{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":322,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":322,"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":"ddf14c3bdf01","filters":{"topic":"Data Stream Mining Techniques"}},"results":[{"id":"W2947014533","doi":"10.1007/s10994-020-05910-7","title":"Evaluating time series forecasting models: an empirical study on performance estimation methods","year":2020,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":386,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia; Canada Research Chairs","keywords":"Series (stratigraphy); Computer science; Time series; Independent and identically distributed random variables; Dependency (UML); Machine learning; Data mining; Pipeline (software); Sample (material); Estimation; Artificial intelligence; Statistics; Mathematics; Random variable; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2227258883317751,"gpt":0.4461106063891386,"spread":0.2233847180573635,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002022339,0.0002054051,0.0002370464,0.00009567495,0.0003589314,0.0002753486,0.0007855791,0.00004541466,0.0000134662],"category_scores_gemma":[0.0009736035,0.0001905029,0.00003319782,0.0004320681,0.00002063014,0.001680084,0.0005567123,0.0004593974,0.00002853004],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003988345,"about_ca_system_score_gemma":0.00003585907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572107,"about_ca_topic_score_gemma":6.304853e-7,"domain_scores_codex":[0.9976035,0.0008404233,0.000309073,0.0005851585,0.0003968904,0.000264973],"domain_scores_gemma":[0.9989898,0.0002381279,0.0001759291,0.0004236317,0.00006096451,0.0001115301],"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":[0.00003345795,0.00008482142,0.01283607,0.00001784265,0.00001384492,0.000009724229,0.01068433,0.2386116,0.0005024699,0.0001394863,0.00003356554,0.7370328],"study_design_scores_gemma":[0.0001929182,0.002742896,0.00179676,0.00003048672,0.0000104596,0.00001237748,0.0000859712,0.9939082,0.000591326,0.0003786011,0.00004915857,0.0002008493],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3462314,0.000007882085,0.6515204,0.0004135149,0.00002401126,0.0001759307,0.00000100388,0.0009903993,0.0006354444],"genre_scores_gemma":[0.4618991,3.203216e-7,0.5378457,0.000148994,0.00003325177,0.00001757212,0.00001417836,0.00001573779,0.00002516716],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7552966,"threshold_uncertainty_score":0.7768481,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4311543603","doi":"10.1016/j.asoc.2022.109924","title":"The choice of scaling technique matters for classification performance","year":2022,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":342,"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","funders":"","keywords":"Computer science; Scaling; Normalization (sociology); Preprocessor; Pipeline (software); Data mining; Data pre-processing; Range (aeronautics); Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02762515347572305,"gpt":0.2739750754989949,"spread":0.2463499220232718,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001193235,0.0001049573,0.0001246899,0.00007355097,0.0008891475,0.0000578061,0.00163435,0.00002587678,8.808482e-7],"category_scores_gemma":[0.00003571409,0.00009613101,0.00004159959,0.0003530525,0.00005892666,0.00009622137,0.0008907455,0.0001792934,0.000001212547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007118226,"about_ca_system_score_gemma":0.00004474202,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007976309,"about_ca_topic_score_gemma":3.386439e-7,"domain_scores_codex":[0.9988347,0.00003695211,0.0003158299,0.0003125432,0.0002457799,0.0002542036],"domain_scores_gemma":[0.9982278,0.0007558252,0.0002956638,0.0006488034,0.00004760211,0.00002433923],"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":[0.00002523976,0.00008649071,0.0009688889,0.0001169543,0.00003192222,4.242522e-7,0.001149266,0.002334679,0.09248815,0.153286,0.00688312,0.7426288],"study_design_scores_gemma":[0.0003406462,0.0001445792,0.00249973,0.00004743952,0.0000118643,0.00001473234,0.0003088032,0.8704174,0.07944652,0.005032215,0.04134708,0.0003889468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01230407,0.00001416794,0.9855074,0.0005731006,0.0001127529,0.0005975346,0.000004902454,0.0004107136,0.0004753839],"genre_scores_gemma":[0.6887048,0.000001053063,0.3107503,0.0002418806,0.00002337879,0.0002515841,0.000008413526,0.00001068338,0.000007905507],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8680828,"threshold_uncertainty_score":0.6838693,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753683282","doi":"10.6000/1927-5129.2017.13.76","title":"Classification Techniques in Machine Learning: Applications and Issues","year":2017,"lang":"en","type":"article","venue":"Journal of Basic & Applied Sciences","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":312,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Support vector machine; Decision tree; Structured support vector machine; Linear classifier; Naive Bayes classifier; Classifier (UML); Data classification; Field (mathematics); Relevance vector machine; Statistical classification; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04146337630792019,"gpt":0.3277040750463144,"spread":0.2862406987383942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001874549,0.00009897176,0.000187206,0.0002963466,0.0004764048,0.0006245918,0.002096986,0.0000486215,0.000002809077],"category_scores_gemma":[0.0001064405,0.00007879457,0.0000254185,0.0002302598,0.0004346452,0.0009934469,0.000309719,0.0002459908,0.000002789285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002925836,"about_ca_system_score_gemma":0.0000829921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003244506,"about_ca_topic_score_gemma":0.00001638428,"domain_scores_codex":[0.9988531,0.00003472848,0.0003406484,0.0002592594,0.0003491363,0.0001631073],"domain_scores_gemma":[0.9986499,0.00008242641,0.0006959867,0.0004411021,0.00006732839,0.00006325466],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000910804,0.000121708,0.03464182,0.00001607679,0.000007820917,0.000008761464,0.0006531235,0.000004706878,0.02570049,0.2421533,0.0009362716,0.6957468],"study_design_scores_gemma":[0.001212101,0.00158138,0.2759162,0.000437089,0.00004276586,0.000455894,0.001074155,0.02420734,0.1768127,0.2788312,0.2381578,0.001271335],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1394335,0.001715174,0.7638282,0.0243246,0.000266135,0.001151289,0.000007674466,0.0005425803,0.06873085],"genre_scores_gemma":[0.7817535,0.0002409323,0.2178463,0.00004599812,0.00005459124,0.00002030122,3.732001e-7,0.00000329488,0.00003462794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6944755,"threshold_uncertainty_score":0.6022953,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2048442462","doi":"10.1145/2133803.2184450","title":"StreamKM++","year":2012,"lang":"en","type":"article","venue":"ACM Journal of Experimental Algorithmics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":295,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Algorithm; Computer science; Data stream; Tree (set theory); Sample (material); Sampling (signal processing); Streaming algorithm; Cluster analysis; Mathematics; Combinatorics; Upper and lower bounds; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02788303691864616,"gpt":0.3083020289660293,"spread":0.2804189920473832,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003475197,0.0001373649,0.0001886724,0.0001337478,0.00005650009,0.00008637566,0.001767455,0.00005266305,0.00002395898],"category_scores_gemma":[0.0000956285,0.0001178886,0.00009713603,0.0001777498,0.00004531553,0.001825046,0.0007353874,0.0001750977,0.00002141087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001224859,"about_ca_system_score_gemma":0.00004923008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001004742,"about_ca_topic_score_gemma":7.775659e-8,"domain_scores_codex":[0.9987592,0.00004236103,0.0003575585,0.000111665,0.0003605142,0.0003686972],"domain_scores_gemma":[0.9986714,0.00007244753,0.0002875946,0.0006366975,0.00007916179,0.0002527418],"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":[0.00007460069,0.004403681,0.03103404,0.00001573638,0.0003947454,0.0003081261,0.01192599,0.000005435208,0.2136094,0.07450914,0.09041564,0.5733034],"study_design_scores_gemma":[0.0007544169,0.0008913094,0.002532327,0.00005782641,0.00001676105,0.00168089,0.0007087431,0.0006172594,0.9634644,0.002509906,0.02635401,0.0004120979],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5332254,0.01280798,0.4422491,0.000838172,0.004561166,0.0002444987,0.00002332772,0.000383401,0.005666959],"genre_scores_gemma":[0.4857931,0.0000498434,0.5137334,0.00011274,0.0002866804,0.000001486826,0.000001203057,0.000008073275,0.00001352718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.749855,"threshold_uncertainty_score":0.4807359,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2118079529","doi":"","title":"Collaborative Filtering: A Machine Learning Perspective","year":2004,"lang":"en","type":"article","venue":"TSpace","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":181,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"University of Toronto","keywords":"Perspective (graphical); Artificial intelligence; Computer science; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.01534535806987036,"gpt":0.3209898047101817,"spread":0.3056444466403114,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001331404,0.0001216196,0.0001195904,0.00008659148,0.0001122182,0.000137039,0.0006146518,0.00003658507,0.0000201431],"category_scores_gemma":[0.0001579907,0.0001176809,0.0000259172,0.0005076174,0.00004520678,0.0003276409,0.0003689353,0.0001865372,0.00007226947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001795113,"about_ca_system_score_gemma":0.0001031469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005297229,"about_ca_topic_score_gemma":0.00004043015,"domain_scores_codex":[0.9991723,0.00004342144,0.00008088192,0.0003331915,0.0001637347,0.0002064841],"domain_scores_gemma":[0.9993024,0.00003788706,0.00006504113,0.0004111592,0.0001195077,0.0000639713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002486602,0.0001676694,0.0003549815,0.00001203039,0.00006142742,0.0002157241,0.1024416,0.0006456555,0.01687924,0.8691038,0.002914372,0.007178562],"study_design_scores_gemma":[0.004256641,0.003763837,0.003261864,0.000469748,0.00004749282,0.0004019337,0.02765057,0.02080923,0.59522,0.1423972,0.1987781,0.002943383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01635933,0.0002860545,0.9305319,0.006317913,0.0001102961,0.000212303,0.000006910027,0.001725183,0.04445014],"genre_scores_gemma":[0.5742182,0.00002207342,0.4245963,0.0001319087,0.0000321932,0.00001965165,0.000004135557,0.000012505,0.0009631556],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7267067,"threshold_uncertainty_score":0.4798886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2078842512","doi":"10.1007/s10619-005-3296-1","title":"Stream Cube: An Architecture for Multi-Dimensional Analysis of Data Streams","year":2005,"lang":"en","type":"article","venue":"Distributed and Parallel Databases","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":155,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Computer science; Data cube; Data stream mining; Data stream; Data structure; Volume (thermodynamics); Online analytical processing; Computation; Stream processing; Data mining; Algorithm; Parallel computing; Data warehouse","retraction":null,"screen_n_in":null,"score":{"opus":0.1019794799530335,"gpt":0.3616370861324058,"spread":0.2596576061793723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002988997,0.0002215685,0.000386401,0.0002208216,0.0001256974,0.00008041713,0.001576912,0.00005266347,0.00001706631],"category_scores_gemma":[0.0001325731,0.0001912545,0.00007159979,0.0005874456,0.0001081581,0.001247656,0.0009794796,0.00009897045,0.000001226999],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001229822,"about_ca_system_score_gemma":0.0000593102,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003020335,"about_ca_topic_score_gemma":0.001030182,"domain_scores_codex":[0.9982651,0.00006358415,0.0003489541,0.0007975914,0.000230011,0.0002946959],"domain_scores_gemma":[0.9970852,0.0002532401,0.0001717594,0.002234048,0.00009580702,0.0001599799],"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":[0.0002946364,0.003259085,0.0256718,0.0001491125,0.002680881,0.0000338477,0.0004732824,0.01004978,0.001669161,0.04151941,0.07079311,0.8434059],"study_design_scores_gemma":[0.0008478487,0.0001761114,0.009802936,0.00004310677,0.0005436765,0.00001252793,0.00004427719,0.9455583,0.001407113,0.0001586681,0.04097816,0.0004272684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03369131,0.00023517,0.8506371,0.000222375,0.00001939239,0.000197815,0.1148118,0.0001779674,0.000007082804],"genre_scores_gemma":[0.1482135,0.00004034166,0.7219681,0.00008972347,0.00003703253,0.000020206,0.1296145,0.000008435046,0.000008220772],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9355085,"threshold_uncertainty_score":0.7799131,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883325838","doi":"10.1109/access.2018.2851790","title":"E-Learning: Challenges and Research Opportunities Using Machine Learning & Data Analytics","year":2018,"lang":"en","type":"article","venue":"IEEE Access","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Field (mathematics); Data science; Process (computing); Analytics; Machine learning; Learning analytics; Artificial intelligence; Data analysis; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.699501726311832,"gpt":0.4858837748751497,"spread":0.2136179514366823,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002490678,0.0001625872,0.0002034046,0.0004126518,0.0004876322,0.000910224,0.004230802,0.00008759506,0.00001770021],"category_scores_gemma":[0.0005810396,0.000157011,0.00001514776,0.0003897063,0.0003876764,0.002439043,0.005071987,0.0005654565,0.00001645382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000341802,"about_ca_system_score_gemma":0.000107016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004289531,"about_ca_topic_score_gemma":0.0002436106,"domain_scores_codex":[0.9976805,0.0003966266,0.0002257054,0.0007148125,0.0005318447,0.0004504815],"domain_scores_gemma":[0.9974015,0.000348876,0.0001279766,0.001682532,0.000299899,0.0001392418],"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":[0.00004363296,0.0001994479,0.01339303,0.000245663,0.000176743,0.0002014871,0.009009839,0.0000751431,0.002364084,0.01746268,0.01197437,0.9448539],"study_design_scores_gemma":[0.0003673861,0.000600029,0.002129568,0.0003240494,0.00003695244,0.0001663586,0.0006236313,0.600414,0.004400692,0.007948929,0.3821548,0.0008336542],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5158455,0.005591664,0.4459077,0.004870474,0.0009868244,0.0006340509,0.00008826319,0.002795991,0.02327958],"genre_scores_gemma":[0.9095415,0.004310037,0.08487226,0.00008404307,0.0004006532,0.000006411239,0.00006408065,0.00003776282,0.0006832232],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9440202,"threshold_uncertainty_score":0.8777311,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3153970166","doi":"10.1109/iotm.0001.2100012","title":"A Lightweight Concept Drift Detection and Adaptation Framework for IoT Data Streams","year":2021,"lang":"en","type":"article","venue":"IEEE Internet of Things Magazine","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Concept drift; Adaptation (eye); Internet of Things; Anomaly detection; Big data; Analytics; Data stream mining; Data analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.03850152748969257,"gpt":0.2891220454494537,"spread":0.2506205179597611,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002915262,0.0001529091,0.0002274195,0.00008759194,0.00003326243,0.0001738481,0.001170354,0.0001170796,0.00001164187],"category_scores_gemma":[0.0005208179,0.0001510974,0.00004021207,0.0001975368,0.00006917316,0.0008217937,0.0006499626,0.0001669419,0.000006396265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002424479,"about_ca_system_score_gemma":0.00005628945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006120018,"about_ca_topic_score_gemma":0.00004573382,"domain_scores_codex":[0.9986252,0.0000447399,0.0003538832,0.0005877785,0.000207841,0.0001806042],"domain_scores_gemma":[0.9980709,0.0003023842,0.0002779857,0.001101938,0.0001872567,0.00005952355],"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":[0.00005984343,0.0001799553,0.0001149321,0.0001330977,0.000126554,0.00003418139,0.005041709,0.000008332493,0.03127545,0.05535529,0.01976078,0.8879099],"study_design_scores_gemma":[0.0004287984,0.0004471618,0.000144109,0.0004425305,0.00004274434,0.00007273875,0.00006046972,0.4592238,0.4754947,0.04154332,0.0217952,0.0003044393],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01068837,0.0001930097,0.9872318,0.0006305515,0.0005351337,0.0001703735,0.00005865586,0.0002337367,0.000258394],"genre_scores_gemma":[0.3652934,0.0000164634,0.6341034,0.0001785712,0.0000672705,0.0000125064,0.0000575217,0.00001225957,0.0002586771],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8876054,"threshold_uncertainty_score":0.6161574,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2517990807","doi":"10.1007/978-3-319-46227-1_7","title":"Fast Hoeffding Drift Detection Method for Evolving Data Streams","year":2016,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Concept drift; Computer science; False positive paradox; Sliding window protocol; Data stream mining; Data stream; Detector; Streaming data; False positives and false negatives; Artificial intelligence; Data mining; False alarm; Task (project management); Probability distribution; Algorithm; Machine learning; Pattern recognition (psychology); Window (computing); Statistics; Mathematics; Telecommunications","retraction":null,"screen_n_in":null,"score":{"opus":0.03581273767652872,"gpt":0.3102016126300555,"spread":0.2743888749535268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002398325,0.0006543754,0.0006203223,0.001042114,0.0003821847,0.001006574,0.01026673,0.0004156682,0.0000142613],"category_scores_gemma":[0.0005420619,0.0005550084,0.000122748,0.0005006086,0.0003812437,0.002273117,0.004667825,0.000601152,0.00001730946],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003202402,"about_ca_system_score_gemma":0.0004470748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004678261,"about_ca_topic_score_gemma":0.0002198421,"domain_scores_codex":[0.9946375,0.00005771194,0.0006246364,0.002925704,0.0008859105,0.000868474],"domain_scores_gemma":[0.9926552,0.00165302,0.0004918473,0.004699991,0.0003195316,0.0001803645],"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":[0.000003658506,0.000008784715,0.00001153985,0.00002956419,0.00001200839,0.00001323174,0.0001104406,0.0003822915,0.0005119618,0.004336067,0.00007161011,0.9945089],"study_design_scores_gemma":[0.0002241806,0.0002168663,0.00002491037,0.000737433,0.00001622511,0.00005939939,1.318257e-7,0.8636667,0.009212605,0.1220547,0.003037919,0.0007489315],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000002737659,0.0001788529,0.9941131,0.0003850161,0.001674162,0.0006879065,0.0001556226,0.0006294897,0.002173128],"genre_scores_gemma":[0.0105689,0.00002452526,0.988107,0.0003332911,0.0006764012,0.00001885681,0.00003856543,0.00005059329,0.000181926],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9937599,"threshold_uncertainty_score":0.9996901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2565966100","doi":"10.1109/tfuzz.2016.2646746","title":"On Distributed Fuzzy Decision Trees for Big Data","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Scalability; Big data; Fuzzy logic; SPARK (programming language); Data mining; Decision tree; Scheme (mathematics); Artificial intelligence; Machine learning; Partition (number theory); Database; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.09363454549895964,"gpt":0.3205916024368531,"spread":0.2269570569378935,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006557344,0.0002841366,0.0003494091,0.0002262294,0.0009913744,0.001107753,0.005206457,0.0001617597,0.000001676321],"category_scores_gemma":[0.000138063,0.0002516961,0.0001124745,0.0001692323,0.00008415823,0.00101508,0.00003690795,0.0002131835,0.00009466468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057785,"about_ca_system_score_gemma":0.00008268188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003315238,"about_ca_topic_score_gemma":0.0002381257,"domain_scores_codex":[0.9976731,0.00007463712,0.0004263526,0.0009503794,0.0004822124,0.0003933202],"domain_scores_gemma":[0.9921203,0.0006231727,0.0002762401,0.00667984,0.000144546,0.0001558716],"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":[0.0002575257,0.0007908358,0.00003818149,0.0001006945,0.0001812271,0.00003645177,0.0001588704,0.002379953,0.0007539985,0.00934173,0.1623884,0.8235722],"study_design_scores_gemma":[0.01239897,0.00770077,0.004023701,0.00622309,0.0005367539,0.0003215839,0.0003427034,0.4781223,0.05679892,0.0474277,0.380172,0.005931534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001454959,0.00002708983,0.9849012,0.0003029617,0.007092392,0.000728983,0.00391607,0.0006523815,0.0009239211],"genre_scores_gemma":[0.9811628,0.00002400168,0.01778409,0.00004410019,0.0003017116,0.0002244821,0.0001237382,0.00003213563,0.0003028754],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9797079,"threshold_uncertainty_score":0.9999935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3087735403","doi":"10.1016/j.inffus.2020.09.004","title":"Preprocessed dynamic classifier ensemble selection for highly imbalanced drifted data streams","year":2020,"lang":"en","type":"article","venue":"Information Fusion","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":106,"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","funders":"Narodowym Centrum Nauki; Narodowe Centrum Nauki","keywords":"Computer science; Preprocessor; Data stream mining; Data mining; Data stream; Classifier (UML); Concept drift; Artificial intelligence; Data pre-processing; Selection (genetic algorithm); Ensemble learning; Dynamic data; Estimator; Machine learning; Pattern recognition (psychology); Statistics; Mathematics; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03278250398426191,"gpt":0.2801424785524984,"spread":0.2473599745682365,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002251234,0.0001347071,0.0001323138,0.0001009718,0.0001474589,0.0002935898,0.001303268,0.00009606579,0.000008635553],"category_scores_gemma":[0.0002500275,0.0001288947,0.00002632994,0.0005053616,0.00001486151,0.005377856,0.000527617,0.0001026321,0.00007127533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004867827,"about_ca_system_score_gemma":0.0001094897,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001944569,"about_ca_topic_score_gemma":0.00001105378,"domain_scores_codex":[0.9988332,0.00002074964,0.0003736981,0.0003093863,0.0002631746,0.000199758],"domain_scores_gemma":[0.9986796,0.00005521581,0.0002590831,0.0007227323,0.0001982543,0.00008509073],"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":[0.0001503815,0.00006857749,0.0003111991,0.000238968,0.00002665746,6.428328e-7,0.002970529,0.0002937671,0.02302857,0.005263176,0.1119065,0.8557411],"study_design_scores_gemma":[0.0004420607,0.0001631418,0.000396194,0.00002662653,0.000006225328,0.000003615725,0.00003885105,0.9196119,0.01021067,0.0004962476,0.06844109,0.0001633236],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009743171,0.000005813461,0.9849818,0.002401076,0.0001141592,0.0004963059,0.0001060932,0.001155037,0.0009965427],"genre_scores_gemma":[0.7684672,0.00001640686,0.2275961,0.001366482,0.000044346,0.00006659194,0.002393361,0.000009316464,0.00004019279],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9193182,"threshold_uncertainty_score":0.5256172,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013050088","doi":"10.1007/978-3-030-44041-1_59","title":"An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Big data; Predictive analytics; Computer science; Data science; Data analysis; Analytics; Variety (cybernetics); Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.08113488816839846,"gpt":0.3304299553003479,"spread":0.2492950671319494,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007610109,0.0005731215,0.0007437709,0.0003425155,0.0001968742,0.0005185727,0.004693665,0.0001574288,4.768884e-7],"category_scores_gemma":[0.0001448301,0.0005196664,0.00003084902,0.0003904183,0.0002164744,0.001411653,0.002517975,0.0005388523,0.000001481402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001025654,"about_ca_system_score_gemma":0.000225966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006478187,"about_ca_topic_score_gemma":0.00005959763,"domain_scores_codex":[0.9957995,0.00006913701,0.0009364584,0.002279087,0.000545745,0.0003700901],"domain_scores_gemma":[0.9933954,0.0005209186,0.001070739,0.004436877,0.0003174548,0.0002586429],"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":[0.0001854701,0.0001528809,0.003837493,0.0007938708,0.000290329,0.00006299828,0.0007921133,0.007154478,0.000001668869,0.2055396,0.0002728501,0.7809163],"study_design_scores_gemma":[0.0001197364,0.0005053831,0.00005644632,0.001731021,0.00009527348,0.00001059987,0.0001579805,0.9169902,0.00001335097,0.01573218,0.06395519,0.0006325927],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001364364,0.002677846,0.9918919,0.000043421,0.0005064052,0.001229912,0.002633255,0.0003050784,0.0005757586],"genre_scores_gemma":[0.7323737,0.001865122,0.2468451,0.0003848361,0.003870995,0.00009920527,0.01402319,0.0002303607,0.0003075467],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9098358,"threshold_uncertainty_score":0.9997255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4296412543","doi":"10.1016/j.engappai.2022.105366","title":"IoT data analytics in dynamic environments: From an automated machine learning perspective","year":2022,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":92,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Analytics; Data analysis; Anomaly detection; Machine learning; Data science; Field (mathematics); Domain (mathematical analysis); Internet of Things; Artificial intelligence; Construct (python library); Perspective (graphical); Data mining; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03088288453879309,"gpt":0.3171758765009199,"spread":0.2862929919621269,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003894071,0.0001216223,0.0001468783,0.0002667769,0.0001016818,0.00004847211,0.002708675,0.00002941996,0.00002709829],"category_scores_gemma":[0.00009099234,0.000155477,0.00001948022,0.0008340917,0.0000390981,0.0002476959,0.001259375,0.0003149269,0.00001064247],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002027319,"about_ca_system_score_gemma":0.00003291314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000874181,"about_ca_topic_score_gemma":0.00006262161,"domain_scores_codex":[0.9986385,0.00004928299,0.00035105,0.0005347026,0.000254485,0.0001720539],"domain_scores_gemma":[0.998211,0.0001263491,0.0001145634,0.001480843,0.00002034741,0.00004687618],"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":[0.000006577845,0.0004542926,0.0001931765,0.000005824143,0.00003105087,0.000006057151,0.001478698,0.8637791,0.01511561,0.05580881,0.00002847948,0.06309228],"study_design_scores_gemma":[0.00001074414,0.0000526635,0.0002316816,0.00000586747,0.000005609731,0.000001793089,0.0003483951,0.9890606,0.005754825,0.003193585,0.001195022,0.0001391586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007997291,0.0001087719,0.9906397,0.0001770184,0.00003432535,0.0002072883,0.0002399343,0.0005743889,0.00002131271],"genre_scores_gemma":[0.7822405,0.00001413017,0.2173175,0.000009968208,0.00001006895,0.0001013808,0.0002855352,0.00001363795,0.000007302463],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7742432,"threshold_uncertainty_score":0.6340168,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2789731619","doi":"10.1016/j.eswa.2018.03.021","title":"Adapting dynamic classifier selection for concept drift","year":2018,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":84,"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","funders":"","keywords":"Concept drift; Computer science; Classifier (UML); Artificial intelligence; Machine learning; A priori and a posteriori; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0181693000240935,"gpt":0.2960006961471375,"spread":0.277831396123044,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001622429,0.0001340376,0.0001414389,0.00008408385,0.0003592478,0.000179339,0.0006661809,0.00006983231,0.000002999669],"category_scores_gemma":[0.00001474184,0.0001145114,0.00002674557,0.0004000656,0.0000940718,0.0003310942,0.00007466461,0.00006297476,0.00003291697],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008866387,"about_ca_system_score_gemma":0.00007917069,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001263411,"about_ca_topic_score_gemma":0.00005060916,"domain_scores_codex":[0.9988703,0.00003106047,0.0002237026,0.0004703198,0.0001599667,0.0002446997],"domain_scores_gemma":[0.9987212,0.00009247186,0.0001552851,0.0007116663,0.0002480268,0.00007128123],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002717943,0.0002222692,0.0004511134,0.00005726226,0.0001167629,7.619198e-7,0.004834186,0.00004999031,0.01921463,0.73181,0.1341497,0.1090661],"study_design_scores_gemma":[0.000314907,0.0003674132,0.00009285232,0.00008586671,0.00000751613,0.00006181993,0.0003064032,0.3031678,0.005283291,0.0005538239,0.6894059,0.0003524105],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001295773,0.0001243286,0.9953316,0.0003261187,0.0001155358,0.00121875,0.0000166582,0.0008898433,0.00184762],"genre_scores_gemma":[0.5540445,0.000002770734,0.439763,0.000105994,0.0003072168,0.005072756,0.00003203141,0.00002180958,0.0006498782],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7312562,"threshold_uncertainty_score":0.4669639,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2468396395","doi":"10.1016/j.conengprac.2016.05.021","title":"A local alignment approach to similarity analysis of industrial alarm flood sequences","year":2016,"lang":"en","type":"article","venue":"Control Engineering Practice","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"ALARM; Computation; Computer science; Flood myth; Smith–Waterman algorithm; Similarity (geometry); Data mining; Matching (statistics); Algorithm; Artificial intelligence; Engineering; Sequence alignment; Mathematics; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.0243301452670849,"gpt":0.2558899702717198,"spread":0.2315598250046349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108206,0.0001766353,0.0003805822,0.0003690916,0.00002924139,0.00007957059,0.001024763,0.0001064474,0.000004308503],"category_scores_gemma":[0.001885892,0.0001366568,0.0001037886,0.001074181,0.00003239966,0.0009082651,0.000239527,0.0001402148,0.000006025408],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001113529,"about_ca_system_score_gemma":0.00007515073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009855731,"about_ca_topic_score_gemma":0.000001764517,"domain_scores_codex":[0.9983866,0.0001058368,0.0003447199,0.000445017,0.0004218114,0.0002960356],"domain_scores_gemma":[0.997744,0.0009517731,0.0001682112,0.0008575689,0.0001292112,0.000149212],"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":[0.0004031078,0.00170945,0.001840406,0.00006792794,0.01026826,0.0001171658,0.00199158,0.5096317,0.0222707,0.1449854,0.006128761,0.3005855],"study_design_scores_gemma":[0.001828894,0.0004138645,0.0008053533,0.00009795847,0.001486117,0.00002831532,0.00005778418,0.955556,0.00979694,0.00009392615,0.02921285,0.000622028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006217256,0.00003439181,0.99626,0.001771854,0.0001296523,0.000231955,0.00004915814,0.0002982909,0.0006029761],"genre_scores_gemma":[0.8224759,0.000005500434,0.1772176,0.0001863853,0.00003987534,0.00005301846,0.000002954658,0.000008661155,0.00001011726],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8218542,"threshold_uncertainty_score":0.5572704,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3158701715","doi":"10.1016/j.eswa.2021.115127","title":"Deep graph convolutional reinforcement learning for financial portfolio management – DeepPocket","year":2021,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Reinforcement learning; Computer science; Exploit; Graph; Artificial intelligence; Autoencoder; Portfolio; Financial market; Project portfolio management; Investment management; Machine learning; Finance; Deep learning; Theoretical computer science; Economics; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.01290398708640117,"gpt":0.2548392925997628,"spread":0.2419353055133617,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001877268,0.0001626824,0.0001782645,0.0001180645,0.0003638864,0.0001619735,0.0006019144,0.00005801552,0.00001061052],"category_scores_gemma":[0.00001659174,0.0001556479,0.00005764901,0.0004922237,0.00004167885,0.0002359996,0.0002165609,0.00008534108,0.00002288257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009311255,"about_ca_system_score_gemma":0.0001198537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002889353,"about_ca_topic_score_gemma":0.000007421623,"domain_scores_codex":[0.9985137,0.00003401463,0.0003182411,0.0005306809,0.0003071417,0.0002962212],"domain_scores_gemma":[0.9986266,0.00006203348,0.0001621876,0.0008186197,0.0002333442,0.00009723348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009073868,0.00009451686,0.0001823609,0.00006674186,0.00006908768,0.00001444072,0.0002694496,0.002991025,0.0001423285,0.9546697,0.03085758,0.01063367],"study_design_scores_gemma":[0.0007188994,0.0001427596,0.000376631,0.0001218161,0.00002202748,0.0001266338,0.0003486447,0.06258009,0.001276654,0.00286428,0.9309353,0.0004862827],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00003100848,0.000508532,0.9920878,0.0002492385,0.0001035003,0.00114045,0.000005831551,0.0004330084,0.00544063],"genre_scores_gemma":[0.2705971,0.0001292761,0.7035362,0.0004374793,0.0002918641,0.0209201,0.0005711748,0.00003708667,0.003479693],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9518055,"threshold_uncertainty_score":0.6347138,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200219001","doi":"10.1109/globecom46510.2021.9685338","title":"PWPAE: An Ensemble Framework for Concept Drift Adaptation in IoT Data Streams","year":2021,"lang":"en","type":"article","venue":"2021 IEEE Global Communications Conference (GLOBECOM)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Anomaly detection; Internet of Things; Data stream mining; Concept drift; Analytics; Big data; Data analysis; Adaptation (eye); Data stream; Data mining; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1904354663803047,"gpt":0.3975175320562871,"spread":0.2070820656759825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0006347657,0.0003207354,0.0004277342,0.00009493435,0.0003333965,0.0007263799,0.0102841,0.0002570684,0.00005911515],"category_scores_gemma":[0.0008032385,0.0003798184,0.00007502925,0.001269305,0.0002297553,0.001430279,0.003148114,0.0004479566,0.00004327413],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002120435,"about_ca_system_score_gemma":0.001151226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009355006,"about_ca_topic_score_gemma":0.006573886,"domain_scores_codex":[0.9967724,0.0005796872,0.0006788208,0.001069223,0.0003645328,0.0005353112],"domain_scores_gemma":[0.986318,0.0006594819,0.0002895269,0.01190793,0.0006310985,0.0001939837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008253951,0.0004429274,0.0005995962,0.00001122746,0.00003078369,0.00001002859,0.0006152393,0.0001131321,0.0001515156,0.6718024,0.00472774,0.3214871],"study_design_scores_gemma":[0.0009984396,0.0002752664,0.001982792,0.0004964913,0.00006234273,0.0000578069,0.002448831,0.7217705,0.002337946,0.2299341,0.03853439,0.001101165],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003072886,0.0006581567,0.9857314,0.004196405,0.0003737576,0.0005250056,0.001469558,0.0003374628,0.00363533],"genre_scores_gemma":[0.4158561,0.0002837089,0.5815862,0.0002789594,0.00003770653,0.0001037135,0.001806487,0.00001163733,0.00003548151],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7216573,"threshold_uncertainty_score":0.9998654,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751686959","doi":"10.1007/s10994-018-5719-z","title":"Reservoir of diverse adaptive learners and stacking fast hoeffding drift detection methods for evolving data streams","year":2018,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada; University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Trillium Foundation; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; University of Ottawa","keywords":"Concept drift; Data stream mining; Data stream; Change detection; Streaming data; False alarm; Intrusion detection system; Resource (disambiguation); Ranging","retraction":null,"screen_n_in":null,"score":{"opus":0.06608287604619553,"gpt":0.3737000284153294,"spread":0.3076171523691339,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002020466,0.0001857689,0.0002547689,0.0002376824,0.0003999285,0.000177125,0.001204203,0.00007742607,0.000009942703],"category_scores_gemma":[0.001524728,0.0001846209,0.00003761805,0.0003660644,0.0001367847,0.001248318,0.001891747,0.0002922092,0.0000013468],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003663198,"about_ca_system_score_gemma":0.00003167146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000861444,"about_ca_topic_score_gemma":0.0002646856,"domain_scores_codex":[0.9982004,0.0003472767,0.000271299,0.0006786298,0.0001853353,0.000317051],"domain_scores_gemma":[0.9979795,0.0006053788,0.000299526,0.0008947076,0.0001483621,0.00007254805],"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":[0.00003408407,0.00001298856,0.007749785,0.00003269219,0.00004093384,0.000001765429,0.001658242,0.0001978528,0.005907605,0.0005123583,0.0000907046,0.983761],"study_design_scores_gemma":[0.0002829403,0.0005974805,0.001220423,0.0001108864,0.0000241945,0.000006962201,0.0005550761,0.9814752,0.01239679,0.0005153699,0.002610247,0.0002043878],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03170109,0.0001398648,0.9669339,0.00006580421,0.0001237563,0.0002061768,0.00002840604,0.0003405248,0.0004604631],"genre_scores_gemma":[0.5076516,0.000009904032,0.4921938,0.000009875712,0.00005298742,0.000003991534,0.00002573012,0.00001303439,0.00003902158],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9835566,"threshold_uncertainty_score":0.7528623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2904344771","doi":"10.1007/s11276-018-01896-2","title":"A framework for social media data analytics using Elasticsearch and Kibana","year":2018,"lang":"en","type":"article","venue":"Wireless Networks","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; NoSQL; Search engine indexing; Context (archaeology); Process (computing); Analytics; Set (abstract data type); Social media; Relational database; Enhanced Data Rates for GSM Evolution; Database; Big data; Data science; World Wide Web; Data mining; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.1618337897448391,"gpt":0.3728418159850527,"spread":0.2110080262402136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005558152,0.0001538767,0.0002230873,0.00008615308,0.0003203132,0.0003112236,0.001943662,0.0001975414,0.000004257918],"category_scores_gemma":[0.0002626541,0.0001544767,0.00002551514,0.0004193572,0.0002965232,0.0003928442,0.001848662,0.0002447437,0.000002177457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003139503,"about_ca_system_score_gemma":0.0000732217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001458414,"about_ca_topic_score_gemma":0.00004429342,"domain_scores_codex":[0.9984645,0.00005102538,0.0002165627,0.0005837248,0.0002302412,0.0004539342],"domain_scores_gemma":[0.9977524,0.0008016233,0.0001072003,0.001101075,0.0001328149,0.0001048791],"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":[0.00005376646,0.00009355866,0.00111336,0.00004571728,0.0001154533,0.00001881088,0.002006458,0.00008273643,0.00005991014,0.4015271,0.03732884,0.5575542],"study_design_scores_gemma":[0.0001284428,0.00005102274,0.0003131437,0.00006830417,0.00002306641,0.000006512427,0.00002435523,0.9799745,0.00005161812,0.01772685,0.001445836,0.0001863539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006653709,0.00006661608,0.9921959,0.0002051373,0.0003891026,0.0001421783,0.0000718223,0.0002211508,0.00005435347],"genre_scores_gemma":[0.4841464,0.00002061525,0.5143785,0.0001041932,0.001274227,0.000005343038,0.00005008633,0.00001714547,0.000003542278],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9798918,"threshold_uncertainty_score":0.6299376,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2810132194","doi":"10.1109/tii.2018.2850930","title":"Cost-Sensitive Weighting and Imbalance-Reversed Bagging for Streaming Imbalanced and Concept Drifting in Electricity Pricing Classification","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; Guangzhou Municipal Science and Technology Project; Guangdong University of Technology; National Natural Science Foundation of China","keywords":"Concept drift; Computer science; Weighting; Smart grid; Electricity; Artificial intelligence; Machine learning; Data mining; Class (philosophy); Statistical classification; Data stream mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05842192385699823,"gpt":0.2952243161546479,"spread":0.2368023922976497,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005681746,0.0001932478,0.0002583532,0.0003169912,0.0003560552,0.0002235294,0.0002254771,0.0001854411,9.638437e-7],"category_scores_gemma":[0.0001076484,0.0002008635,0.00003049885,0.0005319768,0.0001224513,0.001129463,0.00001013697,0.0003904681,0.000001207935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001586754,"about_ca_system_score_gemma":0.0000943349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006542396,"about_ca_topic_score_gemma":0.00002616348,"domain_scores_codex":[0.9985892,0.00005633077,0.0005798461,0.0002404149,0.0001759963,0.0003582225],"domain_scores_gemma":[0.9986507,0.0005585461,0.0003162147,0.000268015,0.0001268225,0.00007974201],"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":[0.0001276067,0.00009331021,0.000790705,0.00005450939,0.00005662517,0.000002377997,0.01813576,0.0004131727,0.006037014,0.001923745,0.0003184785,0.9720467],"study_design_scores_gemma":[0.002183656,0.0004557174,0.0005290589,0.0003745619,0.00002647154,0.00002118806,0.001985685,0.8586849,0.1348866,0.0001741359,0.0002938087,0.0003842853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1619636,0.000002621948,0.836599,0.0001146182,0.0002330437,0.0006585797,0.00003416613,0.0001888837,0.0002054978],"genre_scores_gemma":[0.9088529,0.00001398957,0.09086,0.0001084323,0.0000834189,0.00005341839,0.000007118857,0.00001034653,0.00001037419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716624,"threshold_uncertainty_score":0.8190975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3184231327","doi":"10.1145/3447876","title":"An Empirical Study of the Impact of Data Splitting Decisions on the Performance of AIOps Solutions","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University; École de Technologie Supérieure; Polytechnique Montréal; Queen's University","funders":"","keywords":"Computer science; Concept drift; Leakage (economics); Cloud computing; Data mining; Context (archaeology); Data science; TRACE (psycholinguistics); Data stream mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2584045887855763,"gpt":0.416978530640578,"spread":0.1585739418550018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00128023,0.0001090522,0.0002395892,0.0001055903,0.0001248292,0.0000106598,0.001444897,0.00006044004,0.000004706066],"category_scores_gemma":[0.002157301,0.00006819873,0.0000615481,0.0005192804,0.00006559415,0.0001742668,0.0001577104,0.0002617435,1.71239e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001496826,"about_ca_system_score_gemma":0.00008928108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006921813,"about_ca_topic_score_gemma":0.000008743124,"domain_scores_codex":[0.9986985,0.0004303037,0.0002841391,0.0002864558,0.0001499656,0.0001506352],"domain_scores_gemma":[0.992331,0.004918979,0.00009269165,0.002529755,0.00009073278,0.00003686042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000121569,0.003835294,0.03593044,0.0001126409,0.0008398703,0.000009968004,0.0122431,0.2329169,0.02280841,0.001602079,0.0003009905,0.6892787],"study_design_scores_gemma":[0.001379069,0.007200676,0.5400544,0.0007024916,0.000340774,0.0002914001,0.001870408,0.3412456,0.1047537,0.00126071,0.0002055807,0.0006951144],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4734015,0.000017387,0.5263311,0.00004940678,0.00005294392,0.00006206836,0.00004313125,0.00004154245,9.623911e-7],"genre_scores_gemma":[0.5791912,0.00001886032,0.4207627,0.000007676166,0.000004333511,0.000006319928,0.000002085768,0.000004884895,0.000001899547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6885836,"threshold_uncertainty_score":0.2781064,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2402498022","doi":"","title":"Cardinality estimation using neural networks","year":2015,"lang":"en","type":"article","venue":"Computer Science and Software Engineering","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); York University; University of Waterloo","funders":"","keywords":"Cardinality (data modeling); Estimator; Computer science; Bounded function; Artificial neural network; Range (aeronautics); Column (typography); Algorithm; Data mining; Theoretical computer science; Artificial intelligence; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.031090544868678,"gpt":0.2570836142534774,"spread":0.2259930693847994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001098497,0.0001249635,0.0001282827,0.0001585912,0.0001269086,0.0005023266,0.0008553343,0.00003436782,1.207435e-7],"category_scores_gemma":[0.0002739784,0.0001231951,0.00001818909,0.0007217527,0.00009410084,0.001709538,0.000823183,0.000106594,7.767732e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001002296,"about_ca_system_score_gemma":0.00009237914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002401856,"about_ca_topic_score_gemma":2.094444e-7,"domain_scores_codex":[0.9987708,0.00001670416,0.0001403284,0.0003951544,0.0003726766,0.0003043632],"domain_scores_gemma":[0.999041,0.00006246389,0.00003871514,0.0004704103,0.0001766827,0.0002107773],"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":[6.9267e-7,0.000008494232,0.00211587,0.00001045655,0.00000354939,0.00001755741,0.0003749687,0.7384527,0.00003405179,0.001957014,0.0002497735,0.2567748],"study_design_scores_gemma":[0.00005960838,0.00003404263,0.001589322,0.00002098825,0.000002121414,0.00007372801,0.000001505168,0.9977146,0.0001314348,0.0001387488,0.00008738355,0.0001464558],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06685996,0.00008140155,0.9316941,0.00002964312,0.0005871691,0.00006396235,6.100063e-7,0.0006791942,0.000003992298],"genre_scores_gemma":[0.4374268,7.237877e-7,0.5624659,0.00004499072,0.00005493762,0.000001841312,6.858579e-7,0.000003653411,4.331169e-7],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3705669,"threshold_uncertainty_score":0.5023751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071416419","doi":"10.1007/s11390-008-9115-1","title":"Clustering Text Data Streams","year":2008,"lang":"en","type":"article","venue":"Journal of Computer Science and Technology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Simon Fraser University; Chinese University of Hong Kong; University of Hong Kong; Sun Yat-sen University","keywords":"Computer science; Cluster analysis; Data mining; Data stream mining; Data stream clustering; Smoothing; Document clustering; Fuzzy clustering; Semantics (computer science); Context (archaeology); Information retrieval; CURE data clustering algorithm; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.03598818950116101,"gpt":0.2789750984262266,"spread":0.2429869089250656,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00100642,0.0001143577,0.0002288988,0.0009693207,0.000244663,0.000151062,0.006268324,0.00007188895,0.000001153525],"category_scores_gemma":[0.0001384584,0.00009210185,0.00001685018,0.001611306,0.0009135813,0.002421502,0.004355715,0.0002591946,0.000003741926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003699298,"about_ca_system_score_gemma":0.000381945,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004105707,"about_ca_topic_score_gemma":0.000001596516,"domain_scores_codex":[0.9984441,0.00001612282,0.0003494718,0.0003922626,0.0005034505,0.0002946364],"domain_scores_gemma":[0.9978046,0.00004904453,0.0002853108,0.001332598,0.0004229986,0.0001054354],"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":[0.000002188936,0.00005157555,0.001953748,0.000004183909,0.0000101737,0.0002941315,0.0001561203,0.000005431815,0.00132763,0.005605311,0.005541744,0.9850478],"study_design_scores_gemma":[0.001394882,0.003043954,0.007718349,0.0003052738,0.00002460721,0.05636745,0.00007683987,0.8330725,0.02548843,0.02166189,0.04995553,0.0008902934],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07902014,0.000182051,0.9171684,0.002893626,0.0003628439,0.00004623554,0.000001798171,0.0001783689,0.0001465336],"genre_scores_gemma":[0.4818583,0.0001135073,0.5178334,0.000125687,0.00006089588,3.999756e-7,2.502643e-7,0.000002962461,0.000004713998],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9841574,"threshold_uncertainty_score":0.9991083,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034360859","doi":"","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Feature (linguistics); Generative model; Generative grammar; Computer science; Artificial intelligence; Feature learning; Machine learning; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03676985648599293,"gpt":0.3016793059080322,"spread":0.2649094494220393,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001396669,0.0001553088,0.0001533308,0.0001963088,0.00006383585,0.0002301274,0.000452266,0.00004346145,0.0000147455],"category_scores_gemma":[0.0001466169,0.0001272661,0.00001156448,0.0002871142,0.00004081209,0.000503702,0.0001968386,0.0007994889,0.000003871478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004215606,"about_ca_system_score_gemma":0.00008214632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001090176,"about_ca_topic_score_gemma":0.000352205,"domain_scores_codex":[0.9987976,0.0001169535,0.0001422503,0.0004875796,0.0002999755,0.0001556275],"domain_scores_gemma":[0.9995325,0.00008081152,0.0001085777,0.0001276811,0.00008617042,0.00006426317],"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":[0.0004541698,0.0001201021,0.3867161,0.00001929194,0.00006406941,0.0003392762,0.01305251,0.3971556,0.00232004,0.1753837,0.0001294842,0.0242456],"study_design_scores_gemma":[0.0006227838,0.000390454,0.009510461,0.0001282283,0.000002106011,0.00001787546,0.0001655002,0.9878534,0.0003470824,0.0006155302,0.0001831125,0.0001634667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.305977,0.00003492242,0.6438507,0.02425132,0.00003225096,0.0003419724,0.00001930018,0.0003920832,0.02510046],"genre_scores_gemma":[0.9239329,0.00002264084,0.07527363,0.00028884,0.00001875973,0.00003010893,0.00004868552,0.00001110798,0.0003733231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6179559,"threshold_uncertainty_score":0.5189759,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2798255764","doi":"10.1109/tie.2018.2826477","title":"A Novelty Detector and Extreme Verification Latency Model for Nonstationary Environments","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Electronics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":57,"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":"Computer science; Novelty detection; Fault detection and isolation; Data stream; Novelty; Data modeling; Detector; Data mining; Latency (audio); Condition monitoring; Fault (geology); Concept drift; Real-time computing; Artificial intelligence; Data stream mining; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07948879409924113,"gpt":0.2700748393610954,"spread":0.1905860452618542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002055896,0.0001564589,0.0001228724,0.0001338819,0.0002716904,0.00007089573,0.0003828842,0.00017616,0.000009371767],"category_scores_gemma":[0.00001434263,0.0001683152,0.00004521995,0.0002087628,0.00008618864,0.0005607309,0.000004066264,0.0002440302,0.00001075399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001756737,"about_ca_system_score_gemma":0.0002104908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001182515,"about_ca_topic_score_gemma":0.00002685135,"domain_scores_codex":[0.9988089,0.00003237791,0.0002326321,0.0004329683,0.0001879723,0.0003051787],"domain_scores_gemma":[0.9992397,0.00009268765,0.00009116258,0.0004641566,0.00003869948,0.00007356053],"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":[0.0004330212,0.0005916258,0.000008881623,0.000009652607,0.0001160017,0.000001200566,0.0007415552,0.00263491,0.07056746,0.010237,0.003413417,0.9112453],"study_design_scores_gemma":[0.001174755,0.001077943,0.00001329658,0.00001924025,0.00003518064,0.000009617575,0.000005882951,0.8450686,0.1423196,0.004575309,0.005411131,0.0002894353],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006149509,0.00001798347,0.9925246,0.0003001503,0.0002134425,0.0004529273,0.0001073809,0.0001791581,0.00005488222],"genre_scores_gemma":[0.8827264,0.00005805727,0.1164919,0.0001299784,0.00009126354,0.0002126227,0.00001450611,0.00002207757,0.0002532438],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9109558,"threshold_uncertainty_score":0.6863694,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4283807683","doi":"10.1609/aaai.v36i6.20618","title":"Reinforcement Learning Based Dynamic Model Combination for Time Series Forecasting","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":55,"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":"Reinforcement learning; Computer science; Machine learning; Artificial intelligence; Time series; Series (stratigraphy); Ensemble learning; Raw data; Ensemble forecasting; Selection (genetic algorithm)","retraction":null,"screen_n_in":null,"score":{"opus":0.0729605973150735,"gpt":0.2881855701715623,"spread":0.2152249728564888,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009151863,0.0001767556,0.0001918639,0.0001607689,0.0005974968,0.0002136315,0.002146218,0.00003804518,0.00003717419],"category_scores_gemma":[0.0004620072,0.0001613311,0.00009434195,0.0004468069,0.0001072459,0.0005211039,0.0008577863,0.0002779068,0.000006250406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001374272,"about_ca_system_score_gemma":0.0001309421,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008859861,"about_ca_topic_score_gemma":0.00000125773,"domain_scores_codex":[0.9983011,0.0000190206,0.0004406265,0.0004109763,0.0005345446,0.0002937649],"domain_scores_gemma":[0.9986869,0.0001073123,0.0004783944,0.0002547491,0.0004313877,0.00004126835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001402529,0.0001470476,0.00002898736,0.00006347041,0.00001303703,2.774944e-7,0.001417173,0.07272042,0.02919778,0.8474551,0.000420998,0.04839541],"study_design_scores_gemma":[0.00002567775,0.0004964438,0.000002218559,0.00005688661,0.000006231588,0.000002096853,0.00012083,0.777064,0.1175493,0.10447,0.0000698598,0.0001364563],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0186769,0.000003777139,0.9737478,0.003121804,0.0001585242,0.0008595169,0.00001695502,0.0003335847,0.003081064],"genre_scores_gemma":[0.9515653,0.000001693611,0.04734838,0.0001278708,0.000008094979,0.0002458342,0.000008848968,0.00001473656,0.0006792916],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9328883,"threshold_uncertainty_score":0.6578889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100368765","doi":"10.1155/2012/580186","title":"Real-Time Clinical Decision Support System with Data Stream Mining","year":2012,"lang":"en","type":"article","venue":"Journal of Biomedicine and Biotechnology","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Data science; Field (mathematics); Decision support system; Data mining; Software; Data stream; Data stream mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03656716972369448,"gpt":0.3334920832397414,"spread":0.2969249135160469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002502622,0.0001497469,0.0004977899,0.0005281486,0.00005275192,0.00003268852,0.001702579,0.0002984536,0.000005824057],"category_scores_gemma":[0.0002024906,0.00009007089,0.00003026931,0.0004806742,0.0003175368,0.000685575,0.0009738472,0.0003024447,0.000008173958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003011304,"about_ca_system_score_gemma":0.0001064974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001493648,"about_ca_topic_score_gemma":0.000001518928,"domain_scores_codex":[0.9982569,0.00005823952,0.0007676893,0.0002833723,0.000321532,0.0003122229],"domain_scores_gemma":[0.9976737,0.000265996,0.0006365578,0.001134049,0.00009317746,0.0001965582],"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":[0.000107603,0.0002259924,0.0120521,0.00003556046,0.0001284355,0.0004368833,0.0001158016,3.367172e-8,0.005737519,0.00203609,0.06219197,0.916932],"study_design_scores_gemma":[0.01956822,0.07708953,0.07010455,0.008433308,0.001482147,0.1541344,0.006069799,0.02299846,0.04710863,0.0009547297,0.5888844,0.003171818],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5722888,0.0005999696,0.4191311,0.005815263,0.0008451738,0.0001750522,0.00003656887,0.0005267839,0.0005813757],"genre_scores_gemma":[0.4920665,0.0006760604,0.5068137,0.00007757043,0.0003260326,5.877847e-7,0.00001278333,0.000009666641,0.00001713072],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9137602,"threshold_uncertainty_score":0.3672984,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3135908355","doi":"10.1007/s10994-022-06188-7","title":"STUDD: a student–teacher method for unsupervised concept drift detection","year":2022,"lang":"en","type":"article","venue":"Machine Learning","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação para a Ciência e a Tecnologia","keywords":"Concept drift; Computer science; Unsupervised learning; Context (archaeology); Data stream mining; Artificial intelligence; Data stream; Machine learning; Set (abstract data type); Task (project management); State (computer science); Algorithm; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0163969870871684,"gpt":0.3182022068596486,"spread":0.3018052197724801,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001388879,0.0001705781,0.000211561,0.0001653576,0.000690171,0.0001643631,0.00123002,0.00003588365,0.0001150241],"category_scores_gemma":[0.0001677509,0.0001796069,0.00009231448,0.0003873542,0.0000174678,0.0002591246,0.001256254,0.0005098768,0.000004814703],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001039884,"about_ca_system_score_gemma":0.0000295294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002368371,"about_ca_topic_score_gemma":0.00002690933,"domain_scores_codex":[0.9979177,0.0006217664,0.0002335621,0.0005380798,0.0003805377,0.0003084236],"domain_scores_gemma":[0.9990208,0.000243998,0.000136773,0.0004979799,0.00004159277,0.00005886767],"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":[0.00004262427,0.0003062868,0.009698974,0.00001878852,0.0001188466,0.00002384555,0.0140125,0.006243857,0.009222832,0.005080339,0.002294186,0.9529369],"study_design_scores_gemma":[0.001260932,0.001340103,0.001951416,0.000008758881,0.00003273455,0.00004606399,0.0007971368,0.7819194,0.004665144,0.001082651,0.2064294,0.0004662534],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01101777,0.000122662,0.9862059,0.000411941,0.000228625,0.0004184342,0.00001911473,0.001033173,0.0005424288],"genre_scores_gemma":[0.6411549,0.000001732769,0.3562974,0.0002839061,0.00007421859,0.000418426,0.00004608622,0.00003368786,0.00168963],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9524707,"threshold_uncertainty_score":0.7324156,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4303449845","doi":"10.1109/tii.2022.3212003","title":"A Multi-Stage Automated Online Network Data Stream Analytics Framework for IIoT Systems","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Industrial Informatics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Analytics; Stream processing; Data analysis; Automation; Big data; Data mining; Data stream; Distributed computing; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.233338610719602,"gpt":0.3689120298725712,"spread":0.1355734191529692,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001035967,0.0003206102,0.0004320459,0.0003249341,0.0008057237,0.0004607695,0.003503292,0.0002823973,0.0000364844],"category_scores_gemma":[0.00009608855,0.0003361922,0.000109652,0.001351371,0.00006051283,0.00114508,0.0001151121,0.00117721,0.00001050322],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002716724,"about_ca_system_score_gemma":0.000386832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001205261,"about_ca_topic_score_gemma":0.00001912219,"domain_scores_codex":[0.9971843,0.0001371384,0.001129353,0.000360756,0.0006158435,0.0005725889],"domain_scores_gemma":[0.9958005,0.0007090671,0.0005517626,0.002659234,0.0001098089,0.0001696491],"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":[0.00009081153,0.0007848386,0.00001054674,0.00006401242,0.0002661062,0.000007884654,0.0008858325,0.9006001,0.000004745388,0.003444702,0.06832757,0.02551281],"study_design_scores_gemma":[0.0009471849,0.0004796761,0.000001657309,0.00009063977,0.00006881745,0.00001710275,0.0007380174,0.967639,0.0001033546,0.00009215787,0.02948152,0.0003408597],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006215838,0.00001365408,0.982411,0.0001756956,0.003090241,0.001140272,0.01031681,0.00219411,0.00003668219],"genre_scores_gemma":[0.0698984,0.000020179,0.9274589,0.0005257607,0.0003319984,0.0003182355,0.001114724,0.00004915009,0.0002826792],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06927682,"threshold_uncertainty_score":0.999909,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2995435218","doi":"10.1109/bigdata.2018.8622360","title":"A Scalable and Robust Framework for Data Stream Ingestion","year":2018,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Scalability; Stream processing; Data stream mining; Robustness (evolution); Volume (thermodynamics); Big data; Analytics; Data stream; Distributed computing; Database; Data science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.08237272958804882,"gpt":0.3257427582771607,"spread":0.2433700286891119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002927381,0.00007225971,0.0000748914,0.00004627533,0.00009380907,0.0002205266,0.001192738,0.00006099274,0.00001279365],"category_scores_gemma":[0.0003101974,0.00006281601,0.000006430358,0.0001470735,0.00006840717,0.0008066116,0.001157357,0.00005111024,0.00001206476],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009204911,"about_ca_system_score_gemma":0.00002429264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006798255,"about_ca_topic_score_gemma":0.00003678056,"domain_scores_codex":[0.9992358,0.00001205261,0.00009344112,0.0004135629,0.00008537426,0.0001597513],"domain_scores_gemma":[0.9983559,0.0001496029,0.00003713379,0.001351896,0.0000562097,0.00004924048],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008905416,0.00004594154,0.00108857,0.00001423366,0.000009642882,9.315167e-7,0.0001264482,5.688891e-7,0.00004531083,0.494151,0.1235397,0.3809688],"study_design_scores_gemma":[0.0002833639,0.0007463595,0.001326283,0.0001892492,0.00001693904,0.00002596993,0.000031845,0.6667079,0.01113978,0.2620301,0.05708224,0.0004199978],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001662345,0.00001824198,0.9953266,0.0008293249,0.00009483692,0.000137274,0.00002818717,0.0004826551,0.001420494],"genre_scores_gemma":[0.03963343,0.000007948457,0.9598629,0.0002230003,0.00009772957,0.00001225952,0.0000392088,0.000005673354,0.0001178407],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6667073,"threshold_uncertainty_score":0.2561563,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2059979378","doi":"10.1007/s10472-013-9371-9","title":"Domain adaptation–can quantity compensate for quality?","year":2013,"lang":"en","type":"article","venue":"Annals of Mathematics and Artificial Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Machine learning; Domain adaptation; Test data; Training set; Sample (material); Labeled data; Adaptation (eye); Probability distribution; Pattern recognition (psychology); Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2925720871620803,"gpt":0.4001518648282202,"spread":0.1075797776661399,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008117649,0.0001100271,0.0002310661,0.00007265341,0.00008631471,0.00018315,0.0005793017,0.00004097303,0.00001146828],"category_scores_gemma":[0.0001939015,0.00009868852,0.00005671604,0.0001377826,0.0001169784,0.0002959124,0.0001644662,0.00004765904,0.00001677621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002653597,"about_ca_system_score_gemma":0.00002236093,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002017431,"about_ca_topic_score_gemma":0.00005448468,"domain_scores_codex":[0.9988492,0.00002853307,0.0005293379,0.000218571,0.000185209,0.0001891843],"domain_scores_gemma":[0.998555,0.0004283324,0.0002481189,0.000417501,0.0002851879,0.00006587202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001374126,0.0001029027,0.0000152113,0.00006794433,0.000008868313,2.174494e-7,0.001468708,0.000007633503,0.001459219,0.9272805,0.0002473312,0.06934005],"study_design_scores_gemma":[0.000009077531,0.0001124157,0.00006692293,0.00007798602,0.000002181451,0.000001410117,0.0007084615,0.05435481,0.06997985,0.8743364,0.0002273586,0.0001231442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07978868,0.0000416112,0.9173024,0.002263315,0.00004187703,0.0003084769,0.0000237196,0.00007009602,0.0001597726],"genre_scores_gemma":[0.4061909,0.00004952956,0.5935245,0.000168717,0.0000138146,0.00003286973,0.000003537241,0.000005500474,0.0000105959],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3264022,"threshold_uncertainty_score":0.4024401,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2760845379","doi":"10.1111/coin.12146","title":"Threaded ensembles of autoencoders for stream learning","year":2017,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":48,"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; Anomaly detection; Autoencoder; Benchmark (surveying); Data stream; Artificial intelligence; Data stream mining; Concept drift; Streaming data; Class (philosophy); Machine learning; Data mining; Pattern recognition (psychology); Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.07278026847176025,"gpt":0.3580306338209599,"spread":0.2852503653491997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003119141,0.0001177744,0.0001627213,0.00008967106,0.0003381435,0.0002354638,0.002058766,0.00004720213,0.000007001346],"category_scores_gemma":[0.0005452317,0.0001193735,0.00007179653,0.00006858239,0.0001789707,0.000552764,0.0003954016,0.00009248677,0.00001187151],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002265706,"about_ca_system_score_gemma":0.0001019359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004193754,"about_ca_topic_score_gemma":0.000004995391,"domain_scores_codex":[0.9989371,0.00002546079,0.0002750391,0.0003285742,0.0002532862,0.000180531],"domain_scores_gemma":[0.9982475,0.0005009785,0.0003432737,0.0005787289,0.0002796913,0.00004981375],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000143199,0.00008170187,0.001730582,0.00004788897,0.00003670027,0.000004131604,0.000754443,0.09181251,0.000191231,0.6150451,0.001498435,0.288783],"study_design_scores_gemma":[0.00006159287,0.0001606448,0.002066944,0.00006965447,0.000004904966,0.00000718308,0.00004585377,0.731242,0.01736825,0.2481288,0.0006935679,0.0001505816],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002559531,0.00003763402,0.9952007,0.0004008511,0.0001388208,0.0001637684,0.00001492889,0.0001902814,0.001293489],"genre_scores_gemma":[0.5437852,0.000006146034,0.4560681,0.00002446455,0.00001706811,0.00001496864,0.00001354646,0.000005233327,0.00006533822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6394295,"threshold_uncertainty_score":0.486791,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2744444471","doi":"10.1002/cjs.11330","title":"Online updating method with new variables for big data streams","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Cancer Institute","keywords":"Computer science; Data stream mining; Big data; Data stream; Context (archaeology); Data mining; Set (abstract data type); Data set; Linear regression; Algorithm; Machine learning; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1247159512766345,"gpt":0.3397142720643705,"spread":0.214998320787736,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006325534,0.0001196342,0.0002211296,0.0001432608,0.000332151,0.0007263304,0.003863299,0.00004080649,0.000006726264],"category_scores_gemma":[0.001604916,0.0001015384,0.00001524935,0.00006466945,0.00007089252,0.0006992554,0.0001788251,0.0001627277,7.359442e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006480764,"about_ca_system_score_gemma":0.003546098,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01423008,"about_ca_topic_score_gemma":0.07791575,"domain_scores_codex":[0.998998,0.00002553909,0.0003106615,0.0002133807,0.0001654969,0.0002869002],"domain_scores_gemma":[0.9966996,0.0002881923,0.0006579699,0.001500343,0.0002923286,0.0005615367],"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":[0.000005261143,0.0000125361,0.001197619,0.00001584441,0.00005665769,0.0001786991,0.0001360419,0.00001821803,0.00001193963,0.03996838,0.1800518,0.778347],"study_design_scores_gemma":[0.003670872,0.00267567,0.01428446,0.001461996,0.0004829268,0.002075842,0.0004834562,0.1388573,0.001179644,0.2083063,0.6249704,0.001551093],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001039619,0.00003605988,0.9929419,0.000871092,0.000453381,0.00007781299,0.005300081,0.00001288244,0.0002028442],"genre_scores_gemma":[0.005022185,0.000009531899,0.9940924,0.0001332886,0.0004616572,5.654611e-7,0.0001633131,0.00001541418,0.0001016238],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7767959,"threshold_uncertainty_score":0.9923342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3139625059","doi":"10.1109/ideas.2007.4318108","title":"Streaming Random Forests","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Random forest; Computer science; Data stream mining; Data stream; Streaming data; Data mining; Decision tree; Tree (set theory); Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.014424832053807,"gpt":0.2755089235482516,"spread":0.2610840914944446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005018875,0.00006804517,0.00007406709,0.00008558255,0.00004244958,0.000081507,0.0007549764,0.0000304087,0.00001596874],"category_scores_gemma":[0.00005455374,0.00005633023,0.00002596938,0.0001859675,0.00001832977,0.0003869917,0.0002619331,0.00005030058,0.00004475566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001694785,"about_ca_system_score_gemma":0.00001406264,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005355606,"about_ca_topic_score_gemma":0.0001454951,"domain_scores_codex":[0.9993029,0.000009286246,0.0001293218,0.0001964075,0.0001434652,0.0002185998],"domain_scores_gemma":[0.9992282,0.0001391949,0.00003082385,0.0005179138,0.00002428368,0.00005957501],"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":[0.00001071062,0.0000441231,0.0121206,0.000003885432,0.000008833384,0.00006959434,0.0002231584,0.00000127166,0.000680187,0.1941907,0.01841079,0.7742361],"study_design_scores_gemma":[0.005132171,0.0006346126,0.2292552,0.000151145,0.0000198964,0.0002953567,0.0001680799,0.04169153,0.4725851,0.1184411,0.1298319,0.001793948],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0119186,0.00001113365,0.9359006,0.0001104689,0.00007925643,0.00006405301,6.0246e-7,0.0008483498,0.05106694],"genre_scores_gemma":[0.60471,0.000001037639,0.3948164,0.0001126462,0.00002293889,0.000001886878,0.000001600489,0.000003194782,0.0003303531],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7724422,"threshold_uncertainty_score":0.229708,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891373952","doi":"10.1109/tnnls.2019.2927301","title":"Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"Canada Research Chairs","keywords":"Graph; Curvature; Constant curvature; Computer science; Constant (computer programming); Mathematics; Theoretical computer science; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.01162015393602412,"gpt":0.2252255567862819,"spread":0.2136054028502578,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005148397,0.0003506737,0.0003748724,0.0004135454,0.0003732642,0.000383705,0.0003832119,0.0002836779,0.000007736486],"category_scores_gemma":[0.000006356779,0.0003334226,0.0001001276,0.0007813975,0.00005196788,0.0006200807,0.000008525196,0.001778057,0.00001209085],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006219641,"about_ca_system_score_gemma":0.000007771595,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005436795,"about_ca_topic_score_gemma":0.00006299889,"domain_scores_codex":[0.9975865,0.0004649934,0.000365279,0.0007625245,0.0003182785,0.0005024304],"domain_scores_gemma":[0.9989224,0.0003040638,0.0002170287,0.0003916783,0.00004335061,0.0001214497],"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":[0.0002156248,0.0002642997,0.00516211,0.0001700473,0.000119153,0.00007206326,0.001737886,0.5636597,0.002539712,0.0008981315,0.0004993698,0.4246619],"study_design_scores_gemma":[0.0006857612,0.001588274,0.000549024,0.0005205371,0.00001956674,0.00009757504,0.0003317802,0.992957,0.0005347283,0.00002464341,0.002131613,0.0005594759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.412199,0.0004743186,0.5835527,0.0001157697,0.001642358,0.0007557524,0.00001041824,0.0009613135,0.0002884049],"genre_scores_gemma":[0.9989309,0.0002247443,0.0001538131,0.000102032,0.00007359378,0.0001066203,0.000009937538,0.00003820062,0.0003601566],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5867319,"threshold_uncertainty_score":0.9999118,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2968628173","doi":"10.3390/s19163594","title":"An Edge-Fog-Cloud Architecture of Streaming Analytics for Internet of Things Applications","year":2019,"lang":"en","type":"article","venue":"Sensors","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":37,"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":"Cloud computing; Internet of Things; Computer science; Architecture; Analytics; Enhanced Data Rates for GSM Evolution; Data stream mining; The Internet; Edge computing; Smart city; Data science; Fog computing; Big data; Business intelligence; Computer security; World Wide Web; Telecommunications; Database; Data mining; Operating system; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01238497126300916,"gpt":0.2682587392492548,"spread":0.2558737679862457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001802293,0.00009732874,0.0001871937,0.0001343699,0.00001485536,0.00002547511,0.0009553498,0.00005597026,0.000004942265],"category_scores_gemma":[0.00003328715,0.00009067741,0.00005990818,0.0002216531,0.00005227223,0.0001442972,0.0001446931,0.00007886856,0.000003998213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001434107,"about_ca_system_score_gemma":0.00002874077,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005962874,"about_ca_topic_score_gemma":0.000004257977,"domain_scores_codex":[0.999184,0.00002432153,0.0002355938,0.0002744996,0.000139407,0.0001421433],"domain_scores_gemma":[0.9986505,0.0001401251,0.0001956484,0.0008668753,0.0001051792,0.00004170421],"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":[0.00005568894,0.0005877527,0.009629844,0.0006986851,0.0002045765,0.00000281392,0.01494561,0.002081675,0.07346682,0.378686,0.003459495,0.5161811],"study_design_scores_gemma":[0.0006269874,0.001219364,0.002163389,0.0002707306,0.00006698957,0.0000200426,0.0005216276,0.5130733,0.4354852,0.02953505,0.01639343,0.000623858],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2551913,0.000009543653,0.7432107,0.00006960057,0.00005701839,0.0003598023,0.00004048368,0.0001325908,0.0009289644],"genre_scores_gemma":[0.6658785,0.000001352669,0.3339134,0.00002696541,0.00002121317,0.000009646111,0.00001958389,0.000008240064,0.0001211205],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5155572,"threshold_uncertainty_score":0.3697717,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097523548","doi":"10.48550/arxiv.1302.4853","title":"Consistency of Online Random Forests","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":37,"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":"","keywords":"Consistency (knowledge bases); Random forest; Computer science; Data science; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.05044808000416271,"gpt":0.1854984864079621,"spread":0.1350504064037994,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009106628,0.0001001358,0.0001652532,0.0001284373,0.00004503474,0.00002666067,0.001082474,0.00005080703,0.00004843148],"category_scores_gemma":[0.00005501872,0.0001022008,0.00006835737,0.0004323949,0.000116456,0.0006707269,0.0003830184,0.00007467194,0.00006407093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002460237,"about_ca_system_score_gemma":0.00005388981,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002755808,"about_ca_topic_score_gemma":0.00007221738,"domain_scores_codex":[0.9992748,0.00004663002,0.0001327474,0.0003206847,0.00005073339,0.0001743842],"domain_scores_gemma":[0.9988048,0.0001156019,0.000110286,0.0007642048,0.0001267817,0.00007833149],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004929376,0.0005451603,0.1009614,0.00005366957,0.0001057119,0.0001983987,0.0003071427,0.0008957831,0.001325301,0.8615833,0.01399055,0.01998427],"study_design_scores_gemma":[0.005070928,0.0006456872,0.1485295,0.0001921211,0.00008537298,0.00003971575,0.0002308751,0.5708209,0.008659192,0.2620508,0.002648914,0.001025997],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5161428,0.00001356821,0.4803204,0.00008980124,0.00005771467,0.0001570722,0.00001131973,0.0002359011,0.00297136],"genre_scores_gemma":[0.9805474,0.00001811894,0.01890114,0.00005169243,0.000009346108,4.369192e-7,0.000006983475,0.00000499466,0.0004599215],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5995325,"threshold_uncertainty_score":0.4167629,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020732464","doi":"10.1109/3pgcic.2012.55","title":"Performance Evaluation of Yahoo! S4: A First Look","year":2012,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Stream processing; Scalability; Data stream mining; Fault tolerance; Analytics; Data processing; Distributed computing; Batch processing; Complex event processing; Data science; Database; Data mining; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.05153751702399197,"gpt":0.300014013550307,"spread":0.2484764965263151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001074655,0.00005725836,0.00006817205,0.00006113237,0.00003233133,0.0000183658,0.0005311955,0.0000264284,0.00008972162],"category_scores_gemma":[0.00005534605,0.00004835457,0.00001782249,0.0001649931,0.00002178842,0.0009792445,0.0002189676,0.00003360479,0.00007191522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003270859,"about_ca_system_score_gemma":0.00003810422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002274229,"about_ca_topic_score_gemma":0.000004379047,"domain_scores_codex":[0.9991986,0.00002941133,0.0001274009,0.0001141895,0.0003759244,0.0001544508],"domain_scores_gemma":[0.9992069,0.00003119269,0.0000607474,0.0005533998,0.0001084682,0.00003931923],"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":[0.000004354446,0.0002757461,0.1349335,0.00004258433,0.00002147793,2.346267e-7,0.002025262,0.00003733408,0.0007847791,0.04017944,0.03632534,0.78537],"study_design_scores_gemma":[0.0005094054,0.0002534037,0.2140971,0.0001023836,0.00003871997,0.00002081388,0.00004390608,0.6259059,0.1445395,0.001135525,0.01296386,0.000389488],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7152424,0.0001152932,0.1903839,0.0002694345,0.0002548922,0.000290818,0.00000299112,0.0004807669,0.09295949],"genre_scores_gemma":[0.8682092,0.000007009017,0.13161,0.00003760685,0.00002427485,0.00001701061,0.000002349326,0.000002687765,0.00008986183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7849805,"threshold_uncertainty_score":0.1971842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4385444778","doi":"10.1109/tsmc.2023.3293462","title":"FedStream: Prototype-Based Federated Learning on Distributed Concept-Drifting Data Streams","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundamental Research Funds for the Central Universities; Sichuan Province Science and Technology Support Program; Fok Ying Tong Education Foundation; National Natural Science Foundation of China","keywords":"Data stream mining; Computer science; Federated learning; Focus (optics); Metric (unit); Streaming data; Distributed learning; Data stream; STREAMS; Transformation (genetics); Data mining; Data science; Distributed computing; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.04251270373771712,"gpt":0.2751769021600894,"spread":0.2326641984223723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0007872742,0.0004564679,0.0005259823,0.0003638213,0.000637386,0.001354991,0.001273144,0.0002422301,0.000003888],"category_scores_gemma":[0.00003124203,0.0004318103,0.00006653619,0.001005466,0.000104876,0.0003669919,0.00003330486,0.0005464096,0.0001429961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001192227,"about_ca_system_score_gemma":0.0001166439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009027358,"about_ca_topic_score_gemma":0.00003658065,"domain_scores_codex":[0.9963366,0.0004984228,0.0007115239,0.001156219,0.0006885063,0.0006087007],"domain_scores_gemma":[0.9972282,0.0004098542,0.0003211074,0.001648426,0.0001502573,0.0002421728],"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":[0.0005627999,0.002236076,0.001858472,0.003122153,0.001459754,0.001087986,0.004098431,0.6266158,0.006109751,0.01758686,0.05362133,0.2816406],"study_design_scores_gemma":[0.0008896091,0.0009599309,0.00009157031,0.001177185,0.00004126463,0.00005854658,0.0006353506,0.9815254,0.002995112,0.00001315932,0.01098247,0.0006304515],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01586947,0.0001094504,0.9753689,0.0001830201,0.001391594,0.001984213,0.0009959367,0.003222072,0.0008753086],"genre_scores_gemma":[0.9972981,0.00002731638,0.0005604875,0.00002803095,0.00009400408,0.0003584918,0.0004765053,0.00006119157,0.001095842],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9814287,"threshold_uncertainty_score":0.9998134,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2886334640","doi":"10.1145/3205455.3205612","title":"Benchmarking evolutionary computation approaches to insider threat detection","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmarking; Genetic programming; Insider threat; Adaptation (eye); Context (archaeology); Set (abstract data type); Class (philosophy); Machine learning; Insider; Evolutionary computation; Artificial intelligence; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.06690114304704498,"gpt":0.2462901134470578,"spread":0.1793889704000128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002161225,0.0001947931,0.0001870917,0.0002077298,0.0004128853,0.0001298211,0.0006076338,0.00008479017,0.000004636336],"category_scores_gemma":[0.00007412225,0.0001719552,0.00004664594,0.0006497318,0.0002746799,0.0005633154,0.0007290908,0.0001154402,0.000009248865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008421852,"about_ca_system_score_gemma":0.00009607785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000511783,"about_ca_topic_score_gemma":0.000005489145,"domain_scores_codex":[0.9984262,0.0000287543,0.0003659395,0.000538105,0.0004032598,0.0002377615],"domain_scores_gemma":[0.9988235,0.00007137439,0.0002575505,0.0001582682,0.0005960682,0.0000931908],"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":[0.0001537734,0.000357952,0.04660948,0.0003317046,0.0001475535,0.00000141643,0.0104603,0.004684251,0.0189231,0.1010073,0.01503595,0.8022873],"study_design_scores_gemma":[0.0001926964,0.000368273,0.3326073,0.0001371918,0.00001917918,0.00008541247,0.0001543035,0.5769267,0.003907045,0.08516878,0.0001746797,0.000258396],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3229256,0.0000799457,0.6743255,0.0009031629,0.0002376053,0.0003650807,0.000005905702,0.000169123,0.0009880097],"genre_scores_gemma":[0.6971005,0.000008294046,0.3026506,0.00008105073,0.00009933337,0.00002560316,0.000003547044,0.000007481764,0.00002361719],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8020288,"threshold_uncertainty_score":0.701213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1560789270","doi":"10.1007/978-3-540-85654-2_54","title":"Classifying Evolving Data Streams Using Dynamic Streaming Random Forests","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Streaming data; Concept drift; Data stream mining; Data stream; Data mining; Entropy (arrow of time); Class (philosophy); STREAMS; Random forest; Dynamic data; Artificial intelligence; Machine learning; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.04767385452498472,"gpt":0.2982100470538764,"spread":0.2505361925288917,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001368841,0.0009643226,0.0009831794,0.00148357,0.0006543151,0.001212838,0.01337551,0.0005087177,0.00001318234],"category_scores_gemma":[0.0004193972,0.0009429568,0.0001498294,0.0009235851,0.00106059,0.003180811,0.01025986,0.001326937,0.00001690171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000843777,"about_ca_system_score_gemma":0.001257725,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001606821,"about_ca_topic_score_gemma":0.0005377424,"domain_scores_codex":[0.9927684,0.00007461711,0.0009559854,0.003367845,0.001610073,0.001223044],"domain_scores_gemma":[0.9915258,0.001001715,0.000690743,0.006244955,0.0002719134,0.0002648403],"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":[0.000007754398,0.00003409115,0.0003391311,0.00005193169,0.0000266995,0.0004386939,0.0004723369,0.00803497,0.0001747553,0.0004610694,0.0001191551,0.9898394],"study_design_scores_gemma":[0.0004580696,0.00009228063,0.0001721182,0.001317731,0.00002031344,0.0005559015,2.836798e-7,0.9820786,0.0003083456,0.01353455,0.0004811777,0.0009806968],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004005935,0.001080309,0.994705,0.0001320536,0.001242529,0.0005694309,0.00007851447,0.000720495,0.001071075],"genre_scores_gemma":[0.1757261,0.0001464596,0.823355,0.0002172406,0.0002880704,0.000006202199,0.0001054214,0.00008361899,0.00007191161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9888587,"threshold_uncertainty_score":0.999824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1967848549","doi":"10.3745/jips.2012.8.2.191","title":"An Adaptive Approach to Learning the Preferences of Users in a Social Network Using Weak Estimators","year":2012,"lang":"en","type":"article","venue":"Journal of Information Processing Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Estimator; Computer science; Stationary distribution; Range (aeronautics); Recommender system; Distribution (mathematics); Tracking (education); Mathematical optimization; Artificial intelligence; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04396156569965768,"gpt":0.2987358727229033,"spread":0.2547743070232456,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002443024,0.00009611363,0.0002211706,0.000260371,0.000177681,0.0003351734,0.000729556,0.00005838571,1.779131e-7],"category_scores_gemma":[0.00009741372,0.00006548387,0.00003084334,0.0006773326,0.0000318483,0.007060419,0.0000780329,0.0002297062,6.903204e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009020214,"about_ca_system_score_gemma":0.0001807914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003424435,"about_ca_topic_score_gemma":4.768157e-7,"domain_scores_codex":[0.9983697,0.0001704196,0.0007647879,0.00005335546,0.0004269147,0.0002148108],"domain_scores_gemma":[0.9980855,0.00004673945,0.001399629,0.0001160968,0.0002875155,0.00006451821],"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":[0.0001522945,0.0002655728,0.05273193,0.0007033864,0.00008385217,8.621171e-7,0.1815865,0.5769119,0.0002577357,0.03025597,0.002393721,0.1546562],"study_design_scores_gemma":[0.000259378,0.0003068483,0.006796683,0.001086291,0.00001891887,0.0001701915,0.01428611,0.9753724,0.000184637,0.0002825141,0.001006948,0.0002290978],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1104593,0.000109756,0.8880426,0.00001915819,0.0001760916,0.0001420986,8.27791e-7,0.00003588209,0.0010142],"genre_scores_gemma":[0.8465101,0.00000105243,0.1533332,0.00001515157,0.0001301763,0.000004627983,9.583728e-7,0.000003452405,0.000001305443],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7360508,"threshold_uncertainty_score":0.5118634,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3030026364","doi":"10.1145/3318464.3380568","title":"SCODED: Statistical Constraint Oriented Data Error Detection","year":2020,"lang":"en","type":"article","venue":"","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Leverage (statistics); Computer science; Constraint (computer-aided design); Data mining; Statistical model; Key (lock); Data integrity; Error detection and correction; Data modeling; Algorithm; Machine learning; Database; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08881471810412497,"gpt":0.3212253166233988,"spread":0.2324105985192738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001621293,0.00008974605,0.0001010359,0.00002974322,0.00004877369,0.0001106139,0.001437932,0.00003476481,0.00009505155],"category_scores_gemma":[0.0003691219,0.00008030333,0.000009819036,0.0002410791,0.00007534288,0.0005643178,0.001283814,0.0001137317,0.0001258264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001521954,"about_ca_system_score_gemma":0.00005748284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005270432,"about_ca_topic_score_gemma":0.00002185852,"domain_scores_codex":[0.9989059,0.00004115569,0.0001680376,0.0005158328,0.0001989159,0.0001701397],"domain_scores_gemma":[0.9987139,0.00008056362,0.00003842463,0.0009880193,0.00003553847,0.0001436078],"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":[0.00001604301,0.00007556388,0.0001868973,0.00002128621,0.0000268789,0.0001206339,0.0003179237,0.000001636635,0.004357881,0.3594631,0.08282553,0.5525866],"study_design_scores_gemma":[0.0003225727,0.0003747994,0.0004539234,0.00001457356,0.00001199633,0.00006502889,0.00008833144,0.9167633,0.02581163,0.002441574,0.05331932,0.0003329254],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004116807,0.0000032285,0.9937465,0.001769376,0.00009053777,0.000103815,0.0001891503,0.001111733,0.002573972],"genre_scores_gemma":[0.4091396,8.832062e-7,0.5900291,0.0007049943,0.00002668817,0.000003323094,0.00008036301,0.000004301317,0.00001070188],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9167617,"threshold_uncertainty_score":0.3274674,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3090849921","doi":"10.1016/j.eswa.2020.114061","title":"Catering for unique tastes: Targeting grey-sheep users recommender systems through one-class machine learning","year":2020,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Recommender system; Computer science; Benchmark (surveying); Class (philosophy); Collaborative filtering; Machine learning; Artificial intelligence; Focus (optics); Decision tree; Similarity (geometry); Process (computing); Outlier; Revenue; Data mining; Information retrieval; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.04910518600000155,"gpt":0.2781326979616612,"spread":0.2290275119616597,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003821173,0.0003282128,0.0004343981,0.00008090089,0.0004918345,0.0005498492,0.001346309,0.0001179101,0.000003744773],"category_scores_gemma":[0.00008845449,0.0003004877,0.00006211466,0.000562804,0.0000500203,0.0008137386,0.0003196338,0.0002655176,0.00002976396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001510448,"about_ca_system_score_gemma":0.00007986042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008632373,"about_ca_topic_score_gemma":0.000009240452,"domain_scores_codex":[0.9975865,0.0001573236,0.0005886569,0.0008851336,0.0003040441,0.0004782666],"domain_scores_gemma":[0.9980245,0.0002843222,0.0004027977,0.0008759986,0.0002152999,0.0001971473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001788699,0.0007358607,0.004323717,0.003759027,0.001148937,0.00002971113,0.05245627,0.01993079,0.04846596,0.6473628,0.209269,0.01233911],"study_design_scores_gemma":[0.0003841703,0.0002681689,0.000006973966,0.0003391531,0.00001626222,0.00003087445,0.001656005,0.265651,0.002816536,0.00009534937,0.7281227,0.0006128415],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0001034036,0.000923748,0.9906043,0.003110029,0.0001366192,0.002359195,0.0000664426,0.001754927,0.0009413303],"genre_scores_gemma":[0.5517938,0.0000804797,0.4361303,0.0006250942,0.0004571431,0.01037364,0.0002826911,0.0001090239,0.0001478319],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6472674,"threshold_uncertainty_score":0.9999447,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2163909061","doi":"10.1155/2013/274193","title":"Evaluation of Stream Mining Classifiers for Real-Time Clinical Decision Support System: A Case Study of Blood Glucose Prediction in Diabetes Therapy","year":2013,"lang":"en","type":"article","venue":"BioMed Research International","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University","funders":"Universidade de Macau","keywords":"Computer science; Decision tree; Classifier (UML); Clinical decision support system; Machine learning; Data mining; Data stream mining; Artificial intelligence; Decision tree learning; Decision support system; Decision system; Data stream; Operations research","retraction":null,"screen_n_in":null,"score":{"opus":0.1885235096077606,"gpt":0.4654404337020863,"spread":0.2769169240943257,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01494279,0.0001131056,0.0002549557,0.001097693,0.00005912221,0.0000957982,0.001054399,0.0001133044,0.00005123189],"category_scores_gemma":[0.001699919,0.00009838125,0.0000693988,0.0006109231,0.0001359783,0.0005602432,0.0003541619,0.0001400385,0.000006183672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001896666,"about_ca_system_score_gemma":0.0003615301,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000667837,"about_ca_topic_score_gemma":0.00005274533,"domain_scores_codex":[0.9951105,0.0009068573,0.0009656725,0.0004911043,0.002246588,0.0002792468],"domain_scores_gemma":[0.9948562,0.001639299,0.0002986023,0.0006050268,0.002507,0.0000938445],"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":[0.0001675377,0.005727213,0.09034915,0.00005982271,0.0005515654,0.00008122801,0.002359215,0.00002412705,0.03661664,0.0003622714,0.01206536,0.8516359],"study_design_scores_gemma":[0.009497372,0.008498707,0.07057428,0.000440121,0.00006178195,0.00008000007,0.004425675,0.8872681,0.01760498,0.001206231,0.0001091075,0.0002336156],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9953572,0.00001715057,0.001874459,0.00006138396,0.000376257,0.00188265,0.00009247803,0.00007211509,0.0002663376],"genre_scores_gemma":[0.9671198,0.0000206575,0.03197927,0.000002020073,0.00008570639,0.0007013166,0.00005622189,0.00001120597,0.00002383425],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.887244,"threshold_uncertainty_score":0.5178902,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090439194","doi":"10.1080/10618600.2000.10474890","title":"Users, Programmers, and Statistical Software","year":2000,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Software analytics; Software engineering; Software; Programmer; Software construction; Data science; Software development; Human–computer interaction; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.009443144865113733,"gpt":0.2565643840606938,"spread":0.24712123919558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002501104,0.0001114801,0.0001968991,0.0001076053,0.00009617242,0.0001852018,0.0002349172,0.00004692112,0.00003435783],"category_scores_gemma":[0.0001289581,0.0000915655,0.00002314985,0.000178292,0.0002138303,0.0002633937,0.00006415017,0.0002049374,0.000001870477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008904783,"about_ca_system_score_gemma":0.00005885748,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007035044,"about_ca_topic_score_gemma":0.000001351747,"domain_scores_codex":[0.9988611,0.00006411462,0.000371903,0.0001606034,0.0003865912,0.0001556854],"domain_scores_gemma":[0.998702,0.0006980972,0.000131261,0.00008328272,0.0001755734,0.0002097786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002836007,0.0000811953,0.003542553,0.00001895865,0.0000350446,0.0001184217,0.00008512578,0.00007378098,0.000001050765,0.2887788,0.007645368,0.6995914],"study_design_scores_gemma":[0.0005269334,0.0007158358,0.1075243,0.00004087714,0.00002865811,0.0007925289,0.00000767933,0.02034842,0.000003106231,0.8602011,0.009623846,0.0001866925],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01463795,0.0001489885,0.9842725,0.0006202273,0.00004077185,0.00005260686,0.0001628836,0.00003648927,0.00002754026],"genre_scores_gemma":[0.1177413,0.000142196,0.8818188,0.0002252658,0.00003344523,0.000001075783,0.00002143819,0.00000533202,0.0000111113],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6994047,"threshold_uncertainty_score":0.3733933,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W39904068","doi":"","title":"A simple sketching algorithm for entropy estimation over streaming data.","year":2013,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Rényi entropy; Estimator; Mathematics; Entropy (arrow of time); Maximum entropy probability distribution; Min entropy; Joint entropy; Entropy estimation; Shannon's source coding theorem; Streaming algorithm; Computation; Upper and lower bounds; Entropy rate; Applied mathematics; Algorithm; Principle of maximum entropy; Statistics; Joint quantum entropy; Maximum entropy thermodynamics; Mathematical analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.1188387014756424,"gpt":0.3807147191308058,"spread":0.2618760176551633,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002578376,0.0001612653,0.0001397202,0.0001311949,0.0001330752,0.0008885598,0.001163695,0.00005193686,0.0001556188],"category_scores_gemma":[0.0005012244,0.0001574168,0.00001796541,0.00008338628,0.00007857991,0.0009755577,0.0003676044,0.0001163458,0.00006168478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000039534,"about_ca_system_score_gemma":0.00006538631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002842555,"about_ca_topic_score_gemma":0.00003547802,"domain_scores_codex":[0.9986047,0.0000369915,0.0003354569,0.0004909613,0.0003114235,0.0002205226],"domain_scores_gemma":[0.9984549,0.0005224516,0.0001537255,0.0004892339,0.0002982066,0.0000814324],"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":[0.000002874065,0.00003345032,0.000008795458,0.000002495448,0.000008815592,0.000001723862,0.00008325766,0.00001725157,0.0001342856,0.4560744,0.001129074,0.5425036],"study_design_scores_gemma":[0.00001921262,0.00008036389,0.0001026779,0.00002264649,0.000003808596,0.000003031879,0.00007954017,0.6555883,0.0009859368,0.3426429,0.0003571319,0.0001144446],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007041552,0.000004114479,0.9964786,0.0006440799,0.0002951734,0.0002945998,0.001096543,0.0001175448,0.0003651971],"genre_scores_gemma":[0.272797,0.00003122575,0.7262564,0.0001533315,0.00007240252,0.00004791821,0.0005889151,0.000008444783,0.00004433798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.655571,"threshold_uncertainty_score":0.8568403,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3045238515","doi":"10.1016/j.ins.2020.07.026","title":"A hybrid distributed batch-stream processing approach for anomaly detection","year":2020,"lang":"en","type":"article","venue":"Information Sciences","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Stream processing; Computer science; Batch processing; Data stream; Data processing; Architecture; Distributed computing; Data mining; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.03791095620452836,"gpt":0.2701837831675817,"spread":0.2322728269630534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004552997,0.0001067514,0.0001073301,0.0001167053,0.0003560267,0.0009666967,0.001087406,0.00003013695,0.000001546642],"category_scores_gemma":[0.0002626393,0.00009159771,0.00003798274,0.0007756818,0.0001094837,0.007239698,0.0001755456,0.0000611629,0.00001272092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002891749,"about_ca_system_score_gemma":0.0001216846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001681904,"about_ca_topic_score_gemma":5.023497e-7,"domain_scores_codex":[0.9988739,0.00001708411,0.0003060971,0.0002330489,0.0003447904,0.0002250959],"domain_scores_gemma":[0.9993224,0.00004129933,0.0002250399,0.0001793581,0.000143862,0.00008800887],"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":[0.00001453207,0.00002973407,0.0002491142,0.0001069686,0.000005566154,4.635665e-7,0.002518214,0.001017188,0.000546662,0.003820887,0.004575874,0.9871148],"study_design_scores_gemma":[0.0001361543,0.0002021078,0.0002491598,0.000008785927,0.000002814665,0.00001255814,0.0001927307,0.9662223,0.02108433,0.0006074573,0.01113476,0.0001468695],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004164916,0.000009114921,0.9922773,0.0007725153,0.00005035826,0.0002888945,0.00006644136,0.0006516859,0.001718771],"genre_scores_gemma":[0.725082,9.85205e-7,0.2743129,0.0004566786,0.00002676697,0.00005924639,0.00005821304,0.000001669925,0.000001542805],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9869679,"threshold_uncertainty_score":0.9321879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901153708","doi":"10.1016/j.bdr.2018.11.001","title":"Label-Aware Distributed Ensemble Learning: A Simplified Distributed Classifier Training Model for Big Data","year":2018,"lang":"en","type":"article","venue":"Big Data Research","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); Queen's University","funders":"","keywords":"Computer science; Classifier (UML); Big data; Data mining; Machine learning; SPARK (programming language); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.72474036327115,"gpt":0.4627651775700344,"spread":0.2619751857011156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006154601,0.0003720792,0.0004610755,0.0004204068,0.00106911,0.001193128,0.01728046,0.0002862188,0.000008023857],"category_scores_gemma":[0.005558135,0.0003556625,0.00004436456,0.001953894,0.0005941198,0.001694246,0.01924838,0.0009477636,0.00009374799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000167606,"about_ca_system_score_gemma":0.00127327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000212479,"about_ca_topic_score_gemma":0.0004531641,"domain_scores_codex":[0.9933143,0.0004758724,0.0005982956,0.002464965,0.001417662,0.001728958],"domain_scores_gemma":[0.9867419,0.001244639,0.0001830588,0.01041267,0.0009835563,0.000434162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001271442,0.0002382074,0.00009078832,0.00006287715,0.00007747657,0.00003270503,0.0004360279,0.00001731861,0.001498988,0.002379782,0.5699521,0.4250866],"study_design_scores_gemma":[0.0006749828,0.000287997,0.00005716614,0.00007163992,0.00001257898,0.00001340512,0.0001286383,0.7455682,0.000797228,0.002101301,0.2499517,0.0003351819],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005186178,0.00005966037,0.9506995,0.001862755,0.0003666434,0.0007793141,0.04462689,0.0008155096,0.0002710951],"genre_scores_gemma":[0.7522509,0.00008633828,0.1183348,0.0001359976,0.001461657,0.0002330858,0.126477,0.0001037017,0.0009164897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8323647,"threshold_uncertainty_score":0.9998896,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2551857043","doi":"","title":"Launch and Iterate: Reducing Prediction Churn","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":23,"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; Machine learning; Classifier (UML); Benchmark (surveying); Artificial intelligence; Usability; Operator (biology); Markov chain; Monte Carlo method; Mathematical optimization; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01383656552888091,"gpt":0.2326989134256209,"spread":0.21886234789674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003136711,0.0001083577,0.0001056601,0.0001547765,0.0001571323,0.0009511455,0.0003051953,0.00005939942,0.000001417977],"category_scores_gemma":[0.00007020209,0.00007230877,0.00001237094,0.0002188136,0.00003136964,0.0100727,0.0001171424,0.00006089985,0.00001873847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004768126,"about_ca_system_score_gemma":0.00003820531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001987631,"about_ca_topic_score_gemma":2.034754e-7,"domain_scores_codex":[0.9990273,0.00003317079,0.0003806147,0.0001580039,0.0002300726,0.0001709061],"domain_scores_gemma":[0.9992539,0.00002934181,0.0002406087,0.0002653965,0.0001517195,0.00005904826],"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":[0.000005742025,0.000007963952,0.001019257,0.0002921654,0.000004688232,0.000001296144,0.002145202,0.0000320649,0.002826302,0.00373462,0.006554934,0.9833758],"study_design_scores_gemma":[0.001022374,0.0003217805,0.004642302,0.002364248,0.00001141328,0.0007793456,0.0002444242,0.896428,0.01084853,0.0006000127,0.08209531,0.0006422832],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07409646,0.0002012369,0.9182176,0.001171393,0.0008275343,0.0003652888,0.00004043968,0.001888598,0.003191459],"genre_scores_gemma":[0.9944967,0.000009859365,0.005083153,0.0001014621,0.00007057571,0.00003732686,0.00001068699,0.000004704928,0.0001855046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9827335,"threshold_uncertainty_score":0.9171917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}