{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Vítor Cerqueira","is_ca":false},{"name":"Luı́s Torgo","is_ca":true},{"name":"Igor Mozetič","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06269631,0.001619071,0.001540588,0.003461691,0.000533007,0.003145619,0.001688063,0.002234378,0.0009880771],"category_scores_gemma":[0.238976,0.0004193472,0.001115725,0.003751607,0.001194526,0.006911852,0.001211724,0.001973297,0.0002180698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002121568,"about_ca_system_score_gemma":0.001482831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003298999,"about_ca_topic_score_gemma":0.00172362,"domain_scores_codex":[0.973111,0.01983759,0.001191589,0.001573063,0.0038126,0.0004741537],"domain_scores_gemma":[0.5285546,0.4442889,0.007990859,0.009076698,0.009070683,0.001018248],"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":[0.001514358,0.0008903836,0.1175065,0.0006239092,0.00105957,0.0001369357,0.0008070355,0.5465503,0.001722551,0.03194461,0.003467767,0.2937761],"study_design_scores_gemma":[0.0000359586,0.0005372001,0.01137591,0.0001146245,0.0001963167,0.00006030438,0.00022841,0.9749883,0.001520966,0.01019481,0.0007156186,0.00003157351],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6567836,0.00877769,0.3253814,0.001695097,0.0001912203,0.0001956273,0.0004066571,0.0005503955,0.00601834],"genre_scores_gemma":[0.9596854,0.001360566,0.03768284,0.00009638788,0.0001042428,0.00006392613,0.0004386982,0.000104745,0.000463198],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06269631,"threshold_uncertainty_score":0.3315737,"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","authors":[{"name":"Lucas Amorim","is_ca":false},{"name":"George D. C. Cavalcanti","is_ca":false},{"name":"Rafael M. O. Cruz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006879713,0.001332384,0.001813182,0.001792543,0.0009495445,0.004587837,0.001208418,0.00207702,0.006267045],"category_scores_gemma":[0.04544812,0.0004487346,0.0008379299,0.003621918,0.001084833,0.005252711,0.001172306,0.002131833,0.005119657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003273333,"about_ca_system_score_gemma":0.0009103965,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006848201,"about_ca_topic_score_gemma":0.0009640818,"domain_scores_codex":[0.99709,0.0009483534,0.0003657236,0.0006222915,0.0007476455,0.0002259453],"domain_scores_gemma":[0.9843584,0.008913347,0.0005024094,0.002956575,0.002725875,0.0005433771],"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":[0.001149446,0.001009154,0.01328669,0.0008014378,0.0003273692,0.0003374403,0.0004782187,0.01798071,0.1303659,0.006720267,0.0161164,0.811427],"study_design_scores_gemma":[0.0006643573,0.002343073,0.0510213,0.001387964,0.0009043625,0.002427013,0.002393956,0.6374383,0.2021025,0.05889113,0.03982456,0.0006013986],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3332424,0.01021037,0.6119822,0.006892423,0.005779434,0.0008338571,0.001155534,0.006207708,0.02369612],"genre_scores_gemma":[0.7379632,0.004535563,0.246617,0.001013797,0.001439367,0.0003063297,0.0009243838,0.001481708,0.005718603],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006879713,"threshold_uncertainty_score":0.03638387,"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","authors":[{"name":"Aized Amin Soofi","is_ca":false},{"name":"Muhammad Arshad Awan","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01075976,0.001086956,0.001998937,0.00468976,0.001263588,0.00674698,0.002797887,0.004006983,0.003602968],"category_scores_gemma":[0.02184201,0.0008039875,0.00124585,0.01106661,0.003895218,0.01037002,0.001836391,0.006295597,0.003300676],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002004705,"about_ca_system_score_gemma":0.002133738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001436427,"about_ca_topic_score_gemma":0.0006872598,"domain_scores_codex":[0.9895667,0.003800691,0.0009364186,0.001061909,0.004395823,0.0002384965],"domain_scores_gemma":[0.9787648,0.01444091,0.0008204565,0.001441521,0.004257028,0.0002753293],"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":[0.00005238327,0.0001397868,0.001920111,0.002894019,0.0001230903,0.0002281408,0.0005961981,0.004520596,0.000751264,0.3625076,0.03962205,0.5866448],"study_design_scores_gemma":[0.00002016594,0.0001106263,0.001754577,0.002660615,0.00007513342,0.0009849507,0.0005936462,0.03536615,0.001348018,0.5884499,0.3685256,0.0001105985],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.00276461,0.5610937,0.381837,0.02346826,0.00453924,0.0001932231,0.0002293662,0.0004173825,0.02545725],"genre_scores_gemma":[0.07842842,0.4874637,0.4011935,0.004322398,0.01626409,0.0005718193,0.0005691604,0.0002486831,0.01093833],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01075976,"threshold_uncertainty_score":0.05690372,"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","authors":[{"name":"Marcel R. Ackermann","is_ca":false},{"name":"Marcus Märtens","is_ca":false},{"name":"Christoph Raupach","is_ca":false},{"name":"Kamil Swierkot","is_ca":false},{"name":"Christiane Lammersen","is_ca":true},{"name":"Christian Sohler","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001416698,0.00220538,0.001638081,0.001827882,0.0008975592,0.004056428,0.006345148,0.001649876,0.03837227],"category_scores_gemma":[0.005814671,0.001442612,0.002260164,0.002772977,0.0007494696,0.005651424,0.004418093,0.002936071,0.03703525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398686,"about_ca_system_score_gemma":0.001826805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00371392,"about_ca_topic_score_gemma":0.00556512,"domain_scores_codex":[0.9979037,0.0002367241,0.0002376502,0.0005688017,0.0008857895,0.0001673569],"domain_scores_gemma":[0.9981711,0.0003088138,0.00009848836,0.000669945,0.0006318412,0.0001197506],"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":[0.0008142507,0.0002171424,0.001295197,0.001073527,0.0001568372,0.0001861348,0.0001931528,0.0287595,0.008816073,0.05227346,0.2879987,0.618216],"study_design_scores_gemma":[0.000370313,0.0001940432,0.0005569643,0.00009858889,0.00005702526,0.0003973061,0.00006130176,0.4190661,0.02349471,0.06423175,0.4913373,0.0001345724],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00256059,0.000488618,0.8480858,0.0005317923,0.0006148643,0.0006105235,0.009648777,0.1239257,0.01353335],"genre_scores_gemma":[0.01873788,0.0005400174,0.9210148,0.0008476967,0.0001786903,0.0009624561,0.02571058,0.0124311,0.01957687],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03837227,"threshold_uncertainty_score":0,"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","authors":[{"name":"Benjamin M. Marlin","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009714823,0.001361376,0.003029449,0.002942155,0.001446557,0.00530915,0.003152546,0.004011953,0.00242383],"category_scores_gemma":[0.0220634,0.000736251,0.001636673,0.004455847,0.003205806,0.0081172,0.001351673,0.003969298,0.001039031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002061684,"about_ca_system_score_gemma":0.001309525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00352827,"about_ca_topic_score_gemma":0.001890689,"domain_scores_codex":[0.9919796,0.003497317,0.000399961,0.001467307,0.002312329,0.0003435184],"domain_scores_gemma":[0.9762221,0.01837193,0.001176661,0.002211862,0.001714414,0.0003030146],"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":[0.0001578205,0.0002764305,0.00476908,0.0006709031,0.0004719353,0.0002367021,0.0006496132,0.1276098,0.002695604,0.5753277,0.007474133,0.2796602],"study_design_scores_gemma":[0.00005045629,0.000247749,0.001532362,0.000166533,0.0001089447,0.0002767846,0.0001432731,0.6099399,0.002570471,0.3663826,0.01849839,0.00008255209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.004699651,0.004379116,0.982967,0.002810863,0.0001907132,0.00006566256,0.00008311836,0.0001706679,0.004633241],"genre_scores_gemma":[0.3981266,0.01265969,0.5759264,0.001398441,0.003108896,0.0003243148,0.0003680489,0.00009374158,0.007993959],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.009714823,"threshold_uncertainty_score":0.05137753,"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","authors":[{"name":"Jiawei Han","is_ca":false},{"name":"Yixin Chen","is_ca":false},{"name":"Guozhu Dong","is_ca":false},{"name":"Jian Pei","is_ca":true},{"name":"Benjamin W. Wah","is_ca":false},{"name":"Jianyong Wang","is_ca":false},{"name":"Yonghua Cai","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001416215,0.0008792945,0.001197318,0.001650781,0.0007687686,0.002640029,0.002882491,0.0007365436,0.006929668],"category_scores_gemma":[0.003274651,0.0006357793,0.0008463705,0.003502876,0.000649701,0.002789508,0.002178707,0.001430221,0.002572368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007778517,"about_ca_system_score_gemma":0.002226165,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005413161,"about_ca_topic_score_gemma":0.004793311,"domain_scores_codex":[0.9991358,0.0001493765,0.00009149202,0.0001181457,0.0004250769,0.00008014939],"domain_scores_gemma":[0.9981917,0.0004648254,0.00007923576,0.0004784862,0.0006161162,0.0001696427],"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":[0.003534649,0.0004562729,0.006702319,0.000945957,0.0006750419,0.0007056603,0.0008050214,0.05700444,0.04265647,0.05215815,0.1454743,0.6888818],"study_design_scores_gemma":[0.000312147,0.0003500751,0.001276444,0.0001058635,0.0003037711,0.0005064694,0.0002128893,0.8270568,0.04970467,0.06654923,0.05347073,0.0001510083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01080861,0.0006717095,0.9556461,0.0004456774,0.0001952305,0.0001867021,0.001370755,0.02829397,0.002381292],"genre_scores_gemma":[0.1615884,0.002251177,0.8191268,0.0006958062,0.0002826515,0.0006530093,0.006528421,0.001796905,0.007076782],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006929668,"threshold_uncertainty_score":0.02318203,"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","authors":[{"name":"Abdallah Moubayed","is_ca":true},{"name":"MohammadNoor Injadat","is_ca":true},{"name":"Ali Bou Nassif","is_ca":false},{"name":"Hanan Lutfiyya","is_ca":true},{"name":"Abdallah Shami","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006654792,0.001091797,0.001409613,0.004138786,0.001062969,0.00919723,0.00304643,0.004825742,0.002617833],"category_scores_gemma":[0.01247049,0.0006228609,0.0008230574,0.01110777,0.003464355,0.02091742,0.003200148,0.004834252,0.001803374],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307651,"about_ca_system_score_gemma":0.001879376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000691828,"about_ca_topic_score_gemma":0.0006593672,"domain_scores_codex":[0.9952955,0.002170108,0.0003569024,0.000549194,0.001405068,0.0002233129],"domain_scores_gemma":[0.9824796,0.01381283,0.000635598,0.001145912,0.001404693,0.0005213267],"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":[0.00009051769,0.0003085161,0.004514915,0.002728557,0.00008172829,0.0003406944,0.0007898231,0.008757631,0.00125717,0.199816,0.01549708,0.7658175],"study_design_scores_gemma":[0.00002837439,0.0002073571,0.002095313,0.003397465,0.00005023175,0.001151129,0.005589733,0.1474236,0.003765379,0.5703774,0.2657882,0.0001259174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.0186277,0.3155511,0.5420003,0.08481562,0.002240371,0.0002946465,0.0003588607,0.0006239321,0.0354875],"genre_scores_gemma":[0.2377979,0.3859322,0.3565125,0.005417713,0.005514461,0.0003326779,0.0006723805,0.0001503881,0.007669771],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.00919723,"threshold_uncertainty_score":0.03519428,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002313841,0.0009349337,0.001065613,0.001435918,0.0005426816,0.001009689,0.002319907,0.0008266151,0.000992095],"category_scores_gemma":[0.004271225,0.000393591,0.001176356,0.001445085,0.0005676051,0.002036026,0.001722009,0.001873537,0.0004535898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009680497,"about_ca_system_score_gemma":0.001505101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00679292,"about_ca_topic_score_gemma":0.006158593,"domain_scores_codex":[0.9990394,0.000130112,0.00006613114,0.0002816352,0.0003913661,0.00009137655],"domain_scores_gemma":[0.9991803,0.0002351084,0.0001194332,0.000135264,0.000265154,0.00006475329],"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":[0.0002929586,0.0003229149,0.008031396,0.000142901,0.000163465,0.0003073842,0.0003431912,0.2247741,0.01040454,0.0124217,0.008209378,0.7345861],"study_design_scores_gemma":[0.000008736084,0.00002449637,0.0004218029,0.000004949095,0.000009107069,0.00004175519,0.0000175687,0.9927148,0.001169227,0.004512514,0.001065924,0.000009086473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01040779,0.0003549072,0.9860722,0.0001654724,0.0000582382,0.0001194281,0.000160772,0.00229651,0.00036461],"genre_scores_gemma":[0.3688431,0.0005513825,0.6260775,0.0003996665,0.000173771,0.0004930861,0.0009776411,0.0002206001,0.002263346],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00679292,"threshold_uncertainty_score":0.01350677,"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","authors":[{"name":"Ali Pesaranghader","is_ca":true},{"name":"Herna L. Viktor","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001925549,0.001119126,0.001354815,0.002374123,0.0006437758,0.00103981,0.001578703,0.0009048308,0.002020386],"category_scores_gemma":[0.005403122,0.0004805044,0.0008796469,0.001894569,0.0004148663,0.001477735,0.000947918,0.001443076,0.0008463725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005672113,"about_ca_system_score_gemma":0.001531339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005956419,"about_ca_topic_score_gemma":0.007811715,"domain_scores_codex":[0.9991575,0.00008462184,0.00008028891,0.0001946966,0.0004094381,0.00007337776],"domain_scores_gemma":[0.9982185,0.0007484709,0.0001185653,0.0002111357,0.0006372235,0.0000662046],"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":[0.0003217833,0.00008909646,0.00215117,0.0001933048,0.0001073194,0.0001829613,0.0001286969,0.05604061,0.02248159,0.006572018,0.005653096,0.9060784],"study_design_scores_gemma":[0.00002195867,0.00006066199,0.0009322723,0.00001610424,0.00003386908,0.0002328497,0.00001777637,0.9834292,0.009761933,0.00302264,0.00245128,0.0000193979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008933198,0.0006791218,0.9888952,0.00006089274,0.0001014965,0.00005621747,0.00009477724,0.000713806,0.0004653608],"genre_scores_gemma":[0.1235181,0.001018792,0.86819,0.00008328512,0.0001567068,0.0001390885,0.0007314399,0.0002166755,0.005945935],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005956419,"threshold_uncertainty_score":0.0118435,"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","authors":[{"name":"Armando Segatori","is_ca":false},{"name":"Francesco Marcelloni","is_ca":false},{"name":"Witold Pedrycz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003063587,0.0006662384,0.001052089,0.001056045,0.0008261919,0.001195206,0.001385509,0.0008887914,0.001498276],"category_scores_gemma":[0.007979411,0.0003928796,0.001201943,0.00148646,0.0009670398,0.002212025,0.001127056,0.001903926,0.0003896187],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001205137,"about_ca_system_score_gemma":0.001611096,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005121654,"about_ca_topic_score_gemma":0.005673797,"domain_scores_codex":[0.9984236,0.0005768523,0.0001007889,0.0002827751,0.0005040069,0.0001118894],"domain_scores_gemma":[0.9964024,0.002423706,0.0001568969,0.0003484317,0.0005511513,0.0001174438],"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":[0.0001715554,0.0001284895,0.00128469,0.0001762631,0.00008651243,0.0001388061,0.0001634777,0.7615935,0.001547069,0.05839467,0.003563051,0.1727519],"study_design_scores_gemma":[0.00001227447,0.00002191914,0.0001168137,0.000009085276,0.000006320783,0.00002095462,0.00001992025,0.9429269,0.0005090702,0.05545891,0.000891938,0.000005818537],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01102639,0.0003636834,0.9867127,0.0003315344,0.00005735427,0.0000671496,0.0001248527,0.0003181662,0.0009982055],"genre_scores_gemma":[0.3813449,0.0005659765,0.6150456,0.0002933513,0.0001728927,0.0002486255,0.0006379431,0.00008235706,0.001608245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005121654,"threshold_uncertainty_score":0.01620197,"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","authors":[{"name":"Paweł Zyblewski","is_ca":false},{"name":"Robert Sabourin","is_ca":true},{"name":"Michał Woźniak","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002563175,0.0009618519,0.001149786,0.001978559,0.0009307372,0.001355293,0.001009158,0.0006870961,0.001998395],"category_scores_gemma":[0.004338858,0.0002991063,0.0008102325,0.001576719,0.0002338469,0.001339186,0.001029604,0.001256019,0.001179735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004373893,"about_ca_system_score_gemma":0.001131723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003016674,"about_ca_topic_score_gemma":0.005578401,"domain_scores_codex":[0.9990356,0.0001040855,0.00007849936,0.0002227637,0.0004035603,0.0001555159],"domain_scores_gemma":[0.998038,0.0004327187,0.0001017746,0.0003028678,0.001033003,0.00009180038],"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":[0.0005660532,0.0004344511,0.009153321,0.00006811473,0.0001826678,0.0002278317,0.000158021,0.05056596,0.03873612,0.001571829,0.009608721,0.8887269],"study_design_scores_gemma":[0.00002019137,0.0001696019,0.005455436,0.00001442236,0.00007958458,0.0001598222,0.0001054819,0.9610415,0.02561948,0.002604208,0.004703622,0.00002669586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1504647,0.0009826004,0.8410617,0.0004307465,0.0005126513,0.0002206442,0.0007335719,0.003469169,0.002124243],"genre_scores_gemma":[0.6720398,0.0003767151,0.3192991,0.0001750555,0.0002984001,0.00018853,0.002622143,0.000280163,0.004720039],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003016674,"threshold_uncertainty_score":0.01355553,"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","authors":[{"name":"Joglas Souza","is_ca":true},{"name":"Carson K. Leung","is_ca":true},{"name":"Alfredo Cuzzocrea","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008819796,0.0008403391,0.0005706863,0.001291191,0.0004857831,0.00232628,0.001430059,0.0006255696,0.002769198],"category_scores_gemma":[0.001841773,0.0003268141,0.0009646363,0.002130003,0.0005268297,0.002790011,0.001755127,0.001643732,0.001043558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004022325,"about_ca_system_score_gemma":0.0006900076,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002682649,"about_ca_topic_score_gemma":0.004321224,"domain_scores_codex":[0.9996226,0.00004630561,0.0000202432,0.00007650371,0.000208469,0.00002584823],"domain_scores_gemma":[0.9995031,0.000204688,0.00003107195,0.00008109273,0.0001357829,0.00004414514],"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":[0.0002451985,0.000251575,0.004474051,0.000353953,0.0002790298,0.0009907574,0.0003898154,0.09687538,0.01056771,0.2707279,0.07627494,0.5385697],"study_design_scores_gemma":[0.00001212962,0.00004207313,0.0008279217,0.00004462665,0.0000570888,0.0002917904,0.00008662468,0.807773,0.003667508,0.1482814,0.03888396,0.00003190077],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004432601,0.001249892,0.9848217,0.0007976701,0.0003048358,0.00005992507,0.0006790371,0.002668951,0.004985422],"genre_scores_gemma":[0.1544267,0.002699228,0.8224087,0.0008232828,0.0006950189,0.0001830749,0.002612412,0.0005240837,0.01562739],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002769198,"threshold_uncertainty_score":0.009263933,"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","authors":[{"name":"Li Yang","is_ca":true},{"name":"Abdallah Shami","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001380374,0.000729332,0.0008357203,0.001850225,0.0005157511,0.004262952,0.001231368,0.00110559,0.0009736018],"category_scores_gemma":[0.005916092,0.0004586116,0.000527107,0.002400824,0.001585741,0.005920615,0.001277786,0.001658431,0.0003718637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007316333,"about_ca_system_score_gemma":0.0009714127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001558178,"about_ca_topic_score_gemma":0.001324008,"domain_scores_codex":[0.9988943,0.0002676646,0.00008029677,0.0002013155,0.0004833138,0.00007314284],"domain_scores_gemma":[0.9959977,0.002479482,0.0004304045,0.0004842792,0.000495505,0.0001127644],"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":[0.0002088242,0.0005187916,0.01973885,0.0007024198,0.0002748772,0.000684423,0.0005097082,0.2354899,0.008232102,0.2803319,0.0126341,0.440674],"study_design_scores_gemma":[0.000006158981,0.00002985488,0.001504086,0.00005639638,0.00002110629,0.0001475063,0.0002247539,0.8208336,0.002144976,0.1683002,0.006717796,0.00001362002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02835543,0.003708092,0.951538,0.007072865,0.0002247993,0.00008029197,0.0004802815,0.0006183917,0.007921758],"genre_scores_gemma":[0.7506635,0.005652358,0.2392512,0.0005872623,0.0008106377,0.00008612432,0.0006386422,0.00009694075,0.002213291],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004262952,"threshold_uncertainty_score":0.007300198,"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","authors":[{"name":"Paulo Ricardo Lisboa de Almeida","is_ca":false},{"name":"Luiz S. Oliveira","is_ca":false},{"name":"Alceu S. Britto","is_ca":false},{"name":"Robert Sabourin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008375608,0.001395238,0.002782407,0.003033641,0.001145794,0.002545311,0.003930773,0.00251777,0.00242106],"category_scores_gemma":[0.02272746,0.0006927662,0.001329235,0.002579462,0.0006170745,0.003199107,0.00244916,0.00287149,0.001721167],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001094838,"about_ca_system_score_gemma":0.002510848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003243024,"about_ca_topic_score_gemma":0.003559235,"domain_scores_codex":[0.9963273,0.0008399527,0.0002860606,0.001110258,0.001150284,0.0002861662],"domain_scores_gemma":[0.9886798,0.005913348,0.0004217226,0.001401398,0.003207877,0.0003758918],"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":[0.0006725167,0.0007529039,0.009381339,0.0001780393,0.0004491344,0.0003203857,0.0002130977,0.1077642,0.01350598,0.003855002,0.01438634,0.8485209],"study_design_scores_gemma":[0.00004111945,0.0001017009,0.000792411,0.00001536196,0.00007271854,0.0001569906,0.00003772206,0.9898959,0.002673818,0.004293418,0.001903008,0.00001570682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07524928,0.00181227,0.9161742,0.0008310106,0.0007437671,0.0002989649,0.0003516283,0.002852138,0.001686776],"genre_scores_gemma":[0.6458833,0.0007026991,0.3443685,0.0007922705,0.0007803733,0.0004226434,0.001790221,0.0005438485,0.004716122],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008375608,"threshold_uncertainty_score":0.04429501,"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","authors":[{"name":"Wenkai Hu","is_ca":true},{"name":"Jiandong Wang","is_ca":false},{"name":"Tongwen Chen","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00112324,0.0005405626,0.001165866,0.004899955,0.001082324,0.001609068,0.001319582,0.0009094966,0.002078559],"category_scores_gemma":[0.005286858,0.0003703575,0.001063989,0.005626902,0.0005942763,0.001802176,0.001192406,0.001223115,0.001396353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005553045,"about_ca_system_score_gemma":0.001100287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002859868,"about_ca_topic_score_gemma":0.003006999,"domain_scores_codex":[0.9985375,0.0003295593,0.0001642568,0.0003967313,0.0004518831,0.0001200264],"domain_scores_gemma":[0.9976233,0.0008590175,0.0003769912,0.0003472815,0.0006672672,0.0001260943],"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":[0.0008080608,0.0006610773,0.009672411,0.0005305508,0.0003400045,0.0006145641,0.0009015881,0.06537785,0.08200481,0.01832656,0.005597004,0.8151656],"study_design_scores_gemma":[0.00005239581,0.0003929047,0.007879639,0.00004525511,0.0001532151,0.0005834869,0.0005599471,0.941703,0.01970343,0.02198089,0.006892655,0.00005335677],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04142143,0.0004236067,0.9552367,0.0001040792,0.0000435199,0.0001075366,0.0003566711,0.001404528,0.000901948],"genre_scores_gemma":[0.3482785,0.0004281067,0.6460676,0.00009545399,0.0001187945,0.0002304142,0.002476932,0.0003611401,0.00194304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004899955,"threshold_uncertainty_score":0.006953478,"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","authors":[{"name":"Farzan Soleymani","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006760976,0.0005270857,0.0007286234,0.0004928025,0.0002593024,0.0006249088,0.001048804,0.001075243,0.00249936],"category_scores_gemma":[0.002095182,0.0003389213,0.0003095669,0.0005747991,0.0004595608,0.001028144,0.00079423,0.001483774,0.0004785618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008397839,"about_ca_system_score_gemma":0.0008682192,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007302947,"about_ca_topic_score_gemma":0.007930569,"domain_scores_codex":[0.9998148,0.00005172121,0.000008165959,0.00004793554,0.00004647176,0.00003087151],"domain_scores_gemma":[0.9994096,0.0003001986,0.00005739951,0.00006433365,0.0001191708,0.00004934364],"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":[0.00007260285,0.0001033431,0.0008087081,0.00004312893,0.00004043024,0.0000524119,0.00001786258,0.8406721,0.001352954,0.0125546,0.003421281,0.1408606],"study_design_scores_gemma":[0.000001662749,0.000007220857,0.00004195142,0.000001765988,0.000001660802,0.000003263504,6.943372e-7,0.9964523,0.0001457768,0.003191307,0.0001512321,0.000001200703],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05171766,0.001773068,0.9401248,0.0007845815,0.0001660977,0.00004675258,0.0001853428,0.001502192,0.003699462],"genre_scores_gemma":[0.8624276,0.0007421888,0.1277343,0.0002794654,0.00008202183,0.00006593984,0.0003595789,0.0001153274,0.008193498],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007302947,"threshold_uncertainty_score":0.01452088,"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","authors":[{"name":"Li Yang","is_ca":true},{"name":"Dimitrios Michael Manias","is_ca":true},{"name":"Abdallah Shami","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005157166,0.001595626,0.001971359,0.001872493,0.000701273,0.00147698,0.002844553,0.001131569,0.001241946],"category_scores_gemma":[0.01049832,0.0006323698,0.001662328,0.002348468,0.0005365627,0.003297836,0.002327385,0.002875541,0.0006239358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004957424,"about_ca_system_score_gemma":0.001270796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004650071,"about_ca_topic_score_gemma":0.005666344,"domain_scores_codex":[0.9982383,0.0005077475,0.0001290179,0.0004480558,0.0005427515,0.0001340861],"domain_scores_gemma":[0.9966412,0.001438975,0.0002722264,0.0004744847,0.001019499,0.0001536396],"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":[0.0001960368,0.0002895955,0.005063024,0.0001516588,0.0005598679,0.0001955437,0.0002824267,0.4412674,0.004558943,0.01060708,0.006820561,0.530008],"study_design_scores_gemma":[0.000003799906,0.00002142364,0.0002512586,0.000004791626,0.00001547291,0.0000258035,0.00001136282,0.9943677,0.0004282484,0.004178608,0.0006839349,0.000007543176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002956395,0.0002569365,0.9957576,0.00008193893,0.00004640645,0.00004337131,0.00008203745,0.0005701271,0.0002052166],"genre_scores_gemma":[0.2626311,0.001045938,0.7310283,0.0003515091,0.0004639252,0.0004231449,0.001566169,0.0003486243,0.002141207],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005157166,"threshold_uncertainty_score":0.02727407,"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","authors":[],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003593886,0.001012116,0.001628086,0.001377129,0.0007735854,0.001434923,0.002852552,0.001677275,0.001765307],"category_scores_gemma":[0.01254298,0.0008043108,0.001083815,0.001438435,0.0008504008,0.003504925,0.002726602,0.002712359,0.0006269024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006915082,"about_ca_system_score_gemma":0.001859522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004555681,"about_ca_topic_score_gemma":0.005881741,"domain_scores_codex":[0.9990795,0.0002093752,0.0000914339,0.0002349578,0.0002880702,0.00009662412],"domain_scores_gemma":[0.9957754,0.002014807,0.0002511923,0.0005927817,0.001166719,0.0001991136],"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":[0.0004385114,0.0002099722,0.003909418,0.0001448859,0.0001664021,0.0001647065,0.0003037289,0.3945751,0.007229679,0.02311582,0.003848085,0.5658937],"study_design_scores_gemma":[0.000005598908,0.00002777584,0.0001304572,0.000006912192,0.00001033568,0.00002229662,0.000009081469,0.9955813,0.001097794,0.002742038,0.000360225,0.000006085061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01663963,0.0005160649,0.9817399,0.00011982,0.00008587992,0.00003539089,0.00004171192,0.0003675453,0.0004541025],"genre_scores_gemma":[0.3171286,0.0007320809,0.6750444,0.0002164247,0.0002171417,0.0002070862,0.0004050258,0.0002103692,0.005838991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004555681,"threshold_uncertainty_score":0.01900655,"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","authors":[{"name":"Neel Jayesh Shah","is_ca":true},{"name":"Darryl L. Willick","is_ca":true},{"name":"Vijay Mago","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005338663,0.001097361,0.00192164,0.005882842,0.002216983,0.005822772,0.003964352,0.001608228,0.004766567],"category_scores_gemma":[0.01416391,0.001059809,0.002102958,0.007773928,0.001650508,0.01071957,0.005985613,0.0030156,0.00299342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001460407,"about_ca_system_score_gemma":0.002869305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009280298,"about_ca_topic_score_gemma":0.008919301,"domain_scores_codex":[0.9970192,0.0007480081,0.0003523384,0.0005841813,0.00107078,0.000225648],"domain_scores_gemma":[0.9967194,0.001301952,0.0001963762,0.0009008606,0.0006808632,0.000200532],"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":[0.0004199748,0.0004310116,0.003526211,0.0003749892,0.0002310128,0.0004431907,0.0006688039,0.06919111,0.002922412,0.5506902,0.01821654,0.3528846],"study_design_scores_gemma":[0.00002511974,0.00002644748,0.0002582132,0.00006511266,0.00004160948,0.000162023,0.0001682372,0.7878582,0.001451152,0.1876924,0.02221348,0.00003798296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00173996,0.0003518219,0.9936889,0.0004458061,0.00007303226,0.0001044115,0.0002497135,0.001997146,0.001349088],"genre_scores_gemma":[0.07538901,0.0008567763,0.9174237,0.0002671035,0.000123511,0.0004084661,0.001209168,0.0004142655,0.003908152],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009280298,"threshold_uncertainty_score":0.02823395,"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","authors":[{"name":"Wing W. Y. Ng","is_ca":false},{"name":"Jianjun Zhang","is_ca":false},{"name":"Chun Sing Lai","is_ca":false},{"name":"Witold Pedrycz","is_ca":true},{"name":"Loi Lei Lai","is_ca":false},{"name":"Xizhao Wang","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004875325,0.000932067,0.001629927,0.001540885,0.0007979665,0.001181974,0.002206135,0.001113435,0.0007025469],"category_scores_gemma":[0.0111425,0.000380609,0.0007705255,0.001702179,0.0005990147,0.0022942,0.001384613,0.00192082,0.0003137002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009534037,"about_ca_system_score_gemma":0.001172577,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004618987,"about_ca_topic_score_gemma":0.004410109,"domain_scores_codex":[0.998262,0.000499768,0.0001500367,0.0003945827,0.0005385246,0.0001551319],"domain_scores_gemma":[0.9954622,0.002140474,0.0003518318,0.0005979463,0.001256409,0.0001910134],"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":[0.0003256613,0.0005286526,0.007483099,0.0001262541,0.0001889248,0.0001532198,0.0002864797,0.314671,0.005063566,0.005437477,0.003503443,0.6622322],"study_design_scores_gemma":[0.000008202925,0.00005246626,0.0006900711,0.000007030633,0.00002113286,0.00003067155,0.0000211243,0.9946222,0.001077801,0.003054338,0.0004038984,0.00001113734],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08510043,0.0009106814,0.9118118,0.0002669589,0.0001841013,0.0001684056,0.000128706,0.0006563084,0.0007726296],"genre_scores_gemma":[0.7458504,0.0003909683,0.2509892,0.0002546694,0.0002153426,0.0002240509,0.0005187297,0.00008203665,0.001474621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004875325,"threshold_uncertainty_score":0.02578354,"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","authors":[{"name":"Yingzhe Lyu","is_ca":true},{"name":"Heng Li","is_ca":true},{"name":"Mohammed Sayagh","is_ca":true},{"name":"Zhen Ming Jiang","is_ca":true},{"name":"Ahmed E. Hassan","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01195915,0.001043189,0.0005959041,0.001264265,0.00108174,0.001944468,0.001463505,0.001351103,0.001306197],"category_scores_gemma":[0.07403709,0.0003792275,0.0005870179,0.001885981,0.0009079865,0.005070276,0.001543581,0.003126967,0.0005241428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001227524,"about_ca_system_score_gemma":0.001260639,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002438862,"about_ca_topic_score_gemma":0.002173227,"domain_scores_codex":[0.9910377,0.00337769,0.0009790008,0.001299994,0.002311809,0.0009937854],"domain_scores_gemma":[0.9217473,0.05324896,0.00613886,0.007845934,0.007683454,0.003335639],"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":[0.00422508,0.006101967,0.2220129,0.001720294,0.0007717688,0.0004745846,0.001969507,0.3875677,0.02044897,0.00507567,0.01705459,0.332577],"study_design_scores_gemma":[0.0003206305,0.00606828,0.06746844,0.0002240111,0.0002660801,0.000501632,0.003274391,0.8890836,0.01649445,0.006332919,0.009853081,0.0001123726],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877616,0.0009135035,0.007275653,0.0006555979,0.0001009153,0.0002189416,0.0006890076,0.0004693679,0.001915496],"genre_scores_gemma":[0.9855802,0.000282533,0.01168332,0.0001667632,0.00004167565,0.0001377883,0.001600214,0.00005782422,0.0004496844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01195915,"threshold_uncertainty_score":0.06324679,"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","authors":[{"name":"Henry Liu","is_ca":true},{"name":"Mingbin Xu","is_ca":true},{"name":"Ziting Yu","is_ca":true},{"name":"Vincent Corvinelli","is_ca":true},{"name":"Calisto Zuzarte","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001273402,0.0007755898,0.0008248232,0.001314056,0.0003420618,0.001220969,0.001153769,0.0006174483,0.001205025],"category_scores_gemma":[0.008537313,0.0004129416,0.0004980329,0.001212845,0.0003737992,0.002134184,0.001035166,0.000872886,0.000388702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009947674,"about_ca_system_score_gemma":0.0007026772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005120629,"about_ca_topic_score_gemma":0.006100004,"domain_scores_codex":[0.9988668,0.0002535397,0.0001055428,0.0002631907,0.0004210952,0.00008990197],"domain_scores_gemma":[0.9967248,0.001721817,0.0004671267,0.0004688893,0.0005507878,0.0000666343],"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":[0.0005262207,0.0001183066,0.00925108,0.0001212376,0.0001260255,0.00008893962,0.00008173335,0.6582491,0.01196247,0.00709917,0.003244438,0.3091312],"study_design_scores_gemma":[0.000005351873,0.000009618179,0.0004322117,0.00000393142,0.000005076473,0.00001447789,0.000008767112,0.9944911,0.002393461,0.002358123,0.0002733829,0.00000446403],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07837624,0.0004732543,0.9159829,0.0002325791,0.00002682575,0.00005387795,0.0005837516,0.002700584,0.001569926],"genre_scores_gemma":[0.697187,0.0003677785,0.298592,0.0001407191,0.00008191454,0.0001248544,0.001552975,0.0001616027,0.001791073],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005120629,"threshold_uncertainty_score":0.01018167,"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","authors":[{"name":"Yubao Liu","is_ca":false},{"name":"Jiarong Cai","is_ca":false},{"name":"Jian Yin","is_ca":false},{"name":"Ada Wai-Chee Fu","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001522176,0.001063996,0.001283575,0.009087631,0.001132074,0.002856066,0.001189881,0.001142245,0.002501728],"category_scores_gemma":[0.007556651,0.000525563,0.001432164,0.006772095,0.0004699196,0.002391671,0.001080394,0.001242978,0.002017163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000855826,"about_ca_system_score_gemma":0.001280292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002108877,"about_ca_topic_score_gemma":0.002417153,"domain_scores_codex":[0.9980692,0.00022182,0.0002617652,0.0004511868,0.0008579333,0.0001381077],"domain_scores_gemma":[0.9967043,0.0009564135,0.0002618553,0.0004531812,0.001468165,0.0001560493],"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":[0.001097413,0.0006613533,0.01789875,0.0003734989,0.0003211978,0.0003657052,0.0003424887,0.03236965,0.02966657,0.008125515,0.01740556,0.8913723],"study_design_scores_gemma":[0.00009901564,0.0003092639,0.008876882,0.00007474307,0.000243672,0.0005521827,0.0004026192,0.9134007,0.0361388,0.02293777,0.0169031,0.00006127149],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1405475,0.001880565,0.8430446,0.001184435,0.0009966471,0.001082576,0.003294742,0.004141348,0.003827539],"genre_scores_gemma":[0.4376804,0.002010755,0.5300859,0.0002645063,0.0009687713,0.0008120037,0.01408909,0.0003969062,0.0136916],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009087631,"threshold_uncertainty_score":0.008369088,"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","authors":[{"name":"Gellért Weisz","is_ca":false},{"name":"Tor Lattimore","is_ca":false},{"name":"Csaba Szepesvári","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003308018,0.001193407,0.002376899,0.0009009144,0.0008772358,0.002618845,0.002012132,0.003482681,0.003506488],"category_scores_gemma":[0.02240344,0.001492067,0.001190802,0.001149865,0.002978219,0.004883218,0.003479902,0.003540602,0.0007141049],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001139996,"about_ca_system_score_gemma":0.001117548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003311217,"about_ca_topic_score_gemma":0.003261361,"domain_scores_codex":[0.9981852,0.001095964,0.00007826278,0.0002832776,0.0001976314,0.0001596122],"domain_scores_gemma":[0.9868059,0.01110559,0.0004432595,0.000933652,0.0004167691,0.0002948312],"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":[0.000173859,0.00007284684,0.0008870505,0.0001002419,0.00008995599,0.0001128479,0.0001867194,0.8067304,0.0007544821,0.1616021,0.001556422,0.02773298],"study_design_scores_gemma":[0.00001638923,0.00001171279,0.00004116561,0.000009151094,0.000007843156,0.00001189498,0.000008356005,0.9259093,0.0001260813,0.07371467,0.0001368922,0.000006503011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02793323,0.0003372102,0.968564,0.0007430987,0.00004697276,0.00002221182,0.00007770748,0.0004218732,0.001853629],"genre_scores_gemma":[0.8364969,0.0003533042,0.1561261,0.0003908229,0.0001525675,0.0001966646,0.0002653791,0.0003236437,0.005694756],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003506488,"threshold_uncertainty_score":0.01749468,"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","authors":[{"name":"Roozbeh Razavi‐Far","is_ca":true},{"name":"Ehsan Hallaji","is_ca":true},{"name":"Mehrdad Saif","is_ca":true},{"name":"Gregory Ditzler","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002241542,0.0009097289,0.001320032,0.001104366,0.0005125962,0.001499873,0.00233836,0.001496864,0.001529103],"category_scores_gemma":[0.007566936,0.0004691998,0.0011169,0.001010316,0.001036666,0.002503389,0.001837847,0.002597382,0.0005269274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001008135,"about_ca_system_score_gemma":0.00151231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003140821,"about_ca_topic_score_gemma":0.002159907,"domain_scores_codex":[0.9986581,0.0002251949,0.00006963988,0.0003774723,0.0004744946,0.000195135],"domain_scores_gemma":[0.9970927,0.001544969,0.0004094403,0.0002988117,0.0005293819,0.0001245666],"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":[0.0005140812,0.0001650336,0.00390247,0.0001786505,0.0001213331,0.0005662749,0.0001941933,0.7619238,0.01308407,0.09093811,0.002352558,0.1260595],"study_design_scores_gemma":[0.000005887708,0.00002519148,0.0001281943,0.00000258267,0.000006958222,0.000045194,0.00000409852,0.9927545,0.0006515853,0.00610071,0.0002675717,0.000007470979],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006462578,0.0002170366,0.9924264,0.0001002001,0.00003457978,0.00002508667,0.000062554,0.0002643387,0.0004072087],"genre_scores_gemma":[0.7606482,0.0008114972,0.2325276,0.000216149,0.000234364,0.0002606988,0.0004643064,0.0001245181,0.004712589],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003140821,"threshold_uncertainty_score":0.01185453,"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)","authors":[{"name":"Yuwei Fu","is_ca":true},{"name":"Di Wu","is_ca":true},{"name":"Benoît Boulet","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002377647,0.00108123,0.001585184,0.0007365794,0.0004506784,0.0008039837,0.001269293,0.0009354762,0.001376259],"category_scores_gemma":[0.004785138,0.0006206849,0.0008364732,0.0006703805,0.0006260319,0.001176303,0.001072362,0.00200311,0.0002752479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073774,"about_ca_system_score_gemma":0.001097217,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007793649,"about_ca_topic_score_gemma":0.005847155,"domain_scores_codex":[0.9990608,0.000318735,0.00005308375,0.00021592,0.0002377921,0.0001136305],"domain_scores_gemma":[0.9981658,0.001087605,0.0002411493,0.0001281435,0.000275929,0.0001013759],"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":[0.00004144579,0.00005284708,0.0005672842,0.00002167889,0.00005178378,0.00004460976,0.00003099085,0.96879,0.0008581267,0.002107708,0.0003880188,0.02704556],"study_design_scores_gemma":[0.000002320414,0.00001052434,0.00003646322,0.000001286375,0.00000354301,0.000003508254,0.000001088748,0.9990262,0.0001286861,0.0007019112,0.00008216283,0.000002301695],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02960785,0.0005899113,0.9670662,0.0002575409,0.00005780731,0.00005527265,0.00004237881,0.0007268409,0.001596157],"genre_scores_gemma":[0.9163886,0.0002522861,0.0813618,0.0001529313,0.00005867201,0.0001233858,0.0001245391,0.00006167144,0.001476137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007793649,"threshold_uncertainty_score":0.01549655,"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","authors":[{"name":"Yang Zhang","is_ca":false},{"name":"Simon Fong","is_ca":false},{"name":"Jinan Fiaidhi","is_ca":true},{"name":"Sabah Mohammed","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001877597,0.0005286323,0.0008265353,0.001083646,0.0003895831,0.001833898,0.001237375,0.0008348555,0.002923789],"category_scores_gemma":[0.004421962,0.0003635691,0.0006586077,0.0009670781,0.0002723605,0.001474501,0.000923708,0.0008863587,0.001176873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004464624,"about_ca_system_score_gemma":0.001228959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007554733,"about_ca_topic_score_gemma":0.0005840303,"domain_scores_codex":[0.9987913,0.0002810509,0.000222019,0.0002814146,0.000353387,0.00007080855],"domain_scores_gemma":[0.9979323,0.001002695,0.0001859771,0.0002780975,0.0004353467,0.0001655612],"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":[0.002776887,0.001397082,0.02467679,0.001093205,0.0005369802,0.002868433,0.0009200191,0.04885413,0.03962497,0.0185869,0.0381566,0.8205079],"study_design_scores_gemma":[0.0008354767,0.001085827,0.005575877,0.0001838122,0.0004431375,0.003192179,0.0001719302,0.8576559,0.05362822,0.01599824,0.06107588,0.0001534984],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0430611,0.0006888298,0.9304664,0.001923593,0.0004044533,0.0008642865,0.001155324,0.01741596,0.004019911],"genre_scores_gemma":[0.4151015,0.0007622693,0.5737492,0.001238506,0.0005367363,0.001040881,0.002154385,0.0002852497,0.005131261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002923789,"threshold_uncertainty_score":0.009929776,"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","authors":[{"name":"Vítor Cerqueira","is_ca":true},{"name":"Heitor Murilo Gomes","is_ca":false},{"name":"Albert Bifet","is_ca":false},{"name":"Luı́s Torgo","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003716841,0.001227514,0.00134051,0.003908997,0.000840665,0.001426583,0.002057036,0.001592626,0.00608743],"category_scores_gemma":[0.008149181,0.0006040164,0.001296172,0.001631831,0.0004677748,0.001638528,0.002493857,0.001777407,0.003872728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005265591,"about_ca_system_score_gemma":0.001996693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002230191,"about_ca_topic_score_gemma":0.007865376,"domain_scores_codex":[0.998485,0.0003955016,0.0001352002,0.000432273,0.0004422161,0.0001097621],"domain_scores_gemma":[0.9973238,0.0009133049,0.0001689175,0.0005804242,0.0008261147,0.0001873273],"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":[0.0004628211,0.0003327777,0.006606438,0.0001950272,0.000252132,0.0001122866,0.0001489346,0.006507365,0.008289898,0.002503128,0.02126757,0.9533216],"study_design_scores_gemma":[0.0002513269,0.0003646582,0.006215424,0.00006266977,0.0001529775,0.0004254978,0.0001697939,0.9142233,0.02860834,0.009700253,0.03974187,0.00008397483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01163559,0.0003719464,0.9737158,0.0001874133,0.0002874881,0.0003261736,0.001242304,0.01135459,0.0008787363],"genre_scores_gemma":[0.1082743,0.0001722253,0.8763604,0.0002716006,0.0001733399,0.0005589828,0.003817258,0.001001846,0.009370111],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00608743,"threshold_uncertainty_score":0.02036446,"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","authors":[{"name":"Li Yang","is_ca":true},{"name":"Abdallah Shami","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372005,0.001133265,0.001025704,0.001209768,0.0005572978,0.001075572,0.001430584,0.0005934977,0.0007794508],"category_scores_gemma":[0.002488784,0.0003416416,0.0009728979,0.001085779,0.000399934,0.001997236,0.001582828,0.001316439,0.0003384223],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006834411,"about_ca_system_score_gemma":0.001469784,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00755037,"about_ca_topic_score_gemma":0.009291269,"domain_scores_codex":[0.9991366,0.0001529283,0.00005930921,0.0002123462,0.0003444025,0.00009438205],"domain_scores_gemma":[0.9992562,0.0002087297,0.00009558165,0.0001059117,0.0002699615,0.00006366928],"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":[0.0002416862,0.0003245588,0.006523876,0.0001644268,0.0001636027,0.0003413227,0.0002396707,0.5647292,0.0155129,0.015539,0.00839983,0.38782],"study_design_scores_gemma":[0.000002973979,0.00001534778,0.0002377416,0.000002091512,0.00000483759,0.00001652254,0.000009449184,0.9963883,0.0007083619,0.002070901,0.0005383596,0.00000511394],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005781962,0.0001181346,0.9925569,0.00007791306,0.00001697614,0.00008703226,0.0001131965,0.0009633048,0.0002844763],"genre_scores_gemma":[0.3912052,0.000315851,0.6051463,0.0001392104,0.0001040114,0.0003117797,0.001144747,0.0001597291,0.001473075],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00755037,"threshold_uncertainty_score":0.0150128,"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","authors":[{"name":"Haruna Isah","is_ca":true},{"name":"Farhana Zulkernine","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005862489,0.00136716,0.001634937,0.002390862,0.001439486,0.00415758,0.004769624,0.001712219,0.001905967],"category_scores_gemma":[0.01463929,0.001018317,0.001890049,0.002325564,0.001989382,0.005332503,0.005569891,0.003472888,0.001482746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001601267,"about_ca_system_score_gemma":0.003795306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007717507,"about_ca_topic_score_gemma":0.005258694,"domain_scores_codex":[0.995551,0.0005296583,0.0004960471,0.0006466371,0.002453566,0.000323075],"domain_scores_gemma":[0.9949383,0.00135331,0.0004822495,0.001587453,0.001315762,0.0003229455],"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":[0.001100396,0.0006844046,0.008020116,0.0005824236,0.0004830763,0.001829133,0.001254698,0.3145096,0.03925597,0.08099563,0.04192676,0.5093579],"study_design_scores_gemma":[0.00004106772,0.00007902802,0.0003587744,0.00003385356,0.0000469043,0.0002442224,0.00007648294,0.9536848,0.01170856,0.02075058,0.01291695,0.00005880901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002224585,0.0001312338,0.9841605,0.0001812722,0.00005308134,0.0001789114,0.000131697,0.01253119,0.0004074736],"genre_scores_gemma":[0.1074359,0.0003894231,0.8868645,0.0002415705,0.0001549593,0.000372146,0.001445906,0.001246442,0.0018492],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007717507,"threshold_uncertainty_score":0.03100419,"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","authors":[{"name":"Shai Ben-David","is_ca":true},{"name":"Ruth Urner","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01859039,0.0008303045,0.001594091,0.001549552,0.0006743521,0.004372656,0.002182736,0.002055743,0.00583542],"category_scores_gemma":[0.1257245,0.000629493,0.0007859482,0.002162226,0.002918839,0.01597504,0.003757125,0.002859903,0.001545043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001001907,"about_ca_system_score_gemma":0.001147172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001884812,"about_ca_topic_score_gemma":0.001133504,"domain_scores_codex":[0.9938753,0.002493627,0.000515637,0.001408706,0.001438382,0.0002684092],"domain_scores_gemma":[0.9248366,0.03795288,0.004699617,0.02134339,0.009341056,0.001826508],"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":[0.002309038,0.0007693114,0.1051064,0.0009296527,0.001247461,0.0003843077,0.001225212,0.06967559,0.02044456,0.0783633,0.01675772,0.7027873],"study_design_scores_gemma":[0.0003060758,0.000975353,0.07785162,0.0002871297,0.0006125871,0.001013811,0.001093086,0.4508927,0.01232622,0.4239239,0.03047326,0.0002442657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2291571,0.007704872,0.7175262,0.01811749,0.00171585,0.000321795,0.001226304,0.002636906,0.02159345],"genre_scores_gemma":[0.9143863,0.001811573,0.07397972,0.002303692,0.000997192,0.0001183461,0.0006272374,0.0007728237,0.005003151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01859039,"threshold_uncertainty_score":0.09831655,"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","authors":[{"name":"Yue Dong","is_ca":true},{"name":"Nathalie Japkowicz","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001573236,0.0006354607,0.0009864912,0.0007106294,0.0002905952,0.0006752956,0.000972758,0.000551469,0.0009142198],"category_scores_gemma":[0.0042549,0.0004348106,0.0005641704,0.0006278848,0.0004166541,0.001229956,0.0008058732,0.001371986,0.0002533399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000598009,"about_ca_system_score_gemma":0.0008300197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003852681,"about_ca_topic_score_gemma":0.003438709,"domain_scores_codex":[0.9993512,0.000160105,0.00005486666,0.0001709035,0.0002030544,0.00005992256],"domain_scores_gemma":[0.9977285,0.001130533,0.0001834078,0.000321724,0.000553593,0.00008231561],"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":[0.0001857559,0.0001052834,0.003131225,0.0000606841,0.0001391478,0.00006110211,0.00007033694,0.7473477,0.006483789,0.00533134,0.001201378,0.2358824],"study_design_scores_gemma":[0.000001540617,0.000007578511,0.00007515895,0.000001066245,0.000002507215,0.000003745171,0.000001460343,0.9983037,0.0005543362,0.0009433332,0.0001044069,0.000001174938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03549661,0.000330929,0.9625397,0.00007030025,0.00005583192,0.0000269469,0.00004272172,0.00107003,0.0003668955],"genre_scores_gemma":[0.6387516,0.0003079085,0.3589103,0.00006912969,0.0001150713,0.0001049603,0.0002395029,0.0001281283,0.001373435],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003852681,"threshold_uncertainty_score":0.008320153,"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","authors":[{"name":"Chun Wang","is_ca":false},{"name":"Ming‐Hui Chen","is_ca":false},{"name":"Jing Wu","is_ca":false},{"name":"Jun Yan","is_ca":false},{"name":"Yuping Zhang","is_ca":false},{"name":"Elizabeth D. Schifano","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005696665,0.001094729,0.001996015,0.001697896,0.0008960151,0.001968292,0.003644272,0.001237059,0.002322841],"category_scores_gemma":[0.03118837,0.0008357454,0.0009346455,0.002196597,0.001011447,0.004228803,0.002029949,0.002814561,0.0009203943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008268129,"about_ca_system_score_gemma":0.002303984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005084604,"about_ca_topic_score_gemma":0.0059862,"domain_scores_codex":[0.9966207,0.0009581878,0.0002818851,0.0008655222,0.001086511,0.0001872601],"domain_scores_gemma":[0.9864795,0.007574127,0.001021394,0.002312649,0.002301718,0.0003106199],"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":[0.000474653,0.0003208889,0.008407647,0.0003024621,0.0001909803,0.000324703,0.0004826176,0.2664138,0.005577351,0.03494596,0.00783893,0.67472],"study_design_scores_gemma":[0.00003210483,0.00003736777,0.0004141039,0.00001362782,0.000024033,0.00007855501,0.00002116799,0.984908,0.001708253,0.01031668,0.002428229,0.00001800746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005452625,0.0002912589,0.9924994,0.0001455001,0.0001181371,0.00006951291,0.00005964018,0.0009907228,0.0003732025],"genre_scores_gemma":[0.2282992,0.0006098989,0.7652011,0.0004370222,0.0005752663,0.0004583097,0.0006092594,0.0003716437,0.003438349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005696665,"threshold_uncertainty_score":0.03012723,"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","authors":[{"name":"Hanady M. Abdulsalam","is_ca":true},{"name":"David B. Skillicorn","is_ca":true},{"name":"Patrick Martin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003110044,0.001303734,0.001719184,0.002065025,0.0007817862,0.001161941,0.001997692,0.001304718,0.006534094],"category_scores_gemma":[0.01110046,0.0005406981,0.00164803,0.002698334,0.0004431891,0.00227772,0.0007773623,0.001455723,0.003222748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004701218,"about_ca_system_score_gemma":0.000843162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002927696,"about_ca_topic_score_gemma":0.005471493,"domain_scores_codex":[0.9985292,0.0004792665,0.0001100878,0.0003694912,0.0003972084,0.0001146504],"domain_scores_gemma":[0.9955282,0.002738945,0.0002744634,0.0004890375,0.0008343072,0.0001351121],"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":[0.0002753828,0.0001994143,0.003444931,0.0004628493,0.0002202479,0.0002287391,0.00009468181,0.2355984,0.002340348,0.02169092,0.03951631,0.6959278],"study_design_scores_gemma":[0.00004883067,0.00006499288,0.0004870615,0.00005858507,0.00005735377,0.0001806331,0.00002489464,0.9429862,0.001115591,0.04159692,0.01335805,0.00002087562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0118365,0.002595391,0.975845,0.000547427,0.0005444549,0.0002419684,0.001631051,0.003019471,0.003738649],"genre_scores_gemma":[0.2178433,0.003194555,0.7604873,0.0006946157,0.001223935,0.0005130594,0.007875409,0.0005742714,0.007593534],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006534094,"threshold_uncertainty_score":0.02185875,"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","authors":[{"name":"Daniele Grattarola","is_ca":false},{"name":"Daniele Zambon","is_ca":false},{"name":"Lorenzo Livi","is_ca":true},{"name":"Cesare Alippi","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001007048,0.0008900262,0.0007423455,0.00226322,0.000319382,0.001018502,0.001123587,0.001080843,0.0007792933],"category_scores_gemma":[0.006927424,0.0003982548,0.0007518869,0.001144588,0.0009971543,0.002291183,0.001000866,0.001508438,0.0003592301],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008915526,"about_ca_system_score_gemma":0.0004439411,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002908785,"about_ca_topic_score_gemma":0.003082013,"domain_scores_codex":[0.9994243,0.0001653122,0.00003306256,0.0002072121,0.0001072519,0.00006286318],"domain_scores_gemma":[0.9973802,0.001317922,0.0005336791,0.0003193336,0.0003076738,0.0001410926],"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":[0.0003137173,0.0002121856,0.01516214,0.0001325366,0.0001313984,0.0002985399,0.0002940928,0.7633561,0.007412345,0.01560669,0.003259792,0.1938204],"study_design_scores_gemma":[0.000002934845,0.00001584497,0.000813965,0.00000367798,0.000003989851,0.00002250579,0.00001622745,0.9925497,0.0006753704,0.005689261,0.000202207,0.000004330266],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1700296,0.0003515866,0.8264462,0.0003739092,0.00005512052,0.0001135089,0.0003698379,0.001545573,0.0007146468],"genre_scores_gemma":[0.8665192,0.0003008041,0.1306147,0.0001068613,0.0000662096,0.00008728931,0.0009939796,0.0001366314,0.001174408],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002908785,"threshold_uncertainty_score":0.006468713,"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","authors":[{"name":"Hung Cao","is_ca":true},{"name":"Mónica Wachowicz","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005480698,0.000464957,0.000404129,0.0005926464,0.001010138,0.001830767,0.001891085,0.000625482,0.001487094],"category_scores_gemma":[0.0008576731,0.0003063275,0.0005037529,0.0008982106,0.000664676,0.001906435,0.00148488,0.0009867544,0.0005464148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008275215,"about_ca_system_score_gemma":0.001537714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008271453,"about_ca_topic_score_gemma":0.01470921,"domain_scores_codex":[0.9996622,0.00004234967,0.00002619824,0.00007715946,0.0001176721,0.0000744995],"domain_scores_gemma":[0.9995797,0.00005836209,0.00001707504,0.00009336611,0.0001861387,0.00006538831],"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":[0.001537715,0.001212843,0.01638366,0.0005551803,0.0005516122,0.002025924,0.0009699591,0.1223305,0.07993823,0.2891765,0.09200372,0.3933141],"study_design_scores_gemma":[0.00003798644,0.0001155785,0.001742501,0.0000438515,0.00007111552,0.0002835758,0.0001312546,0.9145316,0.01305146,0.0416844,0.02825684,0.00004990339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0581583,0.0009942984,0.914305,0.001874123,0.0005745986,0.0004873291,0.0004940696,0.004010547,0.01910163],"genre_scores_gemma":[0.6809905,0.0009646714,0.3076725,0.001038381,0.0002083542,0.0001918863,0.0009427909,0.0002377981,0.007753105],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008271453,"threshold_uncertainty_score":0.01644665,"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","authors":[{"name":"Misha Denil","is_ca":true},{"name":"David S. Matheson","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02121698,0.001120398,0.002891196,0.002124601,0.002409459,0.004192878,0.005293161,0.003327516,0.006622686],"category_scores_gemma":[0.1345219,0.001208222,0.002261294,0.002511747,0.003350314,0.01543359,0.004799479,0.007464995,0.001891876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001893576,"about_ca_system_score_gemma":0.002544113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001678463,"about_ca_topic_score_gemma":0.001831049,"domain_scores_codex":[0.975669,0.01036694,0.001411118,0.004898993,0.006233493,0.001420372],"domain_scores_gemma":[0.8560813,0.1048088,0.006222056,0.02194427,0.009278098,0.001665454],"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":[0.001491936,0.0003968162,0.01570732,0.0008386738,0.0004741332,0.0006368983,0.000773954,0.165396,0.00578744,0.6102056,0.02202525,0.1762661],"study_design_scores_gemma":[0.00008260631,0.0000881901,0.000875018,0.0001003823,0.00006357356,0.0004058536,0.00007121109,0.3283682,0.002511191,0.6616805,0.005710962,0.00004225782],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03468845,0.002424582,0.9494776,0.003127412,0.0005040776,0.0001372758,0.0009996116,0.001154174,0.007486705],"genre_scores_gemma":[0.6838687,0.001896649,0.2976169,0.002368906,0.002327978,0.000596987,0.002955587,0.001504939,0.006863292],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02121698,"threshold_uncertainty_score":0.1122074,"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","authors":[{"name":"Jagmohan Chauhan","is_ca":true},{"name":"Shaiful Chowdhury","is_ca":true},{"name":"Dwight Makaroff","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004375773,0.001946931,0.001540032,0.002235983,0.001181448,0.00179158,0.003625167,0.001220002,0.003801904],"category_scores_gemma":[0.007825909,0.0005191794,0.0005633592,0.005264524,0.0009587795,0.002408897,0.001211443,0.001175734,0.001765932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002481681,"about_ca_system_score_gemma":0.002020224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01834993,"about_ca_topic_score_gemma":0.007997632,"domain_scores_codex":[0.9935699,0.0008231591,0.0004873093,0.0007958763,0.003413634,0.0009101962],"domain_scores_gemma":[0.9880731,0.003835196,0.0006937298,0.001338457,0.005093265,0.0009663064],"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":[0.01741698,0.006190883,0.06375901,0.00392678,0.0008208501,0.001513682,0.001345913,0.1744591,0.06255706,0.00516125,0.2106246,0.4522239],"study_design_scores_gemma":[0.0007823474,0.005120749,0.09515502,0.0001679061,0.0001772544,0.0007731952,0.001323977,0.7920492,0.07259806,0.002079021,0.02953095,0.0002423714],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9425861,0.003135899,0.01155998,0.001719042,0.0004499545,0.0004229188,0.006710354,0.01707666,0.01633908],"genre_scores_gemma":[0.960192,0.001015948,0.01978446,0.0003416678,0.0001792142,0.0001810071,0.01236016,0.001820541,0.004124983],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01834993,"threshold_uncertainty_score":0.03648627,"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","authors":[{"name":"Cobbinah B. Mawuli","is_ca":false},{"name":"Liwei Che","is_ca":false},{"name":"Jay Kumar","is_ca":true},{"name":"Salah Ud Din","is_ca":false},{"name":"Zhili Qin","is_ca":false},{"name":"Qinli Yang","is_ca":false},{"name":"Junming Shao","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00575419,0.001094233,0.001997764,0.001338415,0.0008359,0.001469294,0.0041034,0.001451607,0.001289245],"category_scores_gemma":[0.01252717,0.0005416462,0.0008259487,0.001667583,0.001078797,0.005262497,0.00352044,0.002037965,0.000429428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001029508,"about_ca_system_score_gemma":0.001893416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003356079,"about_ca_topic_score_gemma":0.002623063,"domain_scores_codex":[0.9980968,0.0005024686,0.0001459343,0.0005586572,0.0005564399,0.0001397001],"domain_scores_gemma":[0.9954728,0.001552151,0.0002823866,0.001227677,0.001200705,0.0002641976],"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":[0.0008057967,0.0006565275,0.004236878,0.0001854445,0.0002055885,0.000281493,0.0003218796,0.299662,0.005795979,0.009113031,0.007234814,0.6715006],"study_design_scores_gemma":[0.00004044913,0.00007962761,0.0001356389,0.000004982519,0.000009790828,0.00005332131,0.0000219217,0.9905604,0.001572761,0.006940364,0.0005717564,0.000008956286],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02955721,0.0003523052,0.9645039,0.0001977382,0.00009842334,0.0001913194,0.0001567859,0.004467342,0.0004749204],"genre_scores_gemma":[0.6006548,0.000300122,0.3956068,0.0003024569,0.00009487686,0.0003966427,0.0009010736,0.0002100478,0.001533138],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00575419,"threshold_uncertainty_score":0.03043139,"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","authors":[{"name":"Duc C. Le","is_ca":true},{"name":"Sara Khanchi","is_ca":true},{"name":"A. Nur Zincir‐Heywood","is_ca":true},{"name":"Malcolm I. Heywood","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004872985,0.001129123,0.001170028,0.002799894,0.0006301548,0.001916579,0.001898922,0.002095117,0.001346674],"category_scores_gemma":[0.0159597,0.0003199189,0.0007443796,0.002196938,0.001003044,0.001530016,0.001467948,0.001675495,0.0002845722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001518792,"about_ca_system_score_gemma":0.00136551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005496836,"about_ca_topic_score_gemma":0.004718116,"domain_scores_codex":[0.9974129,0.00124045,0.0001314387,0.0003419881,0.0006571173,0.0002161536],"domain_scores_gemma":[0.9930264,0.004673404,0.0003099978,0.0006238708,0.001184274,0.0001821164],"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":[0.0001398166,0.000190298,0.004175566,0.0001043777,0.0001032362,0.000068797,0.00005410459,0.8912705,0.0006404857,0.005747837,0.001282487,0.09622246],"study_design_scores_gemma":[0.000008780249,0.00004041974,0.0004388028,0.000008061921,0.000006504425,0.00001449349,0.00001990747,0.9964336,0.0003990711,0.002281365,0.0003455649,0.000003479111],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.453265,0.00493863,0.5169696,0.002630296,0.000486214,0.0003787122,0.0005262113,0.001424398,0.01938096],"genre_scores_gemma":[0.865972,0.0007195201,0.1303935,0.0002313208,0.00009487231,0.0001631825,0.0005733632,0.00009325469,0.001759022],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005496836,"threshold_uncertainty_score":0.02577108,"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","authors":[{"name":"Hanady M. Abdulsalam","is_ca":true},{"name":"David B. Skillicorn","is_ca":true},{"name":"Patrick Martin","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002134826,0.0009620397,0.001274247,0.002893696,0.0004812048,0.001191025,0.001563697,0.001000738,0.0009753393],"category_scores_gemma":[0.00372433,0.0004631737,0.001582522,0.002091893,0.0003075888,0.001969533,0.00060828,0.001164109,0.0006675607],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004752365,"about_ca_system_score_gemma":0.000487564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002471715,"about_ca_topic_score_gemma":0.003519421,"domain_scores_codex":[0.9990578,0.0001493215,0.00009115838,0.0002969806,0.0002908512,0.0001139589],"domain_scores_gemma":[0.9974756,0.001490371,0.0001804036,0.0002757137,0.0004644962,0.0001134651],"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":[0.0003825707,0.0004506668,0.01836335,0.0001377776,0.0002067378,0.0003328689,0.0001082888,0.2059554,0.009013912,0.002266222,0.004941077,0.7578411],"study_design_scores_gemma":[0.000006710119,0.00003325682,0.0007400768,0.000006591494,0.00002240248,0.00008600763,0.00001675335,0.9951367,0.001231156,0.002344732,0.0003701851,0.000005413278],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1220018,0.0009279434,0.8721975,0.0002107742,0.0001772782,0.0002026205,0.0006372269,0.002605394,0.001039449],"genre_scores_gemma":[0.6090953,0.0006524932,0.383871,0.000129471,0.0003033516,0.0001668312,0.003253352,0.0002184095,0.00230979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002893696,"threshold_uncertainty_score":0.01129019,"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","authors":[{"name":"B. John Oommen","is_ca":true},{"name":"Anis Yazidi","is_ca":false},{"name":"Ole‐Christoffer Granmo","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048956,0.0008380684,0.001141465,0.001196252,0.0005236851,0.001219374,0.002679237,0.001463616,0.0009975187],"category_scores_gemma":[0.01504919,0.0005676359,0.0007459461,0.001049489,0.0009376527,0.003503014,0.001976476,0.001656549,0.0003873526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007216429,"about_ca_system_score_gemma":0.0007952031,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002186525,"about_ca_topic_score_gemma":0.002204292,"domain_scores_codex":[0.9982761,0.0007952497,0.00009884332,0.000372618,0.000354115,0.0001029793],"domain_scores_gemma":[0.9924589,0.005221861,0.0006138365,0.0007106069,0.0007880643,0.000206743],"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":[0.0004017177,0.0004055932,0.01171463,0.0002087407,0.000287905,0.0001955859,0.0004853285,0.5809578,0.009869601,0.06412058,0.002313135,0.3290394],"study_design_scores_gemma":[0.000009795201,0.00004574012,0.0003113955,0.00000349241,0.00001227735,0.00002060847,0.00001492108,0.9895663,0.0005806094,0.009070582,0.000357275,0.000006962397],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01237802,0.00009789422,0.9868668,0.0001474624,0.00001495329,0.00003375557,0.00002407421,0.00009075875,0.0003462451],"genre_scores_gemma":[0.6419955,0.0004521379,0.3537011,0.0002893721,0.0002119926,0.0003159388,0.0002092558,0.00005499506,0.002769605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0048956,"threshold_uncertainty_score":0.02589071,"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","authors":[{"name":"Jing Nathan Yan","is_ca":false},{"name":"Oliver Schulte","is_ca":true},{"name":"Mohan Zhang","is_ca":true},{"name":"Jiannan Wang","is_ca":true},{"name":"Reynold Cheng","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01233973,0.001842609,0.001810355,0.005821861,0.001559842,0.003756311,0.004772193,0.001816242,0.002620461],"category_scores_gemma":[0.06975247,0.0009621915,0.002044062,0.0059373,0.00216784,0.005226282,0.006160152,0.003789401,0.001423536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001457151,"about_ca_system_score_gemma":0.006619785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006643284,"about_ca_topic_score_gemma":0.008696856,"domain_scores_codex":[0.9848878,0.002886673,0.002107606,0.002428614,0.007133772,0.0005555116],"domain_scores_gemma":[0.9288532,0.0339185,0.008069137,0.01503035,0.01317354,0.0009551996],"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":[0.001104819,0.0004252129,0.04822168,0.001905905,0.0009284855,0.001365109,0.001434673,0.0765915,0.02397501,0.05282503,0.04145477,0.7497678],"study_design_scores_gemma":[0.0001147932,0.000271501,0.005412639,0.0003211179,0.000179876,0.001053862,0.0004859538,0.8272612,0.06244958,0.06598275,0.03626643,0.0002003023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01033602,0.0003865694,0.9701792,0.0006629218,0.0001158385,0.0004058205,0.002123291,0.01485545,0.000934898],"genre_scores_gemma":[0.1511681,0.0004238116,0.8387986,0.0008038121,0.0001732978,0.0005183054,0.005501305,0.001267848,0.001344956],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01233973,"threshold_uncertainty_score":0.06525952,"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)","authors":[{"name":"Rabaa Alabdulrahman","is_ca":true},{"name":"Herna L. Viktor","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002047759,0.000696017,0.001401548,0.000573431,0.0008231339,0.001298733,0.001151609,0.001697626,0.002316044],"category_scores_gemma":[0.007270542,0.0002887088,0.0005871623,0.0005006627,0.0004874994,0.001804406,0.001374848,0.001447982,0.001095663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004697505,"about_ca_system_score_gemma":0.0005619842,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005483938,"about_ca_topic_score_gemma":0.009555169,"domain_scores_codex":[0.9990236,0.0004160954,0.00002767317,0.0002321076,0.0001863394,0.0001141845],"domain_scores_gemma":[0.9969302,0.001674883,0.000159216,0.0004159459,0.0005266496,0.0002931988],"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":[0.004691057,0.003589634,0.1273957,0.0007034409,0.0009508015,0.001577935,0.001880202,0.07605647,0.04183391,0.019535,0.03196419,0.6898217],"study_design_scores_gemma":[0.00008930029,0.000874104,0.01101901,0.00003245644,0.0001588353,0.0004020068,0.0005219845,0.9706241,0.003167539,0.009207943,0.003847325,0.00005543417],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7192525,0.00177551,0.2641238,0.002466571,0.0003929271,0.0002791254,0.0002945134,0.001272799,0.01014224],"genre_scores_gemma":[0.9609671,0.0001669417,0.03393074,0.0003067669,0.00006417483,0.0000370343,0.0001223238,0.00003601715,0.004368921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005483938,"threshold_uncertainty_score":0.01090401,"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","authors":[{"name":"Simon Fong","is_ca":false},{"name":"Yang Zhang","is_ca":false},{"name":"Jinan Fiaidhi","is_ca":true},{"name":"Osama A. Mohammed","is_ca":true},{"name":"Sabah Mohammed","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004990472,0.0006317538,0.0008298506,0.001056736,0.0004677619,0.001101123,0.0007936304,0.001400607,0.0008766869],"category_scores_gemma":[0.01363868,0.0001864738,0.000487317,0.00101718,0.000464918,0.0008511957,0.0004536019,0.0008440607,0.0002343475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001398852,"about_ca_system_score_gemma":0.000808552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004171448,"about_ca_topic_score_gemma":0.003729353,"domain_scores_codex":[0.9975342,0.001318426,0.0002583338,0.0002441923,0.0005135381,0.0001313116],"domain_scores_gemma":[0.9880122,0.008571138,0.0004136899,0.0005391591,0.002015645,0.0004481049],"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":[0.006966924,0.007867821,0.1190388,0.001572782,0.0006151609,0.004120484,0.001896027,0.3105326,0.01418001,0.006637157,0.01020777,0.5163644],"study_design_scores_gemma":[0.0003766934,0.003337083,0.01905977,0.00007689365,0.0001382931,0.0005629554,0.0009527349,0.9542323,0.01595923,0.001382092,0.003878066,0.00004376624],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9564856,0.001087661,0.03745932,0.001345825,0.0001341754,0.000475758,0.0004054247,0.0003861866,0.002220059],"genre_scores_gemma":[0.9654661,0.0004344276,0.0327337,0.0001158773,0.00004717922,0.0001227593,0.0002946667,0.00001289358,0.0007723823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004990472,"threshold_uncertainty_score":0.02639246,"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","authors":[{"name":"John M. Chambers","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05856427,0.0006382558,0.001061706,0.003299369,0.002431658,0.01362508,0.002266777,0.002362863,0.012653],"category_scores_gemma":[0.2178682,0.001379741,0.0005416956,0.004405489,0.005902857,0.01410335,0.00693232,0.003894586,0.004045285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001519416,"about_ca_system_score_gemma":0.006059704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001678178,"about_ca_topic_score_gemma":0.001255649,"domain_scores_codex":[0.9383633,0.0426232,0.004701988,0.003246309,0.009588648,0.001476594],"domain_scores_gemma":[0.5691357,0.3445128,0.01184187,0.02504214,0.0361127,0.01335479],"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":[0.00100104,0.0003715206,0.05530204,0.001156562,0.0001193599,0.0009825022,0.01802438,0.00279114,0.005913158,0.2816639,0.1048044,0.5278701],"study_design_scores_gemma":[0.0003171257,0.0008405881,0.01850892,0.001875504,0.0002344172,0.003195462,0.01675988,0.07022974,0.008820388,0.500324,0.3784856,0.0004084283],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.108487,0.004955255,0.7046064,0.09678338,0.001289457,0.0005064529,0.0003689954,0.01373305,0.06927001],"genre_scores_gemma":[0.621389,0.002039224,0.3400661,0.0108614,0.001211746,0.0005872762,0.0004926438,0.004087218,0.01926549],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05856427,"threshold_uncertainty_score":0.3097211,"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","authors":[{"name":"Peter Clifford","is_ca":false},{"name":"Ioana A. Cosma","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002290132,0.001155068,0.001358937,0.001831788,0.0005406319,0.001704778,0.002034203,0.00124791,0.004553631],"category_scores_gemma":[0.01832577,0.0006418295,0.001001257,0.001960008,0.0008482747,0.003243809,0.003249497,0.002271709,0.002069472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006983415,"about_ca_system_score_gemma":0.001444655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001245297,"about_ca_topic_score_gemma":0.001601862,"domain_scores_codex":[0.9986371,0.0002886762,0.0001384908,0.0002798357,0.0005858008,0.00007003489],"domain_scores_gemma":[0.9958071,0.002006098,0.0003308103,0.001095067,0.0005718912,0.0001890005],"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":[0.0003722429,0.00008995598,0.001934991,0.0003752536,0.0001519562,0.0002230351,0.000368303,0.126955,0.01725757,0.05854195,0.00640171,0.7873281],"study_design_scores_gemma":[0.00005855064,0.00008156184,0.0003466925,0.00004023539,0.00002718138,0.0002552755,0.0000518581,0.9306257,0.005751018,0.0564209,0.006306062,0.00003501026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001470706,0.0001530097,0.9973221,0.0000506216,0.00003395723,0.0000740304,0.00008114707,0.000603963,0.0002104273],"genre_scores_gemma":[0.06878362,0.0003345243,0.9280542,0.0000893787,0.0001216797,0.0003882278,0.0005579421,0.0001584423,0.001511983],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004553631,"threshold_uncertainty_score":0.01523346,"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","authors":[{"name":"Boshra Pishgoo","is_ca":false},{"name":"Bijan Raahemi","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001081156,0.001137598,0.001064503,0.001376319,0.0006943975,0.001310273,0.00257809,0.0009012806,0.001930522],"category_scores_gemma":[0.001827494,0.000462269,0.0009847292,0.001421404,0.0007200228,0.002176483,0.001072628,0.001486244,0.000812976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001028611,"about_ca_system_score_gemma":0.001403257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005957233,"about_ca_topic_score_gemma":0.005802309,"domain_scores_codex":[0.9990829,0.0001392948,0.00005468192,0.0002982753,0.000345574,0.00007920749],"domain_scores_gemma":[0.9988576,0.0002861678,0.0000766237,0.0002111393,0.0004997412,0.00006863181],"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":[0.0009776427,0.0003949468,0.005503546,0.0003109626,0.0003537847,0.0003663808,0.0003318566,0.2169804,0.06865951,0.02108346,0.009737143,0.6753003],"study_design_scores_gemma":[0.00002397059,0.00009358546,0.0004278593,0.000005599709,0.0000376776,0.00007418541,0.00002521419,0.9820215,0.009635114,0.005150077,0.002485035,0.00002032023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006865121,0.0002093662,0.9905524,0.000110935,0.00007590258,0.0000660569,0.00004684235,0.001491691,0.0005817384],"genre_scores_gemma":[0.2633393,0.000419891,0.7305992,0.0002597959,0.0002178239,0.0002209808,0.0003747233,0.0002242524,0.004343966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005957233,"threshold_uncertainty_score":0.01184511,"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","authors":[{"name":"Shadi Khalifa","is_ca":true},{"name":"Patrick Martin","is_ca":true},{"name":"Rebecca C. Young","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00200847,0.0008986053,0.001860843,0.0005914084,0.00105826,0.001520215,0.003904176,0.001561925,0.003182174],"category_scores_gemma":[0.005247181,0.000675851,0.000990986,0.001097981,0.0005444711,0.003694092,0.002691079,0.002705659,0.001638658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007606695,"about_ca_system_score_gemma":0.001878547,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005877874,"about_ca_topic_score_gemma":0.0122133,"domain_scores_codex":[0.9988305,0.0002542454,0.00005976758,0.0003476012,0.0003697744,0.0001380751],"domain_scores_gemma":[0.9974636,0.000678102,0.0001021047,0.0009112055,0.000697122,0.0001477547],"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":[0.0005932327,0.0005234783,0.002729523,0.0000774855,0.0001730104,0.0001373586,0.0001586918,0.5143271,0.007383924,0.009248092,0.008701949,0.4559462],"study_design_scores_gemma":[0.000008284867,0.0000203189,0.00007985581,0.00000181692,0.00001156286,0.00001374112,0.000007583071,0.9949493,0.0006333975,0.003891747,0.0003780884,0.000004185889],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009580781,0.0001156764,0.9878194,0.000143673,0.0000706374,0.00005822728,0.00008269201,0.001491165,0.000637796],"genre_scores_gemma":[0.448376,0.0002421932,0.542465,0.0003143918,0.0003056724,0.000380343,0.0007679663,0.0005217772,0.00662671],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005877874,"threshold_uncertainty_score":0.01168734,"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","authors":[{"name":"Mahdi Milani Fard","is_ca":true},{"name":"Quentin Cormier","is_ca":false},{"name":"Kevin Robert Canini","is_ca":false},{"name":"Maya R. Gupta","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006843185,0.001152659,0.001882011,0.0009698988,0.0008822578,0.001354884,0.002978078,0.002459132,0.001606128],"category_scores_gemma":[0.0374422,0.0009787389,0.001070208,0.0007156654,0.002110028,0.003328057,0.003508403,0.00353776,0.0008733585],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001051131,"about_ca_system_score_gemma":0.002652299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00328941,"about_ca_topic_score_gemma":0.00340275,"domain_scores_codex":[0.9962744,0.001410557,0.0001851449,0.0006884687,0.001148278,0.000293307],"domain_scores_gemma":[0.9760873,0.01555877,0.001816927,0.003755581,0.002145959,0.0006354892],"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":[0.0007050936,0.0004414196,0.007378304,0.0001193676,0.0001163358,0.0002398419,0.000796414,0.7228616,0.01366653,0.01806774,0.004461861,0.2311454],"study_design_scores_gemma":[0.00001205813,0.000057715,0.0001472946,0.000005086207,0.000006018195,0.00001790815,0.00001413674,0.9944471,0.001436014,0.003639071,0.0002108061,0.000006714696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06365862,0.0002173807,0.9318861,0.0005010628,0.00004721496,0.0001136678,0.0000398306,0.002678378,0.0008575898],"genre_scores_gemma":[0.6907898,0.0001395077,0.3052122,0.000399584,0.0001130173,0.0002605238,0.000215448,0.0006256437,0.002244431],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006843185,"threshold_uncertainty_score":0.03619063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}