{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":993,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":993,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2c5a9e04f9ca","filters":{"topic":"Energy Load and Power Forecasting"}},"results":[{"id":"W2809317444","doi":"10.3390/en11071636","title":"Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches †","year":2018,"lang":"en","type":"article","venue":"Energies","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":902,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"United Arab Emirates University","keywords":"Computer science; Machine learning; Artificial intelligence; Hyperparameter; Mean absolute percentage error; Mean squared error; Feature selection; Artificial neural network; Time series; Scheduling (production processes); Feature engineering; Feature (linguistics); Genetic algorithm; Model selection; Deep learning; Algorithm; Mathematical optimization; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02982244564177539,"gpt":0.2186246528030399,"spread":0.1888022071612645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001448614,0.0003052183,0.0002906687,0.0001506006,0.0005381189,0.0001227505,0.00008814233,0.0001390603,0.000003014211],"category_scores_gemma":[0.00004146008,0.0002842465,0.00004687075,0.0003300228,0.00004637944,0.0001975001,0.00003666662,0.0004203962,5.203057e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009980975,"about_ca_system_score_gemma":0.00003094204,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004136504,"about_ca_topic_score_gemma":0.0001233224,"domain_scores_codex":[0.9987563,0.00003339912,0.0002075253,0.0003185619,0.000178459,0.0005057717],"domain_scores_gemma":[0.9995821,0.00008183064,0.00008997529,0.00007837392,0.00009140149,0.00007635614],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003194001,0.000007453474,0.001828049,0.00005833848,0.00006205313,0.000001464877,0.001257577,0.9374834,0.003081522,0.00002427544,0.000009477033,0.05615447],"study_design_scores_gemma":[0.0004048045,0.0002731001,0.00009165822,0.00006458208,0.00006773309,0.0001085076,0.0001901444,0.9907103,0.007282781,0.00001586232,0.0004252863,0.0003652452],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.525897,0.001890741,0.4715687,0.000003488432,0.00005755206,0.00007594959,0.00000103886,0.0002720705,0.0002334052],"genre_scores_gemma":[0.7195566,0.00003858496,0.2798149,0.000003548058,0.0002974998,0.00001949266,0.00001453212,0.00007660784,0.0001781601],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1936596,"threshold_uncertainty_score":0.999961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060606400","doi":"10.1109/naps.2010.5619586","title":"A review of wind power and wind speed forecasting methods with different time horizons","year":2010,"lang":"en","type":"review","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":873,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Intermittency; Wind power; Wind power forecasting; Wind speed; Renewable energy; Meteorology; Computer science; Artificial neural network; Electric power system; Power (physics); Environmental science; Engineering; Artificial intelligence; Electrical engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.03647778405806498,"gpt":0.3008323776487027,"spread":0.2643545935906377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005201699,0.000706551,0.002564985,0.0001785888,0.00004852608,0.00003422254,0.000244282,0.0003470802,0.0004433471],"category_scores_gemma":[0.0001072541,0.0004468736,0.0003312247,0.0003298079,0.00007762778,0.00008348662,0.0001021143,0.0007737018,0.000008851859],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003269699,"about_ca_system_score_gemma":0.00005071935,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004336119,"about_ca_topic_score_gemma":0.000003462419,"domain_scores_codex":[0.9980814,0.0001261931,0.0008320542,0.0003736545,0.0001815437,0.0004051203],"domain_scores_gemma":[0.9985421,0.0004839524,0.0002722109,0.0004640616,0.00005861114,0.0001790256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001014513,0.00001110898,0.000001359409,0.1031398,0.0002279135,0.000006318674,0.00002375365,0.000009833866,0.00001106688,0.00005429536,0.0003295061,0.896184],"study_design_scores_gemma":[0.00009704138,0.0000859055,6.33008e-7,0.1748898,0.0007626109,0.0002114795,0.000002100953,0.0003473044,0.00001717974,0.000006979926,0.8230867,0.0004922894],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000356213,0.9722255,0.0004733235,0.000003825032,0.0003270146,0.0005293333,0.00002909006,0.0001410121,0.02623531],"genre_scores_gemma":[0.000003930765,0.9868885,0.01207908,0.00001911489,0.0001203497,0.00000473736,0.00005479859,0.0001557121,0.0006738288],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8956917,"threshold_uncertainty_score":0.9997983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2095731600","doi":"10.1109/tpwrs.2008.2008606","title":"Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":409,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Particle swarm optimization; Artificial neural network; Computer science; Wavelet; Term (time); Backpropagation; Algorithm; Preprocessor; Data pre-processing; Mathematical optimization; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02992717806607406,"gpt":0.2363314054395546,"spread":0.2064042273734805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002315648,0.000418758,0.0003896028,0.0002628601,0.0003048522,0.0001722639,0.0002203486,0.0001963344,0.00002129599],"category_scores_gemma":[0.000003781847,0.0004410168,0.0001867273,0.000515827,0.00001753401,0.0002103971,0.000001064924,0.0004511068,0.00001258763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003114624,"about_ca_system_score_gemma":0.00002960537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004323651,"about_ca_topic_score_gemma":0.00002559103,"domain_scores_codex":[0.9979218,0.00004770915,0.0005522955,0.0003847852,0.0003752381,0.0007181792],"domain_scores_gemma":[0.9991202,0.00009293454,0.00004734596,0.0003873473,0.00007792655,0.0002742081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000176704,0.00003334003,0.0000308396,0.0000389201,0.00003485485,0.00003765108,0.0001880977,0.9834571,0.003915721,0.000006478907,0.00006022615,0.01217903],"study_design_scores_gemma":[0.0002799643,0.0001381172,0.00003029031,0.0004137303,0.00003569369,0.00009394097,0.00005071099,0.9945646,0.003216794,0.000001022114,0.0006937014,0.0004814602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1451431,0.0001957094,0.8478839,0.00001353726,0.004160905,0.0005220104,0.00001482064,0.000619096,0.001446904],"genre_scores_gemma":[0.9986382,0.00000280607,0.0008261927,0.0001432506,0.0001269044,0.0001050265,0.000003680652,0.00009040718,0.00006354479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8534951,"threshold_uncertainty_score":0.9998041,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3129054759","doi":"10.1109/tii.2021.3056867","title":"A Stacked GRU-RNN-Based Approach for Predicting Renewable Energy and Electricity Load for Smart Grid Operation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":388,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"Fundamental Research Funds for the Central Universities","keywords":"Recurrent neural network; Computer science; Smart grid; Robustness (evolution); Renewable energy; Electricity; Electricity generation; Wind power; Artificial intelligence; Machine learning; Engineering; Artificial neural network; Power (physics)","retraction":null,"screen_n_in":null,"score":{"opus":0.03356084192651567,"gpt":0.2200618236794241,"spread":0.1865009817529084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002698704,0.0002045703,0.0002423267,0.000117704,0.0003391933,0.0001366215,0.00007545547,0.0002715081,0.00001005197],"category_scores_gemma":[0.00004390231,0.0002173917,0.0001017539,0.0002761293,0.00002223918,0.0003207765,9.988679e-7,0.0002104385,3.708175e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001526897,"about_ca_system_score_gemma":0.0002270979,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009935938,"about_ca_topic_score_gemma":0.0001563104,"domain_scores_codex":[0.998819,0.00002077323,0.000532505,0.0001252066,0.0001762826,0.0003262374],"domain_scores_gemma":[0.9992526,0.0002651468,0.0000729452,0.0001610239,0.0001478671,0.0001004645],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008663509,0.00004526589,0.000006686141,0.0001246119,0.00007091297,2.114138e-7,0.0002725771,0.987008,0.0005239136,0.00003859355,0.001491004,0.01033161],"study_design_scores_gemma":[0.001931496,0.0001580234,2.60225e-7,0.00004801038,0.00006542155,0.000005431908,0.0001845629,0.8308698,0.1577666,0.00001771167,0.008752911,0.00019979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01031257,0.00002701191,0.9865664,0.00002038203,0.001058327,0.0003358319,0.0002457039,0.000206147,0.00122767],"genre_scores_gemma":[0.9610555,0.00004892571,0.03677676,0.0001820009,0.0005920907,0.0004962533,0.0003326888,0.0000669802,0.0004488187],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9507429,"threshold_uncertainty_score":0.8864976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2111528621","doi":"10.1016/j.enbuild.2005.02.005","title":"On-line building energy prediction using adaptive artificial neural networks","year":2005,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":327,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Concordia University","funders":"Natural Resources Canada","keywords":"Artificial neural network; Sliding window protocol; Training (meteorology); Variance (accounting); Computer science; Window (computing); Energy (signal processing); Line (geometry); Artificial intelligence; Training set; Machine learning; Engineering; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01770223546562169,"gpt":0.216357825445661,"spread":0.1986555899800393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001053752,0.000263512,0.000204691,0.0001475156,0.0002270299,0.00006550415,0.00009676935,0.0001696716,0.00002889704],"category_scores_gemma":[0.00001189191,0.0002645287,0.00006776265,0.0002233151,0.00004904183,0.0002697447,0.00004137661,0.0001789255,4.758248e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006910984,"about_ca_system_score_gemma":0.000006487325,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009715731,"about_ca_topic_score_gemma":0.00008292872,"domain_scores_codex":[0.998848,0.00002326017,0.0002864924,0.0002842504,0.0001463277,0.0004116807],"domain_scores_gemma":[0.9995854,0.00008290004,0.00005081169,0.0001257854,0.0000262208,0.0001288919],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003080735,0.0000137543,0.00002278584,0.000003076663,0.00003034583,0.000004205278,0.00004062523,0.860337,0.003940811,0.06171133,0.0001847821,0.07368053],"study_design_scores_gemma":[0.0001848515,0.00009230075,0.00001163318,0.00006719484,0.00002211937,0.00003344359,0.00001200411,0.9750742,0.01419506,0.0008967743,0.009151956,0.0002584407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5484329,0.0009441628,0.4472704,0.00004466354,0.0009165394,0.0000227391,0.00000731816,0.0004074942,0.001953815],"genre_scores_gemma":[0.9944615,0.0001176462,0.003151699,0.0001991684,0.001908513,0.000006715313,0.0000128742,0.00005450056,0.00008735914],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4460286,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3004665554","doi":"10.1016/j.energy.2020.117081","title":"Wind power forecasting using attention-based gated recurrent unit network","year":2020,"lang":"en","type":"article","venue":"Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":321,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Wind power forecasting; Feature selection; Computer science; Wind power; Selection (genetic algorithm); Task (project management); Artificial intelligence; Machine learning; Model selection; Electric power system; Feature (linguistics); Power (physics); Sequence (biology); Data mining; Engineering; Systems engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03768735253833277,"gpt":0.2186283451525827,"spread":0.1809409926142499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007949199,0.0002204435,0.0002042381,0.00005052967,0.0001299062,0.00004709983,0.0001388517,0.0000933218,0.0002511526],"category_scores_gemma":[0.00003181362,0.0002351753,0.00009559273,0.0005026288,0.00002122682,0.0001204765,0.00003370904,0.0001717625,0.00001109617],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003770983,"about_ca_system_score_gemma":0.00002688075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003571821,"about_ca_topic_score_gemma":0.00002336811,"domain_scores_codex":[0.9988672,0.00003636269,0.000286468,0.0002161232,0.0001586895,0.0004351663],"domain_scores_gemma":[0.9995161,0.00006483581,0.00005465957,0.000140889,0.00004119992,0.000182321],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001133688,0.000006794332,0.0005928281,0.00002201701,0.00003492502,0.00002059924,0.00006529467,0.9913771,0.001450831,0.0005544125,0.001002492,0.004861385],"study_design_scores_gemma":[0.0002397845,0.00004710533,0.00008314735,0.0001474156,0.00001895853,0.000005086082,0.00001692908,0.9284602,0.001301085,0.00004971142,0.06934153,0.0002890625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8496078,0.002090591,0.11695,0.0002527439,0.003058895,0.0001079888,0.00002104778,0.001470365,0.02644055],"genre_scores_gemma":[0.9962878,0.000007981284,0.00248716,0.0003860435,0.0006505918,0.000001922362,0.00006055458,0.00007276477,0.00004514758],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1466801,"threshold_uncertainty_score":0.959017,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2070960910","doi":"10.1016/j.apenergy.2013.08.025","title":"Short-term wind speed prediction using an unscented Kalman filter based state-space support vector regression approach","year":2013,"lang":"en","type":"article","venue":"Applied Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":307,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"","keywords":"Kalman filter; Wind speed; Control theory (sociology); Autoregressive model; Support vector machine; State vector; State-space representation; Extended Kalman filter; State space; Computer science; Wind power; Machine learning; Engineering; Artificial intelligence; Algorithm; Mathematics; Statistics; Meteorology; Control (management)","retraction":null,"screen_n_in":null,"score":{"opus":0.01974524898331919,"gpt":0.2147096499951622,"spread":0.194964401011843,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00009017724,0.0003508498,0.0002653446,0.0001576993,0.000125744,0.00008739813,0.000185999,0.0001782865,0.0002440247],"category_scores_gemma":[0.000002749329,0.0003249632,0.00006607388,0.0002411051,0.00004131897,0.0002872498,0.00003759172,0.0001941867,0.00001458636],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062068,"about_ca_system_score_gemma":0.00002331697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001286833,"about_ca_topic_score_gemma":0.00001390107,"domain_scores_codex":[0.998456,0.00002798585,0.0003320616,0.000393918,0.0002701006,0.0005199237],"domain_scores_gemma":[0.9992366,0.00002262554,0.000052689,0.0004124441,0.00004044837,0.0002351535],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002682773,0.0001165403,0.0009327573,0.00006373405,0.00005072394,0.000006793015,0.000245096,0.7566321,0.2345119,0.0002475776,0.001477304,0.005688574],"study_design_scores_gemma":[0.0006505382,0.0000699607,0.002956049,0.00007113055,0.00003495152,0.00001142541,0.00007537707,0.880527,0.1124028,0.00005276357,0.002597336,0.000550653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9563963,0.00003333999,0.02921606,0.000007539465,0.0006064703,0.0001761073,0.00002330148,0.0007187565,0.01282206],"genre_scores_gemma":[0.9960331,0.00001145905,0.002572088,0.00005021589,0.0003086404,0.00001644272,0.0006390702,0.0001198706,0.0002490549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1238948,"threshold_uncertainty_score":0.9999202,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285122835","doi":"10.1109/access.2022.3187839","title":"Load Forecasting Techniques for Power System: Research Challenges and Survey","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":298,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Mean absolute percentage error; Mean squared error; Computer science; Electrical load; Electric power system; Electricity; Mean absolute error; Artificial neural network; Artificial intelligence; Power (physics); Machine learning; Operations research; Statistics; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1900834257854434,"gpt":0.3457127124009007,"spread":0.1556292866154572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002489886,0.0001300766,0.0001787204,0.0001594221,0.0003596205,0.00009687752,0.0003655571,0.0000549467,0.00001354735],"category_scores_gemma":[0.00009676403,0.0001359675,0.00003211376,0.0002184136,0.0000315067,0.0002125918,0.0001838712,0.0002902004,9.756492e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001619358,"about_ca_system_score_gemma":0.00002838857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001348695,"about_ca_topic_score_gemma":0.0002257869,"domain_scores_codex":[0.9987049,0.0001329504,0.000198904,0.0002423503,0.0003148789,0.0004059775],"domain_scores_gemma":[0.9990043,0.0005628274,0.00003008888,0.0001997309,0.0001380718,0.00006497979],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007316847,0.0003283674,0.01090826,0.01160866,0.000819325,0.0003285549,0.02626088,0.0615925,0.01403541,0.0187422,0.06876847,0.7858757],"study_design_scores_gemma":[0.004003441,0.002507541,0.01482492,0.002272712,0.000113143,0.0008699147,0.0124021,0.3857652,0.124571,0.005350993,0.442255,0.005064001],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9108356,0.01457311,0.003441501,0.00009416673,0.002345548,0.0009636983,0.0001810573,0.001433695,0.06613162],"genre_scores_gemma":[0.9988423,0.0001636712,0.0003041548,0.000009922315,0.0001467771,0.0003725136,0.000009467846,0.00005663215,0.00009456204],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7808117,"threshold_uncertainty_score":0.5544592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3131110071","doi":"10.1109/access.2021.3060290","title":"On Short-Term Load Forecasting Using Machine Learning Techniques and a Novel Parallel Deep LSTM-CNN Approach","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":287,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Mean absolute percentage error; Computer science; Mean squared error; Artificial intelligence; Artificial neural network; Term (time); Electrical load; Deep learning; Scheduling (production processes); Convolutional neural network; Energy consumption; Machine learning; Power (physics); Statistics; Mathematical optimization; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05566551343136726,"gpt":0.2734295795453011,"spread":0.2177640661139338,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001730141,0.0002808942,0.0002789734,0.0001026152,0.0001962128,0.0002470436,0.0002076243,0.0001360549,0.00001684834],"category_scores_gemma":[0.00005062626,0.0002858091,0.00006588319,0.0002743341,0.00003282273,0.0003691431,0.0001116499,0.0004489006,0.000001094945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000849047,"about_ca_system_score_gemma":0.00002591584,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005985984,"about_ca_topic_score_gemma":0.00005755123,"domain_scores_codex":[0.9987176,0.00002583818,0.0002817354,0.000352702,0.0002179359,0.0004041812],"domain_scores_gemma":[0.9994809,0.0001038396,0.00004718811,0.0002015857,0.00006341802,0.00010308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005358031,0.0001457194,0.01851216,0.0007005866,0.0002048703,0.000378999,0.001043877,0.8405167,0.08009749,0.0008350716,0.00003615587,0.05747473],"study_design_scores_gemma":[0.0003539846,0.00003158631,0.000112449,0.0002824298,0.00003525804,0.000393159,0.00003453212,0.939545,0.05800952,0.0001282494,0.0006105022,0.0004633398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7723202,0.001033824,0.2114885,0.000006370802,0.0002984812,0.0001177189,0.00000621309,0.0005361306,0.01419256],"genre_scores_gemma":[0.9745242,0.00006619027,0.02488423,0.00003573019,0.0002798416,0.0000212565,0.00002387604,0.00008246169,0.00008220844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.202204,"threshold_uncertainty_score":0.9999594,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2952133925","doi":"10.1016/j.petrol.2019.106187","title":"Conventional models and artificial intelligence-based models for energy consumption forecasting: A review","year":2019,"lang":"en","type":"review","venue":"Journal of Petroleum Science and Engineering","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":255,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"China Scholarship Council","keywords":"Artificial neural network; Predictive modelling; Mean absolute percentage error; Computer science; Energy consumption; Benchmark (surveying); Model selection; Machine learning; Artificial intelligence; Consumption (sociology); Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1341996585916335,"gpt":0.2977740448513552,"spread":0.1635743862597217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001207425,0.0003274176,0.001035085,0.0005717448,0.00008667853,0.0001206105,0.0002559916,0.0001249135,0.000005065665],"category_scores_gemma":[0.00009408235,0.0002777638,0.0002549118,0.0002916685,0.00008987357,0.0005949623,0.00003750437,0.000292781,5.199794e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001319468,"about_ca_system_score_gemma":0.0002511876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":9.613591e-7,"about_ca_topic_score_gemma":5.727715e-7,"domain_scores_codex":[0.9980962,0.00001306924,0.0008877282,0.0002312314,0.0004102657,0.0003615078],"domain_scores_gemma":[0.9989638,0.0002317744,0.0002979846,0.0001237069,0.0001969519,0.0001858015],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003096346,0.000006911318,1.321214e-7,0.027884,0.00004740933,0.000004248411,0.00001139314,0.4971358,0.00001202699,0.005111868,0.00004712174,0.469736],"study_design_scores_gemma":[0.00006566395,0.0000667722,5.236719e-8,0.03295524,0.0002782613,0.0002238158,0.000003307327,0.8913225,0.00001020323,0.0003773967,0.07443483,0.0002619791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00001501632,0.7141466,0.2851233,0.00000821785,0.0005197707,0.00008668318,0.00001238018,0.00002197379,0.00006603519],"genre_scores_gemma":[0.00195561,0.9936151,0.004101641,0.0000191944,0.0002272968,0.00002132688,0.000007475209,0.00004318642,0.000009157284],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.469474,"threshold_uncertainty_score":0.9999675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045941597","doi":"10.1109/icc40277.2020.9148937","title":"Electrical Load Forecasting Using Edge Computing and Federated Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":246,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Smart meter; Deep learning; Big data; Smart grid; Enhanced Data Rates for GSM Evolution; Edge computing; Federated learning; Machine learning; Artificial intelligence; Scheme (mathematics); Data modeling; Edge device; Variety (cybernetics); Information privacy; Data mining; Computer security; Database; Engineering; Cloud computing","retraction":null,"screen_n_in":null,"score":{"opus":0.039734403292077,"gpt":0.2449674601139583,"spread":0.2052330568218813,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002391129,0.0004787743,0.0005422187,0.00011032,0.0002950705,0.000357772,0.0001518067,0.000376676,0.00002600894],"category_scores_gemma":[0.0001968378,0.0005148248,0.0001043935,0.0002580573,0.00003034985,0.00007707872,0.0005459983,0.001856235,0.000006224909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002075562,"about_ca_system_score_gemma":0.0001032467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001091549,"about_ca_topic_score_gemma":0.00001610267,"domain_scores_codex":[0.9981216,0.00005907872,0.000487165,0.0005232831,0.0002411527,0.000567746],"domain_scores_gemma":[0.9993098,0.0001760565,0.0001065349,0.0001177856,0.00008228202,0.0002075269],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008564125,0.000007031283,0.00147733,0.0004740266,0.0001513414,0.00006857963,0.0006826542,0.9450969,0.004374821,0.0001622286,0.0001987775,0.04729781],"study_design_scores_gemma":[0.0001981525,0.00002518352,0.0000586896,0.0003745372,0.00004259236,0.00007034586,0.00004545608,0.9962078,0.001443611,0.0001316727,0.0008474525,0.0005544577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7514983,0.002177193,0.2106847,0.00003840025,0.001005312,0.0002248889,0.000003831494,0.002163263,0.03220408],"genre_scores_gemma":[0.9832343,0.00005365967,0.01579189,0.00004939049,0.0006398962,0.000002644538,0.00003311462,0.0001253537,0.00006973947],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.231736,"threshold_uncertainty_score":0.9997303,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2999869395","doi":"10.3390/en13020391","title":"Multi-Sequence LSTM-RNN Deep Learning and Metaheuristics for Electric Load Forecasting","year":2020,"lang":"en","type":"article","venue":"Energies","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":246,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure","funders":"United Arab Emirates University","keywords":"Computer science; Hyperparameter; Artificial intelligence; Machine learning; Smart grid; Metaheuristic; Energy consumption; Domain knowledge; Mathematical optimization; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03967173078159233,"gpt":0.2379846056737035,"spread":0.1983128748921112,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001148481,0.0001945497,0.0002147208,0.00004740928,0.0001507015,0.00006700405,0.0001036193,0.00007056265,0.000008531098],"category_scores_gemma":[0.0005249726,0.0001972911,0.00005636643,0.0002107622,0.00002537268,0.0001240919,0.00004024106,0.0001982097,0.000003528812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003310433,"about_ca_system_score_gemma":0.00001598052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001123863,"about_ca_topic_score_gemma":0.00001577034,"domain_scores_codex":[0.9990903,0.00001727362,0.0002127432,0.0002154083,0.0001153889,0.0003488892],"domain_scores_gemma":[0.999495,0.0002341095,0.00004357182,0.00006500974,0.00005320271,0.0001091348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001893755,0.000007289188,0.0009644881,0.0003022207,0.00009386605,0.00002104721,0.001881685,0.836117,0.08546162,0.001138307,0.0001910137,0.07380252],"study_design_scores_gemma":[0.0003120471,0.0000710758,0.00005056765,0.0000286561,0.00003276591,0.00001187994,0.0001276824,0.9595637,0.01354058,0.000056852,0.02594777,0.0002564367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8102875,0.0180875,0.163408,0.0001471499,0.0007022825,0.000274553,0.00001622497,0.001792011,0.005284691],"genre_scores_gemma":[0.9638089,0.0003656877,0.03527211,0.00005976679,0.0002626064,0.00002595477,0.00001105444,0.00005722018,0.0001367037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1535213,"threshold_uncertainty_score":0.8045297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2341910059","doi":"10.1109/tpwrs.2015.2438322","title":"A Novel Wavelet-Based Ensemble Method for Short-Term Load Forecasting with Hybrid Neural Networks and Feature Selection","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Taiyuan University of Technology; University of Saskatchewan","keywords":"Extreme learning machine; Artificial neural network; Computer science; Feature selection; Ensemble learning; Artificial intelligence; Ensemble forecasting; Machine learning; Feature (linguistics); Wavelet; Wavelet transform; Term (time); Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02736188120161452,"gpt":0.2353228971134645,"spread":0.20796101591185,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003385655,0.0003243207,0.0003229131,0.000136579,0.0001823608,0.0001269841,0.00008508766,0.0001473565,0.000001907256],"category_scores_gemma":[0.000005405484,0.0002884368,0.00008657173,0.0002455944,0.0000221481,0.0001853983,7.460793e-7,0.0003376134,7.132565e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001756977,"about_ca_system_score_gemma":0.00004964696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005559153,"about_ca_topic_score_gemma":0.0002037729,"domain_scores_codex":[0.9986954,0.00003842872,0.000260839,0.0003312414,0.0002389618,0.0004351584],"domain_scores_gemma":[0.9992273,0.000174593,0.00004991918,0.0001791505,0.0001644212,0.0002046513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001430704,0.00003321112,0.00002040413,0.0001044862,0.00009313408,0.000006737609,0.0001792722,0.9904041,0.0025233,0.00001072442,0.0003503957,0.006131137],"study_design_scores_gemma":[0.001056957,0.0003768578,0.000008060791,0.0001949619,0.00007337019,0.0005102577,0.00006866475,0.9900423,0.006139831,0.000001189214,0.00118211,0.0003454094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02164055,0.0002487608,0.9748194,0.00002108993,0.001926917,0.000444001,0.00004087422,0.0003852373,0.0004731301],"genre_scores_gemma":[0.9836295,0.000002299701,0.01576251,0.0000288127,0.00009109134,0.0001709626,0.000009894373,0.0000980515,0.0002068952],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9619889,"threshold_uncertainty_score":0.9999568,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226449636","doi":"10.1109/access.2022.3160484","title":"Solar Power Forecasting Using Deep Learning Techniques","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":220,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"","keywords":"Mean absolute percentage error; Photovoltaic system; Computer science; Artificial intelligence; Mean squared error; Perceptron; Deep learning; Artificial neural network; Machine learning; Multilayer perceptron; Electricity; Statistics; Engineering; Mathematics; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03364399308681013,"gpt":0.2604231443911935,"spread":0.2267791513043833,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002600818,0.0001729885,0.0001649412,0.0001612328,0.0004950137,0.0001263752,0.0003882405,0.00004937878,0.0003040559],"category_scores_gemma":[0.00002435708,0.0001993585,0.00006985937,0.0003711716,0.00001720537,0.0004110404,0.0001812173,0.0005245317,0.000003216578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001225978,"about_ca_system_score_gemma":0.00001265313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000473626,"about_ca_topic_score_gemma":0.000008047342,"domain_scores_codex":[0.9989261,0.00004678554,0.0002299273,0.0001925311,0.0002168061,0.0003878463],"domain_scores_gemma":[0.9996396,0.00005963243,0.0000588499,0.0001550713,0.00002618016,0.00006064601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006142779,0.00001274692,0.003347628,0.00003901493,0.00003488356,0.0000607058,0.000628959,0.9526774,0.01477775,0.0000465592,0.0001719027,0.02819629],"study_design_scores_gemma":[0.0002118247,0.00007961492,0.0001230838,0.00007387941,0.00002803442,0.0001993603,0.0002410389,0.854413,0.09500277,0.0002735243,0.0486675,0.0006863492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9301028,0.00045004,0.04739884,0.000008112935,0.001433215,0.000118788,0.000004809583,0.001262853,0.01922056],"genre_scores_gemma":[0.9970279,0.00001009546,0.002511068,0.00005901407,0.0001932571,0.00003460469,0.000006840693,0.00008073176,0.00007645614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0982644,"threshold_uncertainty_score":0.8129606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2792046648","doi":"10.1016/j.enbuild.2018.01.034","title":"Transfer learning with seasonal and trend adjustment for cross-building energy forecasting","year":2018,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":215,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Transfer of learning; Time series; Energy (signal processing); Energy consumption; Feature (linguistics); Smart meter; Machine learning; Data mining; Electricity; Building automation; Artificial intelligence; Engineering; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01035953064858992,"gpt":0.2156853650967058,"spread":0.2053258344481159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001412329,0.0002810174,0.0002316388,0.0001042714,0.0003921647,0.0001143135,0.0000797842,0.0001185647,0.00002378654],"category_scores_gemma":[0.00001414975,0.0002454169,0.0000486769,0.0001517876,0.000156825,0.0003157641,0.00003219748,0.0001063927,1.201725e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002581488,"about_ca_system_score_gemma":0.00001048923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000537017,"about_ca_topic_score_gemma":0.0001596326,"domain_scores_codex":[0.9988381,0.00001377055,0.0002037106,0.0003433878,0.0001287708,0.0004722565],"domain_scores_gemma":[0.9995651,0.000129133,0.0000272727,0.00008143869,0.00004290668,0.0001541464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000440346,0.00004252961,0.004911915,0.0002990204,0.0004288279,0.00002342986,0.001602188,0.079919,0.0386669,0.1774063,0.0006772785,0.6955823],"study_design_scores_gemma":[0.002706508,0.0010843,0.0006353598,0.0005299269,0.000122433,0.0002909694,0.0001548566,0.3727735,0.109055,0.001122612,0.510366,0.001158511],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9011492,0.001809995,0.09379099,0.00002845189,0.0003109314,0.00003774388,0.000009156465,0.0002443111,0.002619207],"genre_scores_gemma":[0.9916377,0.0001929864,0.006457425,0.0001071951,0.0008806089,0.00003697448,0.00001767415,0.00007034844,0.0005990674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6944237,"threshold_uncertainty_score":0.9999998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4210349096","doi":"10.1109/access.2022.3147602","title":"Machine Learning-Based Digital Twin for Predictive Modeling in Wind Turbines","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":212,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Thapar Institute of Engineering and Technology; Singapore University of Technology and Design; Queen's University; Soongsil University; Soonchunhyang University; Queen's University Belfast","keywords":"Wind power; Computer science; Renewable energy; Wind speed; Cloud computing; Time series; Real-time computing; Simulation; Artificial intelligence; Machine learning; Meteorology; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02595213542104619,"gpt":0.2434532232560014,"spread":0.2175010878349553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001039267,0.0001255336,0.0001347738,0.000134717,0.0001091656,0.00008846101,0.0002366345,0.00003079987,0.00003079709],"category_scores_gemma":[0.00002981051,0.0001356876,0.00005238396,0.0002194805,0.000008130392,0.000323306,0.00004656814,0.0002579294,0.000001016317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007021115,"about_ca_system_score_gemma":0.00001805603,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004968365,"about_ca_topic_score_gemma":0.00002309802,"domain_scores_codex":[0.9992887,0.00001373259,0.0001768757,0.0001601601,0.0001270647,0.0002334508],"domain_scores_gemma":[0.9997472,0.00008501234,0.00002363277,0.00008865952,0.00001840302,0.0000370866],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003688767,0.00001777672,0.00556183,0.00003215217,0.00001215183,0.000005580336,0.0001699657,0.9924743,0.00007545471,0.000006208822,0.0000620315,0.001545636],"study_design_scores_gemma":[0.0005276907,0.00005524858,0.00005863588,0.00002121654,0.000005283187,0.000002032524,0.00003304557,0.9963151,0.0005349964,0.0001771053,0.00211404,0.0001556174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9265165,0.0003327061,0.06993217,0.00002809007,0.000746499,0.0001836224,0.0001287071,0.0002937845,0.001837942],"genre_scores_gemma":[0.9994755,0.000002801986,0.00006467036,0.0000340338,0.0001307897,0.00007578414,0.00009147738,0.00004456259,0.00008035999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07295904,"threshold_uncertainty_score":0.5533181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2024032348","doi":"10.1016/j.procs.2012.09.080","title":"Forecasting Power Output of Solar Photovoltaic System Using Wavelet Transform and Artificial Intelligence Techniques","year":2012,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":208,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Photovoltaic system; Grid-connected photovoltaic power system; Electric power system; Wavelet transform; Solar power; Electricity generation; Maximum power point tracking; Renewable energy; Power (physics); Reliability engineering; Wavelet; Artificial intelligence; Electrical engineering; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03443551176320986,"gpt":0.2310668240486201,"spread":0.1966313122854103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006608875,0.0001681086,0.0001942668,0.0002044962,0.0001502481,0.0000699695,0.0002484581,0.00005722473,0.000001659783],"category_scores_gemma":[0.00002050873,0.0001568779,0.0000349563,0.0005234782,0.0002001744,0.0006878328,0.00008245229,0.0001301811,0.000001028932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006557062,"about_ca_system_score_gemma":0.00004233215,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000120196,"about_ca_topic_score_gemma":0.000001769366,"domain_scores_codex":[0.9986926,0.000007279691,0.0003342517,0.0002101191,0.000260547,0.0004951605],"domain_scores_gemma":[0.9995213,0.00004602651,0.00006010242,0.0001329637,0.00009401402,0.0001456515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001369051,0.00007023998,0.003123575,0.001462831,0.00003062929,0.000008375442,0.01304137,0.009105115,0.1266775,0.004453262,0.00001574762,0.8419976],"study_design_scores_gemma":[0.00001340215,0.00003057514,0.00004944085,0.0001936982,0.000005615949,0.00008521741,0.00007702793,0.7035614,0.2957168,0.00007571899,0.00004534076,0.0001457811],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4210137,0.0001704648,0.5773076,0.000002169579,0.0005297881,0.0001188247,0.000002342971,0.0001997783,0.0006552518],"genre_scores_gemma":[0.869432,0.000004837943,0.1303574,0.000008635997,0.0001738627,0.00000550298,4.29044e-7,0.00001646941,9.031978e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8418518,"threshold_uncertainty_score":0.6397296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2768891253","doi":"10.1109/tste.2017.2774195","title":"Direct Interval Forecast of Uncertain Wind Power Based on Recurrent Neural Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Sustainable Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":204,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Wind power; Artificial neural network; Interval (graph theory); Computer science; Power (physics); Control theory (sociology); Engineering; Artificial intelligence; Electrical engineering; Mathematics; Control (management); Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.01212446752455444,"gpt":0.2255846224387511,"spread":0.2134601549141966,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001922855,0.0003182401,0.0003580442,0.0002482178,0.0004209561,0.0001037571,0.0003622887,0.0001563815,0.0001451479],"category_scores_gemma":[0.0000169322,0.0003106899,0.0002416829,0.0001733132,0.00009368978,0.0002422407,0.000003518903,0.0003128368,0.000001784852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795136,"about_ca_system_score_gemma":0.0000365142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000379137,"about_ca_topic_score_gemma":0.0001311688,"domain_scores_codex":[0.9984834,0.00005240411,0.000346409,0.0002881701,0.0002332111,0.0005963718],"domain_scores_gemma":[0.9988185,0.0001563235,0.0001112232,0.000669353,0.0001045517,0.0001400193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001267066,0.00009912829,0.00001530015,0.00005571484,0.00005290425,0.00004700381,0.00007367563,0.9699926,0.00005834734,0.000429451,0.0002677571,0.02878142],"study_design_scores_gemma":[0.0006920731,0.0004545246,0.00006194471,0.0001718678,0.00003530865,0.000004776926,0.0001763967,0.9730222,0.01646129,0.0000403516,0.00850818,0.0003710653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08216647,0.0002097285,0.8329577,0.000146225,0.004777697,0.0002346372,0.00005001969,0.0004855213,0.07897194],"genre_scores_gemma":[0.9974693,0.00003110141,0.0000876008,0.00005827648,0.00009806328,0.00003088559,0.000006920307,0.00007241318,0.002145406],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9153029,"threshold_uncertainty_score":0.9999345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149906128","doi":"10.1109/tpwrs.2014.2299801","title":"A Hybrid Intelligent Model for Deterministic and Quantile Regression Approach for Probabilistic Wind Power Forecasting","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":203,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Teshmont (Canada)","funders":"National Renewable Energy Laboratory","keywords":"Wind power; Wind power forecasting; Probabilistic forecasting; Probabilistic logic; Support vector machine; Electric power system; Wind speed; Computer science; Particle swarm optimization; Quantile regression; Engineering; Mathematical optimization; Artificial intelligence; Machine learning; Power (physics); Meteorology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03460675173194757,"gpt":0.23671738082361,"spread":0.2021106290916624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003748692,0.0003389133,0.0003918911,0.0001602921,0.0002685345,0.0001067,0.0001392933,0.0001275864,0.000003433476],"category_scores_gemma":[0.0000336226,0.000301105,0.000155247,0.00008078141,0.00004615732,0.0001270219,0.000001699962,0.0001750069,0.000002104667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007112372,"about_ca_system_score_gemma":0.00002096138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000523565,"about_ca_topic_score_gemma":0.000003993004,"domain_scores_codex":[0.9984524,0.00003292207,0.0004916869,0.0004120065,0.0001638458,0.0004471148],"domain_scores_gemma":[0.9989933,0.0003835235,0.00008514799,0.0003013482,0.00008385942,0.0001528159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006670842,0.00005986791,0.000001677205,0.0006777244,0.00004979908,7.082615e-7,0.0006904277,0.9951965,0.000442406,0.0003807804,0.0001679538,0.002265457],"study_design_scores_gemma":[0.0005111979,0.0002844676,6.373169e-7,0.0003486301,0.00006140007,0.00006217514,0.00009957259,0.9956656,0.001421148,0.0001333919,0.001062028,0.0003497862],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03162325,0.0001351691,0.9642396,0.000004569795,0.001599723,0.001035406,0.0001431764,0.0002554624,0.0009636327],"genre_scores_gemma":[0.9932534,0.000006008884,0.005696605,0.00001445513,0.0000394591,0.0004624079,0.00001464007,0.0001093062,0.0004037712],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9616301,"threshold_uncertainty_score":0.9999441,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008533347","doi":"10.1109/access.2020.2975738","title":"Deep Learning for Load Forecasting: Sequence to Sequence Recurrent Neural Networks With Attention","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Recurrent neural network; Artificial intelligence; Deep learning; Artificial neural network; Feed forward; Encoder; Machine learning; Sequence learning; Scheduling (production processes); Sequence (biology); Feedforward neural network; Time horizon; Control engineering; Engineering; Mathematical optimization","retraction":null,"screen_n_in":null,"score":{"opus":0.0776218189074291,"gpt":0.2843502902902904,"spread":0.2067284713828613,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107168,0.0002162499,0.0001922076,0.00003923487,0.0001374211,0.0001741013,0.0003376537,0.0000653284,0.00001033789],"category_scores_gemma":[0.00007326106,0.0002025368,0.00005807162,0.0003980639,0.00002125875,0.000434181,0.00004379341,0.0002815939,0.000005216177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008315261,"about_ca_system_score_gemma":0.00001552595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001907322,"about_ca_topic_score_gemma":0.0000653709,"domain_scores_codex":[0.9988172,0.00001964155,0.0002295687,0.0003112799,0.0001844542,0.0004378305],"domain_scores_gemma":[0.9994274,0.00008317766,0.00006119233,0.0001173406,0.0001051139,0.0002057768],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003956505,0.000003541962,0.002189408,0.0000886166,0.00001741212,0.00001371841,0.0002585885,0.9424357,0.001373565,0.00001482227,0.0001589078,0.05340609],"study_design_scores_gemma":[0.0002709522,0.000180409,0.0001546912,0.0001301385,0.00001941702,0.00001608579,0.00002465449,0.9961735,0.001049047,0.000009415819,0.001686374,0.0002853045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4483853,0.000142312,0.5493989,0.0001591914,0.0007178169,0.0002742927,0.000003535645,0.0004210152,0.0004976096],"genre_scores_gemma":[0.9970534,0.00001537827,0.001955834,0.0002426461,0.0005465385,0.0000830044,0.0000225237,0.00005810882,0.00002250686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5486681,"threshold_uncertainty_score":0.8259209,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176181793","doi":"10.1109/tsg.2021.3093515","title":"Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":200,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Term (time); Margin (machine learning); Artificial neural network; Electrical load; Geographic information system; Graph; Data mining; Machine learning; Engineering; Voltage; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01875905799342236,"gpt":0.2162581475251442,"spread":0.1974990895317218,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001349641,0.0003286004,0.000292924,0.000133233,0.0003030285,0.0001091625,0.0001547094,0.0001789008,0.0002244936],"category_scores_gemma":[0.000004200351,0.0003684092,0.0002796917,0.000423476,0.00004781063,0.0002441637,0.00000300617,0.000595395,0.00001700343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009042145,"about_ca_system_score_gemma":0.0000387428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002647132,"about_ca_topic_score_gemma":0.00423691,"domain_scores_codex":[0.9982672,0.00005682272,0.0004466318,0.0003650256,0.0003206822,0.0005436452],"domain_scores_gemma":[0.9992485,0.00009482822,0.00003519945,0.0003484658,0.00009214878,0.000180852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000354587,0.00006296291,0.0006610855,0.00004300537,0.0001149728,0.0002259598,0.0001405082,0.9489908,0.002164314,0.000002762276,0.0005876204,0.04697055],"study_design_scores_gemma":[0.0005184329,0.0001025811,0.0004712869,0.0001387079,0.0001076407,0.000268625,0.00002965525,0.9531689,0.04310061,0.00002755602,0.001454955,0.000611076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1713618,0.0002146758,0.8170171,0.00003158192,0.009290002,0.00009963877,0.00003045649,0.0004962967,0.001458432],"genre_scores_gemma":[0.9979986,0.00006115079,0.0005508632,0.00005031696,0.0009495527,0.00003240003,0.00004093847,0.00008775039,0.0002284563],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8266368,"threshold_uncertainty_score":0.9998768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2074911163","doi":"10.1109/tsg.2014.2377178","title":"Fuzzy Prediction Interval Models for Forecasting Renewable Resources and Loads in Microgrids","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":193,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Microgrid; Renewable energy; Interval (graph theory); Prediction interval; Wind power; Computer science; Fuzzy logic; Probabilistic forecasting; Representation (politics); Mathematical optimization; Energy management system; Electric power system; Electricity generation; Reliability engineering; Data mining; Energy management; Power (physics); Engineering; Energy (signal processing); Machine learning; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01962241966229981,"gpt":0.2025635714247892,"spread":0.1829411517624894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002525226,0.0001775349,0.0001906496,0.0002039391,0.0001316202,0.00004747635,0.00007711403,0.0001113846,0.000005306429],"category_scores_gemma":[0.00000516941,0.000186984,0.00007429151,0.000157511,0.00003099901,0.0002324085,0.00000123916,0.0001923714,0.000001879721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000500291,"about_ca_system_score_gemma":0.000006001237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001372001,"about_ca_topic_score_gemma":0.0005965059,"domain_scores_codex":[0.9990754,0.0000245548,0.0002859849,0.0002256772,0.0000918174,0.0002966043],"domain_scores_gemma":[0.9995902,0.0001436983,0.00002601912,0.0001403288,0.000023996,0.00007572687],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004464384,0.00002676786,0.00008298566,0.00008465789,0.00002377435,6.97065e-7,0.0005578533,0.9703982,0.001993809,0.00001734188,0.000284925,0.02648432],"study_design_scores_gemma":[0.0007339263,0.0001827015,0.00005210954,0.0002221283,0.00002663415,0.0000212646,0.00007367843,0.9731342,0.01690433,0.0005246955,0.007913858,0.0002105291],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3581791,0.0001112244,0.6355689,0.00003092695,0.001638997,0.0001642348,0.00006906714,0.00026455,0.00397299],"genre_scores_gemma":[0.9966888,0.00005452843,0.002644305,0.000031904,0.0002665372,0.00008528206,0.000009005128,0.00004578613,0.0001738195],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6385097,"threshold_uncertainty_score":0.7624986,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2974046511","doi":"10.1109/tii.2019.2942353","title":"Bayesian Deep Learning-Based Probabilistic Load Forecasting in Smart Grids","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"China Scholarship Council; Beijing University of Posts and Telecommunications; National Natural Science Foundation of China","keywords":"Computer science; Probabilistic logic; Smart grid; Smart meter; Overfitting; Machine learning; Artificial intelligence; Pooling; Cluster analysis; Data mining; Bayesian probability; Deep learning; Energy consumption; Scheduling (production processes); Artificial neural network; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02537672286951327,"gpt":0.2091032948278648,"spread":0.1837265719583515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003533148,0.0002675079,0.0002898334,0.0002875926,0.0001042187,0.00007919627,0.0001631942,0.0003140022,0.0002046453],"category_scores_gemma":[0.00003871213,0.0002775584,0.0001059942,0.0005515495,0.00003228227,0.000340433,0.000001285999,0.001139067,0.0001145258],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003304601,"about_ca_system_score_gemma":0.0001072089,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004678201,"about_ca_topic_score_gemma":0.0001540861,"domain_scores_codex":[0.9983696,0.00003672741,0.0007307687,0.0001133842,0.0003028397,0.0004467212],"domain_scores_gemma":[0.9992639,0.0002634928,0.00008892056,0.0002206284,0.00004906886,0.0001139744],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003452165,0.00003037216,0.0002892174,0.00009575806,0.00001986298,0.00000212991,0.0007189055,0.9730008,0.00001872111,0.00001066168,0.0000314988,0.02574759],"study_design_scores_gemma":[0.001520021,0.0001864,0.00001047781,0.0002856242,0.0000199047,0.000007889935,0.0002729935,0.9929435,0.002184545,0.00001723408,0.002233289,0.0003180798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4776878,0.00001570429,0.4992122,0.00002446852,0.003623616,0.0006766675,0.00002112481,0.0006276835,0.0181107],"genre_scores_gemma":[0.9988267,0.000004614013,0.000771857,0.00003969556,0.00009017531,0.00004106476,0.00001096152,0.00004329588,0.0001716435],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5211388,"threshold_uncertainty_score":0.9999676,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2040414337","doi":"10.1016/j.epsr.2015.03.027","title":"Improved short-term load forecasting using bagged neural networks","year":2015,"lang":"en","type":"article","venue":"Electric Power Systems Research","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":173,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Artificial neural network; Computer science; Term (time); Range (aeronautics); Set (abstract data type); Artificial intelligence; Machine learning; Data set; Process (computing); Electrical load; Training set; Sampling (signal processing); Data mining; Engineering; Voltage","retraction":null,"screen_n_in":null,"score":{"opus":0.1009726259969573,"gpt":0.3113299849015657,"spread":0.2103573589046084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002975729,0.0003413883,0.0004261722,0.0004754463,0.000282458,0.0003498377,0.0005085447,0.0002675714,0.00001269805],"category_scores_gemma":[0.0002851367,0.0003294659,0.0001024172,0.001782343,0.00004993954,0.0003242034,0.0001381778,0.001232732,0.00001419958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009751271,"about_ca_system_score_gemma":0.0002380425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004058524,"about_ca_topic_score_gemma":0.00004093755,"domain_scores_codex":[0.995783,0.0003251754,0.0005878999,0.0004467495,0.001066695,0.001790531],"domain_scores_gemma":[0.9980736,0.0002903548,0.00004879022,0.0004902746,0.0005690086,0.0005280023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001429518,0.00008045237,0.004338809,0.0002898443,0.0002899008,0.0004073489,0.001654876,0.9224864,0.04195885,0.0001596811,0.007020314,0.02117052],"study_design_scores_gemma":[0.0003633894,0.0001754889,0.00003641058,0.0001151103,0.000009156276,0.0002401637,0.0001216932,0.9961034,0.0008021267,0.000007073576,0.001672908,0.0003530547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9144002,0.01619167,0.04376848,0.00001155805,0.003834314,0.0007585983,0.000004695823,0.0007355394,0.02029501],"genre_scores_gemma":[0.9985239,0.00002562864,0.0001214727,0.000005617994,0.0007027214,0.00005445302,0.0000084704,0.0001315059,0.0004262307],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08412376,"threshold_uncertainty_score":0.9999157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1992778383","doi":"10.1016/j.ijepes.2006.02.014","title":"An efficient approach for short term load forecasting using artificial neural networks","year":2006,"lang":"en","type":"article","venue":"International Journal of Electrical Power & Energy Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":171,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"École de Technologie Supérieure; Université du Québec","funders":"","keywords":"Artificial neural network; Term (time); Computer science; Wind speed; Meteorology; Artificial intelligence; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02098137224467834,"gpt":0.2426970252067401,"spread":0.2217156529620618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004485573,0.0002547655,0.0003594069,0.0002855079,0.00009093145,0.0002272006,0.0004626332,0.0001542508,0.00000386316],"category_scores_gemma":[0.0000381129,0.0002302075,0.0002431751,0.00023173,0.00002844748,0.0002160932,0.00002043327,0.0002704093,1.581637e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004372913,"about_ca_system_score_gemma":0.00005570295,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009616039,"about_ca_topic_score_gemma":0.000007796207,"domain_scores_codex":[0.9976123,0.00005605447,0.0009893409,0.0002063687,0.0006729909,0.0004629681],"domain_scores_gemma":[0.9988153,0.0001293568,0.0002357033,0.0001216597,0.0005543854,0.0001435848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008590113,0.0001205094,0.0003346466,0.000005997401,0.0001172578,0.00004607911,0.00002261054,0.9856944,0.004611629,0.005644841,0.0001494663,0.003166648],"study_design_scores_gemma":[0.0003014673,0.0001580403,0.00005199614,0.00005252114,0.00003239588,0.0007031485,0.00001571153,0.9968705,0.000907155,0.00006788552,0.0005981193,0.0002410253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2501765,0.001007898,0.7438281,0.000005724981,0.003519813,0.00007040862,0.000006807868,0.00006429055,0.001320429],"genre_scores_gemma":[0.9939418,0.000004591263,0.001924546,0.00001843108,0.00399468,0.000008357116,0.00002755855,0.00006102011,0.00001896579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7437653,"threshold_uncertainty_score":0.938759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3206913269","doi":"10.3390/en14206782","title":"A Comparative Analysis of the ARIMA and LSTM Predictive Models and Their Effectiveness for Predicting Wind Speed","year":2021,"lang":"en","type":"article","venue":"Energies","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":165,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Autoregressive integrated moving average; Mean squared error; Computer science; Recurrent neural network; Artificial neural network; Wind speed; Autoregressive model; Time series; Artificial intelligence; Machine learning; Moving average; Grid; Deep learning; Statistics; Mathematics; Meteorology","retraction":null,"screen_n_in":null,"score":{"opus":0.01842675593570652,"gpt":0.2308896495189234,"spread":0.2124628935832169,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001205972,0.0001272839,0.0003281121,0.00006831013,0.00008881738,0.00002558551,0.00005489474,0.00004688694,0.000001595695],"category_scores_gemma":[0.0000287629,0.00008991124,0.00008445317,0.0003304254,0.00007593072,0.0001139168,0.00006031875,0.00007016328,1.7542e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001457962,"about_ca_system_score_gemma":0.00001423707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001957467,"about_ca_topic_score_gemma":0.00005532189,"domain_scores_codex":[0.999466,0.00005249215,0.0001374169,0.0001542519,0.0000629253,0.0001269171],"domain_scores_gemma":[0.9992471,0.0004983381,0.00003928287,0.0001230359,0.00006484148,0.00002741005],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001797017,0.000007233826,0.004576994,0.00007083153,0.0009910607,3.698943e-7,0.004290907,0.9767554,0.01211983,0.0008537371,0.000005863041,0.0003097345],"study_design_scores_gemma":[0.0002476127,0.00002416955,0.01986565,0.00009124799,0.0002817352,0.000002482541,0.001159674,0.8647787,0.112727,0.0006766476,0.00005165056,0.00009339471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908184,0.001593466,0.005729518,0.000007533735,0.0001269204,0.00008430382,0.00008640684,0.00004716988,0.001506299],"genre_scores_gemma":[0.999624,0.00004891435,0.0002248947,0.000006122919,0.00003330658,0.000005788844,0.00001353551,0.00001041338,0.00003308205],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1119768,"threshold_uncertainty_score":0.3666474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2201233344","doi":"10.1016/j.enbuild.2015.12.010","title":"Energy Forecasting for Event Venues: Big Data and Prediction Accuracy","year":2015,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":162,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"London Hydro; Western University","funders":"","keywords":"Computer science; Context (archaeology); Support vector machine; Predictive modelling; Big data; Energy consumption; Granularity; Event (particle physics); Data mining; Artificial neural network; Machine learning; Engineering; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.05950155995618753,"gpt":0.2427230675325105,"spread":0.1832215075763229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002184274,0.0001478193,0.0001404373,0.00006871404,0.0001053454,0.00005779699,0.0001343182,0.00008728955,0.000001199213],"category_scores_gemma":[0.0001149219,0.0001457846,0.000019827,0.00009042327,0.00003063746,0.0002707523,0.0001206705,0.0000553798,1.417431e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000205026,"about_ca_system_score_gemma":0.00001572968,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008349439,"about_ca_topic_score_gemma":0.00005764208,"domain_scores_codex":[0.9992344,0.00001066762,0.0001824912,0.0002457115,0.00009278147,0.0002339806],"domain_scores_gemma":[0.9994785,0.0001187192,0.00004361699,0.0001923967,0.00003078574,0.000135975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004589669,0.00001820823,0.0007701883,0.00009925016,0.00008731346,0.000007457703,0.0006531763,0.01157437,0.001977354,0.006193549,0.01234603,0.9662272],"study_design_scores_gemma":[0.0004702579,0.00006630174,0.0000266144,0.0001055462,0.00002644458,0.00004667597,0.00006558192,0.3359126,0.002458927,0.001743082,0.6589007,0.0001772022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6082895,0.01584419,0.3671123,0.0001691985,0.003836048,0.0001145789,0.0002917589,0.0006119119,0.003730444],"genre_scores_gemma":[0.9962388,0.0004830956,0.001832311,0.00006295105,0.001013765,0.00002044626,0.0001607554,0.00003563624,0.0001522068],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.96605,"threshold_uncertainty_score":0.5944923,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081576544","doi":"10.3390/su12177076","title":"Short-Term Load Forecasting of Microgrid via Hybrid Support Vector Regression and Long Short-Term Memory Algorithms","year":2020,"lang":"en","type":"article","venue":"Sustainability","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":158,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Windsor","funders":"","keywords":"Support vector machine; Term (time); Computer science; Long short term memory; Microgrid; Artificial intelligence; Machine learning; Artificial neural network; Regression; Algorithm; Data mining; Recurrent neural network; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01727014048706359,"gpt":0.2432673267034357,"spread":0.2259971862163721,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004353058,0.0003776583,0.0005113157,0.00006784156,0.0001230473,0.00004583428,0.0002344714,0.0001330695,0.00005544622],"category_scores_gemma":[0.0002861204,0.000360401,0.0001562042,0.0002282183,0.0001843868,0.0002775611,0.0002166758,0.0003797076,0.00000141122],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000372387,"about_ca_system_score_gemma":0.0001397135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002222925,"about_ca_topic_score_gemma":0.00001622117,"domain_scores_codex":[0.9978725,0.00005994852,0.0006184874,0.0005217981,0.0003158674,0.0006113877],"domain_scores_gemma":[0.998776,0.000117186,0.00006576466,0.0003802122,0.0003454855,0.0003153519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001783526,0.0001273282,0.3498912,0.006081091,0.0001660917,0.0008075345,0.005767304,0.004637387,0.01250509,0.00002123053,0.0004737827,0.6193436],"study_design_scores_gemma":[0.002391864,0.001371847,0.2537232,0.0009332086,0.0004205154,0.0007365705,0.002778484,0.2853501,0.4460947,0.0008343331,0.00179529,0.003569867],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9946222,0.0008422989,0.003031282,0.0001116933,0.0003346264,0.0003771239,0.00003245226,0.0002882979,0.0003599981],"genre_scores_gemma":[0.9989145,0.00003821369,0.0005725758,0.00002083255,0.0002896873,0.00002190897,0.00004573433,0.00006508543,0.00003147681],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6157738,"threshold_uncertainty_score":0.9998848,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4284962670","doi":"10.3390/en15144993","title":"Transformer-Based Model for Electrical Load Forecasting","year":2022,"lang":"en","type":"article","venue":"Energies","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":157,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Transformer; Computer science; Workflow; Electricity; Recurrent neural network; Architecture; Artificial intelligence; Artificial neural network; Engineering; Voltage; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02583157043852243,"gpt":0.2125115797646871,"spread":0.1866800093261647,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001480485,0.00014239,0.0001425889,0.0000796652,0.0002641488,0.00002157882,0.000146892,0.00003448685,0.00004444152],"category_scores_gemma":[0.00002055709,0.0001530573,0.0001134343,0.0001903949,0.00001329816,0.00007134071,0.00001149073,0.0001566009,9.171808e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001386944,"about_ca_system_score_gemma":0.00006909505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008628082,"about_ca_topic_score_gemma":0.00003053998,"domain_scores_codex":[0.9991063,0.00001032863,0.0001786718,0.0001451575,0.0001980836,0.0003613941],"domain_scores_gemma":[0.9996967,0.000111041,0.00001805525,0.0001049696,0.00002184034,0.00004743435],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002037615,0.00001165591,0.0000162878,0.00002504632,0.00001443622,0.000002032943,0.0002776192,0.983018,0.00301661,0.001843371,0.001392153,0.0103624],"study_design_scores_gemma":[0.0003817867,0.00006369458,0.000001895412,0.00000620207,0.00001190796,0.000005314744,0.00003464629,0.9689882,0.01022725,0.0004956544,0.01958865,0.0001948071],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5875633,0.001677306,0.3852851,0.0001172707,0.0008963857,0.0002705257,0.0001117975,0.001343561,0.02273477],"genre_scores_gemma":[0.9926376,0.000006880231,0.006292565,0.00008365841,0.00009552637,0.000250211,0.00003389823,0.00005329061,0.000546403],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4050743,"threshold_uncertainty_score":0.6241494,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965525929","doi":"10.1109/tsg.2019.2933413","title":"Multiple Kernel Learning-Based Transfer Regression for Electric Load Forecasting","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Boosting (machine learning); Machine learning; Multiple kernel learning; Artificial intelligence; Ensemble learning; Probabilistic forecasting; Kernel (algebra); Flexibility (engineering); Electrical load; Scheduling (production processes); Support vector machine; Transfer of learning; Mathematical optimization; Kernel method; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01658990716444639,"gpt":0.2103884315114873,"spread":0.193798524347041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001880329,0.0002859292,0.0002591739,0.0001877623,0.0002177122,0.00003747771,0.0001289152,0.0001639727,0.0001221561],"category_scores_gemma":[0.00001084051,0.0002715371,0.0002434339,0.0003193875,0.00001394148,0.0001449508,3.913953e-7,0.0004657778,0.00008237836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000133649,"about_ca_system_score_gemma":0.00004929031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002775169,"about_ca_topic_score_gemma":0.0000780991,"domain_scores_codex":[0.9986611,0.00003010297,0.0002930815,0.0003045536,0.0002351041,0.0004760523],"domain_scores_gemma":[0.999204,0.0003811019,0.00002438859,0.00021258,0.00007049343,0.0001074213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001333965,0.00005179779,0.0002366959,0.0001287551,0.00004291489,0.000002185606,0.0001561909,0.9557619,0.02593039,0.000003371585,0.0001617815,0.01739059],"study_design_scores_gemma":[0.001368382,0.0002458461,0.0000438506,0.0001686139,0.00003321137,0.000007225308,0.00001792687,0.791566,0.192148,0.000004376898,0.01408688,0.0003097046],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4145959,0.00008311272,0.5807966,0.00002281408,0.002379826,0.0003460376,0.0000303984,0.000553879,0.001191434],"genre_scores_gemma":[0.9979816,0.00002030589,0.0006648549,0.0000481912,0.0001725196,0.0001136489,0.00001764942,0.0001005462,0.0008806848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5833857,"threshold_uncertainty_score":0.9999737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121955751","doi":"10.1109/pesw.2001.916876","title":"ANN-based short-term load forecasting in electricity markets","year":2002,"lang":"en","type":"article","venue":"2001 IEEE Power Engineering Society Winter Meeting. Conference Proceedings (Cat. No.01CH37194)","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Waterloo","funders":"","keywords":"Electricity; Term (time); Computer science; Electricity market; Artificial neural network; Electric power system; Electricity system; Electricity price; Operations research; Electricity generation; Artificial intelligence; Engineering; Power (physics); Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02038956401250017,"gpt":0.2024929108094017,"spread":0.1821033467969015,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009540338,0.001111856,0.000886968,0.000329021,0.0001858779,0.0004076229,0.0008753184,0.0005645453,0.0003375298],"category_scores_gemma":[0.0003729183,0.001262281,0.0005013277,0.001117088,0.0001056147,0.0007299809,0.000116396,0.001062386,0.00008806243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009296825,"about_ca_system_score_gemma":0.00008585232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003345868,"about_ca_topic_score_gemma":0.00001463349,"domain_scores_codex":[0.994854,0.00001763435,0.001136615,0.001021948,0.0007818202,0.002187945],"domain_scores_gemma":[0.9982226,0.0002248871,0.0001734619,0.0003649258,0.0005592543,0.0004548041],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000129913,0.0005900941,0.04587563,0.002907039,0.0006541885,0.0001351624,0.01951871,0.09174252,0.7883809,0.00007943503,0.04273419,0.007252173],"study_design_scores_gemma":[0.0007886454,0.0001182125,0.001038001,0.001488139,0.00004458061,0.00004499966,0.0002180746,0.9804633,0.01313104,0.000009613531,0.001314346,0.00134106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9673499,0.000147259,0.00756337,0.00009489601,0.001652347,0.0004692198,0.00002193632,0.001742969,0.02095812],"genre_scores_gemma":[0.973312,0.0002150198,0.02484647,0.0001670372,0.0005084672,0.0001418641,0.00001494462,0.0002851257,0.0005091261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8887208,"threshold_uncertainty_score":0.9989827,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2344823099","doi":"10.1109/tsg.2015.2502140","title":"A Data-Driven Approach for Estimating the Power Generation of Invisible Solar Sites","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Smart Grid","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":143,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Photovoltaic system; Cluster analysis; Electric power system; Solar power; Principal component analysis; Power (physics); Function (biology); Computer science; Dimension (graph theory); Block (permutation group theory); Electricity generation; Engineering; Mathematics; Electrical engineering; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.09231131024793797,"gpt":0.2660205589908784,"spread":0.1737092487429404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002640644,0.0001201325,0.000132284,0.00006495644,0.0001207872,0.00003300808,0.0002077911,0.00005719485,0.000009027381],"category_scores_gemma":[0.00001260826,0.00009548497,0.00005324523,0.0001460583,0.00002762961,0.0002181612,0.000001950518,0.0001366874,0.000004094399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000024414,"about_ca_system_score_gemma":0.0000242302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000148696,"about_ca_topic_score_gemma":0.00004509561,"domain_scores_codex":[0.9993028,0.00002222707,0.0002168795,0.0001591012,0.0001387291,0.0001602715],"domain_scores_gemma":[0.9993967,0.00007568905,0.00003592881,0.0003819247,0.00005547609,0.00005426738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007446822,0.00003218366,0.00001057953,0.00002376668,0.00004611801,1.76341e-7,0.0003889542,0.9911025,0.003396728,0.00002680865,0.00319488,0.00176983],"study_design_scores_gemma":[0.0002462417,0.00005956938,0.000003299262,0.00001277756,0.00003571611,0.000005151415,0.0000688068,0.9772819,0.01943738,0.00001067423,0.00273255,0.0001059613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03299008,0.00005237372,0.9643803,0.00003897532,0.001261335,0.0001726285,0.0002395844,0.0001164212,0.0007482581],"genre_scores_gemma":[0.8927915,0.000003680877,0.1066521,0.00003214716,0.0002554359,0.00005031217,0.0001338115,0.00003163623,0.00004932081],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8598015,"threshold_uncertainty_score":0.3893764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2060261774","doi":"10.1049/iet-gtd.2009.0297","title":"Day-ahead electricity price forecasting by modified relief algorithm and hybrid neural network","year":2010,"lang":"en","type":"article","venue":"IET Generation Transmission & Distribution","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":141,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Volatility (finance); Electricity price forecasting; Electricity; Electricity market; Artificial neural network; Computer science; Electricity price; Feature selection; Econometrics; SIGNAL (programming language); Economics; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01152777507184824,"gpt":0.2028623232543782,"spread":0.19133454818253,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000349256,0.0002545363,0.0001916019,0.0000342943,0.0003938609,0.000119782,0.00009513392,0.0001660694,0.00003623165],"category_scores_gemma":[0.00003133785,0.0002533566,0.00006273077,0.0002595388,0.00003091797,0.0002823455,0.00001107018,0.0004520781,0.000002403847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004460305,"about_ca_system_score_gemma":0.00002020842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001948738,"about_ca_topic_score_gemma":0.000006621376,"domain_scores_codex":[0.9985902,0.00005374975,0.0003790047,0.0003152271,0.00022189,0.000439895],"domain_scores_gemma":[0.9994476,0.00005635745,0.00006402952,0.0001537964,0.0000735393,0.0002047069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001541753,0.00004537152,0.00007041898,0.00003911162,0.00002471794,0.000006186681,0.00008916012,0.1685821,0.2659673,0.0003846012,0.02735821,0.5374174],"study_design_scores_gemma":[0.0003499481,0.00004402694,0.0001147432,0.0000196268,0.00001944729,0.00003508673,0.000002071081,0.8920532,0.08035114,0.0001213225,0.02662635,0.0002629729],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3011225,0.0006023193,0.696683,0.0001031241,0.0006485924,0.00014179,0.0001194709,0.0002820621,0.0002971572],"genre_scores_gemma":[0.9919168,0.0001791406,0.004303684,0.00004492151,0.0007574495,0.00002450974,0.002667965,0.00003581796,0.00006974079],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7234711,"threshold_uncertainty_score":0.9999919,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2965751469","doi":"10.1109/tii.2019.2933009","title":"A Novel Electricity Price Forecasting Approach Based on Dimension Reduction Strategy and Rough Artificial Neural Networks","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":139,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial neural network; Computer science; Artificial intelligence; Electricity; Dimensionality reduction; Electric power system; Benchmarking; Dimension (graph theory); Benchmark (surveying); Machine learning; Electricity market; Field (mathematics); Data mining; Power (physics); Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04992311691369354,"gpt":0.2172596967360863,"spread":0.1673365798223928,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002404726,0.0002654624,0.0002407589,0.0002205101,0.0001976449,0.0001166242,0.00008611157,0.000331603,0.00001645543],"category_scores_gemma":[0.000009869039,0.0002599224,0.00007548861,0.0005094481,0.00002636206,0.0004153223,0.000001286115,0.0009338775,0.000005536037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001094344,"about_ca_system_score_gemma":0.00003319714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002281301,"about_ca_topic_score_gemma":0.000002061011,"domain_scores_codex":[0.9986493,0.00002345862,0.0005625942,0.0001419924,0.0002415664,0.0003811167],"domain_scores_gemma":[0.9994181,0.0001228647,0.0001129125,0.000190538,0.00005051431,0.0001050839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001031729,0.00006111529,0.000002464978,0.00003139189,0.00002230458,2.915111e-7,0.0001933955,0.9577267,0.0004962188,0.00004596536,0.00004883565,0.04126812],"study_design_scores_gemma":[0.0008176945,0.0003189108,0.000002648188,0.0000715076,0.00003055994,0.00002920097,0.000175062,0.9925347,0.005670981,0.000005049424,0.00008180689,0.0002618589],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3807124,0.000005236999,0.6129798,0.00001115672,0.001558139,0.0003568764,0.00001498577,0.0002326643,0.004128771],"genre_scores_gemma":[0.9979014,0.000004782525,0.001667888,0.00004729189,0.0002612342,0.00001982776,0.00002000564,0.00003418616,0.00004339862],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.617189,"threshold_uncertainty_score":0.9999853,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1990193139","doi":"10.1016/j.ijepes.2014.11.027","title":"Short term load forecast using fuzzy logic and wavelet transform integrated generalized neural network","year":2014,"lang":"en","type":"article","venue":"International Journal of Electrical Power & Energy Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":136,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Artificial neural network; Computer science; Wavelet transform; Fuzzy logic; Maxima and minima; Term (time); Artificial intelligence; Selection (genetic algorithm); Genetic algorithm; Neuro-fuzzy; Adaptive neuro fuzzy inference system; Wavelet; Algorithm; Pattern recognition (psychology); Machine learning; Fuzzy control system; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01434534247282897,"gpt":0.2310390309815314,"spread":0.2166936885087024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000492348,0.0003035163,0.0004880371,0.0002416104,0.00006815914,0.0001750873,0.000390886,0.0001716124,0.00001419238],"category_scores_gemma":[0.00005754536,0.0002450653,0.0001920776,0.0002666433,0.00004356883,0.0002840572,0.00002657986,0.0003772936,9.163018e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000342614,"about_ca_system_score_gemma":0.00005473151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009481217,"about_ca_topic_score_gemma":0.00002395431,"domain_scores_codex":[0.9977028,0.0001001009,0.0008922359,0.0001881915,0.0006318436,0.0004848554],"domain_scores_gemma":[0.9989406,0.0001254231,0.0001752775,0.0001110659,0.0004173601,0.0002302787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003435298,0.00009289094,0.002202669,0.00002736679,0.001076992,0.0002775824,0.0002234718,0.8559902,0.01350178,0.02866794,0.002280915,0.0953147],"study_design_scores_gemma":[0.001349848,0.0003675646,0.0004018226,0.0003038958,0.0000783802,0.002682486,0.00001952984,0.9459283,0.001118672,0.001203614,0.04599735,0.000548515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7784115,0.006722724,0.1950393,0.0001516572,0.009151607,0.0001179474,0.0000137147,0.0001653265,0.01022615],"genre_scores_gemma":[0.9970101,0.0001941896,0.0009262761,0.0001133862,0.001599209,0.000003433606,0.00001184963,0.00005112223,0.00009046793],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2185985,"threshold_uncertainty_score":0.9993474,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4229443704","doi":"10.1016/j.energy.2022.124212","title":"Electricity price forecasting with high penetration of renewable energy using attention-based LSTM network trained by crisscross optimization","year":2022,"lang":"en","type":"article","venue":"Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":134,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China","keywords":"Renewable energy; Computer science; Wind power; Electricity; Electricity market; Electricity price forecasting; Volatility (finance); Econometrics; Economics; Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009770477575652355,"gpt":0.1808823922646826,"spread":0.1711119146890303,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001997812,0.000219717,0.0002413442,0.0001240337,0.0003943907,0.00003951952,0.0001547647,0.0000689025,0.0001203159],"category_scores_gemma":[0.00001415607,0.0002396146,0.00006238131,0.000973883,0.0000245228,0.000162024,0.00002929481,0.0001158416,7.017095e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001727536,"about_ca_system_score_gemma":0.0000735257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002878973,"about_ca_topic_score_gemma":0.0003309555,"domain_scores_codex":[0.9985399,0.00008525401,0.0003760642,0.0002552579,0.0003192697,0.0004242755],"domain_scores_gemma":[0.9993944,0.00009289917,0.0001840163,0.0001815938,0.00007757633,0.00006949103],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000465344,0.00003387357,0.0002561287,0.00002102278,0.00004125303,0.000004009034,0.00002793882,0.9875533,0.01009151,0.0003818625,0.0009604483,0.0005821382],"study_design_scores_gemma":[0.0005167398,0.000154627,0.00002372007,0.00003563247,0.00002939074,0.00001176901,0.00002179149,0.97432,0.02188908,0.00006164763,0.002664569,0.0002710098],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.100401,0.0004637202,0.896503,0.00001255532,0.0003002632,0.00004846431,0.00002278864,0.0002028225,0.002045366],"genre_scores_gemma":[0.9833276,0.00001577305,0.01555024,0.00006707172,0.0001707104,0.00004045004,0.0004448704,0.0000742328,0.00030903],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8829266,"threshold_uncertainty_score":0.97712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2998878989","doi":"10.1007/s42835-020-00346-4","title":"A Framework of Using Machine Learning Approaches for Short-Term Solar Power Forecasting","year":2020,"lang":"en","type":"article","venue":"Journal of Electrical Engineering and Technology","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":133,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"University of Regina","keywords":"Feature selection; Machine learning; Artificial intelligence; Random forest; Computer science; Artificial neural network; Solar power; Gradient boosting; Feature (linguistics); Ensemble learning; Term (time); Data mining; Power (physics)","retraction":null,"screen_n_in":null,"score":{"opus":0.02997243206190802,"gpt":0.2157055501234421,"spread":0.1857331180615341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001452162,0.0001586158,0.0003921532,0.0003013357,0.00003963129,0.0000133877,0.0001327296,0.0002267815,0.000002071577],"category_scores_gemma":[0.0005984221,0.0001480127,0.0000881543,0.0005306146,0.00002405051,0.0000703926,0.00002959934,0.0007589528,6.412056e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000248866,"about_ca_system_score_gemma":0.00001466758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":3.888407e-7,"about_ca_topic_score_gemma":8.821022e-8,"domain_scores_codex":[0.9990969,0.000006459939,0.000415766,0.0001052554,0.00009532284,0.0002803372],"domain_scores_gemma":[0.9995322,0.0001681885,0.00009253215,0.00005562396,0.00005756347,0.00009386852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005271449,0.00002976118,0.005603393,0.0003447041,0.0002922362,0.00004037069,0.0003468609,0.8876754,0.06194512,0.004352586,0.00001010067,0.03930673],"study_design_scores_gemma":[0.0002105543,0.0004044677,0.00002136314,0.0001285643,0.00004314051,0.0002326979,0.00001639081,0.985135,0.01288672,0.0002142821,0.0005620181,0.0001448162],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5873207,0.004001373,0.4082874,0.00008320248,0.0001005231,0.0000533597,0.000001752393,0.000126487,0.00002512637],"genre_scores_gemma":[0.9567021,0.0000744475,0.04306213,0.000005523357,0.0001123601,0.000001809516,7.050237e-7,0.00003992349,0.000001051121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3693813,"threshold_uncertainty_score":0.6035784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2465887865","doi":"10.1109/tii.2016.2585378","title":"Probabilistic Forecasting of Hourly Electricity Price by Generalization of ELM for Usage in Improved Wavelet Neural Network","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Electricity price forecasting; Probabilistic forecasting; Computer science; Probabilistic logic; Electricity market; Bootstrapping (finance); Artificial neural network; Generalization; Machine learning; Time series; Extreme learning machine; Artificial intelligence; Electricity; Econometrics; Wavelet; Engineering; Economics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03247552482087535,"gpt":0.217652325557131,"spread":0.1851768007362557,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003185198,0.0001710337,0.0002853385,0.0001494531,0.0000528246,0.00001342293,0.0001229806,0.0002060838,0.00001009779],"category_scores_gemma":[0.0000622531,0.0001404686,0.00008468686,0.0004891253,0.00003321777,0.0002917864,0.000001163973,0.0001918384,3.653567e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001018414,"about_ca_system_score_gemma":0.00004422518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003475374,"about_ca_topic_score_gemma":0.00003628366,"domain_scores_codex":[0.9985321,0.00002574127,0.0009082832,0.0000743872,0.000135024,0.0003244257],"domain_scores_gemma":[0.9991276,0.0003725346,0.0002289114,0.0001381885,0.00007983796,0.00005293384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008964639,0.00004171201,0.00003091749,0.0001377301,0.00003882614,1.001486e-7,0.000302588,0.9379901,0.004098907,0.00004648617,0.0004210349,0.05680191],"study_design_scores_gemma":[0.001608241,0.0002890246,0.000004842302,0.0002181408,0.00003247849,0.000002421064,0.00002513605,0.9170056,0.08028052,0.00006216625,0.0002859791,0.0001854426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.38267,0.00001063136,0.6159248,0.00000956724,0.0005447569,0.0004160794,0.0001711591,0.00005466827,0.0001983376],"genre_scores_gemma":[0.997129,0.00001868226,0.002614876,0.00001136596,0.00010048,0.00004944423,0.0000136482,0.00002549596,0.00003705579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.614459,"threshold_uncertainty_score":0.5728143,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077031811","doi":"10.1016/j.epsr.2011.08.007","title":"Short-term wind power forecasting using ridgelet neural network","year":2011,"lang":"en","type":"article","venue":"Electric Power Systems Research","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":128,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Wind power; Wind power forecasting; Artificial neural network; Electric power system; Crossover; Computer science; Term (time); Power (physics); Recurrent neural network; Operator (biology); Artificial intelligence; Engineering; Electrical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1178178607108047,"gpt":0.2968851132288222,"spread":0.1790672525180176,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001998981,0.0003993677,0.0004707353,0.0005778045,0.0004800984,0.0002122122,0.0006213654,0.0002732165,0.0001417957],"category_scores_gemma":[0.0001107436,0.0003893619,0.000140784,0.00199886,0.00007138525,0.0003544925,0.0001514236,0.001228472,0.00006384811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003138361,"about_ca_system_score_gemma":0.00008112693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763519,"about_ca_topic_score_gemma":0.00001123743,"domain_scores_codex":[0.9953243,0.0003306231,0.000664934,0.0005139995,0.0009144074,0.002251785],"domain_scores_gemma":[0.9984695,0.0002749006,0.00005767664,0.0005830969,0.0002570248,0.00035783],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000493083,0.0004873596,0.1160912,0.001430585,0.001801108,0.003848199,0.0138961,0.7168003,0.05924629,0.005641053,0.05416918,0.02609551],"study_design_scores_gemma":[0.0005412081,0.000510163,0.00600591,0.0005977245,0.00003214586,0.0009707269,0.0002237409,0.9786683,0.002763992,0.00009747322,0.008352729,0.001235839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9268336,0.006283752,0.002035615,0.000003385057,0.002500998,0.0004771141,0.000006286323,0.0004487987,0.06141042],"genre_scores_gemma":[0.9985819,0.00003590334,0.0002156797,0.000007279124,0.0005735396,0.00002881781,0.000007457808,0.0001630668,0.0003862946],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.261868,"threshold_uncertainty_score":0.9998558,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2807887237","doi":"10.1109/tpwrs.2018.2848207","title":"A Fuzzy Adaptive Probabilistic Wind Power Prediction Framework Using Diffusion Kernel Density Estimators","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":124,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Saskatchewan","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Kernel density estimation; Wind power; Computer science; Probabilistic logic; Wind power forecasting; Probability density function; Electric power system; Mathematical optimization; Prediction interval; Kernel (algebra); Engineering; Power (physics); Machine learning; Mathematics; Artificial intelligence; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01651968419172244,"gpt":0.2222424718126623,"spread":0.2057227876209398,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000202669,0.0003819528,0.0003475646,0.0002322847,0.0004038708,0.0001007727,0.0001599195,0.0003477468,0.00006736072],"category_scores_gemma":[0.00001501685,0.0003756366,0.0001428214,0.0004450534,0.0001278038,0.0002658761,0.0000025473,0.000494906,0.000105937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003127761,"about_ca_system_score_gemma":0.00004169085,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001563725,"about_ca_topic_score_gemma":0.00003989001,"domain_scores_codex":[0.9981684,0.00007880011,0.0004809015,0.0004191202,0.0003794984,0.0004732576],"domain_scores_gemma":[0.998982,0.000131415,0.0000852193,0.0004539997,0.0001477278,0.0001996715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000142303,0.0002198844,0.0004550547,0.0001387141,0.0002741487,0.00002601449,0.00388043,0.987251,0.006156486,0.0008646302,0.0002281262,0.0003631906],"study_design_scores_gemma":[0.0008998715,0.0008773489,0.001138521,0.002409677,0.0002058667,0.0003072296,0.0007907682,0.9836498,0.006915491,0.0005118587,0.001153031,0.001140556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4015113,0.00006502683,0.588468,0.000003377609,0.006974993,0.0002699307,0.00005088052,0.0005070372,0.002149481],"genre_scores_gemma":[0.998147,0.000005828638,0.001438232,0.00001843114,0.0001299788,0.00002456016,0.000002713403,0.00009802035,0.0001353122],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5966356,"threshold_uncertainty_score":0.9998696,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2319709116","doi":"10.1016/j.enconman.2016.03.078","title":"Using data-driven approach for wind power prediction: A comparative study","year":2016,"lang":"en","type":"article","venue":"Energy Conversion and Management","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Universiti Malaya; Ryerson University","keywords":"Wind power; Feature selection; Data mining; Computer science; Wind speed; Adaptive neuro fuzzy inference system; Multilayer perceptron; Support vector machine; Random forest; Crossover; Wind power forecasting; Mutual information; Artificial neural network; Electric power system; Artificial intelligence; Machine learning; Power (physics); Engineering; Fuzzy logic; Fuzzy control system; Meteorology","retraction":null,"screen_n_in":null,"score":{"opus":0.05906736449610096,"gpt":0.2589633877705562,"spread":0.1998960232744553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009088832,0.0001222087,0.0001290025,0.00007545543,0.00009585464,0.0000228251,0.000134855,0.00002786635,0.00003112155],"category_scores_gemma":[0.000001215492,0.00009100257,0.00002041909,0.00006714357,0.00002327211,0.0001753292,0.0001623736,0.00002290181,0.000001413787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003112008,"about_ca_system_score_gemma":0.000002830456,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009393352,"about_ca_topic_score_gemma":0.000004150333,"domain_scores_codex":[0.9993499,0.00001721942,0.0001288399,0.0002483147,0.0001018019,0.0001539378],"domain_scores_gemma":[0.9996378,0.00002258841,0.00002290188,0.0002442587,0.00001520896,0.0000572131],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007470715,0.001898192,0.009706126,0.001196861,0.007066077,0.0001244199,0.009712674,0.654201,0.005120771,0.07860175,0.1452106,0.08641446],"study_design_scores_gemma":[0.003152451,0.0001873635,0.0006499225,0.00007912171,0.0001414614,0.000004529948,0.002477685,0.7397727,0.000311935,0.00003158171,0.2528619,0.0003294129],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1971677,0.0003310104,0.7520378,0.00005391767,0.001377926,0.0007598223,0.0001095678,0.0004505088,0.04771166],"genre_scores_gemma":[0.9945285,0.00008163784,0.004340742,0.00003137553,0.00006061346,0.00001400242,0.00003894689,0.000014674,0.0008895181],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7973608,"threshold_uncertainty_score":0.3710977,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983664186","doi":"10.1016/j.asoc.2011.07.001","title":"Short-term load forecasting using bayesian neural networks learned by Hybrid Monte Carlo algorithm","year":2011,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Artificial neural network; Algorithm; Overfitting; Computer science; Mean squared error; Monte Carlo method; Bayesian probability; Feedforward neural network; Support vector machine; Artificial intelligence; Machine learning; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02906903108889821,"gpt":0.2143056865226848,"spread":0.1852366554337866,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003366958,0.0004946104,0.0004508928,0.00008954418,0.0003904742,0.0001126534,0.0003575767,0.0001546243,0.00001804065],"category_scores_gemma":[0.00001442722,0.0005605287,0.0001358315,0.0002742569,0.00006466285,0.0001574797,0.0001868352,0.0006317188,0.000004115171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001504661,"about_ca_system_score_gemma":0.00001822372,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001009687,"about_ca_topic_score_gemma":0.000009403532,"domain_scores_codex":[0.9975302,0.00002916988,0.000601357,0.000511258,0.0002820683,0.001045965],"domain_scores_gemma":[0.9991537,0.0001292083,0.0001087416,0.0003260133,0.00005352157,0.0002288353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007226351,0.00001512493,0.0008962195,0.00003151494,0.00006280101,0.00004441153,0.0007514546,0.5848009,0.000647021,0.00002112779,0.0000923417,0.4126298],"study_design_scores_gemma":[0.000291139,0.00002000561,0.00008848197,0.00008597563,0.00003985118,0.00009530009,0.0001009187,0.9971863,0.001345607,0.00004555979,0.0001034334,0.0005974538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4189955,0.00048155,0.5743665,0.000001604739,0.0006890713,0.0001592802,0.000005446145,0.000827461,0.004473635],"genre_scores_gemma":[0.9671782,0.00000664824,0.03202882,0.0000537597,0.0005223356,0.000006825539,0.00001973235,0.0001666409,0.00001701071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5481828,"threshold_uncertainty_score":0.9996846,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076371332","doi":"10.1016/j.enpol.2007.04.006","title":"Electricity market price volatility: The case of Ontario","year":2007,"lang":"en","type":"article","venue":"Energy Policy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":119,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Waterloo; University of Calgary","funders":"","keywords":"Volatility (finance); Electricity; Electricity market; Economics; Electricity price; Volatility swap; Volatility smile; Financial economics; Econometrics; Implied volatility; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.007850362691639337,"gpt":0.2157781559530746,"spread":0.2079277932614353,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003215558,0.0001252888,0.0001277136,0.0001197309,0.00007262109,0.00001132741,0.0001321463,0.00007056319,0.0001276098],"category_scores_gemma":[0.00005065244,0.000097764,0.00006293236,0.000424082,0.00003177288,0.00005822458,0.00002900688,0.0001533986,0.000001384909],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00024357,"about_ca_system_score_gemma":0.0001112621,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.145573,"about_ca_topic_score_gemma":0.1767243,"domain_scores_codex":[0.9992321,0.00001919779,0.0002309567,0.00009926216,0.00008019908,0.0003383326],"domain_scores_gemma":[0.9994625,0.000150524,0.00003914585,0.0002476957,0.00002635269,0.00007379051],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002072083,0.000261285,0.01406024,0.0002326074,0.000761091,0.001944462,0.01755702,0.04808428,0.008208475,0.3765621,0.02497201,0.5071492],"study_design_scores_gemma":[0.0006388419,0.0001127997,0.01502309,0.00005112027,0.00004973855,0.001594368,0.0001056526,0.06838913,0.0567833,0.003375128,0.8532035,0.0006732676],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6694437,0.0001980956,0.005176317,0.00003231382,0.0001523727,0.00002386104,0.000003144657,0.0001026631,0.3248675],"genre_scores_gemma":[0.9945356,0.00001086183,0.0002787494,0.0001084847,0.0003009496,0.000002429385,0.000002154716,0.00002019657,0.004740626],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8282316,"threshold_uncertainty_score":0.8601167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3207946173","doi":"10.1016/j.apenergy.2021.118011","title":"A hybrid model for multi-step coal price forecasting using decomposition technique and deep learning algorithms","year":2021,"lang":"en","type":"article","venue":"Applied Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":118,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Lakes Environmental (Canada)","funders":"Fundamental Research Funds for the Central Universities; National University's Basic Research Foundation of China","keywords":"Coal; Computer science; Stability (learning theory); Mode (computer interface); Support vector machine; Decomposition; Artificial neural network; Deep learning; Artificial intelligence; Machine learning; Algorithm; Data mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02740709233706792,"gpt":0.2455491956576503,"spread":0.2181421033205824,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001191061,0.0002206612,0.0002227245,0.00007793691,0.0002208099,0.00006007938,0.00006929176,0.0001039676,0.000004055553],"category_scores_gemma":[0.0000147979,0.0002601852,0.00005682971,0.0001075538,0.00002176647,0.0000962101,0.00006423531,0.000163533,3.5812e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006934137,"about_ca_system_score_gemma":0.00002080995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002526353,"about_ca_topic_score_gemma":0.00003541727,"domain_scores_codex":[0.9989669,0.00001307241,0.0002498953,0.0002947148,0.00009571412,0.0003797149],"domain_scores_gemma":[0.9996033,0.00008307535,0.00005412133,0.0001168795,0.000049316,0.00009330443],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008033633,0.00001651736,0.000008906228,0.00007272596,0.00003437877,0.00001135885,0.0001229462,0.8799086,0.0667449,0.002903835,0.000007546254,0.05016023],"study_design_scores_gemma":[0.0004089283,0.00001280777,0.000002398068,0.00005263885,0.0000241462,0.0001207843,0.00004809574,0.9076891,0.08987057,0.0003137482,0.001179257,0.000277517],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03283397,0.0003685069,0.9643242,0.000002481681,0.00009300825,0.0000975861,0.000006390287,0.0003059746,0.001967839],"genre_scores_gemma":[0.6217621,0.0000423485,0.3777868,0.0000271807,0.00009547795,0.0001060528,0.00006516523,0.00006273005,0.00005217649],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5889281,"threshold_uncertainty_score":0.999985,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810149872","doi":"10.1016/j.enbuild.2018.06.017","title":"A hybrid teaching-learning artificial neural network for building electrical energy consumption prediction","year":2018,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":118,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"China Postdoctoral Science Foundation; Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China","keywords":"Artificial neural network; Robustness (evolution); Convergence (economics); Computer science; Energy consumption; Artificial intelligence; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.009812603847818221,"gpt":0.2166988923279172,"spread":0.206886288480099,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002770211,0.0002246679,0.000203826,0.0001130933,0.0005888861,0.00009888499,0.00009292819,0.0001226855,0.00002241877],"category_scores_gemma":[0.00006257116,0.0002328726,0.00007512255,0.0001070887,0.00007066859,0.0002033063,0.00003468234,0.0002159635,9.074908e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004364414,"about_ca_system_score_gemma":0.000008318598,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005001841,"about_ca_topic_score_gemma":0.00002134109,"domain_scores_codex":[0.9987246,0.00004615404,0.0002861666,0.0003036507,0.0001235095,0.00051591],"domain_scores_gemma":[0.9995329,0.0001587128,0.00006043204,0.00009280676,0.00003886387,0.0001163201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002597852,0.00003861467,0.002157662,0.00005604357,0.0001549304,0.00000920736,0.0002325244,0.2268038,0.04038782,0.2492706,0.01036999,0.470259],"study_design_scores_gemma":[0.0002675595,0.0002595065,0.000111854,0.000067098,0.0000368717,0.00006090098,0.000004761459,0.7908732,0.02162764,0.003142299,0.1832574,0.0002909231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.673072,0.0006877175,0.3234679,0.00003044979,0.001113335,0.00004131655,0.000006028437,0.0006049967,0.0009761651],"genre_scores_gemma":[0.9909121,0.0001109604,0.005259035,0.0001135833,0.003306199,0.000031379,0.00004216435,0.00005453904,0.0001699781],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5640694,"threshold_uncertainty_score":0.9496267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3129379202","doi":"10.1038/s41597-021-00851-9","title":"Author Correction: The FLUXNET2015 dataset and the ONEFlux processing pipeline for eddy covariance data","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University; University of Manitoba; Centre de Géomatique du Québec; University of Saskatchewan; Canadian Forest Service; Environment and Climate Change Canada; University of British Columbia; University of Waterloo; Global Institute for Water Security; Université Laval; Natural Resources Canada; Ministère des Ressources naturelles et des Forêts; Ontario Drive & Gear (Canada); McMaster University","funders":"Natural Environment Research Council; Sight Research UK","keywords":"Pipeline (software); Eddy covariance; Covariance; Computer science; Data science; Statistics; Mathematics; Biology; Ecosystem; Ecology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08306270731006536,"gpt":0.3033050218793115,"spread":0.2202423145692461,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002479391,0.0001238273,0.0001341094,0.00002496981,0.0007298022,0.0009195416,0.001681935,0.00003688802,0.00004762658],"category_scores_gemma":[0.0006500531,0.00007662269,0.00001266334,0.0004214607,0.0003070802,0.0006699727,0.00118535,0.0001664827,0.00001625688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009272072,"about_ca_system_score_gemma":0.000104498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001723024,"about_ca_topic_score_gemma":0.0003009245,"domain_scores_codex":[0.9986556,0.00004817297,0.0002288146,0.0006008586,0.0002143088,0.0002522721],"domain_scores_gemma":[0.9964256,0.0002617325,0.00004919301,0.003133091,0.00007621141,0.00005419329],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009428001,0.000008347152,0.000002775446,0.00004594439,0.00001425716,0.000001730183,0.00014313,0.002395477,0.0001435724,0.0001852173,0.9530935,0.04395657],"study_design_scores_gemma":[0.0002021701,0.000001047896,0.000003861239,0.00003318215,0.00002810572,0.00002086787,0.0001045533,0.4882306,0.0002005878,0.00007272739,0.5110424,0.00005995887],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.000558262,0.01761505,0.7144811,0.008220402,0.03551864,0.001053447,0.2192475,0.0005158246,0.00278974],"genre_scores_gemma":[0.09012617,0.000194708,0.04371051,0.0009680737,0.003489571,0.0001032686,0.8074135,0.0001603181,0.05383388],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6707706,"threshold_uncertainty_score":0.8867161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159040640","doi":"10.1109/tpwrs.2009.2030380","title":"Economic Impact of Electricity Market Price Forecasting Errors: A Demand-Side Analysis","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Power Systems","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; University of Calgary","funders":"","keywords":"Electricity market; Electricity; Electricity price; Economics; Economic forecasting; Electricity price forecasting; Econometrics; Electricity generation; Engineering; Power (physics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01109273901985659,"gpt":0.2251323746541929,"spread":0.2140396356343363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003133946,0.0002852633,0.0005278328,0.0006277649,0.00009691928,0.00004905227,0.0001734327,0.0001384291,0.0001736582],"category_scores_gemma":[0.000005892631,0.0002701506,0.0005333526,0.0007908292,0.00001656511,0.0002072147,4.980948e-7,0.0002403204,0.00001257475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004230317,"about_ca_system_score_gemma":0.00006087272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003598562,"about_ca_topic_score_gemma":0.00009942777,"domain_scores_codex":[0.9985228,0.00006322564,0.0005817358,0.0002534829,0.0001601525,0.0004186367],"domain_scores_gemma":[0.9991879,0.000144098,0.0001301283,0.0003324618,0.00004089948,0.0001645063],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000034383,0.00003464769,0.0001685091,0.00002974802,0.0009025687,0.000005100232,0.0002502293,0.9965337,0.001171367,0.00001312081,0.0002427713,0.0006138409],"study_design_scores_gemma":[0.0003625273,0.0003268032,0.00160966,0.0001155822,0.0003464262,0.00004941475,0.00004636484,0.9912034,0.005393145,0.0000110934,0.0001609941,0.0003746315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3946447,0.0002265378,0.5892391,0.000004054067,0.0006202213,0.0001564399,0.00006559021,0.0002339024,0.01480949],"genre_scores_gemma":[0.9994922,0.00002797614,0.0001527732,0.000007126789,0.00002454137,0.00001448096,0.000003460673,0.00003227323,0.0002452029],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6048474,"threshold_uncertainty_score":0.9999751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3180293405","doi":"10.1109/access.2021.3095420","title":"Load Forecasting Under Concept Drift: Online Ensemble Learning With Recurrent Neural Network and ARIMA","year":2021,"lang":"en","type":"article","venue":"IEEE Access","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":112,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"London Hydro; Western University","funders":"Ontario Centres of Excellence","keywords":"Computer science; Concept drift; Autoregressive integrated moving average; Recurrent neural network; Ensemble learning; Artificial intelligence; Machine learning; Energy consumption; Adaptation (eye); Adaptive learning; Artificial neural network; Energy (signal processing); Electricity; Time series; Data stream mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03371358459248409,"gpt":0.2559262365046391,"spread":0.222212651912155,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008478727,0.000212577,0.0002289424,0.00002856252,0.0001626549,0.0001962782,0.0001320162,0.00007452788,0.00003090283],"category_scores_gemma":[0.00002676358,0.0001966727,0.00003614655,0.0002971155,0.00004019691,0.0003121797,0.00006934084,0.0004117962,0.000001589592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004408915,"about_ca_system_score_gemma":0.00004170639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003328192,"about_ca_topic_score_gemma":0.0004354845,"domain_scores_codex":[0.9988805,0.00003678378,0.0002133609,0.0002638691,0.0001768895,0.0004286182],"domain_scores_gemma":[0.9994741,0.0001386217,0.00005473418,0.0001419168,0.00008277428,0.000107822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001028143,0.00001240224,0.005197811,0.00004974647,0.00004572746,0.00007836948,0.0002887477,0.9491531,0.0004098874,0.00008464506,0.0003833932,0.04428586],"study_design_scores_gemma":[0.001278593,0.0001396242,0.00454204,0.0007426327,0.00008510944,0.0003625279,0.000322123,0.9744757,0.007772531,0.0002971464,0.009111534,0.0008704339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9815732,0.002534562,0.01113601,0.00005978957,0.001024981,0.0000607901,0.000004505059,0.0002636446,0.003342566],"genre_scores_gemma":[0.9976044,0.00009550317,0.001243366,0.0001143532,0.0006533732,0.000005868626,0.00003444528,0.00005348515,0.0001952632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04341543,"threshold_uncertainty_score":0.802008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2066269320","doi":"10.1016/j.energy.2012.10.019","title":"Electricity demand estimation using an adaptive neuro-fuzzy network: A case study from the Ontario province – Canada","year":2012,"lang":"en","type":"article","venue":"Energy","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":111,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Waterloo","funders":"","keywords":"Adaptive neuro fuzzy inference system; Electricity; Electricity demand; Neuro-fuzzy; Gross domestic product; Econometrics; Fuzzy logic; Electricity market; Estimation; Artificial neural network; Asset (computer security); Renewable energy; Computer science; Electricity generation; Economics; Engineering; Fuzzy control system; Artificial intelligence; Power (physics); Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.02081644449747444,"gpt":0.2053501945717852,"spread":0.1845337500743108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001368103,0.0001604051,0.0001279557,0.00001631823,0.0002452524,0.00003553471,0.0001067633,0.00003861172,0.00001708346],"category_scores_gemma":[0.00001665822,0.000131138,0.0000198097,0.0001402473,0.000009348545,0.0002362592,0.00002991993,0.0001635267,3.190814e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003577761,"about_ca_system_score_gemma":0.0002128607,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.989054,"about_ca_topic_score_gemma":0.9983643,"domain_scores_codex":[0.9990755,0.00009246398,0.0001648357,0.0001399731,0.0001454086,0.0003818231],"domain_scores_gemma":[0.9994524,0.0001541021,0.00004345783,0.0002033257,0.00001707244,0.0001296017],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007280242,0.00003295413,0.009367889,0.000001055722,0.00003994484,0.0002167867,0.001233861,0.9850498,0.00003637603,0.0001755226,0.0002906534,0.003547818],"study_design_scores_gemma":[0.0002563735,0.00009092501,0.005048549,0.00001443665,0.00007521965,0.0003232979,0.0003731285,0.9890819,0.000347584,0.00007843789,0.003990906,0.0003192575],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9758083,0.000309023,0.02252471,0.000004736225,0.0005529826,0.00007618199,0.000004132928,0.00007883493,0.0006411352],"genre_scores_gemma":[0.9982129,0.000001209285,0.00108403,0.0001092456,0.0005029071,0.0000092902,0.00001199587,0.00002800496,0.00004042831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02240462,"threshold_uncertainty_score":0.5347651,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2975391820","doi":"10.1016/j.jcomm.2019.100107","title":"Econometric modelling and forecasting of intraday electricity prices","year":2019,"lang":"en","type":"article","venue":"Journal of commodity markets","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":108,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Narodowym Centrum Nauki; Narodowe Centrum Nauki; Deutsche Forschungsgemeinschaft","keywords":"Econometrics; Lasso (programming language); Electricity price forecasting; Benchmark (surveying); Electricity market; Economics; Electricity; Sample (material); Multivariate statistics; Econometric model; Quarter (Canadian coin); Computer science; Statistics; Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01733338125675517,"gpt":0.1924414586771334,"spread":0.1751080774203782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007848103,0.0001125471,0.0003439239,0.0003340722,0.00002786935,0.00002626351,0.0001488915,0.00006054267,0.00002937293],"category_scores_gemma":[0.0000670236,0.0001029252,0.00008015383,0.0002761266,0.0000155735,0.0002932075,0.00002751847,0.0002812592,7.705302e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003902152,"about_ca_system_score_gemma":0.00001941685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004889087,"about_ca_topic_score_gemma":0.000001959752,"domain_scores_codex":[0.9990549,0.00003127648,0.0005150868,0.00006624183,0.000156819,0.0001756713],"domain_scores_gemma":[0.9989914,0.0004635498,0.0002946721,0.0000942726,0.00008088384,0.00007525083],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009045903,0.00004162032,0.01954348,0.0004213624,0.0001589433,0.000007562238,0.0002318585,0.939552,0.0007270138,0.0002925675,0.0002408488,0.03869228],"study_design_scores_gemma":[0.0005238285,0.0001262987,0.006061164,0.0001836639,0.00002660203,0.0001126881,0.00002375442,0.9865762,0.00365983,0.0005664162,0.001963191,0.000176383],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783393,0.001579962,0.01009453,0.00001176496,0.0003428895,0.00004102346,0.000003140284,0.00001354026,0.009573894],"genre_scores_gemma":[0.9960896,0.0003524995,0.003417408,0.000006795027,0.000100636,2.615885e-7,7.068459e-7,0.00001528248,0.00001679258],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.04702417,"threshold_uncertainty_score":0.4197166,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}