topic_score_codex":0.00012009383,"about_ca_topic_score_gemma":0.000012283105,"teacher_disagreement_score":0.9667335,"about_ca_system_score_codex":0.00028243408,"about_ca_system_score_gemma":0.00044725658,"threshold_uncertainty_score":0.9996885},"labels":[],"label_agreement":null},{"id":"W7124291073","doi":"10.65109/yptr7088","title":"MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Generalization; Reinforcement learning; Focus (optics); Artificial neural network; Contrast (vision); Deep learning; Control (management)","score_opus":0.021834263229059014,"score_gpt":0.31080222842538047,"score_spread":0.28896796519632145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124291073","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":[0.0024581684,0.00026223517,0.9860392,0.0016626051,0.0026789524,0.0014740097,5.40849e-7,0.0005818425,0.0048424234],"genre_scores_gemma":[0.90674007,0.00016549729,0.024003454,0.00032674588,0.0004503028,0.00021061009,0.000101299156,0.0000935749,0.06790847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949588,0.00024386453,0.0013845584,0.0012978468,0.00085309584,0.001261843],"domain_scores_gemma":[0.99822444,0.00050327723,0.00023184203,0.00044822934,0.00022403637,0.00036820665],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013133984,0.0005743781,0.0004540123,0.0010448399,0.00092475675,0.0034721321,0.00073434523,0.0002761574,0.00066424144],"category_scores_gemma":[0.0006446293,0.00063529593,0.00026827693,0.0022651951,0.00007714285,0.0014915795,0.0005571561,0.0011381378,0.00072248536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029469229,0.000039434803,0.0007568306,0.00027084484,0.000074047064,0.00002290821,0.0058885813,0.93244994,0.00064482354,0.028097091,0.0003489477,0.031377114],"study_design_scores_gemma":[0.00044802655,0.0011288029,0.00025919353,0.00037799275,0.00005222136,0.00001448085,0.00073121476,0.9087389,0.00040977896,0.0000709657,0.08708652,0.00068188854],"about_ca_topic_score_codex":0.00016802638,"about_ca_topic_score_gemma":0.00007092818,"teacher_disagreement_score":0.9620358,"about_ca_system_score_codex":0.00084897416,"about_ca_system_score_gemma":0.00041911425,"threshold_uncertainty_score":0.9996098},"labels":[],"label_agreement":null},{"id":"W7124291660","doi":"10.65109/mrqs8697","title":"Multiagent Q-learning with Sub-Team Coordination","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Huawei Technologies (Canada)","funders":"","keywords":"Exploit; Factorization; Class (philosophy); Monotonic function; Function (biology); Ranging","score_opus":0.012972007803506958,"score_gpt":0.22243070602490664,"score_spread":0.20945869822139968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124291660","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":[0.011534986,0.00009464612,0.9635098,0.0012442023,0.001028892,0.000613574,7.85354e-7,0.00034690986,0.021626217],"genre_scores_gemma":[0.94456285,0.000021557149,0.012795338,0.00044804768,0.00007587992,0.00007088198,0.000017299108,0.00004280156,0.041965354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955371,0.0006040861,0.00055226544,0.000849937,0.0017000221,0.0007566131],"domain_scores_gemma":[0.998139,0.00019293328,0.0004913184,0.0007444751,0.000229692,0.0002025836],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011458667,0.00036637235,0.00030021847,0.00030599767,0.002033071,0.0005607147,0.0013417349,0.00005971931,0.0020290206],"category_scores_gemma":[0.00010489812,0.0003638145,0.00010791737,0.0014050179,0.00010537417,0.00067299925,0.0018989985,0.0012759018,0.00026086016],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033915512,0.00010756526,0.00463886,0.000024573219,0.00006628704,0.00003660685,0.0024680078,0.969704,0.0003052891,0.007331854,0.0020137434,0.013269302],"study_design_scores_gemma":[0.0010286815,0.0020338893,0.0011851694,0.000020706146,0.000032843567,0.00006421587,0.0010066535,0.9424774,0.0007091583,0.000012308554,0.05092186,0.00050708285],"about_ca_topic_score_codex":0.00007417752,"about_ca_topic_score_gemma":0.0000042802412,"teacher_disagreement_score":0.95071447,"about_ca_system_score_codex":0.0005473968,"about_ca_system_score_gemma":0.0003199742,"threshold_uncertainty_score":0.9998814},"labels":[],"label_agreement":null},{"id":"W7124292505","doi":"10.65109/hdvm4783","title":"Monitored Markov Decision Processes","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Markov decision process; Ask price; Partially observable Markov decision process; Formalism (music); Task (project management); Markov process","score_opus":0.01665031143990564,"score_gpt":0.2815242047084176,"score_spread":0.26487389326851196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124292505","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":[0.00054571993,0.0050998265,0.95003194,0.001003505,0.006887988,0.00030658214,0.0000011094578,0.00073814037,0.035385165],"genre_scores_gemma":[0.80913305,0.0013968134,0.13459687,0.00022964319,0.00059466047,0.000014407675,0.000002754348,0.000050099377,0.053981707],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99653506,0.00006104481,0.00066632516,0.0009769598,0.001093545,0.00066706975],"domain_scores_gemma":[0.99756926,0.00088066416,0.00008150575,0.0009278282,0.00030994148,0.00023079805],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00054206693,0.0003814502,0.00026701618,0.0003400043,0.00024983688,0.003866858,0.0016251433,0.00019149279,0.0007430856],"category_scores_gemma":[0.0005348395,0.00032360596,0.00013256812,0.0022928142,0.000111378,0.0016059218,0.0008895232,0.00046089364,0.0036226306],"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":[0.000021650583,0.00004948794,0.0005021495,0.0012254524,0.00011370116,0.00024721725,0.0015807945,0.29560074,0.000062286126,0.013710054,0.030814718,0.6560717],"study_design_scores_gemma":[0.00014048174,0.00022478528,0.0002505577,0.0010104938,0.000030587107,0.000036607118,0.000046502184,0.9277019,0.0006857571,0.0008412953,0.0686314,0.00039962554],"about_ca_topic_score_codex":0.000016406186,"about_ca_topic_score_gemma":0.0000014827302,"teacher_disagreement_score":0.8154351,"about_ca_system_score_codex":0.00013509882,"about_ca_system_score_gemma":0.0008724726,"threshold_uncertainty_score":0.9999216},"labels":[],"label_agreement":null},{"id":"W7124294995","doi":"10.65109/igaq8141","title":"Taming Multi-Agent Reinforcement Learning with Estimator Variance Reduction","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Estimator; Variance (accounting); Reinforcement learning; Variance reduction; Range (aeronautics); Sample (material); Reduction (mathematics)","score_opus":0.018782557438471854,"score_gpt":0.26857039620634454,"score_spread":0.2497878387678727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124294995","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":[0.00027921345,0.000209867,0.9669511,0.0011489998,0.0026141047,0.00096301327,1.624435e-7,0.0005045199,0.027329052],"genre_scores_gemma":[0.553359,0.00012844766,0.29001796,0.00025535724,0.00009321443,0.000050096336,0.0000067573296,0.000034675726,0.15605454],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9950272,0.00024817922,0.0011684191,0.0013598353,0.0010365851,0.001159826],"domain_scores_gemma":[0.9970803,0.00014266506,0.0006807234,0.0013757173,0.00046306787,0.00025747775],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010110161,0.0006908292,0.00056565955,0.0005025297,0.001393266,0.0011889299,0.001342342,0.00023960561,0.00027568982],"category_scores_gemma":[0.00025548588,0.00064765505,0.00015266147,0.0018885721,0.00026134445,0.00134006,0.00097115873,0.0011114689,0.00033543396],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005011758,0.00007348459,0.0005809635,0.00021487198,0.0002225681,0.000019005895,0.0015910584,0.9411837,0.00028012626,0.040942743,0.0003626197,0.0144787375],"study_design_scores_gemma":[0.0017594226,0.00056830706,0.00040835605,0.0010176058,0.00012197765,0.000030300922,0.00067470485,0.9796378,0.0020098242,0.000017149265,0.013064928,0.0006896283],"about_ca_topic_score_codex":0.00013949987,"about_ca_topic_score_gemma":0.0000014482682,"teacher_disagreement_score":0.6769331,"about_ca_system_score_codex":0.0006954734,"about_ca_system_score_gemma":0.00077516935,"threshold_uncertainty_score":0.9999068},"labels":[],"label_agreement":null},{"id":"W7124298994","doi":"10.65109/nind4053","title":"Do As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Institut national de psychiatrie légale Philippe-Pinel","funders":"","keywords":"Reinforcement learning; Automation; Robot; State (computer science); Task (project management); Robotics; Robot learning; Train","score_opus":0.0385510444796588,"score_gpt":0.2879504930576487,"score_spread":0.2493994485779899,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124298994","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":[0.0067226794,0.00008125304,0.8710034,0.00059243914,0.0009255485,0.0019547562,1.8062822e-7,0.0014840593,0.117235705],"genre_scores_gemma":[0.7700882,0.00014670103,0.085865125,0.0006732831,0.00019749864,0.00019327296,0.000030274145,0.00012790058,0.14267775],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9902124,0.00074050186,0.0019146325,0.0023026234,0.00213413,0.0026957337],"domain_scores_gemma":[0.99614066,0.0002647751,0.0004914356,0.0020050353,0.00023941307,0.00085866527],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004267755,0.001049787,0.00093057647,0.0017690333,0.0006811721,0.0015178341,0.0031737832,0.0005374193,0.00069120794],"category_scores_gemma":[0.0009855053,0.0010801986,0.0003210179,0.0056252424,0.00011099041,0.0011183283,0.0034762318,0.0022943397,0.012184233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027231516,0.00029980237,0.008247243,0.00011546432,0.00012950286,0.0000677817,0.045156423,0.9303787,0.000064845466,0.0068281693,0.000869034,0.007815845],"study_design_scores_gemma":[0.0019885881,0.0007430831,0.0035116067,0.00015347134,0.000040426075,0.000025753427,0.0038548878,0.9692798,0.000085955275,0.000018739765,0.01901789,0.0012797946],"about_ca_topic_score_codex":0.00042302295,"about_ca_topic_score_gemma":0.0000152055945,"teacher_disagreement_score":0.78513825,"about_ca_system_score_codex":0.00086750096,"about_ca_system_score_gemma":0.0004084605,"threshold_uncertainty_score":0.9995187},"labels":[],"label_agreement":null},{"id":"W7124299647","doi":"10.65109/njvx2967","title":"Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Noise (video); Focus (optics); Robot; Code (set theory); Training (meteorology); Transfer of learning; Deep learning","score_opus":0.028281085939947218,"score_gpt":0.2598315582196306,"score_spread":0.2315504722796834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124299647","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":[0.06483551,0.00003917511,0.9213515,0.00046649593,0.00073315593,0.00086953805,1.6321364e-7,0.0012764203,0.010428055],"genre_scores_gemma":[0.963608,0.00014227271,0.02373097,0.00018065509,0.00005351035,0.00008181617,0.000023125805,0.000101585756,0.0120780505],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99331933,0.00028931047,0.001542077,0.0012352542,0.0014530352,0.0021609922],"domain_scores_gemma":[0.997244,0.0004502355,0.00060985965,0.001202777,0.0001217059,0.00037142637],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017952691,0.00079026335,0.000824107,0.0013391129,0.00053467206,0.0009630975,0.0016320178,0.00022364128,0.000855497],"category_scores_gemma":[0.0003189336,0.0007672829,0.00016237884,0.004060273,0.0001944331,0.0014013774,0.0012495434,0.0012860384,0.0014557886],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018407693,0.000016038699,0.0010833114,0.0002451996,0.000074574215,0.00036295736,0.024474299,0.91275376,0.00020556987,0.0010644424,0.00001625518,0.059685215],"study_design_scores_gemma":[0.0015261743,0.00084903446,0.0043446166,0.0011485495,0.000035935183,0.000055008917,0.004119162,0.98654634,0.000071888026,0.000044499262,0.00028982453,0.0009689895],"about_ca_topic_score_codex":0.00009360758,"about_ca_topic_score_gemma":0.0001285253,"teacher_disagreement_score":0.8987725,"about_ca_system_score_codex":0.00056349084,"about_ca_system_score_gemma":0.00050841545,"threshold_uncertainty_score":0.9994778},"labels":[],"label_agreement":null},{"id":"W7124301226","doi":"10.65109/reoc9270","title":"Boosting Robustness in Preference-Based Reinforcement Learning with Dynamic Sparsity","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Boosting (machine learning); Robustness (evolution); Focus (optics); Artificial neural network; Training set","score_opus":0.029300188627362417,"score_gpt":0.24804607384247793,"score_spread":0.2187458852151155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124301226","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":[0.01764418,0.00011836831,0.9426981,0.0008866877,0.0005459133,0.0009859245,1.9441848e-7,0.00029964568,0.036820944],"genre_scores_gemma":[0.94466835,0.000041698775,0.029876543,0.00040250082,0.000016669648,0.000035318444,0.000012084328,0.000027710192,0.024919137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9945796,0.00040018983,0.0012343226,0.0013268042,0.0010453463,0.0014137133],"domain_scores_gemma":[0.99720126,0.00039168017,0.0005841965,0.0012591031,0.00036750294,0.0001962806],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013380692,0.00071014854,0.0007208917,0.00095620105,0.00066367345,0.0008643596,0.0018903696,0.0002892869,0.00020597759],"category_scores_gemma":[0.00034916375,0.00067599915,0.00012499889,0.0029239536,0.00025639613,0.0008797163,0.0010755917,0.0016137045,0.000051068433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012014462,0.000074638156,0.042101156,0.00036080525,0.00006349678,0.000043735447,0.00039796674,0.9446107,0.000026755062,0.004465562,0.000025120798,0.007709931],"study_design_scores_gemma":[0.0024600802,0.00063393766,0.011993195,0.002690621,0.000056056673,0.0000033005729,0.00023737889,0.9805359,0.00029432648,0.000023108689,0.0003441181,0.0007279449],"about_ca_topic_score_codex":0.00031779427,"about_ca_topic_score_gemma":0.00027188504,"teacher_disagreement_score":0.9270242,"about_ca_system_score_codex":0.00093321403,"about_ca_system_score_gemma":0.0015381854,"threshold_uncertainty_score":0.9995691},"labels":[],"label_agreement":null},{"id":"W7124301997","doi":"10.65109/tjqd1268","title":"PORTAL: Automatic Curricula Generation for Multiagent Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"","keywords":"Reinforcement learning; Task (project management); Curriculum; Feature (linguistics); Space (punctuation); Active learning (machine learning); Key (lock); Transfer of learning","score_opus":0.05505160572722048,"score_gpt":0.3059342340578389,"score_spread":0.2508826283306185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124301997","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":[0.004094966,0.0000730368,0.9840531,0.0009218756,0.0034344743,0.0021924847,0.0000010523639,0.001566283,0.0036627399],"genre_scores_gemma":[0.8902926,0.00025631877,0.039514285,0.00046979237,0.0006549035,0.00034535196,0.00030837528,0.00009145357,0.06806695],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994498,0.00018668517,0.0015502257,0.0011116578,0.0012802982,0.0013731216],"domain_scores_gemma":[0.9971176,0.00030607506,0.0007427464,0.0010708935,0.0004241993,0.0003384982],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0018855736,0.0005975485,0.0005217462,0.00055155024,0.0010883176,0.0010266635,0.0011039077,0.00024657647,0.00079360086],"category_scores_gemma":[0.0007208987,0.0005957566,0.0004021754,0.001628498,0.00009514337,0.0009531162,0.00078876794,0.00043459464,0.0020103978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028105637,0.000029869425,0.00018465985,0.00019749186,0.000102902675,0.000021685297,0.0014520946,0.9330119,0.0008133367,0.011612841,0.017640384,0.034930047],"study_design_scores_gemma":[0.0010920553,0.0006799938,0.0002532306,0.00014308335,0.0000820239,0.000010501755,0.00023444992,0.9816387,0.0011752624,0.000036065558,0.013934987,0.00071961794],"about_ca_topic_score_codex":0.000028170523,"about_ca_topic_score_gemma":0.0000035879266,"teacher_disagreement_score":0.94453883,"about_ca_system_score_codex":0.00021518249,"about_ca_system_score_gemma":0.00025134132,"threshold_uncertainty_score":0.9996494},"labels":[],"label_agreement":null},{"id":"W7124304825","doi":"10.65109/vzns8734","title":"A Model-Based Solution to the Offline Multi-Agent Reinforcement Learning Coordination Problem","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Reinforcement learning; Leverage (statistics); Observability; Online and offline; Simple (philosophy); Offline learning; Online algorithm","score_opus":0.04538121631456204,"score_gpt":0.2906629308777778,"score_spread":0.24528171456321574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124304825","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":[0.000078932455,0.00032072494,0.96762395,0.023835743,0.0015960038,0.0021612803,0.0000011654029,0.00073077355,0.0036514238],"genre_scores_gemma":[0.7995208,0.0000387921,0.12885639,0.0013650537,0.00018831663,0.00016182328,0.000029483172,0.00005497696,0.06978438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947692,0.00029104477,0.0012081083,0.0011721918,0.0014800403,0.0010793769],"domain_scores_gemma":[0.9976558,0.00022021783,0.00026473813,0.0010524825,0.0004886387,0.00031811045],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0025473638,0.0005882421,0.0003458372,0.0005177119,0.0010092307,0.0021298083,0.0014728901,0.00020421778,0.00022447082],"category_scores_gemma":[0.00024995726,0.00045042447,0.00028735545,0.0018520053,0.00010457995,0.0008767156,0.00096462725,0.0010325374,0.0017163039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019082978,0.000054306238,0.000021755464,0.0002325381,0.00007691906,0.000008526648,0.003151089,0.94672203,0.0006529949,0.017253272,0.0053338967,0.026473561],"study_design_scores_gemma":[0.00056681625,0.0006796095,0.00001957204,0.0005294704,0.00008358627,0.000004885373,0.00008033254,0.95919174,0.0005298116,0.000035648038,0.037723552,0.00055499776],"about_ca_topic_score_codex":0.00009935995,"about_ca_topic_score_gemma":0.000028663504,"teacher_disagreement_score":0.8387676,"about_ca_system_score_codex":0.00089795626,"about_ca_system_score_gemma":0.0008042773,"threshold_uncertainty_score":0.9997947},"labels":[],"label_agreement":null},{"id":"W7124307291","doi":"10.65109/qtfy6777","title":"The Importance of Credo in Multiagent Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Context (archaeology); Population; Multi-agent system; Social learning","score_opus":0.03153244086601935,"score_gpt":0.2863773328859435,"score_spread":0.25484489201992416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124307291","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":[0.087420575,0.0014770438,0.8487922,0.0033502174,0.003150738,0.0010692482,5.349089e-7,0.00046082662,0.054278612],"genre_scores_gemma":[0.9467697,0.0012572374,0.0030470383,0.00013398187,0.00004631925,0.000015276524,0.0000017573785,0.000020488207,0.048708163],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969039,0.00024129766,0.00097264175,0.0004534634,0.0007177439,0.0007109352],"domain_scores_gemma":[0.997757,0.0006928508,0.0004420267,0.00087204523,0.00014139972,0.00009464768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019315651,0.00021757786,0.00026578637,0.00021986001,0.00032404443,0.00023171035,0.0015515006,0.000100595396,0.00009721853],"category_scores_gemma":[0.00079959095,0.00016624582,0.00012222891,0.0021710317,0.00019527473,0.00028731776,0.0011144677,0.0005852946,0.00038579747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063944453,0.000020204978,0.09313632,0.000035311936,0.000017120346,0.000017461129,0.0011674617,0.85475785,0.000083683844,0.018487021,0.00076701824,0.031504143],"study_design_scores_gemma":[0.00027490433,0.0001377246,0.03487358,0.00010220971,0.0000043752034,0.0000019475328,0.00072100863,0.9496719,0.00026530656,0.00015897513,0.013608618,0.00017940617],"about_ca_topic_score_codex":0.00007348365,"about_ca_topic_score_gemma":0.00005635278,"teacher_disagreement_score":0.8593492,"about_ca_system_score_codex":0.00007901393,"about_ca_system_score_gemma":0.00033237453,"threshold_uncertainty_score":0.6779308},"labels":[],"label_agreement":null},{"id":"W7124309298","doi":"10.65109/vlwf1223","title":"Transfer Learning based Agent for Automated Negotiation","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta","funders":"Universiteit Maastricht; National Natural Science Foundation of China","keywords":"Negotiation; Transfer of learning; Adaptation (eye); Context (archaeology); Knowledge transfer; Key (lock); Task (project management); Boosting (machine learning)","score_opus":0.03994887653339272,"score_gpt":0.2890886402997899,"score_spread":0.2491397637663972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124309298","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":[0.0022250635,0.000017546707,0.98546094,0.002934643,0.001810786,0.0010394289,0.0000023293137,0.005222414,0.0012868461],"genre_scores_gemma":[0.9501805,0.00004201658,0.024672432,0.0012769899,0.00016705827,0.00010249833,0.00013704438,0.000075805285,0.02334571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965708,0.00022361614,0.00075046375,0.00075752125,0.0007264332,0.00097116036],"domain_scores_gemma":[0.9982469,0.0006182842,0.00012359233,0.00056856475,0.0002785463,0.00016409488],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011944842,0.0003657698,0.0003320768,0.0004596299,0.00065708114,0.0006681503,0.0008280599,0.00022218301,0.00034556727],"category_scores_gemma":[0.00033845668,0.00038345333,0.00028955386,0.0018717304,0.000059276535,0.0008012738,0.00013540582,0.00033521655,0.0013975521],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018850029,0.000025126265,0.00021004942,0.00017453461,0.00004948749,0.000006241748,0.0008206958,0.98017967,0.00074836175,0.003916725,0.0054465965,0.008403688],"study_design_scores_gemma":[0.0013526574,0.00058615446,0.0012328492,0.00008882711,0.00004603146,0.0000010489499,0.00010136667,0.96989423,0.0019581562,0.000020761634,0.024273392,0.0004445368],"about_ca_topic_score_codex":0.00001781738,"about_ca_topic_score_gemma":0.000001914076,"teacher_disagreement_score":0.9607885,"about_ca_system_score_codex":0.00015212368,"about_ca_system_score_gemma":0.00030268714,"threshold_uncertainty_score":0.9998617},"labels":[],"label_agreement":null},{"id":"W7124313799","doi":"10.65109/vmil8420","title":"Off-the-Grid MARL: Datasets and Baselines for Offline Multi-Agent Reinforcement Learning","year":2023,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Institut National de la Recherche Scientifique","funders":"","keywords":"Reinforcement learning; Bespoke; Online and offline; Measure (data warehouse); Power (physics)","score_opus":0.05639460265554716,"score_gpt":0.3100390074822671,"score_spread":0.2536444048267199,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124313799","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":[0.0004439493,0.0005097089,0.9881077,0.0055106287,0.002552854,0.0020289358,0.000065383196,0.00049894553,0.00028190622],"genre_scores_gemma":[0.37059885,0.019773167,0.23573685,0.010399621,0.004547171,0.0011484493,0.008770355,0.0005547107,0.34847084],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9946089,0.00027298974,0.0014270755,0.0012543696,0.0010092511,0.0014274598],"domain_scores_gemma":[0.9957938,0.0013375495,0.00059835846,0.0015616873,0.00032610455,0.0003824958],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003428652,0.00068417436,0.0005743796,0.00036828208,0.0014784035,0.0010669132,0.0017397874,0.00019935735,0.0002384882],"category_scores_gemma":[0.0014567402,0.0005414913,0.00022948779,0.0011832281,0.00028984676,0.0008138176,0.00281709,0.00063422014,0.0005794273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044253276,0.000035170164,0.0004604026,0.00023933196,0.00013936391,0.000017103202,0.0007749003,0.90483594,0.000114863375,0.0017883955,0.05627861,0.03527165],"study_design_scores_gemma":[0.0014427471,0.00046694023,0.0004262399,0.00010066244,0.00007646018,0.0000111172985,0.0002513522,0.6853937,0.00020702706,0.000012143131,0.31114784,0.00046376404],"about_ca_topic_score_codex":0.00008500217,"about_ca_topic_score_gemma":0.000023109154,"teacher_disagreement_score":0.75237083,"about_ca_system_score_codex":0.00010456321,"about_ca_system_score_gemma":0.00020864666,"threshold_uncertainty_score":0.9999701},"labels":[],"label_agreement":null},{"id":"W7124317253","doi":"10.65109/gzci2494","title":"Value Iteration for Learning Concurrently Executable Robotic Control Tasks","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Executable; Task (project management); Reinforcement learning; Set (abstract data type); Independence (probability theory); Robot; Property (philosophy); Control (management)","score_opus":0.013691952864955292,"score_gpt":0.2791122585949014,"score_spread":0.2654203057299461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124317253","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":[0.00005549626,0.0007430037,0.97038037,0.0026300976,0.0054452033,0.0019740644,0.0000021796952,0.00032596008,0.018443627],"genre_scores_gemma":[0.8739147,0.000059113725,0.03322142,0.0026113666,0.0002796848,0.00013855545,0.0000354698,0.0000373544,0.089702345],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99568284,0.00030657146,0.0012007784,0.0010862561,0.0005822751,0.0011412826],"domain_scores_gemma":[0.9966937,0.0010865707,0.0005181782,0.00084495376,0.0007004966,0.00015611833],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012288786,0.00055717456,0.0007308047,0.00045457832,0.0010506933,0.002288779,0.0012771587,0.00030237355,0.00018355207],"category_scores_gemma":[0.0010596144,0.0005892897,0.00033852534,0.0010006316,0.00014938452,0.0014507715,0.00039059157,0.000722104,0.00021452829],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003615133,0.00004815766,0.0008173174,0.0002150604,0.00013499553,0.0000018518601,0.00024948322,0.7448843,0.00026736484,0.24059406,0.003153094,0.009598149],"study_design_scores_gemma":[0.0033507904,0.00052760815,0.00017617563,0.00034231163,0.00021203858,0.0000037063617,0.00006983667,0.95399487,0.00047595965,0.0009990213,0.03932269,0.0005250103],"about_ca_topic_score_codex":0.000043514443,"about_ca_topic_score_gemma":0.0000021453018,"teacher_disagreement_score":0.93715894,"about_ca_system_score_codex":0.00028987805,"about_ca_system_score_gemma":0.000630051,"threshold_uncertainty_score":0.99965584},"labels":[],"label_agreement":null},{"id":"W7124317441","doi":"10.65109/ltgs2519","title":"Be Considerate: Avoiding Negative Side Effects in Reinforcement Learning","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Vector Institute","funders":"","keywords":"Reinforcement learning; Agency (philosophy); Reinforcement; Control (management); Action (physics); Discretion","score_opus":0.02380526822181108,"score_gpt":0.25947887441085216,"score_spread":0.23567360618904107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124317441","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":[0.007137528,0.00022075188,0.9189725,0.0022623516,0.002397187,0.0016281108,6.0376885e-7,0.00030678647,0.06707419],"genre_scores_gemma":[0.963586,0.0000637466,0.0068598483,0.003138145,0.00008401846,0.00019929456,0.000011049528,0.00006121953,0.025996681],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9906412,0.0029131775,0.0015071299,0.0013477457,0.0019396306,0.0016511104],"domain_scores_gemma":[0.99410605,0.003645427,0.0007985655,0.0009660033,0.00017075498,0.00031318885],"candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0035025128,0.00071551546,0.0008038353,0.00080332253,0.0028614327,0.0008675394,0.0015673904,0.00014012711,0.0016189757],"category_scores_gemma":[0.0023668057,0.0008423391,0.00019082772,0.0022484178,0.00020155571,0.0011285291,0.004694565,0.0040659937,0.00017893028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005003851,0.00006109346,0.0010647054,0.00012080152,0.000088532455,0.0003986719,0.013583728,0.93700486,0.00061557966,0.043954603,0.00061508076,0.0024423278],"study_design_scores_gemma":[0.0023767962,0.0020192105,0.00042404543,0.00015727377,0.000032223656,0.000055476754,0.0036151295,0.9824513,0.002753106,0.00057653245,0.0046081124,0.0009307708],"about_ca_topic_score_codex":0.00052873406,"about_ca_topic_score_gemma":0.000024463136,"teacher_disagreement_score":0.9564485,"about_ca_system_score_codex":0.0015058692,"about_ca_system_score_gemma":0.0007488346,"threshold_uncertainty_score":0.99940276},"labels":[],"label_agreement":null},{"id":"W7124320264","doi":"10.65109/jazo1666","title":"A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Microsoft (Canada)","funders":"","keywords":"Discounting; Perspective (graphical); Representation (politics); Term (time); Trajectory; Task (project management); Value (mathematics); Empirical research","score_opus":0.019374595721380002,"score_gpt":0.25472915205792435,"score_spread":0.23535455633654434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124320264","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":[0.042371172,0.0005092598,0.931664,0.002547257,0.0033086874,0.00075364095,0.0000041488024,0.00020269536,0.018639123],"genre_scores_gemma":[0.9265905,0.00004457466,0.023942707,0.0015908516,0.0001742568,0.00009267841,0.000012638488,0.00006407808,0.047487687],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937825,0.0006163981,0.0011311851,0.0012170417,0.0017685519,0.0014843247],"domain_scores_gemma":[0.9975674,0.0005166561,0.00030175957,0.0012850547,0.00009653056,0.00023258221],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019619893,0.0005016681,0.0005214893,0.0004152177,0.0011940963,0.0006850871,0.0024643796,0.000110622146,0.006860349],"category_scores_gemma":[0.00019705931,0.00055829453,0.00021389843,0.0015150448,0.00017010276,0.0010064037,0.006336753,0.0012062906,0.00052551774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002452956,0.00018310276,0.017475773,0.0001009563,0.000044406526,0.00027553894,0.008320481,0.95981324,0.0002423673,0.0069119567,0.0012497612,0.005357902],"study_design_scores_gemma":[0.0009469313,0.00026349333,0.002155929,0.000061633444,0.000020711592,0.00010253332,0.0014003982,0.9833219,0.00018973663,0.00023185399,0.010578179,0.0007267107],"about_ca_topic_score_codex":0.0003750695,"about_ca_topic_score_gemma":0.00004981717,"teacher_disagreement_score":0.9077213,"about_ca_system_score_codex":0.001499956,"about_ca_system_score_gemma":0.0003404136,"threshold_uncertainty_score":0.99968684},"labels":[],"label_agreement":null},{"id":"W7124320494","doi":"10.65109/vaba4866","title":"PADDLE: Logic Program Guided Policy Reuse in Deep Reinforcement Learning","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reuse; Reinforcement learning; Metric (unit); Transferability; Task (project management); Similarity (geometry); Measure (data warehouse)","score_opus":0.04022714982400774,"score_gpt":0.33431780415230783,"score_spread":0.29409065432830006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124320494","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":[0.0004892696,0.001188567,0.9012169,0.008925286,0.0017226472,0.0018268842,1.8598766e-7,0.0018123654,0.08281787],"genre_scores_gemma":[0.83802295,0.0012604574,0.06416119,0.0012979984,0.0006494627,0.00020479294,0.000023904333,0.000109848945,0.09426937],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99201125,0.00046690428,0.0021136845,0.001712554,0.0015069812,0.0021886223],"domain_scores_gemma":[0.9961861,0.00032297618,0.00033329974,0.0024424002,0.00024764854,0.00046760432],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0020220676,0.00088498974,0.0007091046,0.0017087366,0.0003812775,0.0034868708,0.0036589198,0.00045742735,0.0010120906],"category_scores_gemma":[0.0019943167,0.0008394296,0.00035789763,0.005445724,0.00027617667,0.0016330142,0.0036776117,0.0020042728,0.0024227109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000986149,0.00008097304,0.00048512503,0.00032930952,0.000086599684,0.00030430104,0.0038738954,0.7942291,0.000054469507,0.11373333,0.0015922326,0.085220814],"study_design_scores_gemma":[0.0006136302,0.0013231311,0.00028165168,0.00068215944,0.000033528086,0.000041944706,0.00017481584,0.91280454,0.00014290604,0.0011112074,0.0819179,0.0008726031],"about_ca_topic_score_codex":0.00057008915,"about_ca_topic_score_gemma":0.000024002495,"teacher_disagreement_score":0.8375337,"about_ca_system_score_codex":0.0012570512,"about_ca_system_score_gemma":0.0012452105,"threshold_uncertainty_score":0.9999011},"labels":[],"label_agreement":null},{"id":"W7124326325","doi":"10.65109/sjgw9760","title":"Empowering Generalization for Deep Reinforcement Learning via Symbolic Planning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Reinforcement learning; Generalization; Pearl; Planner; Limiting; Automated planning and scheduling; Plan (archaeology); Deep learning","score_opus":0.019387053090284885,"score_gpt":0.30838076534145553,"score_spread":0.28899371225117065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124326325","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":[0.0004467044,0.0005841643,0.9662664,0.00051086734,0.002976453,0.0012504873,1.3443108e-7,0.00043975768,0.027525062],"genre_scores_gemma":[0.8922126,0.00012168953,0.050265122,0.0012690561,0.00026298026,0.00012132482,0.000048126585,0.00005604805,0.055643037],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99559253,0.0001481325,0.0013608447,0.0010295892,0.00064455223,0.0012243342],"domain_scores_gemma":[0.99758446,0.00032698247,0.00054727186,0.00090347236,0.00044326283,0.00019452299],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00096585025,0.0005972619,0.00056935515,0.0006915769,0.0013031366,0.0011157584,0.0013429398,0.0003018034,0.0001716269],"category_scores_gemma":[0.00040014836,0.0006692622,0.00027676235,0.0013005971,0.00008930647,0.0009378238,0.0009864665,0.000533171,0.00006963349],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003043476,0.000019595578,0.0017538001,0.0002937861,0.00017542382,0.0000037490697,0.0025523365,0.9311686,0.00078334345,0.04914995,0.00043682574,0.013632141],"study_design_scores_gemma":[0.0011361578,0.00037313643,0.00024372507,0.0004341434,0.00009042551,0.000004343658,0.00018430145,0.972623,0.0027874229,0.00030939985,0.021181148,0.0006328049],"about_ca_topic_score_codex":0.000043246073,"about_ca_topic_score_gemma":0.0000023798827,"teacher_disagreement_score":0.91600126,"about_ca_system_score_codex":0.00040439196,"about_ca_system_score_gemma":0.00027500512,"threshold_uncertainty_score":0.999997},"labels":[],"label_agreement":null},{"id":"W7125578405","doi":"10.1109/mecatronics-rem67547.2025.11349467","title":"Learning Multistage Robotic Manipulation Using Chained Options and Composable Subtask Rewards","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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; Interpretability; Task (project management); Benchmark (surveying); Stability (learning theory); Decomposition; Sequence (biology); Process (computing)","score_opus":0.031009359942283158,"score_gpt":0.29120584357066337,"score_spread":0.2601964836283802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125578405","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":[0.014708801,0.00043260268,0.97586954,0.00080466626,0.0012350266,0.0006240131,6.347414e-7,0.00029703436,0.00602768],"genre_scores_gemma":[0.82204205,0.0001676535,0.14111389,0.00017668257,0.000062775645,0.0000055115906,0.000014418088,0.000026561991,0.036390472],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964542,0.00039422142,0.00091299094,0.0009275898,0.0005198887,0.0007911223],"domain_scores_gemma":[0.99807036,0.00031299194,0.00037156648,0.00076328166,0.00029263392,0.00018917787],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009160973,0.00047702415,0.0005362108,0.00056665833,0.0014284713,0.0012814892,0.0006371148,0.00024941625,0.00013167453],"category_scores_gemma":[0.00023117397,0.0005213184,0.00012545174,0.0013046027,0.00022382062,0.0010259307,0.0010455229,0.0007262407,0.00004699558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013400045,0.000039748535,0.008224838,0.00018299135,0.00008209849,0.000011546836,0.0007020809,0.93433976,0.0014023688,0.05282768,0.000044247303,0.002129242],"study_design_scores_gemma":[0.000882482,0.00017611677,0.010847594,0.00038205335,0.000117479016,0.000018068833,0.0002642614,0.98579234,0.00016922859,0.00019824675,0.00068214384,0.00046999252],"about_ca_topic_score_codex":0.00037676294,"about_ca_topic_score_gemma":0.000010432239,"teacher_disagreement_score":0.83475566,"about_ca_system_score_codex":0.0003499173,"about_ca_system_score_gemma":0.00026576727,"threshold_uncertainty_score":0.99987155},"labels":[],"label_agreement":null},{"id":"W7125650556","doi":"10.1109/cascon66301.2025.00079","title":"Supervised Semantic Similarity-Based Conflict Detection Algorithm: S3CDA","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"IBM (Canada); Toronto Metropolitan University","funders":"","keywords":"Pattern recognition (psychology); Feature (linguistics); Noise (video); Semantics (computer science)","score_opus":0.02035180397387599,"score_gpt":0.2674203222397192,"score_spread":0.2470685182658432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125650556","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":[0.00044362957,0.0002156125,0.9756548,0.0027459138,0.004513126,0.0008937756,0.0000028809254,0.0006004109,0.014929877],"genre_scores_gemma":[0.83514315,0.00012580783,0.12818691,0.008176811,0.00022969602,0.000048594153,0.000018660225,0.00005571217,0.028014664],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951179,0.0004228485,0.0011342908,0.0012617179,0.0009567233,0.0011065394],"domain_scores_gemma":[0.99649525,0.00052951404,0.00026638788,0.0018820631,0.0005601149,0.00026667208],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010523032,0.0006580724,0.000647024,0.0007628962,0.0008249033,0.0013305363,0.0018885845,0.00046270218,0.0005490152],"category_scores_gemma":[0.00027094668,0.00070348254,0.00036900796,0.0024388093,0.0002649777,0.0007177756,0.000693282,0.0009441572,0.00048158347],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033974327,0.00018453109,0.00084486214,0.00040763852,0.00022508079,0.000044451644,0.0004012532,0.7256387,0.001293789,0.0043691136,0.00114578,0.26541087],"study_design_scores_gemma":[0.0018646979,0.00037265354,0.0009596619,0.00023164434,0.00012911695,0.00000465707,0.00006230797,0.95477027,0.02021243,0.00013246608,0.02062637,0.00063370843],"about_ca_topic_score_codex":0.00030553315,"about_ca_topic_score_gemma":0.000033380733,"teacher_disagreement_score":0.84746784,"about_ca_system_score_codex":0.00032139535,"about_ca_system_score_gemma":0.0008027226,"threshold_uncertainty_score":0.99970615},"labels":[],"label_agreement":null},{"id":"W7125958253","doi":"10.1145/3768292.3793403","title":"10.1145/3768292.3793403","year":2000,"lang":"en","type":"article","venue":"Time to knit","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Session (web analytics); Reinforcement; Reinforcement learning; Component (thermodynamics); Training (meteorology)","score_opus":0.006230724881324144,"score_gpt":0.179140084893979,"score_spread":0.17290936001265486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125958253","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006487106,0.000013741543,0.015425208,0.0005159994,0.000008166245,0.00013801477,6.0557505e-7,0.0003586159,0.9834748],"genre_scores_gemma":[0.00029660892,2.5623376e-7,0.0076874117,0.00021019927,0.00006953092,0.000007827495,0.0000030547737,0.000013719568,0.9917114],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988353,0.000038454607,0.00018849288,0.00028870092,0.00030839568,0.00034063405],"domain_scores_gemma":[0.9990357,0.000053515112,0.000034908255,0.0006803966,0.000042535627,0.00015290492],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00017066865,0.00013392078,0.00013124118,0.00008106683,0.00009669308,0.0001717662,0.0009759598,0.00004901446,0.9547186],"category_scores_gemma":[0.000035660727,0.00013369205,0.00005089297,0.00036454957,0.000022150574,0.00027711832,0.00016393003,0.00011380671,0.9872884],"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":[0.000008837448,0.000018891136,5.1741006e-7,0.000003833589,0.000012366038,0.000010440839,0.00005592347,0.21831119,0.00003054063,0.00008516681,0.119375885,0.6620864],"study_design_scores_gemma":[0.00012137321,0.00013127211,0.00003182536,0.000009135395,0.0000031714378,0.0000070747064,1.7842477e-7,0.11636244,0.00005177994,0.000009108719,0.8831158,0.00015678549],"about_ca_topic_score_codex":0.000006867102,"about_ca_topic_score_gemma":1.7041128e-8,"teacher_disagreement_score":0.76373994,"about_ca_system_score_codex":0.00003809549,"about_ca_system_score_gemma":0.000034089386,"threshold_uncertainty_score":0.5451804},"labels":[],"label_agreement":null},{"id":"W7131116789","doi":"10.1109/robio66223.2025.11378377","title":"A Strategy Adaptive Adjustment Deep Reinforcement Learning Method with Behavior Cloning for Mobile Robot Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Reinforcement learning; Obstacle avoidance; Randomness; Obstacle; Robot; Mobile robot; Trajectory; Training (meteorology); Path (computing)","score_opus":0.025411914609538396,"score_gpt":0.3187286794351319,"score_spread":0.2933167648255935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131116789","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":[0.0005715542,0.00057937566,0.984071,0.000109937246,0.00096642977,0.0059930016,0.0000012168173,0.00035127928,0.0073562167],"genre_scores_gemma":[0.542633,0.00005897895,0.43059474,0.00022611675,0.00011431798,0.0023317998,0.000084567655,0.00005846466,0.023898019],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9937375,0.0004483699,0.0015534171,0.0016495773,0.0011239424,0.0014871994],"domain_scores_gemma":[0.99576545,0.00074859784,0.0010065979,0.0011288889,0.0010481384,0.00030235754],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015819393,0.00093175325,0.0008789406,0.0004960418,0.0012028808,0.0009258385,0.0012985924,0.00036763374,0.00019846136],"category_scores_gemma":[0.00009172258,0.00086592,0.00033395184,0.0014913954,0.00017944073,0.0012762034,0.00073218625,0.0010690562,0.00004313538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023084144,0.0001302259,0.00023209096,0.00018957807,0.0003381257,0.000012934644,0.0015315778,0.83325076,0.0003585125,0.040978827,0.000052838204,0.12269366],"study_design_scores_gemma":[0.0028460147,0.0077178804,0.0005673502,0.0007864141,0.00067873433,0.000020100942,0.0029294356,0.978405,0.003921974,0.00011699871,0.0010890239,0.00092109235],"about_ca_topic_score_codex":0.00023612038,"about_ca_topic_score_gemma":0.000021260048,"teacher_disagreement_score":0.5534762,"about_ca_system_score_codex":0.00096651743,"about_ca_system_score_gemma":0.0008620241,"threshold_uncertainty_score":0.99937916},"labels":[],"label_agreement":null},{"id":"W7132054910","doi":"","title":"Time and temporal abstraction in continual learning: tradeoffs, analogies and regret in an active measuring setting","year":2023,"lang":"en","type":"article","venue":"NPARC","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Abstraction; Regret; Context (archaeology); Class (philosophy); Markov decision process; Relevance (law); Hierarchy; Reinforcement learning; Simple (philosophy)","score_opus":0.03017605342244424,"score_gpt":0.263177105349338,"score_spread":0.2330010519268938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132054910","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":[0.9949915,0.00000780532,0.002444655,0.0004706168,0.000046906956,0.00010996489,3.870215e-7,0.00017731244,0.0017508782],"genre_scores_gemma":[0.9967367,0.000011808947,0.0029695402,0.000014451569,0.000018825242,0.0000041989497,0.0000065428694,0.000007707034,0.0002301928],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896395,0.00012099224,0.00019413438,0.00028827204,0.0001861073,0.000246544],"domain_scores_gemma":[0.99955714,0.00015851522,0.00009139194,0.0001258648,0.00001962069,0.0000474686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006452994,0.000100208235,0.00014123945,0.0002487139,0.000075436175,0.00013437176,0.00015544021,0.0000628044,0.000005109249],"category_scores_gemma":[0.0001696872,0.000105642015,0.000011365244,0.0003473677,0.00005249503,0.00077127863,0.00012400758,0.00033816235,0.000009189553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058693877,0.00003651623,0.315535,0.000061574785,0.000021369959,0.00019392163,0.0195069,0.5198377,0.038263828,0.0008625516,0.00014944797,0.1054725],"study_design_scores_gemma":[0.0002984972,0.000087474284,0.31475893,0.000042995645,0.0000013925176,0.0000075390544,0.0006629619,0.68306464,0.000588038,0.00029623817,0.0000763984,0.0001148929],"about_ca_topic_score_codex":0.000023082,"about_ca_topic_score_gemma":0.00003567139,"teacher_disagreement_score":0.16322695,"about_ca_system_score_codex":0.000041993186,"about_ca_system_score_gemma":0.00002483314,"threshold_uncertainty_score":0.4307956},"labels":[],"label_agreement":null},{"id":"W7132865739","doi":"","title":"Constrained, Curiosity-driven Trajectory Optimization for Learned Quadrotor Control","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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":"Trajectory; Stability (learning theory); Probabilistic logic; Reinforcement learning; Control theory (sociology); Robot; Control (management); Model predictive control; Optimal control; State space","score_opus":0.029156504398305867,"score_gpt":0.33801370815472515,"score_spread":0.3088572037564193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132865739","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":[0.0007641807,0.0004976045,0.98417187,0.0009186748,0.004190091,0.005307594,0.00004043649,0.00037983086,0.003729726],"genre_scores_gemma":[0.44863454,0.0020577433,0.35528538,0.0027930771,0.0018448271,0.0051622014,0.0068269125,0.0008758913,0.17651941],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9940699,0.00061539834,0.0011966575,0.0016086568,0.0013555879,0.0011538538],"domain_scores_gemma":[0.9947699,0.0010966781,0.0018115488,0.0012751794,0.00070170156,0.0003450465],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010021665,0.00096801494,0.0011341744,0.00058104016,0.0015001979,0.00073035044,0.0021200958,0.00059161946,0.003463192],"category_scores_gemma":[0.0007767925,0.0012086413,0.0006592827,0.00081575225,0.00019525216,0.00057816657,0.00019976862,0.0013420999,0.00007165825],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042596285,0.000119060096,0.000072031966,0.0005506091,0.00029687092,0.000019090292,0.012992298,0.9783558,0.00046821072,0.004105631,0.0006847284,0.0019096548],"study_design_scores_gemma":[0.0042426623,0.0013676834,0.000064923595,0.00023370713,0.00033062746,0.000016474305,0.0044930396,0.97637695,0.0001804168,0.000022345945,0.011505097,0.0011660687],"about_ca_topic_score_codex":0.00009838893,"about_ca_topic_score_gemma":0.000022670203,"teacher_disagreement_score":0.62888646,"about_ca_system_score_codex":0.00056919415,"about_ca_system_score_gemma":0.0014523068,"threshold_uncertainty_score":0.9997997},"labels":[],"label_agreement":null},{"id":"W7132871321","doi":"","title":"Who Should I Trust? Uncertainty and Risk for Knowledge Transfer from Multiple Sources in Reinforcement Learning Domains","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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; Knowledge transfer; Transfer of learning; Set (abstract data type); Inference; Quality (philosophy); Bayesian inference; Uncertainty quantification; Bayesian probability","score_opus":0.042537842236209045,"score_gpt":0.326914110571627,"score_spread":0.28437626833541796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132871321","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":[0.4654488,0.0008102744,0.5292394,0.00012185284,0.0012874142,0.001959684,0.000013952419,0.00026395943,0.0008546709],"genre_scores_gemma":[0.93027276,0.0049105682,0.0038335319,0.00005470944,0.00041540293,0.0004787827,0.0010656279,0.00025434428,0.05871428],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9936468,0.0005323701,0.0015008118,0.0019170416,0.00093321805,0.0014697629],"domain_scores_gemma":[0.9940554,0.003610769,0.0006565011,0.0009555374,0.00034418705,0.00037759266],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016650927,0.0011847977,0.0013803286,0.0008010436,0.0010836774,0.00081903255,0.0013578207,0.00095544703,0.00010440217],"category_scores_gemma":[0.0015642168,0.0012794543,0.00036386872,0.00118228,0.00020658052,0.0004729242,0.00034175685,0.0021269657,0.00011637668],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035844068,0.000043513748,0.012025532,0.00040958467,0.00025764943,0.000008887934,0.1749859,0.8022833,0.00020106499,0.00050870026,0.000114142545,0.008803304],"study_design_scores_gemma":[0.004124588,0.00085203204,0.009699032,0.0012252042,0.00029310965,9.2056825e-7,0.029210951,0.9443755,0.0006774419,0.00014407253,0.008104589,0.0012925154],"about_ca_topic_score_codex":0.0067601954,"about_ca_topic_score_gemma":0.005167226,"teacher_disagreement_score":0.5254059,"about_ca_system_score_codex":0.00042222656,"about_ca_system_score_gemma":0.0004329783,"threshold_uncertainty_score":0.99985385},"labels":[],"label_agreement":null},{"id":"W7132969921","doi":"","title":"Learning the Discount Factor in Inverse Reinforcement Learning with Application to Animal Behaviour","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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":"Foraging; Reinforcement learning; Function (biology); Convexity; Preference; Factor (programming language)","score_opus":0.02195637573274086,"score_gpt":0.317475079676105,"score_spread":0.29551870394336416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132969921","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":[0.51963454,0.000025602732,0.47390124,0.0011112458,0.00058881904,0.0027489197,6.8196584e-7,0.00040071047,0.0015882376],"genre_scores_gemma":[0.9300752,0.00009668767,0.0012163455,0.00012879094,0.00014950252,0.0005135833,0.00026405943,0.00016483958,0.06739094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99368846,0.000420933,0.0010774235,0.0015173858,0.0019789874,0.0013168198],"domain_scores_gemma":[0.9964411,0.00039718568,0.0012331078,0.0012198783,0.00038636097,0.00032231698],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011349377,0.0009544466,0.00070988375,0.00072066276,0.0010456374,0.0009768135,0.001999424,0.0003983664,0.000114871385],"category_scores_gemma":[0.000423068,0.0007836461,0.0001744826,0.0027951482,0.000115736555,0.00056399015,0.0006592689,0.0030319109,0.001273436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018525863,0.000027622676,0.023457013,0.00011693376,0.000054143326,0.000025545967,0.1090689,0.8639304,0.00078259944,0.00045957207,0.00007129807,0.0018207112],"study_design_scores_gemma":[0.00073307817,0.0020457872,0.07246872,0.00072690356,0.000090450776,0.0000064040814,0.05711802,0.8630376,0.00046849626,0.0000036526033,0.0021979425,0.0011029637],"about_ca_topic_score_codex":0.0030048082,"about_ca_topic_score_gemma":0.0015030293,"teacher_disagreement_score":0.47268492,"about_ca_system_score_codex":0.0008244862,"about_ca_system_score_gemma":0.000553313,"threshold_uncertainty_score":0.9995042},"labels":[],"label_agreement":null},{"id":"W7133015284","doi":"","title":"Acquiring Information from Bayesian Surprise in Cognitive Linear Gaussian Dynamic Systems","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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":"Surprise; Novelty; Bayesian probability; Gaussian process; State (computer science); Gaussian; Cognition; Credibility","score_opus":0.023101257043908772,"score_gpt":0.33480495346296973,"score_spread":0.311703696419061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133015284","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":[0.06026262,0.0002860932,0.9259274,0.00016147198,0.006445476,0.0017813258,0.00002707025,0.00048534537,0.004623175],"genre_scores_gemma":[0.97717774,0.00048066562,0.0031446884,0.00008038551,0.00022569699,0.00016315922,0.004224094,0.00013306655,0.014370478],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994213,0.00039820874,0.0018072032,0.0009883194,0.0014608206,0.001132485],"domain_scores_gemma":[0.995603,0.0008507735,0.0017204363,0.0010040145,0.0005132263,0.00030851897],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009767651,0.0009163055,0.0009974001,0.0013828275,0.00037986063,0.0014027026,0.0014937848,0.0008718628,0.00010369184],"category_scores_gemma":[0.00079778547,0.0010828073,0.00021947497,0.0021578183,0.000097094264,0.0023419962,0.0004085185,0.001447421,0.0024431178],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015277237,0.000043842756,0.0016496672,0.0007783533,0.00019782572,0.00011229262,0.14798772,0.8394209,0.000064978376,0.00035334256,0.00009755044,0.009140756],"study_design_scores_gemma":[0.0011120855,0.00015349542,0.013247295,0.0046276893,0.00008990648,0.000003789985,0.05010316,0.92937446,0.0000681868,0.000037258007,0.00020380892,0.000978874],"about_ca_topic_score_codex":0.0058639296,"about_ca_topic_score_gemma":0.0006945716,"teacher_disagreement_score":0.9227827,"about_ca_system_score_codex":0.00066403544,"about_ca_system_score_gemma":0.0006614432,"threshold_uncertainty_score":0.9996339},"labels":[],"label_agreement":null},{"id":"W7133070489","doi":"","title":"Optimizing Mechanism Design in Multi-Agent Reinforcement Learning","year":2024,"lang":"","type":"dissertation","venue":"TSpace","topic":"Reinforcement Learning in Robotics","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":"Agencia Nacional de Investigación y Desarrollo; University of Toronto","keywords":"Reinforcement learning; Mechanism design; Markov decision process; Bridging (networking); Benchmark (surveying); Robustness (evolution); Mechanism (biology); Nash equilibrium","score_opus":0.06547687145312808,"score_gpt":0.3433784059699186,"score_spread":0.2779015345167905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133070489","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":[0.0008509895,0.0013193053,0.98563623,0.00026102105,0.0050995345,0.00199362,1.946213e-7,0.0005011085,0.004338002],"genre_scores_gemma":[0.4432975,0.0017227918,0.30093467,0.00018734789,0.00018995725,0.0003027874,0.00016661566,0.00031232336,0.252886],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919261,0.0007220078,0.0017713696,0.0020562876,0.0017598481,0.0017644182],"domain_scores_gemma":[0.9965366,0.0004356048,0.0010632302,0.001272082,0.00030776672,0.00038467752],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002583739,0.0013600879,0.0011030304,0.0014526264,0.00055759633,0.0016364091,0.0021419534,0.00085965515,0.00045771227],"category_scores_gemma":[0.00049786794,0.001544382,0.00041592316,0.001822035,0.000068947,0.0006754839,0.00091877306,0.0035280804,0.002306651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052836276,0.00005025868,0.0000082487295,0.0005932744,0.00014286656,0.00027515044,0.11745285,0.8716714,0.0020778792,0.0063343,0.00009295632,0.0012480232],"study_design_scores_gemma":[0.0010430228,0.00066074467,0.000025373012,0.0027586017,0.00014850097,0.000014217941,0.01270916,0.97360164,0.006065597,0.0001099811,0.00143777,0.0014253834],"about_ca_topic_score_codex":0.00042316475,"about_ca_topic_score_gemma":0.00003719383,"teacher_disagreement_score":0.68470156,"about_ca_system_score_codex":0.0012674928,"about_ca_system_score_gemma":0.00088543847,"threshold_uncertainty_score":0.999915},"labels":[],"label_agreement":null},{"id":"W7133567929","doi":"10.1109/etfg61999.2025.11402119","title":"A Hybrid Learning Framework for State Estimation and Volt/Var Optimization Using Normalizing Flows and Reinforcement Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"","keywords":"Reinforcement learning; State (computer science); Stability (learning theory); Estimation; Noise (video); Key (lock); Control (management); Active learning (machine learning)","score_opus":0.01844932768772126,"score_gpt":0.2829148484919575,"score_spread":0.26446552080423624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133567929","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":[0.0074928342,0.000569703,0.98870367,0.0003206071,0.00071876,0.0013426841,7.4079213e-7,0.00026792946,0.0005830906],"genre_scores_gemma":[0.41279382,0.00057140226,0.5842993,0.00020186146,0.000041594332,0.000025470677,0.000020552146,0.000037360078,0.0020086064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959431,0.0002675418,0.0012353885,0.001053159,0.00054871757,0.0009520753],"domain_scores_gemma":[0.9972323,0.000888821,0.00077148643,0.00045819435,0.0004274969,0.00022168968],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015761831,0.0005990068,0.0005936419,0.0006229642,0.002030506,0.0021061192,0.00041079594,0.00021594691,0.000045257824],"category_scores_gemma":[0.0017499352,0.00068026636,0.00010874695,0.000697308,0.00015394719,0.0018844954,0.0009935031,0.00095961994,0.0000044781254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006197276,0.000013182428,0.0012131431,0.0005401184,0.0001233317,0.0000035905293,0.0018492709,0.94518185,0.00007105368,0.013931092,0.000014755993,0.036996655],"study_design_scores_gemma":[0.0011040004,0.0004853839,0.000069039605,0.001278832,0.00016506015,0.000018609533,0.00026347814,0.99370056,0.0003656556,0.0011543613,0.00075331394,0.0006416769],"about_ca_topic_score_codex":0.000104231876,"about_ca_topic_score_gemma":0.0000014706757,"teacher_disagreement_score":0.40530097,"about_ca_system_score_codex":0.00027688465,"about_ca_system_score_gemma":0.0002815755,"threshold_uncertainty_score":0.9995648},"labels":[],"label_agreement":null},{"id":"W7134200277","doi":"10.1109/bigdata66926.2025.11402252","title":"Goal-Conditioned Reinforcement Learning for Data-Driven Maritime Navigation","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Reinforcement learning; Control (management); Action (physics); Field (mathematics); Stability (learning theory)","score_opus":0.028944629782112315,"score_gpt":0.3041871407674779,"score_spread":0.27524251098536556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134200277","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":[0.00011910023,0.00010273747,0.9630099,0.0025647045,0.002107464,0.0018771339,0.000008988767,0.00038848713,0.029821463],"genre_scores_gemma":[0.7381689,0.00012467732,0.09342303,0.0015241354,0.00026882792,0.00016299168,0.0033296952,0.000048635655,0.1629491],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951238,0.00020867679,0.0014271849,0.0014538452,0.00079177757,0.0009947278],"domain_scores_gemma":[0.99544007,0.0006644838,0.0006213898,0.002504224,0.0005820577,0.00018780248],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013066876,0.000530225,0.0005463795,0.00041119757,0.0012834029,0.0013771196,0.0032228667,0.00030614686,0.00058588723],"category_scores_gemma":[0.00056775403,0.0005958797,0.00020088865,0.0010504066,0.00018799443,0.0024142396,0.0028021988,0.00067716325,0.00039607758],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003713528,0.000039889113,0.00028847271,0.00030739827,0.00022722282,0.000004242896,0.0002982173,0.8605395,0.00015157867,0.110456355,0.012162723,0.01548726],"study_design_scores_gemma":[0.0017454498,0.0004100876,0.00025262646,0.00051743805,0.00016645814,0.000004640321,0.000110958026,0.9281956,0.0004433985,0.00081395044,0.06679982,0.0005395962],"about_ca_topic_score_codex":0.00008765583,"about_ca_topic_score_gemma":0.0000052597734,"teacher_disagreement_score":0.8695869,"about_ca_system_score_codex":0.00037705115,"about_ca_system_score_gemma":0.000630951,"threshold_uncertainty_score":0.99965954},"labels":[],"label_agreement":null},{"id":"W7134938218","doi":"10.1109/aiot66900.2025.00136","title":"A Comparative Evaluation of Teacher-Guided Reinforcement Learning Techniques for Autonomous Cyber Operations","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Polytechnique Montréal; Royal Military College of Canada","funders":"","keywords":"Reinforcement learning; Automation; Control (management); Key (lock); Action (physics)","score_opus":0.08454914817489433,"score_gpt":0.38284402444833376,"score_spread":0.2982948762734394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134938218","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":[0.0011367396,0.0001507762,0.87611115,0.0007678658,0.00047148688,0.004148635,0.0000011600979,0.00022824905,0.11698391],"genre_scores_gemma":[0.82667625,0.000028732222,0.124535486,0.00020452129,0.00005984334,0.000629274,0.000041591637,0.00001693978,0.04780736],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99506986,0.0006508441,0.0017773015,0.00077917334,0.0011400694,0.00058276264],"domain_scores_gemma":[0.9949262,0.00033667023,0.0005447236,0.0009540207,0.0031386698,0.000099711295],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004551079,0.0004602127,0.00075604033,0.00059256377,0.0007096913,0.000444495,0.0010485725,0.00025408756,0.00045670744],"category_scores_gemma":[0.00087267277,0.00046889446,0.0002750894,0.0010160425,0.00021941685,0.0008227305,0.00056403276,0.00048039883,0.000027387416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018499972,0.00009349019,0.00010705478,0.000088048866,0.00025617628,1.3462856e-7,0.0032463532,0.8736769,0.0012942794,0.108543225,0.0018771455,0.0107987095],"study_design_scores_gemma":[0.0013019062,0.00067772425,0.00017755735,0.0003143721,0.00037164803,0.0000014348955,0.0005551659,0.94291526,0.044167455,0.000308151,0.008819673,0.00038966953],"about_ca_topic_score_codex":0.00020820361,"about_ca_topic_score_gemma":0.000035536592,"teacher_disagreement_score":0.8255395,"about_ca_system_score_codex":0.00082648336,"about_ca_system_score_gemma":0.002106766,"threshold_uncertainty_score":0.9997763},"labels":[],"label_agreement":null},{"id":"W7136135934","doi":"10.1109/itsc60802.2025.11423815","title":"Optimizing Pedestrian Safety in Real-Time: An Extreme Value Theory-Based Reinforcement Learning Framework","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pedestrian; Reinforcement learning; Value (mathematics); Extreme learning machine; Control (management); Event (particle physics)","score_opus":0.026060300312092624,"score_gpt":0.2863342966971705,"score_spread":0.26027399638507787,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7136135934","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":[0.0008264272,0.00013225773,0.8878194,0.0011888011,0.0012093562,0.0012664591,6.953851e-7,0.0006407312,0.10691584],"genre_scores_gemma":[0.57445073,0.00051195535,0.37489396,0.0016478002,0.00019376224,0.000055034467,0.000052252795,0.00010388873,0.048090607],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.98927116,0.0024440808,0.0026625001,0.0020592029,0.0014473776,0.0021156673],"domain_scores_gemma":[0.99282765,0.0025792138,0.0008719986,0.0028737753,0.00033411628,0.0005132368],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065783826,0.0011166616,0.0011795755,0.0013982255,0.0012050159,0.0016579469,0.0033365574,0.00084784534,0.0021861976],"category_scores_gemma":[0.0018915071,0.0012051912,0.00039232642,0.003614559,0.00036066154,0.001572183,0.0013659443,0.002666578,0.00034001644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002767902,0.00011435319,0.001098187,0.00013367941,0.000077804216,0.00004120231,0.002050158,0.70879817,0.00017822204,0.27847815,0.00004388933,0.0087094],"study_design_scores_gemma":[0.0022925057,0.00088947115,0.00068927207,0.0019300684,0.00009672969,0.0000025852764,0.0005885028,0.98677844,0.0005146659,0.002845021,0.002233741,0.0011389927],"about_ca_topic_score_codex":0.0004752526,"about_ca_topic_score_gemma":0.000014648431,"teacher_disagreement_score":0.5736243,"about_ca_system_score_codex":0.00119416,"about_ca_system_score_gemma":0.0018709378,"threshold_uncertainty_score":0.9996343},"labels":[],"label_agreement":null},{"id":"W7139921426","doi":"10.1109/acoit66109.2025.11437087","title":"Emergent AI Behaviors in Multi-Modal Fusion Models: Risks, Patterns, and Control","year":2025,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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":"Oakville-Trafalgar Memorial Hospital","funders":"","keywords":"Control (management); Sensor fusion; Fusion; Key (lock); Control system","score_opus":0.04504473877454069,"score_gpt":0.3236207202977955,"score_spread":0.2785759815232548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7139921426","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":[0.06405008,0.0005601058,0.9304927,0.0019236495,0.0014584757,0.00092897925,0.0000060014218,0.00009658884,0.00048343797],"genre_scores_gemma":[0.98668796,0.0011115558,0.007069287,0.0015581052,0.000024933332,0.000038732014,0.000005015661,0.000019758478,0.003484632],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961655,0.00028485764,0.001117254,0.0010365879,0.00057430635,0.0008214831],"domain_scores_gemma":[0.9983781,0.00010886451,0.0002192801,0.0009032416,0.00017262464,0.00021790552],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073801907,0.00048285016,0.00054185116,0.00052577956,0.00027182477,0.00044047457,0.0009722052,0.00028985323,0.00018617052],"category_scores_gemma":[0.000057837522,0.0004803362,0.00012966701,0.00062360696,0.00011079737,0.0008837223,0.0011282221,0.00073676556,0.000029521714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030119452,0.00021944127,0.16886252,0.000084372215,0.000035113586,0.000026241834,0.00083754084,0.80615747,0.00015339279,0.003989917,0.0001462489,0.019457648],"study_design_scores_gemma":[0.0034412802,0.00016662558,0.07305523,0.00027433544,0.00006140655,0.0000023045989,0.00014916039,0.9219953,0.00015159094,0.00012430402,0.00016222942,0.00041622322],"about_ca_topic_score_codex":0.0032387576,"about_ca_topic_score_gemma":0.00041838188,"teacher_disagreement_score":0.9234234,"about_ca_system_score_codex":0.00018875932,"about_ca_system_score_gemma":0.00020633236,"threshold_uncertainty_score":0.99976486},"labels":[],"label_agreement":null},{"id":"W7143646775","doi":"10.71465/ajainn17","title":"Advances in Reinforcement Learning for Autonomous Systems","year":2020,"lang":"","type":"article","venue":"American Journal of Artificial Intelligence and Neural Networks","topic":"Reinforcement Learning in Robotics","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Reinforcement learning; Autonomous system (mathematics); Reinforcement; Autonomous learning; Autonomous agent","score_opus":0.040690444154212566,"score_gpt":0.29102130276723503,"score_spread":0.25033085861302246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143646775","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":[0.0047696354,0.0051117046,0.98633003,0.0017374962,0.0015155601,0.0004491605,3.046847e-7,0.000023113997,0.000062974366],"genre_scores_gemma":[0.98861885,0.007817019,0.0018082558,0.0006453944,0.0010500035,0.0000076497045,0.0000012521488,0.00002861474,0.000022954151],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956965,0.00030487977,0.0022188465,0.0004917572,0.00049249904,0.0007955246],"domain_scores_gemma":[0.99600494,0.0007265638,0.0022567252,0.00019956626,0.00034681038,0.0004654246],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093893986,0.00040207745,0.0009615132,0.00022772118,0.00026424404,0.0005684917,0.0008923277,0.000095893185,0.000011032093],"category_scores_gemma":[0.00037740526,0.0003806005,0.00019640186,0.0010737459,0.00049794605,0.0012342538,0.00022570274,0.0011736008,0.0000036509368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028591164,0.000014832109,0.00024759799,0.000036162783,0.000021211852,0.000031567226,0.0014037894,0.59977454,0.000015213206,0.0015728889,0.000009731398,0.39658654],"study_design_scores_gemma":[0.00010935635,0.009958771,0.000018583636,0.00025065042,0.000043898548,0.000060311697,0.0026662124,0.9846998,0.00008635319,0.000081985076,0.001651697,0.00037238377],"about_ca_topic_score_codex":0.000030917985,"about_ca_topic_score_gemma":0.000003876822,"teacher_disagreement_score":0.9845218,"about_ca_system_score_codex":0.00009039883,"about_ca_system_score_gemma":0.0001299733,"threshold_uncertainty_score":0.9998646},"labels":[],"label_agreement":null},{"id":"W75018201","doi":"10.1007/978-0-387-74483-4_7","title":"GA Based Task Allocation Models","year":2008,"lang":"en","type":"book-chapter","venue":"","topic":"Reinforcement Learning in Robotics","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":"St. Francis Xavier University","funders":"","keywords":"Task (project management); Computer science; Engineering; Systems engineering","score_opus":0.037697866988620175,"score_gpt":0.22151136079020498,"score_spread":0.1838134938015848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75018201","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.413479e-8,0.000034830213,0.51707387,0.00018327578,0.00014370987,0.00010615849,3.8373258e-7,0.00019422048,0.48226354],"genre_scores_gemma":[0.0013569838,0.0001339209,0.09258942,0.0011034746,0.00007901142,0.000005656076,0.000038196205,0.000035806952,0.90465754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984054,0.000011270735,0.0003230358,0.00045570103,0.00058272755,0.00022186659],"domain_scores_gemma":[0.99846315,0.00006524653,0.00020435838,0.0010278617,0.00015069703,0.00008865551],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00010801359,0.00027802982,0.00022438847,0.0001833158,0.000096614174,0.00010522722,0.0010115171,0.00024877177,0.00019094111],"category_scores_gemma":[0.000009257546,0.0002697093,0.000121382705,0.000039057533,0.000049778682,0.00034266216,0.00019289444,0.00029483667,0.00073518243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.567615e-7,0.0000022439137,2.2467987e-7,0.000007655002,0.0000105254585,0.000007342515,0.00003405057,0.60001373,0.0000018754287,0.39052644,0.00839502,0.001000229],"study_design_scores_gemma":[0.00011409241,0.00004416245,9.3426013e-7,0.000040045532,0.0000068661843,0.0000057245816,2.5927724e-7,0.84775335,0.00001982431,0.005214895,0.1465247,0.000275154],"about_ca_topic_score_codex":0.0000067716596,"about_ca_topic_score_gemma":0.0000012137292,"teacher_disagreement_score":0.42448443,"about_ca_system_score_codex":0.00007328833,"about_ca_system_score_gemma":0.0002081984,"threshold_uncertainty_score":0.9999755},"labels":[],"label_agreement":null},{"id":"W75140964","doi":"","title":"Agnostic KWIK learning and efficient approximate reinforcement learning","year":2011,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Simple (philosophy); Artificial intelligence; Algorithm; Theoretical computer science; Machine learning","score_opus":0.034468881668759915,"score_gpt":0.247999907469349,"score_spread":0.21353102580058908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75140964","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":[0.017019885,0.00009492735,0.8758206,0.000076507,0.00031101788,0.0003280215,9.822605e-8,0.00089724554,0.10545173],"genre_scores_gemma":[0.98171395,0.00019023856,0.0056754756,0.00012803718,0.00005254315,0.00004115337,0.000008373858,0.00005470215,0.01213555],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99615914,0.0007645282,0.00057113275,0.00092906423,0.0006612925,0.00091486034],"domain_scores_gemma":[0.99765784,0.00075680215,0.00050134567,0.0005801079,0.00020414306,0.00029978508],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021377462,0.0005079146,0.00044418368,0.00036733935,0.0008935704,0.0003867545,0.0009923064,0.00018763426,0.00046184173],"category_scores_gemma":[0.0017786014,0.00048528158,0.00011213999,0.0003967939,0.00029837602,0.00032189363,0.0008197119,0.001859389,0.0005078994],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006105223,0.000034288492,0.0015322778,0.00004390314,0.00003994525,0.000029814808,0.0059436164,0.6265475,0.00029458746,0.350251,0.000010193542,0.015211828],"study_design_scores_gemma":[0.0007592156,0.0013526543,0.0010371263,0.00031104253,0.00003470396,0.000030337871,0.0011588521,0.9881581,0.00081188773,0.0029925024,0.0026252882,0.00072827766],"about_ca_topic_score_codex":0.000012577679,"about_ca_topic_score_gemma":2.8962842e-7,"teacher_disagreement_score":0.964694,"about_ca_system_score_codex":0.00009725716,"about_ca_system_score_gemma":0.00011955744,"threshold_uncertainty_score":0.9997599},"labels":[],"label_agreement":null},{"id":"W75509695","doi":"","title":"A new Q(lambda) with interim forward view and Monte Carlo equivalence","year":2014,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":26,"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; University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Monte Carlo method; Markov decision process; Algorithm; Equivalence (formal languages); Q-learning; Markov process; Mathematical optimization; Artificial intelligence; Mathematics; Discrete mathematics; Statistics","score_opus":0.03106032801753098,"score_gpt":0.2875444306336761,"score_spread":0.25648410261614507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W75509695","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":[0.0058020637,0.000039453327,0.96132034,0.0031802608,0.00027388183,0.000101508915,6.2678805e-7,0.00018687545,0.029095018],"genre_scores_gemma":[0.96463466,0.00007349564,0.029527644,0.0005087558,0.00009552104,0.000008056833,0.000004363942,0.000017892475,0.005129643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982998,0.000119026976,0.00025315658,0.00046917453,0.0005884228,0.00027041783],"domain_scores_gemma":[0.9990155,0.00014582435,0.00020950189,0.00031188517,0.00016285018,0.0001544155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003330419,0.00022769332,0.00020464147,0.00016338739,0.00012920039,0.00049456133,0.0009886603,0.000052767038,0.00017736766],"category_scores_gemma":[0.0002251644,0.00019371982,0.000043594882,0.00013641789,0.0000549234,0.00047791295,0.00039539495,0.0005431382,0.00007747731],"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":[0.000104523155,0.000026052054,0.02129933,0.000042235155,0.00011702433,0.000026306325,0.0013384855,0.30017272,0.000511555,0.46526465,0.00020744055,0.2108897],"study_design_scores_gemma":[0.00056254346,0.0007122847,0.0018067358,0.0002505214,0.0000075706766,0.00003886014,0.00002873256,0.97990346,0.00011449504,0.0008080657,0.015504364,0.0002623498],"about_ca_topic_score_codex":0.00014961127,"about_ca_topic_score_gemma":0.000024258123,"teacher_disagreement_score":0.95883256,"about_ca_system_score_codex":0.000046968547,"about_ca_system_score_gemma":0.000072106945,"threshold_uncertainty_score":0.7899665},"labels":[],"label_agreement":null},{"id":"W80327629","doi":"10.2316/journal.206.2009.3.206-3270","title":"INTERNAL REPRESENTATION OF THE ENVIRONMENT IN COGNITIVE ROBOTICS","year":2009,"lang":"en","type":"article","venue":"International Journal of Robotics and Automation","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Representation (politics); Artificial intelligence; Cognitive robotics; Computer science; Cognition; Robotics; Psychology; Robot; Neuroscience; Political science","score_opus":0.017317283841722236,"score_gpt":0.2809598773564247,"score_spread":0.26364259351470243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W80327629","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":[0.036775395,0.00004361922,0.9584441,0.0038527723,0.00051157945,0.0000737883,5.0095196e-7,0.000005853638,0.00029238776],"genre_scores_gemma":[0.9723266,0.00009857409,0.027345382,0.00013228122,0.000045108525,2.7728498e-7,0.0000011238121,0.0000025675574,0.000048125374],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998693,0.000059653124,0.00052163086,0.00008939115,0.000557685,0.00007865436],"domain_scores_gemma":[0.9988947,0.000106190324,0.00066458434,0.00010113343,0.00020562524,0.000027803679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025881192,0.00007278437,0.00012499119,0.00017397755,0.000023589912,0.00008161936,0.0004948959,0.000035179055,0.000004116046],"category_scores_gemma":[0.00015790193,0.00005584634,0.00006315555,0.00012044933,0.00003738467,0.00043623926,0.00010014858,0.00015272776,0.0000011304658],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009840488,0.000048639562,0.007451946,0.0000022216884,0.000027912747,0.000007862943,0.00045265598,0.9599904,0.00068770925,0.011505368,0.000019692969,0.019795788],"study_design_scores_gemma":[0.00076134066,0.00016684091,0.1910892,0.00024535254,0.0000147047995,0.00007272929,0.0000707152,0.7996474,0.0022811028,0.005554956,0.0000205879,0.00007506172],"about_ca_topic_score_codex":0.000004627642,"about_ca_topic_score_gemma":6.4238304e-7,"teacher_disagreement_score":0.93555117,"about_ca_system_score_codex":0.00007145691,"about_ca_system_score_gemma":0.000036533642,"threshold_uncertainty_score":0.22773476},"labels":[],"label_agreement":null},{"id":"W84951255","doi":"","title":"Learning subjective representations for planning","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Alberta; University of Waterloo","funders":"","keywords":"Embedding; Representation (politics); Computer science; Artificial intelligence; Domain (mathematical analysis); Construct (python library); Action (physics); Domain knowledge; Robot; Sequence (biology); Knowledge representation and reasoning; Machine learning; Mathematics","score_opus":0.02995310586468893,"score_gpt":0.31831261305652775,"score_spread":0.28835950719183884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W84951255","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":[0.0014727119,0.00001121587,0.95556366,0.00076941913,0.000097468466,0.00015421523,8.502141e-8,0.0002945279,0.04163671],"genre_scores_gemma":[0.6496452,0.0000012385347,0.33587438,0.00021755602,0.00010072722,0.000025060168,0.000002952046,0.0000069045877,0.014125952],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928284,0.000024605084,0.00014175303,0.0002115912,0.0001372508,0.00020197588],"domain_scores_gemma":[0.999339,0.0002673408,0.00006256408,0.00021493368,0.000073823234,0.000042342126],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018090963,0.00006805036,0.000069071226,0.00007534156,0.00021210307,0.00013292287,0.00032851176,0.00002774619,0.00002194917],"category_scores_gemma":[0.00019378716,0.00006577455,0.000043497603,0.00016547716,0.000014251727,0.0004968646,0.00009753189,0.000110092304,0.00006878489],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016489977,0.0000044076037,0.0022913173,0.0000018820418,0.000008447307,4.4696904e-7,0.0011948643,0.9548796,0.00011871836,0.036193002,0.0006666098,0.0046391007],"study_design_scores_gemma":[0.00021860958,0.00008155797,0.0015402567,0.0000054245847,0.000002670366,0.0000033190927,0.00014565625,0.97586995,0.0014662115,0.00028402216,0.020284854,0.00009743783],"about_ca_topic_score_codex":0.0000055332416,"about_ca_topic_score_gemma":9.643734e-7,"teacher_disagreement_score":0.6481725,"about_ca_system_score_codex":0.000037010377,"about_ca_system_score_gemma":0.000027223343,"threshold_uncertainty_score":0.2682208},"labels":[],"label_agreement":null},{"id":"W85998123","doi":"10.1609/icaps.v19i1.13355","title":"Incremental Policy Generation for Finite-Horizon DEC-POMDPs","year":2009,"lang":"en","type":"article","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"National Science Foundation","keywords":"Dynamic programming; Computer science; Scalability; Reachability; Mathematical optimization; State (computer science); State space; Reduction (mathematics); Backup; Horizon; Algorithm; Mathematics","score_opus":0.05613533112334739,"score_gpt":0.31798258634313714,"score_spread":0.26184725521978974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W85998123","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":[0.8231798,0.000031377196,0.15691182,0.007752398,0.00059184164,0.00039525726,0.0000054859925,0.0007152855,0.010416759],"genre_scores_gemma":[0.9512043,0.000008926823,0.048234075,0.00033007417,0.00012932987,0.0000070846463,0.00000504657,0.000005372223,0.000075775446],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989807,0.0000054413485,0.00026230398,0.00023771862,0.00034734086,0.00016649182],"domain_scores_gemma":[0.99924546,0.000060393635,0.0002614639,0.00008025338,0.0003101354,0.00004227408],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030832167,0.00012684957,0.00011723971,0.0001721926,0.00017789174,0.00034842748,0.00072171475,0.00006238276,0.0000021578724],"category_scores_gemma":[0.0003896973,0.00010301291,0.000044228243,0.00015665404,0.0000217889,0.00033751375,0.00011052835,0.00012249046,0.0000013592839],"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":[0.000049027694,0.00005552316,0.0020782035,0.000031640335,0.00007153163,5.842673e-7,0.0012936533,0.13279042,0.18110326,0.67777187,0.0005655419,0.0041887416],"study_design_scores_gemma":[0.0003021205,0.00023475828,0.0006775631,0.00017250737,0.000006044,0.000005400974,0.00008238517,0.9712363,0.025428485,0.0016680942,0.00007779745,0.000108543405],"about_ca_topic_score_codex":0.000004935337,"about_ca_topic_score_gemma":1.0594683e-7,"teacher_disagreement_score":0.8384459,"about_ca_system_score_codex":0.00006150985,"about_ca_system_score_gemma":0.00007066078,"threshold_uncertainty_score":0.42007446},"labels":[],"label_agreement":null},{"id":"W87408738","doi":"","title":"Apprentissage de la coordination multiagent : Q-learning par jeu adaptatif","year":2005,"lang":"fr","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","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 Laval","funders":"","keywords":"Humanities; Nash equilibrium; Mathematical economics; Philosophy; Mathematics","score_opus":0.02170017316396445,"score_gpt":0.274899334009066,"score_spread":0.2531991608451016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W87408738","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":[0.002952629,0.00085439964,0.9253612,0.0051078666,0.00077159377,0.00023151438,5.444565e-7,0.0003077622,0.064412475],"genre_scores_gemma":[0.6353641,0.00014224464,0.20976135,0.00023139406,0.00025915893,0.00001158824,0.000006432342,0.000025366548,0.15419833],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970364,0.0007490393,0.0004797661,0.00048755892,0.0005283192,0.00071890163],"domain_scores_gemma":[0.9983377,0.00058900984,0.0002493212,0.00044018094,0.00014429081,0.00023948553],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001368949,0.00028713577,0.00022360001,0.00013402927,0.00036000457,0.00073857413,0.0007011499,0.0002363332,0.001351577],"category_scores_gemma":[0.0004397207,0.00032230152,0.00012809626,0.0004113209,0.00020449181,0.0010611697,0.00038186397,0.0007033596,0.0011730618],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000029692308,0.00007940474,0.0016874768,0.000037241578,0.000035478184,0.00002258467,0.0031886415,0.7678071,0.00033790205,0.041954402,0.005538755,0.17930801],"study_design_scores_gemma":[0.00041280003,0.00008806245,0.0028451544,0.00006913016,0.000023683282,0.000031683387,0.00018652675,0.6816096,0.00087240303,0.000061845276,0.31355134,0.00024778422],"about_ca_topic_score_codex":0.00013110637,"about_ca_topic_score_gemma":0.00001372967,"teacher_disagreement_score":0.71559983,"about_ca_system_score_codex":0.00028564775,"about_ca_system_score_gemma":0.00015654635,"threshold_uncertainty_score":0.99992293},"labels":[],"label_agreement":null},{"id":"W88806592","doi":"10.1007/978-3-642-28499-1_5","title":"Leveraging Domain Knowledge to Learn Normative Behavior: A Bayesian Approach","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick; University of Waterloo","funders":"","keywords":"Normative; Computer science; Reinforcement learning; Norm (philosophy); Domain knowledge; Artificial intelligence; Set (abstract data type); Domain (mathematical analysis); Adaptation (eye); Process (computing); Normative model of decision-making; Bayesian probability; Machine learning; Knowledge management; Psychology; Epistemology; Mathematics","score_opus":0.02530434686639648,"score_gpt":0.26163652532155574,"score_spread":0.23633217845515925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W88806592","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":[0.000033247226,0.00035368378,0.973544,0.00030418916,0.0016737604,0.00090285356,0.0000017209512,0.0002856995,0.022900814],"genre_scores_gemma":[0.1343446,0.000013684536,0.86247706,0.0010193947,0.00060698495,0.00004674334,0.000008863148,0.00007254445,0.0014101212],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9947803,0.00009929289,0.0007508522,0.0016815182,0.0013297973,0.001358211],"domain_scores_gemma":[0.99650615,0.00035105244,0.00037814135,0.0019627986,0.00029583703,0.0005060205],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016231597,0.00082168647,0.0007222875,0.0014571497,0.00048516775,0.0008722865,0.0050901053,0.0003900243,0.000034777077],"category_scores_gemma":[0.00007974366,0.00079125684,0.00018814763,0.0011091799,0.0005245422,0.001064939,0.0033052173,0.0015489612,0.00034430213],"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":[0.0000056648523,0.00006138084,0.00015279684,0.000062051935,0.000017157225,0.00003500262,0.011954408,0.45558053,0.000062913,0.016644659,0.000049158236,0.51537424],"study_design_scores_gemma":[0.00045293896,0.00041585186,0.0003946288,0.00051307416,0.000028624572,0.00018986818,0.0000031913294,0.97145957,0.00035922384,0.01175505,0.012460046,0.001967913],"about_ca_topic_score_codex":0.000015690766,"about_ca_topic_score_gemma":0.0000098806995,"teacher_disagreement_score":0.51587903,"about_ca_system_score_codex":0.0008017113,"about_ca_system_score_gemma":0.0005332526,"threshold_uncertainty_score":0.99945384},"labels":[],"label_agreement":null},{"id":"W9932698","doi":"10.48550/arxiv.1205.2619","title":"Regret-based Reward Elicitation for Markov Decision Processes","year":2012,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Regret; Markov decision process; Computer science; Preference elicitation; Function (biology); Minimax; Preference; Markov process; Markov chain; Mathematical optimization; Machine learning; Mathematics; Economics; Microeconomics","score_opus":0.06076316977610513,"score_gpt":0.3316740532104062,"score_spread":0.2709108834343011,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W9932698","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":[0.006224458,0.000100567726,0.99106616,0.00062897167,0.0008009584,0.0005801766,0.0000021409483,0.00014265958,0.00045393853],"genre_scores_gemma":[0.83595026,0.000015355714,0.16332868,0.00036667445,0.00014285771,0.00010020419,0.000012747715,0.000015301133,0.00006795394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977805,0.00007609058,0.00065835344,0.00039691385,0.00045059447,0.00063751626],"domain_scores_gemma":[0.9971154,0.0016669366,0.00020772919,0.00052001246,0.00036072376,0.00012924668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001253235,0.00020912317,0.00021047328,0.0002943731,0.00016907648,0.00018532133,0.000864263,0.00011956389,0.000029275177],"category_scores_gemma":[0.00340313,0.00019806823,0.00007388119,0.0010691283,0.00008641126,0.00068490417,0.00009730591,0.00018552711,0.0001174913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086741224,0.000088580404,0.00092815625,0.000062485975,0.0000042258166,0.0000011907373,0.0011791738,0.7760761,0.000173311,0.03872203,0.00017677435,0.18250127],"study_design_scores_gemma":[0.00006960314,0.00017097045,0.00019212207,0.0001483679,0.000005887343,0.0000016824342,0.0002495141,0.9661885,0.012210977,0.017191485,0.0032668232,0.0003040811],"about_ca_topic_score_codex":0.00006058887,"about_ca_topic_score_gemma":0.000084854975,"teacher_disagreement_score":0.8297258,"about_ca_system_score_codex":0.00019137963,"about_ca_system_score_gemma":0.000198879,"threshold_uncertainty_score":0.8076988},"labels":[],"label_agreement":null}]}