{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1256,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":1256,"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":"e0fdac2723aa","filters":{"topic":"Data Management and Algorithms"}},"results":[{"id":"W2140190241","doi":"10.5860/choice.49-3305","title":"Data mining: concepts and techniques","year":2012,"lang":"en","type":"article","venue":"Choice Reviews Online","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":28877,"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":"Computer science; Data science; Data mining","authors":[{"name":"Jiawei Han","is_ca":false},{"name":"Micheline Kamber","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1554244839230521,"gpt":0.4082003367705969,"spread":0.2527758528475448,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01151261,0.00344485,0.003938422,0.009593101,0.001705109,0.01173126,0.007147308,0.004474623,0.00888191],"category_scores_gemma":[0.01787223,0.001829905,0.003083982,0.01601791,0.006387398,0.01137742,0.006140475,0.007445849,0.008215756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002772727,"about_ca_system_score_gemma":0.005394414,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001922624,"about_ca_topic_score_gemma":0.0008580576,"domain_scores_codex":[0.977741,0.007931681,0.002618893,0.002649534,0.008520926,0.0005379845],"domain_scores_gemma":[0.9877366,0.008173077,0.0006946042,0.001505356,0.001592512,0.0002978814],"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":[0.00008579978,0.0001661975,0.001583165,0.007680964,0.0004690434,0.000521581,0.001560269,0.01060497,0.0008568575,0.4062727,0.1222358,0.4479627],"study_design_scores_gemma":[0.00004794879,0.00007454823,0.0005915709,0.002800975,0.00007582336,0.0008281257,0.0005025778,0.01535654,0.0005857597,0.5343273,0.4447371,0.00007173193],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.001543738,0.2261644,0.6997766,0.01724962,0.004029798,0.00158659,0.002693799,0.002941851,0.04401358],"genre_scores_gemma":[0.03527581,0.2122546,0.7143649,0.006697761,0.007685497,0.004063362,0.005047382,0.0004884694,0.01412234],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01173126,"threshold_uncertainty_score":0.06088519,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740924709","doi":"10.1145/3068335","title":"DBSCAN Revisited, Revisited","year":2017,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2625,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Computer science; DBSCAN; Data mining; Heuristics; Information retrieval; Algorithm; Artificial intelligence; Cluster analysis","authors":[{"name":"Erich Schubert","is_ca":false},{"name":"Jörg Sander","is_ca":true},{"name":"Martin Ester","is_ca":true},{"name":"Hans Peter Kriegel","is_ca":false},{"name":"Xiaowei Xu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03953632886572851,"gpt":0.2875278022523509,"spread":0.2479914733866224,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02027269,0.001379363,0.002766035,0.007284625,0.002735003,0.01428949,0.006094941,0.005047181,0.005576116],"category_scores_gemma":[0.07993302,0.001349472,0.001376653,0.02133653,0.00722649,0.01425294,0.004312376,0.01246938,0.002477925],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007508904,"about_ca_system_score_gemma":0.0070958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02380819,"about_ca_topic_score_gemma":0.02336793,"domain_scores_codex":[0.9756469,0.008321157,0.001247288,0.00279739,0.01113803,0.0008492405],"domain_scores_gemma":[0.9648389,0.01724369,0.0009839458,0.005956223,0.009832587,0.001144631],"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":[0.0005875294,0.0000773709,0.001860643,0.0003581035,0.0001921986,0.0001801117,0.0004659012,0.03215596,0.0005022414,0.4700712,0.110616,0.3829328],"study_design_scores_gemma":[0.0001149713,0.0001209845,0.0007180002,0.0003255919,0.00007723065,0.0009507195,0.0008897463,0.2602594,0.004560767,0.5548252,0.1770125,0.0001449492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02425857,0.06059712,0.7293007,0.1236185,0.00963214,0.0001707081,0.001193943,0.004991226,0.04623705],"genre_scores_gemma":[0.3181241,0.02714698,0.6015165,0.0228382,0.005715937,0.0002135717,0.001451698,0.001684653,0.02130829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02380819,"threshold_uncertainty_score":0.1072135,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166470254","doi":"10.1145/1963192.1963217","title":"CELF++","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":857,"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":"Heuristics; Computer science; Maximization; Greedy algorithm; Simple (philosophy); Node (physics); Set (abstract data type); Mathematical optimization; Monte Carlo method; Quadratic equation; Algorithm; Mathematics","authors":[{"name":"Amit Goyal","is_ca":true},{"name":"Wei Lu","is_ca":true},{"name":"Laks V. S. Lakshmanan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04872163073464558,"gpt":0.1971299117888966,"spread":0.148408281054251,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009047828,0.001768497,0.001050428,0.001483215,0.001157576,0.002305102,0.004229539,0.001398349,0.06399979],"category_scores_gemma":[0.004268135,0.0006724781,0.001272904,0.0016164,0.0006635816,0.003201952,0.003069949,0.001586386,0.0419457],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001740712,"about_ca_system_score_gemma":0.001821439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005917178,"about_ca_topic_score_gemma":0.007207975,"domain_scores_codex":[0.9987896,0.0001640753,0.00006171764,0.0003444664,0.0003570606,0.0002830722],"domain_scores_gemma":[0.9980925,0.0005109937,0.00007868289,0.0007346565,0.0004670195,0.000116241],"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":[0.001403927,0.0004684755,0.001498841,0.0007004419,0.00006641584,0.0002778346,0.0001194998,0.02631439,0.006850914,0.03463017,0.3410054,0.5866636],"study_design_scores_gemma":[0.0009380186,0.00045445,0.0008661406,0.0001266411,0.00006541675,0.001240687,0.00009939064,0.2686917,0.01847556,0.05147297,0.6574373,0.0001318157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02068347,0.001620897,0.6339163,0.002228702,0.001010874,0.001222388,0.01725266,0.2103424,0.1117224],"genre_scores_gemma":[0.113694,0.0006425483,0.7771363,0.002090118,0.000252592,0.001148415,0.03057355,0.01361451,0.060848],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06399979,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009688537","doi":"10.1145/1391729.1391730","title":"A survey of top- <i>k</i> query processing techniques in relational database systems","year":2008,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":834,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Relational database; Database; Information retrieval; Dimension (graph theory); XML database; XML; Query optimization; Query language; Sargable; Domain (mathematical analysis); View; Database design; Web search query; World Wide Web; Search engine","authors":[{"name":"Ihab F. Ilyas","is_ca":true},{"name":"George Beskales","is_ca":true},{"name":"Mohamed A. Soliman","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1129110638023711,"gpt":0.3416350848872731,"spread":0.228724021084902,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003262497,0.001037455,0.001656648,0.004693703,0.00106449,0.003160234,0.003567164,0.001653815,0.004043497],"category_scores_gemma":[0.006518635,0.001065472,0.001450827,0.01432142,0.0009579508,0.007446582,0.001301243,0.002138832,0.004296133],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001404565,"about_ca_system_score_gemma":0.00259375,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002396486,"about_ca_topic_score_gemma":0.001749692,"domain_scores_codex":[0.9962909,0.0005272554,0.000469872,0.0005692238,0.001884077,0.0002586307],"domain_scores_gemma":[0.9953159,0.002492228,0.0002361555,0.0004991551,0.001343088,0.0001134772],"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":[0.00007697017,0.0001825748,0.00153086,0.008231716,0.0001013578,0.0001891942,0.0002907188,0.002800604,0.00315598,0.03006595,0.02721896,0.9261552],"study_design_scores_gemma":[0.00007558941,0.0004598808,0.0046723,0.003618283,0.000329653,0.005452487,0.0008208776,0.03236962,0.009090717,0.06077152,0.8821216,0.0002174287],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005359139,0.8102048,0.163071,0.002982723,0.0006467254,0.0002822567,0.0003827857,0.0009531224,0.01611737],"genre_scores_gemma":[0.03365676,0.7828611,0.1748392,0.001111038,0.001637467,0.0002112953,0.001015145,0.0001921203,0.004475875],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.004693703,"threshold_uncertainty_score":0.01725399,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110557355","doi":"10.1007/s007780100049","title":"Approximate query processing using wavelets","year":2001,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":477,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Bell (Canada)","funders":"","keywords":"Computer science; Wavelet; Query optimization; Data mining; Tuple; Histogram; Algorithm; Artificial intelligence; Mathematics; Image (mathematics)","authors":[{"name":"Kaushik Chakrabarti","is_ca":false},{"name":"Minos Garofalakis","is_ca":true},{"name":"Rajeev Rastogi","is_ca":true},{"name":"Kyuseok Shim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0412518917975479,"gpt":0.2701677799750619,"spread":0.228915888177514,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002698724,0.0007566524,0.00243333,0.001933353,0.0008061604,0.00291935,0.001408989,0.00108481,0.002794555],"category_scores_gemma":[0.01294768,0.0007078713,0.001120851,0.004012499,0.001021991,0.004041892,0.002198686,0.002001568,0.001187813],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008298015,"about_ca_system_score_gemma":0.001185185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002402531,"about_ca_topic_score_gemma":0.001779978,"domain_scores_codex":[0.9965302,0.00091922,0.0002913128,0.0004194638,0.001517447,0.0003223026],"domain_scores_gemma":[0.9946956,0.002182281,0.0002738486,0.00174522,0.0009329576,0.0001701513],"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":[0.001878235,0.0002778685,0.003008145,0.0002992157,0.0002790189,0.0002583879,0.0003515654,0.2500666,0.03441801,0.1139692,0.0125973,0.5825965],"study_design_scores_gemma":[0.00002869128,0.00006702182,0.0001983092,0.000007317522,0.00002080276,0.00007342384,0.00004600806,0.9685407,0.003322681,0.02622098,0.001462427,0.00001156798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02235579,0.00068946,0.974838,0.0002732595,0.0001211508,0.00002979667,0.00009092833,0.0007114651,0.0008901074],"genre_scores_gemma":[0.4244093,0.001185465,0.56917,0.0002105767,0.0003757897,0.0001452152,0.0008243181,0.0002669368,0.003412316],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00291935,"threshold_uncertainty_score":0.01427239,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1993378086","doi":"10.1145/2806416.2806493","title":"A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Nvidia","keywords":"Computer science; Encoder; Generative grammar; Context (archaeology); Artificial intelligence; Generative model; Natural language processing","authors":[{"name":"Alessandro Sordoni","is_ca":true},{"name":"Yoshua Bengio","is_ca":true},{"name":"Hossein Vahabi","is_ca":false},{"name":"Christina Lioma","is_ca":false},{"name":"Jakob Grue Simonsen","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06969257043282508,"gpt":0.3021491390428253,"spread":0.2324565686100002,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009703735,0.0008971888,0.001223769,0.0006452301,0.0004118071,0.0008598656,0.002138163,0.001370337,0.002938984],"category_scores_gemma":[0.005184024,0.0006977128,0.0007715976,0.0009170408,0.000640537,0.001574198,0.001011782,0.001670536,0.001645591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009294132,"about_ca_system_score_gemma":0.001624891,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0123668,"about_ca_topic_score_gemma":0.01935183,"domain_scores_codex":[0.999347,0.0002101675,0.00004626716,0.000178815,0.0001427183,0.00007508806],"domain_scores_gemma":[0.9976405,0.001624506,0.0001035907,0.0002168757,0.0003262447,0.00008840187],"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":[0.0009740118,0.0003446393,0.002943976,0.0003928415,0.0001689038,0.0005417179,0.0005381213,0.5612447,0.02892229,0.03477764,0.01436279,0.3547884],"study_design_scores_gemma":[0.00001556228,0.00002968503,0.00007393767,0.000005130696,0.00001639277,0.0000465481,0.000007740244,0.9934791,0.001666001,0.003977383,0.0006729155,0.000009546519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02346683,0.0009028175,0.9681705,0.0005671237,0.0001022906,0.00009551403,0.0005888235,0.004150403,0.001955722],"genre_scores_gemma":[0.6452674,0.0006998483,0.3411572,0.0005747725,0.0001718386,0.000322549,0.001751618,0.0004439505,0.0096108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0123668,"threshold_uncertainty_score":0.02458966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1999824796","doi":"10.1145/1102351.1102385","title":"Near-optimal sensor placements in Gaussian processes","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":467,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Intel Corporation","keywords":"Mutual information; Computer science; Gaussian; Entropy (arrow of time); Gaussian process; Algorithm; Global Positioning System; Variance (accounting); Task (project management); Mathematical optimization; Artificial intelligence; Mathematics","authors":[{"name":"Carlos Guestrin","is_ca":false},{"name":"Andreas Krause","is_ca":false},{"name":"Ajit Paul Singh","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01448665043394406,"gpt":0.2504545708919586,"spread":0.2359679204580145,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003052429,0.0008076087,0.001641386,0.001090616,0.0008673994,0.0009927267,0.001293441,0.001409755,0.001200351],"category_scores_gemma":[0.007892799,0.000799922,0.0007297714,0.001689493,0.001752465,0.00180119,0.001867546,0.001068517,0.0002369525],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001379727,"about_ca_system_score_gemma":0.001487609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005193249,"about_ca_topic_score_gemma":0.006963868,"domain_scores_codex":[0.998719,0.0005483124,0.00006182167,0.0002892524,0.0001957742,0.0001859468],"domain_scores_gemma":[0.9958846,0.003032771,0.0004467387,0.0002636493,0.0002030059,0.0001692309],"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":[0.0001160236,0.00004641084,0.0007915313,0.00003097325,0.00002112877,0.00006347725,0.0001026558,0.9703805,0.001185538,0.008803017,0.0005138315,0.01794492],"study_design_scores_gemma":[0.00001901387,0.00002387117,0.0001384204,0.000002784444,0.000003679257,0.00001443319,0.00002283023,0.9874985,0.0004787683,0.01166696,0.0001261945,0.00000452388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1090545,0.0002356337,0.8888803,0.0003327377,0.00001309353,0.00005481399,0.000113068,0.0004270105,0.000888995],"genre_scores_gemma":[0.7302139,0.0001564029,0.2680374,0.0001099711,0.0000290067,0.0001181922,0.0002557847,0.00009739726,0.0009819046],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005193249,"threshold_uncertainty_score":0.01614296,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138414767","doi":"","title":"Probabilistic skylines on uncertain data","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":461,"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":"Skyline; Uncertain data; Probabilistic logic; Computer science; Data mining; Benchmark (surveying); Object (grammar); Set (abstract data type); Data set; Artificial intelligence","authors":[{"name":"Jian Pei","is_ca":true},{"name":"Bin Jiang","is_ca":false},{"name":"Xuemin Lin","is_ca":false},{"name":"Yidong Yuan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.08583155124540513,"gpt":0.3233955027557575,"spread":0.2375639515103523,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004407465,0.001127254,0.002070891,0.003921408,0.001551685,0.003459882,0.002297885,0.001904817,0.001465142],"category_scores_gemma":[0.02636332,0.001296019,0.001941618,0.00702128,0.001871534,0.009824344,0.002514064,0.002442348,0.0006984337],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001677526,"about_ca_system_score_gemma":0.001114797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006422112,"about_ca_topic_score_gemma":0.005951278,"domain_scores_codex":[0.9940975,0.002262639,0.0004795503,0.00131671,0.001568416,0.0002752164],"domain_scores_gemma":[0.976772,0.01502021,0.002932734,0.003077719,0.001819919,0.0003773013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0005850208,0.00007539529,0.01592119,0.0007053145,0.0003267315,0.0006908192,0.0008686275,0.7087315,0.005257751,0.0804782,0.0129695,0.1733899],"study_design_scores_gemma":[0.00002126274,0.0000497851,0.001907937,0.00005054259,0.00003734037,0.0003100922,0.0002066536,0.920188,0.002170478,0.06769123,0.007331964,0.00003482667],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02531887,0.001475715,0.9685796,0.0007694929,0.0000436747,0.0001295923,0.00167584,0.001039501,0.0009677452],"genre_scores_gemma":[0.3779213,0.001801946,0.6128651,0.0002976443,0.0003296751,0.0002714759,0.005087429,0.0002471877,0.001178263],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006422112,"threshold_uncertainty_score":0.02330917,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3138447845","doi":"10.1016/s0925-7721(02)00093-7","title":"Computing contour trees in all dimensions","year":2002,"lang":"en","type":"article","venue":"Computational Geometry","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":460,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"University of North Carolina at Chapel Hill; Natural Sciences and Engineering Research Council of Canada; University of British Columbia","keywords":"Simple (philosophy); Computer science; Contour line; Algorithm; Mathematics; Artificial intelligence; Cartography; Geography","authors":[{"name":"Hamish Carr","is_ca":true},{"name":"Jack Snoeyink","is_ca":false},{"name":"Ulrike Axen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04481388461551654,"gpt":0.2730690683067274,"spread":0.2282551836912108,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008292071,0.0006596583,0.001279406,0.001932447,0.001004916,0.003467733,0.001455477,0.0009760904,0.005385449],"category_scores_gemma":[0.007557273,0.0007632446,0.0006203008,0.003191063,0.00106095,0.005400366,0.002495886,0.001386037,0.001388451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006156068,"about_ca_system_score_gemma":0.0007756648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001860953,"about_ca_topic_score_gemma":0.003060068,"domain_scores_codex":[0.9993332,0.0001015511,0.00007052905,0.000144642,0.0002575826,0.00009243809],"domain_scores_gemma":[0.9970059,0.001330577,0.0002256686,0.0008000748,0.0004556919,0.0001821127],"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":[0.0004666905,0.0001224834,0.005357102,0.0004508989,0.00009372753,0.0002478052,0.000632905,0.2121231,0.0107364,0.2951135,0.01223017,0.4624252],"study_design_scores_gemma":[0.00003364111,0.00006022469,0.0007096301,0.0000402727,0.00003600415,0.0001224226,0.0001247135,0.6350014,0.005699695,0.3487515,0.009400516,0.00002007338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08574105,0.0008702689,0.9049456,0.0003525676,0.00009984215,0.00005441053,0.000554489,0.001701182,0.005680603],"genre_scores_gemma":[0.3707682,0.0009743756,0.6217643,0.00009092058,0.00008809056,0.0000799154,0.001396578,0.0004871991,0.004350392],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005385449,"threshold_uncertainty_score":0.01801616,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2138271690","doi":"10.1109/icde.2007.367935","title":"Top-k Query Processing in Uncertain Databases","year":2007,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":428,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Tuple; Computer science; Semantics (computer science); Probabilistic logic; Construct (python library); Database; Query language; Materialized view; Query optimization; Space (punctuation); Theoretical computer science; Information retrieval; Data mining; View; Programming language; Artificial intelligence; Mathematics; Database design","authors":[{"name":"Mohamed A. Soliman","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true},{"name":"Kevin Chen–Chuan Chang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03869003660168605,"gpt":0.307185340866784,"spread":0.2684953042650979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004960571,0.0008964305,0.002473876,0.001288241,0.002378618,0.006705988,0.003274529,0.001915034,0.002712543],"category_scores_gemma":[0.02107351,0.0009380365,0.002004276,0.003798259,0.002554836,0.01151896,0.004917808,0.002792988,0.0008073563],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001669969,"about_ca_system_score_gemma":0.002175042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003985892,"about_ca_topic_score_gemma":0.005390723,"domain_scores_codex":[0.9916791,0.002702104,0.001051506,0.001474489,0.002412574,0.0006801331],"domain_scores_gemma":[0.9865562,0.00783266,0.0009799878,0.003192014,0.001143989,0.0002952036],"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":[0.0008739089,0.0002465839,0.002822457,0.0007667755,0.0003122126,0.0006709617,0.001560146,0.3793276,0.008131818,0.350167,0.01140848,0.243712],"study_design_scores_gemma":[0.00002909066,0.00005667652,0.0002160018,0.00002504622,0.00005230895,0.0002667432,0.0003046493,0.6771826,0.003972983,0.3150821,0.002760672,0.00005108015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01580681,0.0003544264,0.9806315,0.0006553706,0.00003488864,0.00008037227,0.0002304751,0.0008718481,0.001334263],"genre_scores_gemma":[0.5107709,0.0006143379,0.4857471,0.0003089826,0.0001487179,0.0001290136,0.0005900173,0.0002244509,0.00146657],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006705988,"threshold_uncertainty_score":0.02623427,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135843591","doi":"10.1145/511446.511489","title":"Probabilistic query expansion using query logs","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":427,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Sargable; Query optimization; Query expansion; Computer science; Probabilistic logic; Query language; RDF query language; Web search query; Web query classification; Query by Example; Boolean conjunctive query; Information retrieval; Data mining; Artificial intelligence; Search engine","authors":[{"name":"Hang Cui","is_ca":false},{"name":"Ji-Rong Wen","is_ca":false},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Wei‐Ying Ma","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0558195065342248,"gpt":0.2403360045591247,"spread":0.1845164980248999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004130834,0.001529654,0.001606328,0.003454783,0.0007179966,0.001585986,0.001818159,0.0009773071,0.001843661],"category_scores_gemma":[0.02310297,0.0007421302,0.0009653515,0.003403539,0.0008387431,0.004988394,0.001534879,0.001583472,0.001023743],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006054761,"about_ca_system_score_gemma":0.001194297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003298987,"about_ca_topic_score_gemma":0.003044646,"domain_scores_codex":[0.9940324,0.00239364,0.0004001761,0.0007283003,0.002221975,0.0002234871],"domain_scores_gemma":[0.9836773,0.01169971,0.0008690848,0.001737241,0.00181811,0.0001986673],"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":[0.001488505,0.0008097534,0.008398728,0.000768265,0.0002344647,0.0006948563,0.0008410193,0.1165712,0.06439256,0.01795639,0.0166792,0.771165],"study_design_scores_gemma":[0.0001059927,0.0002214236,0.00180667,0.00003073777,0.00009111105,0.000563607,0.0001293221,0.9604158,0.01526549,0.01399903,0.007277913,0.00009295334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02899498,0.001204552,0.9598117,0.0004759491,0.00006916995,0.0004409288,0.0004770813,0.006747653,0.001777948],"genre_scores_gemma":[0.524208,0.001292095,0.4663219,0.0003898353,0.0003239198,0.0009959579,0.002919786,0.0004753555,0.003073057],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004130834,"threshold_uncertainty_score":0.02184623,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098416578","doi":"10.1145/335191.335419","title":"Efficient and extensible algorithms for multi query optimization","year":2000,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":409,"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; Query optimization; Heuristics; Benchmark (surveying); Overhead (engineering); Greedy algorithm; Heuristic; Algorithm; Data mining; Artificial intelligence","authors":[{"name":"Prasan Roy","is_ca":false},{"name":"S. Seshadri","is_ca":true},{"name":"S. Sudarshan","is_ca":false},{"name":"Siddhesh Bhobe","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04290867931345283,"gpt":0.2807725920124819,"spread":0.2378639126990291,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003566887,0.00293442,0.001710745,0.002522753,0.001004046,0.002652542,0.004536734,0.001996858,0.004806415],"category_scores_gemma":[0.01189258,0.001161961,0.001748612,0.004260821,0.001253707,0.004340238,0.003392059,0.003118163,0.002391477],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001727788,"about_ca_system_score_gemma":0.002300402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005337036,"about_ca_topic_score_gemma":0.006277152,"domain_scores_codex":[0.9957861,0.0009963744,0.0005028958,0.0007386413,0.001511982,0.0004639999],"domain_scores_gemma":[0.9935731,0.003508709,0.0004412684,0.001677369,0.0006742534,0.0001251907],"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":[0.000404842,0.0004769544,0.001650554,0.0003625813,0.0001301768,0.0001441905,0.0002368805,0.3925352,0.006174304,0.03843208,0.01470718,0.5447451],"study_design_scores_gemma":[0.0001300871,0.00007580968,0.0002141489,0.00002491667,0.00003732763,0.000102654,0.00006868371,0.9586068,0.002869847,0.03272983,0.005112834,0.00002704596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004667192,0.00056319,0.9861907,0.0001724722,0.0000512204,0.0002032531,0.0001711205,0.005504806,0.002475924],"genre_scores_gemma":[0.07820176,0.0005470585,0.9176114,0.0001798886,0.00009716884,0.000484605,0.0006516078,0.0006562076,0.001570295],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005337036,"threshold_uncertainty_score":0.01886374,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1544455437","doi":"","title":"Proceedings of the 17th ACM conference on Information and knowledge management","year":2008,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":407,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval; World Wide Web; Data science","authors":[{"name":"James G. Shanahan","is_ca":false},{"name":"Sihem Amer-Yahia","is_ca":false},{"name":"Ioana Manolescu","is_ca":false},{"name":"Yi Zhang","is_ca":false},{"name":"David A. Evans","is_ca":false},{"name":"Alek Kolcz","is_ca":false},{"name":"Key‐Sun Choi","is_ca":false},{"name":"Abdur Chowdury","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02828568575252903,"gpt":0.2294291208878653,"spread":0.2011434351353363,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005278061,0.001424552,0.00250346,0.002542526,0.001704951,0.01152933,0.002732354,0.003031617,0.1526206],"category_scores_gemma":[0.01263145,0.0006127774,0.001097891,0.003622644,0.001806872,0.01071224,0.004674252,0.00524709,0.08739667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366038,"about_ca_system_score_gemma":0.004443785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003596093,"about_ca_topic_score_gemma":0.003804002,"domain_scores_codex":[0.9952212,0.001247352,0.0005290806,0.0006112553,0.002059847,0.0003312806],"domain_scores_gemma":[0.9914799,0.002343189,0.0003881592,0.00151916,0.002729179,0.001540368],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001057361,0.0001334367,0.0009564154,0.0004779631,0.0001049306,0.0001274581,0.0002436975,0.0001941344,0.000904425,0.01088978,0.7719424,0.2139196],"study_design_scores_gemma":[0.0000105022,0.00002685415,0.0004321692,0.0002183574,0.00002897278,0.0001103069,0.0001217812,0.0005310421,0.0001758986,0.004509596,0.9938186,0.00001594445],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.007974539,0.1637332,0.09885882,0.08244898,0.1219965,0.001315361,0.009456987,0.005446611,0.5087691],"genre_scores_gemma":[0.04126769,0.1266267,0.06440855,0.01634431,0.02362395,0.001061432,0.03158807,0.001637757,0.6934416],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1526206,"threshold_uncertainty_score":0.5105668,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143682328","doi":"10.1007/s00778-004-0128-2","title":"Supporting top-k join queries in relational databases","year":2004,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":387,"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":"Joins; Computer science; Join (topology); Sort-merge join; Query optimization; Ranking (information retrieval); Hash join; Database; Relational database; Heuristic; Query language; Sargable; Information retrieval; Rank (graph theory); Heuristics; Relational algebra; Query expansion; Theoretical computer science; Web search query; Search engine; Programming language; Mathematics; Artificial intelligence","authors":[{"name":"Ihab F. Ilyas","is_ca":true},{"name":"WalidG. Aref","is_ca":false},{"name":"AhmedK. Elmagarmid","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04003804845750331,"gpt":0.2958259358899701,"spread":0.2557878874324668,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005228457,0.001087648,0.002600929,0.001444186,0.00243184,0.008435749,0.005038479,0.002322149,0.005461701],"category_scores_gemma":[0.024543,0.001496007,0.001209621,0.003480641,0.002048505,0.01740723,0.006402438,0.002378959,0.003628027],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009942695,"about_ca_system_score_gemma":0.002183656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003360765,"about_ca_topic_score_gemma":0.004614528,"domain_scores_codex":[0.9910232,0.001505855,0.001461646,0.001354981,0.003473944,0.001180373],"domain_scores_gemma":[0.9746523,0.01198386,0.00128786,0.008777367,0.002372137,0.0009265894],"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":[0.009171318,0.001244991,0.03337821,0.002790584,0.0007308449,0.00222956,0.004358225,0.08303259,0.07917921,0.1042169,0.05763362,0.622034],"study_design_scores_gemma":[0.0005810113,0.0006774622,0.003055695,0.0001885187,0.0005458107,0.002211432,0.001933504,0.6167038,0.0685297,0.2791406,0.02617003,0.0002623973],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2319163,0.003700186,0.7254238,0.00212552,0.000427445,0.0002326098,0.002511929,0.02190468,0.01175753],"genre_scores_gemma":[0.7734467,0.001022039,0.2171907,0.0003451017,0.0002487903,0.0000756262,0.002636575,0.001055536,0.00397895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008435749,"threshold_uncertainty_score":0.02765107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1517348552","doi":"","title":"Maximal vector computation in large data sets","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":373,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Curse of dimensionality; Convex hull; Computer science; Set (abstract data type); Computation; Field (mathematics); Algorithm; Running time; Mathematics; Regular polygon; Data mining; Artificial intelligence","authors":[{"name":"Parke Godfrey","is_ca":true},{"name":"J. Ryan Shipley","is_ca":false},{"name":"Jarek Gryz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04080861114137971,"gpt":0.2986350357834028,"spread":0.2578264246420231,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004350649,0.001203317,0.002399388,0.002530894,0.00218912,0.004513795,0.00288161,0.001303433,0.00547983],"category_scores_gemma":[0.02337268,0.001121279,0.001434641,0.006453233,0.001973394,0.01008132,0.005557161,0.002073049,0.00188785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00158485,"about_ca_system_score_gemma":0.002128107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003233821,"about_ca_topic_score_gemma":0.005167018,"domain_scores_codex":[0.9951667,0.001376043,0.0005884602,0.001079734,0.001412893,0.000376215],"domain_scores_gemma":[0.9884351,0.006015866,0.0007450515,0.003143687,0.001197295,0.000462929],"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":[0.001275423,0.0002960356,0.009585002,0.00118958,0.0003534768,0.0004494832,0.001195401,0.285795,0.00723701,0.1280179,0.03729445,0.5273113],"study_design_scores_gemma":[0.0001062191,0.0000813274,0.0008134943,0.00006178276,0.0000398378,0.0001961828,0.0003152908,0.8186747,0.006507737,0.1654635,0.00771369,0.00002623878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06474151,0.001113222,0.9189473,0.001172872,0.0001400351,0.0002041287,0.001327781,0.007660994,0.004692158],"genre_scores_gemma":[0.2725963,0.0005385151,0.7191778,0.0002373656,0.000191397,0.0004033044,0.003460357,0.0006136976,0.002781368],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00547983,"threshold_uncertainty_score":0.0230087,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2117379916","doi":"10.1109/icde.2005.92","title":"Monitoring k-Nearest Neighbor Queries over Moving Objects","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":307,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Search engine indexing; Computer science; Scalability; k-nearest neighbors algorithm; Grid; Data mining; Tree (set theory); Best bin first; Nearest neighbor search; R-tree; Object (grammar); Spatial database; Artificial intelligence; Spatial analysis; Database; Mathematics","authors":[{"name":"Xiaohui Yu","is_ca":true},{"name":"Kevin Pu","is_ca":true},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01336887839657592,"gpt":0.2457943660586419,"spread":0.232425487662066,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00190275,0.0005958396,0.001506262,0.001164935,0.0009538371,0.001265629,0.002065306,0.001196858,0.0004655487],"category_scores_gemma":[0.01159286,0.0003695501,0.0003051574,0.003074684,0.0004825881,0.003604764,0.001567043,0.0006475918,0.0004424706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006015016,"about_ca_system_score_gemma":0.0007873785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005444654,"about_ca_topic_score_gemma":0.006434517,"domain_scores_codex":[0.99768,0.0005079486,0.0002297509,0.0005687528,0.0008611244,0.0001524202],"domain_scores_gemma":[0.9921846,0.003826511,0.001018252,0.001620393,0.001075531,0.0002747927],"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":[0.001457929,0.000674821,0.05375333,0.0005090922,0.0002889951,0.0006635211,0.0007734673,0.4061688,0.04190877,0.006842628,0.008329983,0.4786287],"study_design_scores_gemma":[0.00003808688,0.0001225508,0.005335782,0.000009903931,0.00002876732,0.0003390467,0.000289034,0.9756243,0.01076388,0.005436923,0.001981201,0.00003041356],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4108094,0.001626829,0.5795722,0.0004831239,0.0001050616,0.000215106,0.0009803242,0.003654991,0.002552978],"genre_scores_gemma":[0.8591861,0.000534317,0.1383342,0.00006095121,0.00006021617,0.0000905707,0.001077873,0.00007325949,0.0005826206],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005444654,"threshold_uncertainty_score":0.01082593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2168503413","doi":"10.1109/icde.2000.839397","title":"DB2 advisor: an optimizer smart enough to recommend its own indexes","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":290,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; IBM (Canada)","funders":"","keywords":"Knapsack problem; Computer science; Index (typography); Selection (genetic algorithm); Quality (philosophy); Relational database management system; Interface (matter); Data mining; World Wide Web; Algorithm; Artificial intelligence; Relational database; Operating system","authors":[{"name":"Gary Valentin","is_ca":true},{"name":"Michael J. Zuliani","is_ca":true},{"name":"Daniel C. Zilio","is_ca":true},{"name":"Guy M. Lohman","is_ca":false},{"name":"Alan Skelley","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04929654506499023,"gpt":0.2521579843231119,"spread":0.2028614392581217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002830487,0.001285026,0.001251535,0.0008257031,0.0006588312,0.002493311,0.001761827,0.0009409102,0.00740171],"category_scores_gemma":[0.00743965,0.0008649078,0.0004740217,0.0008920179,0.0004259506,0.003024205,0.001407542,0.001743936,0.004662519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005674073,"about_ca_system_score_gemma":0.001148201,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003907838,"about_ca_topic_score_gemma":0.004130316,"domain_scores_codex":[0.9982677,0.0003706584,0.0001257781,0.0003285493,0.0007798277,0.0001275259],"domain_scores_gemma":[0.9976661,0.0005203184,0.0001186417,0.001049918,0.0004623129,0.000182665],"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":[0.002615956,0.0005118069,0.00907537,0.0005091297,0.000329591,0.0001743991,0.0004331743,0.06496795,0.05827973,0.01139518,0.1185203,0.7331874],"study_design_scores_gemma":[0.0003632887,0.0003197925,0.003547252,0.00004924128,0.00009919635,0.0002091239,0.00008950812,0.808321,0.07623388,0.006489524,0.1041486,0.0001295933],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05129114,0.001204766,0.7751737,0.0009773376,0.0002724154,0.000391812,0.001891077,0.1481565,0.02064126],"genre_scores_gemma":[0.2428253,0.0005945556,0.724879,0.0007106547,0.0001919327,0.000268248,0.003462426,0.01435067,0.01271726],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00740171,"threshold_uncertainty_score":0.02476114,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110610722","doi":"10.1145/872757.872798","title":"Mapping data in peer-to-peer systems","year":2003,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":253,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Semantic mapping; Data mapping; Semantics (computer science); Peer-to-peer; Information retrieval; Data sharing; Listing (finance); Data exchange; Theoretical computer science; Data mining; Database; Programming language; World Wide Web","authors":[{"name":"Anastasios Kementsietsidis","is_ca":true},{"name":"Marcelo Arenas","is_ca":true},{"name":"Renée J. Miller","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06195602089747872,"gpt":0.281265200726068,"spread":0.2193091798285893,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008936899,0.001017408,0.002240965,0.002831918,0.004329105,0.007371242,0.004666781,0.003789118,0.003415873],"category_scores_gemma":[0.03309973,0.001415839,0.001352491,0.007678919,0.003311489,0.0175092,0.007579195,0.002924052,0.001123237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001762503,"about_ca_system_score_gemma":0.002585966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003745782,"about_ca_topic_score_gemma":0.002539515,"domain_scores_codex":[0.9896694,0.004069031,0.001146157,0.001592595,0.003036381,0.0004864686],"domain_scores_gemma":[0.9807365,0.01197788,0.001267761,0.004049629,0.001338514,0.0006297193],"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":[0.0002579984,0.000163587,0.002865863,0.0009366572,0.0002153314,0.001565043,0.002082782,0.2486909,0.003251927,0.5875598,0.007767876,0.1446422],"study_design_scores_gemma":[0.00006781786,0.00007557595,0.000279759,0.00009521344,0.00008119546,0.0005461407,0.0008289728,0.301494,0.004698365,0.648038,0.04371766,0.0000772629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01546124,0.001125654,0.9781029,0.001303115,0.0001481604,0.0003102078,0.0003165992,0.0007078801,0.002524306],"genre_scores_gemma":[0.2116013,0.001884575,0.7814501,0.0002902132,0.0001769547,0.0004670591,0.0009061909,0.0001821183,0.003041516],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008936899,"threshold_uncertainty_score":0.04726338,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2127782281","doi":"","title":"Catching the best views of skyline: a semantic approach based on decisive subspaces","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":245,"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":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Set (abstract data type); Theoretical computer science; Object (grammar); Space (punctuation); Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","authors":[{"name":"Jian Pei","is_ca":true},{"name":"Wen Jin","is_ca":true},{"name":"Martin Ester","is_ca":true},{"name":"Yufei Tao","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03357830335054178,"gpt":0.2713407237238883,"spread":0.2377624203733466,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001646471,0.0006794675,0.001081164,0.003828106,0.001680903,0.003341598,0.001541059,0.001020528,0.002747908],"category_scores_gemma":[0.005588033,0.0005222178,0.001654413,0.004188828,0.002842488,0.01123857,0.003491506,0.001545857,0.0004970282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001003583,"about_ca_system_score_gemma":0.001116185,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003568225,"about_ca_topic_score_gemma":0.003802595,"domain_scores_codex":[0.9983457,0.0004846017,0.0001483408,0.0004015285,0.0004336787,0.0001862137],"domain_scores_gemma":[0.9971378,0.0007292784,0.0004432845,0.0007603325,0.0006591158,0.0002702685],"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":[0.0003004511,0.00007694202,0.003530826,0.0002934885,0.0001129796,0.0002532271,0.002056189,0.05019066,0.005940541,0.8023093,0.004899906,0.1300354],"study_design_scores_gemma":[0.00004316587,0.0001155311,0.001114947,0.0000884683,0.00008878169,0.0002685823,0.001433993,0.3789409,0.005975251,0.5873163,0.02452714,0.00008710004],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01592077,0.0002452098,0.9803453,0.0002675807,0.00002519983,0.00005904797,0.0002729952,0.0004479066,0.002415943],"genre_scores_gemma":[0.3204093,0.0003915732,0.676333,0.0001075054,0.00008949673,0.0001409066,0.000816063,0.0001819748,0.001530137],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003828106,"threshold_uncertainty_score":0.009192705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1991782162","doi":"10.1111/1467-9671.00127","title":"A Perspective on the Fundamentals of Fuzzy Sets and their Use in Geographic Information Systems","year":2003,"lang":"en","type":"article","venue":"Transactions in GIS","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Fuzzy logic; Data mining; Computer science; Geographic information system; Fuzzy set; Sophistication; Perspective (graphical); Relation (database); AM/FM/GIS; Fuzzy set operations; GIS applications; Defuzzification; Artificial intelligence; Fuzzy number; Geography; Cartography","authors":[{"name":"Vincent Β. Robinson","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02144806511388659,"gpt":0.235941126157451,"spread":0.2144930610435644,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003854508,0.001104924,0.001091466,0.004424022,0.002113849,0.00603394,0.001815191,0.003887749,0.003958506],"category_scores_gemma":[0.004703948,0.0005845638,0.001089674,0.004630731,0.009778911,0.006115534,0.001605222,0.00511844,0.001267713],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003556578,"about_ca_system_score_gemma":0.001927831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004669856,"about_ca_topic_score_gemma":0.003076143,"domain_scores_codex":[0.9973459,0.001347327,0.0002051043,0.0002266497,0.0007680319,0.0001071092],"domain_scores_gemma":[0.9964502,0.002748872,0.0001727313,0.0001469202,0.000391797,0.00008953201],"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":[0.000004656868,0.00001210462,0.00007888876,0.0001702324,0.000006743855,0.0001228159,0.0006289926,0.001606699,0.0001554852,0.9760759,0.003725812,0.01741165],"study_design_scores_gemma":[0.000004699218,0.00003934791,0.0002257776,0.0005870067,0.000006638973,0.0002547063,0.0005427992,0.002928678,0.00016289,0.8421155,0.153107,0.00002504561],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004473582,0.1902865,0.5373638,0.05341156,0.005882383,0.0002307683,0.0004187785,0.0002057479,0.2077269],"genre_scores_gemma":[0.2386802,0.278472,0.4310141,0.01174461,0.01336415,0.0008495341,0.0003010072,0.0001089951,0.02546552],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00603394,"threshold_uncertainty_score":0.02580494,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2003043371","doi":"10.1080/03461230601110447","title":"On composite lognormal-Pareto models","year":2007,"lang":"en","type":"article","venue":"Scandinavian Actuarial Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pareto principle; Log-normal distribution; Mathematics; Econometrics; Composite number; Pareto distribution; Statistics; Applied mathematics; Computer science; Mathematical optimization; Mathematical economics; Algorithm","authors":[{"name":"David P. M. Scollnik","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01729185838393545,"gpt":0.2500035017044091,"spread":0.2327116433204737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01856886,0.001893198,0.002204798,0.003558141,0.001095407,0.003184819,0.004781204,0.002500718,0.003505132],"category_scores_gemma":[0.03845654,0.0009594662,0.002580238,0.003086897,0.002327332,0.005930041,0.003807725,0.004571043,0.001656038],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002145137,"about_ca_system_score_gemma":0.001537279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007854871,"about_ca_topic_score_gemma":0.00622789,"domain_scores_codex":[0.9940476,0.003136539,0.000256482,0.0007963433,0.001273448,0.0004896574],"domain_scores_gemma":[0.9685665,0.02309328,0.001765439,0.002606364,0.003291047,0.0006774954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002281391,0.0001010361,0.003229686,0.00007991864,0.00009203265,0.0001716051,0.0001669171,0.8378807,0.0003689882,0.1312438,0.001865594,0.02457168],"study_design_scores_gemma":[0.00001317541,0.00002838252,0.0002403741,0.00001285685,0.00000997263,0.00004378543,0.00001933789,0.9550942,0.00009622398,0.04381814,0.0006073116,0.00001623323],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02350039,0.0004594877,0.972418,0.0004615109,0.00006453873,0.0001251744,0.0003067347,0.0002342096,0.002430115],"genre_scores_gemma":[0.6036789,0.00213703,0.3756084,0.0006930454,0.0004368179,0.0008363895,0.001943003,0.0002791726,0.0143872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01856886,"threshold_uncertainty_score":0.09820271,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2751694342","doi":"10.14778/3137628.3137630","title":"Trajectory similarity join in spatial networks","year":2017,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Beijing Nova Program; King Abdullah University of Science and Technology; National Natural Science Foundation of China; Innovationsfonden","keywords":"Join (topology); Computer science; Pruning; Similarity (geometry); Trajectory; Nearest neighbor search; Heuristic; Matching (statistics); Data mining; Scheduling (production processes); Algorithm; Theoretical computer science; Artificial intelligence; Mathematics; Mathematical optimization","authors":[{"name":"Shuo Shang","is_ca":true},{"name":"Lisi Chen","is_ca":false},{"name":"Zhewei Wei","is_ca":false},{"name":"Christian S. Jensen","is_ca":false},{"name":"Kai Zheng","is_ca":false},{"name":"Panos Kalnis","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01795752554889163,"gpt":0.2326463657509419,"spread":0.2146888402020503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002328805,0.0008499649,0.001586289,0.003559474,0.00172811,0.002500695,0.002268204,0.001384125,0.002884897],"category_scores_gemma":[0.01002742,0.0005220327,0.001092477,0.005867735,0.001128617,0.005080509,0.003660184,0.001085519,0.0009060127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001841219,"about_ca_system_score_gemma":0.001955711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008056411,"about_ca_topic_score_gemma":0.006782762,"domain_scores_codex":[0.9965901,0.0006906189,0.0002682194,0.0009711265,0.001224424,0.0002554696],"domain_scores_gemma":[0.9961858,0.001619811,0.0005216415,0.000822759,0.0006227158,0.0002271729],"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":[0.0007634218,0.000309154,0.009325427,0.0004037155,0.0002460965,0.0004799389,0.0007790136,0.5982834,0.007538519,0.09688129,0.007754865,0.2772351],"study_design_scores_gemma":[0.00003932925,0.00009898534,0.001150754,0.00002310965,0.00003766466,0.0002515283,0.0002579213,0.9164852,0.004638363,0.07045581,0.006537742,0.00002361026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06919332,0.001341047,0.922861,0.0004873965,0.00007873572,0.0002716003,0.001151843,0.001394408,0.003220666],"genre_scores_gemma":[0.5017853,0.0009067567,0.488082,0.0001706108,0.000148851,0.0003003645,0.00370589,0.0001992821,0.004700939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008056411,"threshold_uncertainty_score":0.01601905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2126431245","doi":"10.1007/s00778-006-0029-7","title":"Algorithms and analyses for maximal vector computation","year":2006,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":177,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Curse of dimensionality; Computation; Field (mathematics); Computer science; Running time; Divide and conquer algorithms; Algorithm; Mathematics; Discrete mathematics; Theoretical computer science; Combinatorics; Artificial intelligence; Data mining; Pure mathematics","authors":[{"name":"Parke Godfrey","is_ca":true},{"name":"J. Ryan Shipley","is_ca":false},{"name":"Jarek Gryz","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04801050073090831,"gpt":0.3160797680561167,"spread":0.2680692673252084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005817893,0.002498648,0.002153084,0.005575067,0.002533806,0.00698099,0.005808397,0.002048922,0.01387799],"category_scores_gemma":[0.03881434,0.001335485,0.002844607,0.007361695,0.005171902,0.01723073,0.005553711,0.006791322,0.004388889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003480046,"about_ca_system_score_gemma":0.003017663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002916614,"about_ca_topic_score_gemma":0.002988583,"domain_scores_codex":[0.9932895,0.002234266,0.0004683542,0.00100475,0.002230083,0.0007731044],"domain_scores_gemma":[0.9749116,0.01697567,0.001067221,0.004094638,0.002336722,0.0006141624],"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":[0.0003137983,0.0001582691,0.0009700437,0.0003252389,0.00008653073,0.00004961489,0.000225085,0.02553238,0.0008970145,0.8529319,0.01188647,0.1066236],"study_design_scores_gemma":[0.00001939128,0.00001893421,0.0001651515,0.00004202341,0.00003735662,0.00003040892,0.00003512541,0.09281605,0.000847549,0.9024708,0.003497781,0.00001929792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006338958,0.001954228,0.9792014,0.000897912,0.0002151101,0.00007990056,0.0003003806,0.001523159,0.009488952],"genre_scores_gemma":[0.3147154,0.003627452,0.6537578,0.001149893,0.002264948,0.00067938,0.002153363,0.001980165,0.01967175],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01387799,"threshold_uncertainty_score":0.04642648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2806337402","doi":"10.1016/j.patcog.2018.05.030","title":"A fast clustering algorithm based on pruning unnecessary distance computations in DBSCAN for high-dimensional data","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":170,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"State Key Laboratory of Computer Aided Design and Computer Graphics; National Laboratory of Pattern Recognition; Fujian Provincial Department of Science and Technology; Zhejiang University; Huaqiao University; Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"DBSCAN; Computer science; Pruning; Computation; Cluster analysis; Noise (video); Dimension (graph theory); Algorithm; Search engine indexing; Pattern recognition (psychology); Data mining; Mathematics; Artificial intelligence; CURE data clustering algorithm; Correlation clustering; Combinatorics; Image (mathematics)","authors":[{"name":"Yewang Chen","is_ca":true},{"name":"Shengyu Tang","is_ca":false},{"name":"Nizar Bouguila","is_ca":true},{"name":"Cheng Wang","is_ca":false},{"name":"Ji‐Xiang Du","is_ca":false},{"name":"Hailin Li","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0527162703613487,"gpt":0.285088083781462,"spread":0.2323718134201133,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001526959,0.001587811,0.002858595,0.00388195,0.002631173,0.0028393,0.004864905,0.001606211,0.003368411],"category_scores_gemma":[0.005181411,0.000961136,0.001441972,0.008219852,0.0010221,0.002461762,0.002253666,0.002728702,0.002483765],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105563,"about_ca_system_score_gemma":0.004630564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02178555,"about_ca_topic_score_gemma":0.02654047,"domain_scores_codex":[0.9965878,0.0003973894,0.0002425756,0.0005084055,0.002023081,0.0002407754],"domain_scores_gemma":[0.9971907,0.0005422771,0.0001267934,0.0004737111,0.001545672,0.0001207541],"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":[0.0005108356,0.0002562995,0.001119197,0.0002560013,0.0002078421,0.0001278528,0.0002338914,0.06551039,0.01510171,0.01338836,0.0148116,0.8884761],"study_design_scores_gemma":[0.00006744421,0.0001477157,0.001036805,0.00003656945,0.00008391166,0.0003709462,0.0001564744,0.9480713,0.02144323,0.01499781,0.01347238,0.0001154895],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005593974,0.0004367095,0.9905266,0.0001009888,0.0001627815,0.00009720369,0.0001987544,0.002254933,0.0006280711],"genre_scores_gemma":[0.02856137,0.0002821186,0.9680641,0.00008882674,0.00007140316,0.0001822055,0.0009570763,0.0002621276,0.001530829],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02178555,"threshold_uncertainty_score":0.0433175,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119462844","doi":"10.1109/icde.2001.914848","title":"Spatial clustering in the presence of obstacles","year":2002,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":161,"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":"Cluster analysis; Computer science; Data stream clustering; Pruning; CURE data clustering algorithm; Function (biology); Canopy clustering algorithm; Data mining; Scalability; Space (punctuation); Correlation clustering; Obstacle; Artificial intelligence; Geography","authors":[{"name":"Anthony K. H. Tung","is_ca":true},{"name":"Jun-feng HOU","is_ca":true},{"name":"Jiawei Han","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03443696842166376,"gpt":0.2332489990852773,"spread":0.1988120306636136,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002018687,0.0006770052,0.001187862,0.001475904,0.001629383,0.001297153,0.00164259,0.001280989,0.0006879069],"category_scores_gemma":[0.008334194,0.0005781413,0.0007282003,0.002537772,0.001292085,0.002518314,0.002701291,0.0009210487,0.0002828058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001184002,"about_ca_system_score_gemma":0.001520507,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006156874,"about_ca_topic_score_gemma":0.007538028,"domain_scores_codex":[0.9982361,0.0004891599,0.0001007115,0.0004066788,0.0005980084,0.0001694068],"domain_scores_gemma":[0.9938646,0.003366502,0.0006913731,0.001095569,0.000756063,0.0002260126],"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":[0.0003390431,0.00006681868,0.00556229,0.0001830856,0.0001119753,0.0005408518,0.0004040442,0.8726261,0.006123309,0.02904917,0.00254549,0.08244785],"study_design_scores_gemma":[0.00001752411,0.00004000888,0.000936528,0.00001180325,0.00002099888,0.0001652117,0.0001364044,0.9743494,0.00399028,0.01779369,0.002519741,0.0000183217],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1462739,0.0006606448,0.8490898,0.0006441377,0.0000716071,0.000102902,0.0001900881,0.0007558931,0.002210981],"genre_scores_gemma":[0.5518482,0.0004870242,0.444242,0.0001110321,0.00007469345,0.0001293609,0.0005760434,0.0000922049,0.002439575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006156874,"threshold_uncertainty_score":0.01224208,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2338354263","doi":"","title":"Toward better support for spatial decision making: defining the characteristics of spatial on-line analytical processing (solap)","year":2019,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":154,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Online analytical processing; Exploit; Data warehouse; Computer science; Spatial analysis; Line (geometry); Decision support system; Data mining; Data science; Geography; Cartography; Mathematics; Remote sensing","authors":[{"name":"Sonia Rivest","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02906984507809188,"gpt":0.2903889626372823,"spread":0.2613191175591905,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006578223,0.0008422727,0.001063193,0.002376724,0.001062455,0.00987481,0.002185425,0.001903688,0.002280747],"category_scores_gemma":[0.02441095,0.0007293382,0.0007929403,0.004596235,0.004473123,0.01643271,0.003995338,0.002985594,0.001209225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001386064,"about_ca_system_score_gemma":0.002602357,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003536041,"about_ca_topic_score_gemma":0.001596269,"domain_scores_codex":[0.995589,0.001522793,0.000469605,0.0006182957,0.001518782,0.0002814306],"domain_scores_gemma":[0.9799579,0.008105144,0.002535018,0.004131444,0.004463924,0.000806633],"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":[0.000343462,0.000215153,0.008440039,0.0007831246,0.0001110167,0.0005065869,0.002338555,0.05468691,0.006171235,0.67711,0.007230014,0.242064],"study_design_scores_gemma":[0.00002125031,0.0001155159,0.00163646,0.0001828278,0.00003016847,0.0003372329,0.0008140319,0.3417929,0.004928244,0.6237636,0.02632517,0.00005254469],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01997381,0.000913451,0.9683673,0.003153963,0.00008898957,0.0001215676,0.0002758274,0.0005471308,0.006557976],"genre_scores_gemma":[0.2553742,0.001431032,0.7396495,0.0006932233,0.0002318448,0.0001967898,0.0006494421,0.0001892706,0.00158477],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00987481,"threshold_uncertainty_score":0.03478938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017733151","doi":"10.1109/iccit.2007.148","title":"Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers","year":2007,"lang":"en","type":"article","venue":"2007 International Conference on Convergence Information Technology (ICCIT 2007)","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":151,"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":"Naive Bayes classifier; Artificial intelligence; k-nearest neighbors algorithm; Computer science; Machine learning; Bayes error rate; Classifier (UML); Bayes classifier; Random subspace method; Pattern recognition (psychology); Bayesian probability; Bayes' theorem; Data mining; Support vector machine","authors":[],"retraction":null,"screen_n_in":null,"score":{"opus":0.02490013171729916,"gpt":0.2604650408833423,"spread":0.2355649091660431,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02497856,0.001716046,0.00247018,0.004359988,0.001894285,0.003885977,0.001954323,0.002871073,0.001898506],"category_scores_gemma":[0.1016264,0.0006303834,0.001129974,0.003232703,0.001251755,0.007553869,0.001059398,0.001610738,0.001182721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002820689,"about_ca_system_score_gemma":0.002246718,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01523003,"about_ca_topic_score_gemma":0.01199921,"domain_scores_codex":[0.972265,0.009156005,0.002022311,0.003400401,0.01221915,0.0009371641],"domain_scores_gemma":[0.9158292,0.06108084,0.002818109,0.003646336,0.01587648,0.0007489646],"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":[0.002737798,0.0007120625,0.03973011,0.001219689,0.0009415638,0.0002295474,0.00084799,0.2404572,0.002506417,0.02304417,0.01211093,0.6754625],"study_design_scores_gemma":[0.00007788355,0.0006781075,0.0085443,0.0001624138,0.0001744215,0.0002316601,0.0004847309,0.9636276,0.003033429,0.01852527,0.004346051,0.0001140309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4079919,0.02904348,0.520718,0.003364038,0.002024973,0.001035505,0.001720448,0.002447348,0.03165425],"genre_scores_gemma":[0.7794862,0.003160249,0.2112149,0.0004192465,0.0004650626,0.000240488,0.001432079,0.0002089083,0.003372857],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02497856,"threshold_uncertainty_score":0.1321008,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2133246278","doi":"10.14778/1453856.1453895","title":"Efficient search for the top-k probable nearest neighbors in uncertain databases","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":149,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Query optimization; Online aggregation; k-nearest neighbors algorithm; Query language; Semantics (computer science); Information retrieval; Sargable; Object (grammar); Point (geometry); Database; Feature (linguistics); Web query classification; Web search query; Search engine; Artificial intelligence","authors":[{"name":"George Beskales","is_ca":true},{"name":"Mohamed A. Soliman","is_ca":true},{"name":"Ihab F. Ilyas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.05346318793657699,"gpt":0.2715280562480217,"spread":0.2180648683114447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003984306,0.0009378948,0.003364607,0.004446898,0.001646222,0.003350858,0.003866679,0.002307604,0.001635337],"category_scores_gemma":[0.02511799,0.001014346,0.0009179089,0.006381348,0.0009277032,0.00732142,0.002427203,0.001219946,0.00058644],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001354977,"about_ca_system_score_gemma":0.001827491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007188892,"about_ca_topic_score_gemma":0.01182296,"domain_scores_codex":[0.9953053,0.001268094,0.0006558885,0.001016104,0.001424462,0.0003301212],"domain_scores_gemma":[0.9871206,0.009335232,0.0007983377,0.001407169,0.001049508,0.0002892043],"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":[0.001739551,0.0006127961,0.01521179,0.0006535663,0.0003374173,0.0005832411,0.001135874,0.4595737,0.006966825,0.02360196,0.01573184,0.4738514],"study_design_scores_gemma":[0.00005500209,0.0000708286,0.0007603156,0.00001827822,0.00004516274,0.0002457401,0.0003434478,0.9706444,0.002115364,0.0247543,0.0009205624,0.00002666008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1757375,0.003142703,0.815048,0.00121939,0.00006339722,0.0001918292,0.001227856,0.001691636,0.001677764],"genre_scores_gemma":[0.4844283,0.0006150185,0.5111876,0.0001871843,0.0001036567,0.0001381096,0.00223492,0.0001832989,0.0009218142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007188892,"threshold_uncertainty_score":0.02107126,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W151938044","doi":"10.1137/1.9781611972757.5","title":"Summarizing and Mining Skewed Data Streams","year":2005,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":138,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Crohn's and Colitis Foundation of Canada","keywords":"Skew; Skewness; Data stream mining; Computer science; Data mining; Data stream; Space (punctuation); Zipf's law; Point (geometry); Algorithm; Mathematics; Statistics","authors":[{"name":"Graham Cormode","is_ca":false},{"name":"S. Muthukrishnan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.04579868955532916,"gpt":0.2686245177712225,"spread":0.2228258282158933,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003105537,0.001117254,0.001743375,0.004433203,0.0007644242,0.002101373,0.001429673,0.0008866058,0.0005868638],"category_scores_gemma":[0.01970888,0.0005009691,0.0007487283,0.004827242,0.0005656896,0.003775259,0.001511983,0.001059103,0.0005536935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005345318,"about_ca_system_score_gemma":0.0006635269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009410309,"about_ca_topic_score_gemma":0.001253576,"domain_scores_codex":[0.997635,0.0005164801,0.0003452527,0.0004493259,0.0008919263,0.0001619699],"domain_scores_gemma":[0.9903419,0.004535847,0.001338995,0.00155191,0.001934578,0.0002967235],"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":[0.000855596,0.0002820239,0.04191222,0.0005590905,0.0002814407,0.0007286753,0.0009032156,0.2966869,0.01172053,0.0237361,0.01391959,0.6084146],"study_design_scores_gemma":[0.00002993773,0.00007240969,0.002887233,0.00003074109,0.00003091809,0.0001994187,0.000307864,0.9429041,0.007127322,0.04210357,0.004282346,0.00002407026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1165912,0.001063474,0.8757625,0.0007775279,0.0001354683,0.0001580818,0.002143906,0.002600747,0.00076709],"genre_scores_gemma":[0.5157912,0.001139075,0.4731952,0.0002152818,0.0004533245,0.0002438265,0.007703266,0.000206904,0.00105193],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004433203,"threshold_uncertainty_score":0.01642382,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2141296717","doi":"10.1145/1989734.1989741","title":"MoveMine","year":2011,"lang":"en","type":"article","venue":"ACM Transactions on Intelligent Systems and Technology","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":133,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Army Research Laboratory; Air Force Office of Scientific Research; Division of Computing and Communication Foundations; National Science Foundation","keywords":"Computer science; Data mining; Object (grammar); Swarm behaviour; Focus (optics); Trajectory; Cluster analysis; Data stream mining; Movement (music); Artificial intelligence","authors":[{"name":"Zhenhui Li","is_ca":false},{"name":"Jiawei Han","is_ca":false},{"name":"Ji Ming","is_ca":false},{"name":"Lu‐An Tang","is_ca":false},{"name":"Yintao Yu","is_ca":false},{"name":"Bolin Ding","is_ca":false},{"name":"Jae-Gil Lee","is_ca":true},{"name":"Roland Kays","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03626296199891101,"gpt":0.2355153862271245,"spread":0.1992524242282135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001428582,0.001663989,0.00147221,0.002237334,0.001188996,0.003735716,0.005394406,0.002465969,0.1507937],"category_scores_gemma":[0.004899097,0.001251752,0.001722182,0.002157062,0.0006767252,0.005133281,0.004414848,0.00204875,0.1601153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009718915,"about_ca_system_score_gemma":0.001856236,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003645231,"about_ca_topic_score_gemma":0.006707834,"domain_scores_codex":[0.9984348,0.0001516033,0.0001157001,0.0005453502,0.0005744055,0.0001780914],"domain_scores_gemma":[0.9985227,0.0002767414,0.0001168549,0.0004685054,0.0004716113,0.0001435761],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008325087,0.0001563714,0.00307772,0.001295927,0.0001709108,0.0003724341,0.0003642472,0.002325511,0.006339005,0.01558575,0.8117526,0.157727],"study_design_scores_gemma":[0.0001641729,0.0001218012,0.001592509,0.0001301996,0.00006167119,0.0004429288,0.0001026549,0.01003466,0.004854418,0.009231811,0.9731712,0.00009202574],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"empirical","genre_scores_codex":[0.008668625,0.002665977,0.1459002,0.002634298,0.001557702,0.0008609844,0.1136573,0.5144928,0.2095621],"genre_scores_gemma":[0.06268043,0.002884075,0.2042394,0.005091137,0.0004142302,0.002507312,0.3913552,0.08381043,0.2470178],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1507937,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162783807","doi":"10.14778/2021017.2021025","title":"Keyword search in graphs","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":132,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Substructure; Clique; Computer science; Graph; Combinatorics; Theoretical computer science; Time complexity; Mathematics; Algorithm","authors":[{"name":"Mehdi Kargar","is_ca":true},{"name":"Aijun An","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03651081320407087,"gpt":0.2195111061961708,"spread":0.1830002929920999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00123572,0.0009957463,0.001601656,0.00313985,0.0015226,0.003679835,0.001988003,0.002024083,0.006952313],"category_scores_gemma":[0.01115042,0.0009229629,0.001308278,0.007795485,0.001317765,0.008909615,0.002432011,0.001296253,0.002922565],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002036925,"about_ca_system_score_gemma":0.001629392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004747696,"about_ca_topic_score_gemma":0.004953087,"domain_scores_codex":[0.9972768,0.000910157,0.0002404823,0.0008716729,0.0004500738,0.0002507854],"domain_scores_gemma":[0.9939927,0.004116666,0.0005052529,0.0007695441,0.0004229021,0.0001928289],"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":[0.0006277694,0.0002809465,0.003163277,0.002888471,0.0002971029,0.0008572183,0.00122683,0.2196971,0.01190472,0.3166703,0.05502875,0.3873575],"study_design_scores_gemma":[0.00009206554,0.0001053622,0.0006494442,0.0001269249,0.00007200029,0.0009228826,0.000433453,0.2843508,0.004845701,0.6707673,0.03758225,0.00005171974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04531558,0.005098478,0.9254759,0.002606931,0.00017137,0.0004927976,0.00402356,0.002968161,0.0138472],"genre_scores_gemma":[0.2860639,0.004916594,0.6914189,0.0008215114,0.0002415799,0.0003756056,0.006168046,0.0005171457,0.009476676],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006952313,"threshold_uncertainty_score":0.02325779,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2071465809","doi":"10.1016/j.jmva.2007.01.013","title":"From moments of sum to moments of product","year":2007,"lang":"en","type":"article","venue":"Journal of Multivariate Analysis","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Mathematics; Product (mathematics); Random variable; Moment (physics); Identity (music); Quadratic equation; Multivariate statistics; Applied mathematics; Algebra of random variables; Sum of normally distributed random variables; Multivariate random variable; Statistics; Geometry","authors":[{"name":"Raymond Kan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01762470161886203,"gpt":0.2967131886920912,"spread":0.2790884870732292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00469608,0.001316878,0.001301289,0.003150681,0.0007578824,0.003786474,0.001726599,0.001277487,0.004705013],"category_scores_gemma":[0.03880278,0.0009925375,0.001318307,0.002779308,0.004225057,0.009850633,0.003870132,0.003975613,0.001221539],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001228618,"about_ca_system_score_gemma":0.0009124846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008132806,"about_ca_topic_score_gemma":0.0006514306,"domain_scores_codex":[0.996794,0.001420001,0.0002463033,0.0005694678,0.0007613545,0.0002088237],"domain_scores_gemma":[0.9789839,0.01484299,0.001341463,0.002842454,0.001347596,0.0006415396],"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":[0.00008843694,0.00002201812,0.0007701453,0.0001313384,0.00004993924,0.0001070329,0.0003072898,0.0134834,0.001522034,0.9256921,0.004449888,0.05337633],"study_design_scores_gemma":[0.000006254331,0.00001793562,0.0002753921,0.00002380904,0.00001674546,0.0001414998,0.00003572592,0.04946132,0.0005867908,0.9444413,0.004968215,0.00002497699],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007985077,0.0026343,0.9848053,0.0007175889,0.0003529088,0.00001211723,0.00007991274,0.0002177248,0.003195111],"genre_scores_gemma":[0.4405916,0.009521834,0.5283939,0.001415796,0.004701852,0.0001586085,0.0005368248,0.001444856,0.01323482],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004705013,"threshold_uncertainty_score":0.02483559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160152607","doi":"10.14778/1687627.1687754","title":"Efficient method for maximizing bichromatic reverse nearest neighbor","year":2009,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; k-nearest neighbors algorithm; Point (geometry); Best bin first; Exponential function; Algorithm; Exponential growth; Theoretical computer science; Mathematics; Artificial intelligence","authors":[{"name":"Raymond Chi-Wing Wong","is_ca":false},{"name":"M. TAMER ÖZSU","is_ca":true},{"name":"Philip S. Yu","is_ca":false},{"name":"Ada Wai-Chee Fu","is_ca":false},{"name":"Lian Liu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01458119393423405,"gpt":0.2572641271071092,"spread":0.2426829331728751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00157206,0.0011313,0.001877277,0.002361787,0.0008605612,0.001022602,0.002674639,0.001167936,0.004400157],"category_scores_gemma":[0.006288352,0.0006356133,0.0008446203,0.002812432,0.0006000947,0.002264846,0.002824784,0.000913428,0.001803275],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009242684,"about_ca_system_score_gemma":0.001659337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003892747,"about_ca_topic_score_gemma":0.006198694,"domain_scores_codex":[0.997642,0.0005515056,0.0001347962,0.0004520314,0.001029017,0.0001906925],"domain_scores_gemma":[0.9980293,0.0007052377,0.0001990311,0.0003853452,0.0006047926,0.00007631326],"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":[0.0004481573,0.0002318686,0.001836264,0.0003755607,0.00008333039,0.0001567217,0.0002793113,0.1528829,0.01591794,0.01922286,0.009857926,0.7987072],"study_design_scores_gemma":[0.00006724329,0.00009956697,0.0005798119,0.00002553458,0.00002845482,0.0003891127,0.000107585,0.9690306,0.01016738,0.01329293,0.006174479,0.0000373106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01342903,0.0005591736,0.982529,0.0001304045,0.00004309442,0.000119588,0.0001318259,0.001028171,0.00202968],"genre_scores_gemma":[0.09750411,0.0002296065,0.8994473,0.00008888402,0.00003843769,0.0002012013,0.000406396,0.0001908526,0.001893243],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004400157,"threshold_uncertainty_score":0.01472002,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2057058417","doi":"10.1145/1132863.1132873","title":"Approximation and streaming algorithms for histogram construction problems","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Histogram; Computer science; Algorithm; Approximation algorithm; Artificial intelligence; Image (mathematics)","authors":[{"name":"Sudipto Guha","is_ca":false},{"name":"Nick Koudas","is_ca":true},{"name":"Kyuseok Shim","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02572179603381434,"gpt":0.2438775195296402,"spread":0.2181557234958259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003229405,0.001799141,0.001895851,0.00182935,0.001014513,0.002560741,0.003266516,0.001901751,0.00675954],"category_scores_gemma":[0.02151073,0.000960675,0.001508952,0.004392195,0.001267668,0.006773975,0.002802458,0.004084916,0.001920504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002176328,"about_ca_system_score_gemma":0.001773015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004042483,"about_ca_topic_score_gemma":0.003596257,"domain_scores_codex":[0.9975446,0.0007286948,0.000180392,0.0005269393,0.0007223467,0.0002971133],"domain_scores_gemma":[0.9910372,0.006141248,0.0005208579,0.001265912,0.0007874742,0.0002471737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0004619743,0.0002885616,0.002013644,0.0006725951,0.0001195198,0.0001153475,0.0004225296,0.4449729,0.002640802,0.1588888,0.01893566,0.3704676],"study_design_scores_gemma":[0.00005154217,0.00004881254,0.000149802,0.00002596525,0.00001918796,0.00008077947,0.00006233665,0.8827558,0.0008467631,0.1129096,0.003034397,0.00001505862],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004234343,0.0007106293,0.9924163,0.0003179004,0.00007288921,0.00008143284,0.0001568499,0.0006124793,0.001397205],"genre_scores_gemma":[0.1296832,0.001671365,0.8623673,0.0002487046,0.0003357001,0.0003939544,0.001289884,0.0003542888,0.003655666],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00675954,"threshold_uncertainty_score":0.02261299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1875872827","doi":"10.1007/978-3-540-24627-5_7","title":"Skyline Cardinality for Relational Processing","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":120,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Skyline; Cardinality (data modeling); Computer science; Online analytical processing; Tuple; Extension (predicate logic); Data mining; Theoretical computer science; Database; Mathematics; Discrete mathematics; Data warehouse; Programming language","authors":[{"name":"Parke Godfrey","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03096591432089721,"gpt":0.2674929519471953,"spread":0.2365270376262981,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001366189,0.0008592529,0.00129941,0.001323083,0.001132547,0.003494833,0.002111637,0.0007326179,0.02291428],"category_scores_gemma":[0.004677312,0.0009497174,0.001043743,0.004299388,0.001245997,0.0112635,0.002680843,0.002466575,0.006366547],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001056367,"about_ca_system_score_gemma":0.0009636943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001168228,"about_ca_topic_score_gemma":0.001736941,"domain_scores_codex":[0.9983287,0.0002967373,0.0001894475,0.0002979958,0.0007493437,0.0001377842],"domain_scores_gemma":[0.9970458,0.0008691669,0.0001305181,0.001494776,0.0003599036,0.00009985967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002670372,0.00007745981,0.0005055419,0.0005044775,0.00004255123,0.00008751986,0.000401526,0.008779222,0.005894229,0.5458375,0.07592954,0.3616735],"study_design_scores_gemma":[0.0000559047,0.00007343132,0.0004338628,0.0001599469,0.00005378323,0.0003638407,0.000155686,0.06135251,0.01376145,0.683417,0.2401109,0.00006165748],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.006374164,0.001206257,0.9597185,0.0005822869,0.0002653747,0.0001161885,0.001786973,0.009447668,0.02050259],"genre_scores_gemma":[0.08926879,0.002055263,0.8682544,0.0004078266,0.0005787067,0.0003643184,0.006095291,0.004938281,0.02803722],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.02291428,"threshold_uncertainty_score":0.07665592,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2041121499","doi":"10.1198/016214508000000517","title":"Combining Registration and Fitting for Functional Models","year":2008,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Natural Sciences and Engineering Research Council of Canada","funders":"","keywords":"Computer science; Econometrics; Mathematics; Artificial intelligence","authors":[{"name":"Aloïs Kneip","is_ca":true},{"name":"J. O. Ramsay","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.03196521524814722,"gpt":0.2525504152852148,"spread":0.2205852000370676,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01261951,0.001406914,0.002350193,0.003454026,0.001266397,0.002796142,0.002189215,0.002249192,0.002708229],"category_scores_gemma":[0.03739361,0.001344644,0.002703476,0.003569022,0.003924495,0.003792241,0.004336537,0.003144837,0.0009813444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001584569,"about_ca_system_score_gemma":0.001741586,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003433475,"about_ca_topic_score_gemma":0.003075054,"domain_scores_codex":[0.9911571,0.005429331,0.0003939195,0.001204823,0.001546794,0.0002681683],"domain_scores_gemma":[0.9877678,0.007816385,0.0008743199,0.002415479,0.0009806197,0.0001453731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002124871,0.00009952075,0.002601766,0.0001929048,0.0002774832,0.0001698311,0.0003889727,0.537628,0.006513679,0.2036982,0.001424391,0.2467928],"study_design_scores_gemma":[0.00001489615,0.00004739126,0.0004553983,0.00001377643,0.00001744538,0.00005297501,0.00003245411,0.8886695,0.002111253,0.1068896,0.001668619,0.00002665436],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003581268,0.00004792577,0.995876,0.00007856029,0.000008684289,0.00002367044,0.00001355304,0.00015304,0.0002173552],"genre_scores_gemma":[0.1457812,0.000129587,0.8518436,0.00008089387,0.00006967571,0.0002591074,0.0002335836,0.0004292598,0.001173245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01261951,"threshold_uncertainty_score":0.06673914,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130696419","doi":"10.1145/1189769.1189774","title":"Towards multidimensional subspace skyline analysis","year":2006,"lang":"en","type":"article","venue":"ACM Transactions on Database Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":117,"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":"Skyline; Linear subspace; Subspace topology; Computer science; Semantics (computer science); Theoretical computer science; Space (punctuation); Object (grammar); Online analytical processing; Algorithm; Data mining; Mathematics; Artificial intelligence; Pure mathematics; Programming language","authors":[{"name":"Jian Pei","is_ca":true},{"name":"Yidong Yuan","is_ca":false},{"name":"Xuemin Lin","is_ca":false},{"name":"Wen Jin","is_ca":true},{"name":"Martin Ester","is_ca":true},{"name":"Qing Liu","is_ca":false},{"name":"Wei Wang","is_ca":false},{"name":"Yufei Tao","is_ca":false},{"name":"Jeffrey Xu Yu","is_ca":false},{"name":"Qing Zhang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01799995614887762,"gpt":0.2517425082751469,"spread":0.2337425521262693,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001480806,0.001151441,0.001439685,0.00287127,0.0008965224,0.002861235,0.001278792,0.001037056,0.003505152],"category_scores_gemma":[0.006202721,0.0005003476,0.001762146,0.004168312,0.0014085,0.004678326,0.002876229,0.002546737,0.0009227031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001202725,"about_ca_system_score_gemma":0.001234743,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004613324,"about_ca_topic_score_gemma":0.002814696,"domain_scores_codex":[0.9986136,0.0004836952,0.00008812942,0.0002407784,0.0004206132,0.0001531998],"domain_scores_gemma":[0.9973559,0.001046159,0.0003612429,0.0004348426,0.0006633897,0.000138462],"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":[0.0002268368,0.00009420802,0.004138349,0.0003518979,0.0001487396,0.0002701817,0.0007423505,0.4142062,0.005550241,0.4169173,0.009528934,0.1478247],"study_design_scores_gemma":[0.00001043261,0.00002952208,0.0003035031,0.00002553876,0.00001092368,0.00003888863,0.0001377108,0.8286785,0.0009101667,0.1653244,0.004512894,0.00001754672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006109124,0.0002814343,0.9918046,0.000137274,0.00001735217,0.00003813971,0.0002465628,0.0003751121,0.0009903526],"genre_scores_gemma":[0.2232306,0.0009245921,0.7713571,0.0001822327,0.0001479352,0.0002849384,0.001745021,0.000329444,0.001798255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004613324,"threshold_uncertainty_score":0.01172584,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2028769163","doi":"10.1145/1044731.1044733","title":"Determining approximate shortest paths on weighted polyhedral surfaces","year":2005,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":115,"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":"Discretization; Combinatorics; Face (sociological concept); Mathematics; Shortest path problem; Surface (topology); Euclidean geometry; Polyhedron; Computational geometry; Discrete mathematics; Algorithm; Geometry; Graph; Mathematical analysis","authors":[{"name":"Lyudmil Aleksandrov","is_ca":false},{"name":"Anil Maheshwari","is_ca":true},{"name":"Jörg-Rüdiger Sack","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02130323145929961,"gpt":0.2520038338114481,"spread":0.2307006023521485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008879039,0.00132615,0.001695771,0.001889476,0.0007914501,0.001397268,0.002047748,0.001416314,0.0029248],"category_scores_gemma":[0.007690911,0.0008965697,0.001136578,0.00234902,0.001079305,0.003242007,0.002277142,0.001373355,0.0006858253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001152454,"about_ca_system_score_gemma":0.001108099,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003983574,"about_ca_topic_score_gemma":0.004513556,"domain_scores_codex":[0.9984885,0.0003195217,0.0000855071,0.0003454526,0.0006108222,0.0001501346],"domain_scores_gemma":[0.9974958,0.001453674,0.0002387144,0.00040894,0.0003016675,0.0001010566],"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":[0.0001182682,0.00003780038,0.000968413,0.000133587,0.00004074737,0.0001105551,0.0001363805,0.9023156,0.002796281,0.01949274,0.001327511,0.07252219],"study_design_scores_gemma":[0.00001172843,0.00002039617,0.00008380786,0.000007438626,0.000004161147,0.00003045154,0.00005557055,0.9665436,0.0007984279,0.03168632,0.0007524465,0.000005628764],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05695695,0.0002030683,0.9405017,0.0001115288,0.00002823324,0.00008649098,0.0002313712,0.0007257094,0.001155014],"genre_scores_gemma":[0.34829,0.0003131821,0.647987,0.00004522495,0.00003029266,0.0002778771,0.001308074,0.0002793608,0.001468925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003983574,"threshold_uncertainty_score":0.00978446,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1481798977","doi":"10.1007/11424857_20","title":"A New and Efficient K-Medoid Algorithm for Spatial Clustering","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Medoid; k-medoids; Cluster analysis; Computer science; Algorithm; Canopy clustering algorithm; Computation; CURE data clustering algorithm; Correlation clustering; Data mining; Artificial intelligence","authors":[{"name":"Qiaoping Zhang","is_ca":true},{"name":"Isabelle Couloigner","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01332726406476602,"gpt":0.2370497392728519,"spread":0.2237224752080859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001920137,0.001650956,0.003064554,0.002587553,0.001735039,0.002011591,0.004684165,0.002775328,0.00528899],"category_scores_gemma":[0.006762179,0.001336345,0.002381449,0.005143824,0.001032352,0.003214034,0.003909842,0.0024393,0.005495312],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041285,"about_ca_system_score_gemma":0.00223774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008633177,"about_ca_topic_score_gemma":0.01036836,"domain_scores_codex":[0.9970468,0.0006355075,0.0002352797,0.0005800815,0.001359475,0.0001428052],"domain_scores_gemma":[0.9974037,0.0008493888,0.0001253673,0.0005224139,0.0009854286,0.0001137669],"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":[0.0003617152,0.0001203137,0.0005265024,0.0003097944,0.0002202379,0.0001079549,0.0002855497,0.1565135,0.01143274,0.01176669,0.01467778,0.8036772],"study_design_scores_gemma":[0.00005001214,0.00005980135,0.0002564252,0.00003075111,0.0000470722,0.0003196551,0.0001004829,0.9616148,0.006183655,0.01694492,0.01431962,0.0000727064],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007808413,0.000186136,0.9980226,0.00003822625,0.00006578375,0.00003458463,0.0000604689,0.0004897857,0.0003216928],"genre_scores_gemma":[0.009586876,0.0001935196,0.9882962,0.00005315293,0.00004346042,0.000106389,0.0003026961,0.0001585555,0.001259068],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008633177,"threshold_uncertainty_score":0.0176934,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2154768509","doi":"10.14778/1453856.1453934","title":"Efficient network aware search in collaborative tagging sites","year":2008,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"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":"Computer science; Popularity; Cluster analysis; Seekers; Context (archaeology); Upper and lower bounds; Heuristic; Space (punctuation); Information retrieval; Data mining; Machine learning; Artificial intelligence; Mathematics; Geography","authors":[{"name":"Sihem Amer Yahia","is_ca":false},{"name":"Michael Benedikt","is_ca":false},{"name":"Laks V. S. Lakshmanan","is_ca":true},{"name":"Julia Stoyanovich","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01881665465521546,"gpt":0.234770653360951,"spread":0.2159539987057356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003343349,0.0008142266,0.002247597,0.003186424,0.001752146,0.002921827,0.002772148,0.001806523,0.001515398],"category_scores_gemma":[0.01742416,0.0007578142,0.000850577,0.005506529,0.00119131,0.005478757,0.002698744,0.000906485,0.0009563499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001555894,"about_ca_system_score_gemma":0.001614328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005331591,"about_ca_topic_score_gemma":0.009775597,"domain_scores_codex":[0.9971719,0.0009333146,0.0002133403,0.0006724093,0.0006092726,0.0003997342],"domain_scores_gemma":[0.989407,0.00634803,0.001103732,0.001869678,0.0008283364,0.0004432292],"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":[0.001702193,0.0006145177,0.02922441,0.0007888292,0.0003021344,0.0005879742,0.002218715,0.587754,0.02310791,0.04567719,0.01101087,0.2970113],"study_design_scores_gemma":[0.00005298417,0.0001070943,0.001653003,0.00001774126,0.00005585298,0.0002309767,0.0003338365,0.9607445,0.004027523,0.03103467,0.001715783,0.00002599858],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3467378,0.001554494,0.6432123,0.0007131455,0.00004540091,0.0002427851,0.0008934593,0.001873292,0.004727425],"genre_scores_gemma":[0.7774791,0.0003591123,0.2172243,0.0001038446,0.00006549033,0.0001233702,0.00128899,0.0001815646,0.003174167],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005331591,"threshold_uncertainty_score":0.01768148,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2134161546","doi":"10.1007/s10707-005-4576-7","title":"Continuous Query Processing of Spatio-Temporal Data Streams in PLACE","year":2005,"lang":"en","type":"article","venue":"GeoInformatica","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Scalability; Spatial query; Data stream mining; Variety (cybernetics); Query language; Global Positioning System; Temporal database; Sliding window protocol; Semantics (computer science); Database; Distributed computing; Window (computing); Web search query; Web query classification; Data mining; Information retrieval; Operating system; Search engine; Artificial intelligence; Programming language","authors":[{"name":"Mohamed F. Mokbel","is_ca":false},{"name":"Xiaopeng Xiong","is_ca":false},{"name":"Moustafa A. Hammad","is_ca":true},{"name":"Walid G. Aref","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.01986281270201904,"gpt":0.2529512089406807,"spread":0.2330883962386616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002374092,0.0009105353,0.002105052,0.002224113,0.001224073,0.004002201,0.00258992,0.001505426,0.001944552],"category_scores_gemma":[0.01051579,0.0006268717,0.0007366198,0.005098321,0.0009757929,0.004647794,0.002558333,0.001164158,0.0005902287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008620761,"about_ca_system_score_gemma":0.0009587753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006186962,"about_ca_topic_score_gemma":0.005826801,"domain_scores_codex":[0.9973894,0.0003171731,0.0002269808,0.0004880049,0.001329033,0.0002494492],"domain_scores_gemma":[0.9948249,0.002494012,0.0004388113,0.0009305905,0.0009224949,0.0003892207],"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":[0.006928498,0.001426186,0.02639662,0.001182874,0.0005440473,0.002354791,0.002702354,0.3412249,0.06296802,0.04476816,0.01768574,0.4918179],"study_design_scores_gemma":[0.00009367617,0.0002082308,0.002187513,0.00002048805,0.00006298244,0.0002785268,0.0006432512,0.968478,0.0101694,0.01480371,0.003025095,0.00002905735],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.257112,0.001459965,0.7324326,0.0007593012,0.0002589895,0.0002524297,0.001923935,0.003557019,0.002243744],"genre_scores_gemma":[0.8917595,0.000505631,0.1032456,0.00008339464,0.000171452,0.0001165461,0.002443342,0.0001206704,0.00155397],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006186962,"threshold_uncertainty_score":0.0125556,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2006806998","doi":"10.1016/s0306-4379(03)00038-3","title":"Extending object-oriented databases for fuzzy information modeling","year":2003,"lang":"en","type":"article","venue":"Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Computer science; Fuzzy logic; Object (grammar); Database; Data mining; Measure (data warehouse); Database model; Data model (GIS); Database design; Theoretical computer science; Information retrieval; Artificial intelligence","authors":[{"name":"Zongmin Ma","is_ca":false},{"name":"Wenjun Zhang","is_ca":true},{"name":"Weiyin Ma","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.0335790971528764,"gpt":0.263758301456974,"spread":0.2301792043040976,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003925357,0.0006044939,0.001037176,0.001829677,0.0007633184,0.004622918,0.002447276,0.001138976,0.001967317],"category_scores_gemma":[0.009761606,0.000638476,0.001817963,0.003201209,0.0009248169,0.007025794,0.002607729,0.001462932,0.0008075355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006764531,"about_ca_system_score_gemma":0.0008661176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003170772,"about_ca_topic_score_gemma":0.002603839,"domain_scores_codex":[0.997604,0.0006637787,0.0004641019,0.0002624534,0.0008813445,0.0001243612],"domain_scores_gemma":[0.995854,0.001551516,0.0002770313,0.00155047,0.000645533,0.0001213166],"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":[0.0001667023,0.0002037434,0.002475442,0.0004310732,0.0002120679,0.0006803658,0.001111909,0.06487148,0.004231891,0.6300955,0.003763755,0.2917561],"study_design_scores_gemma":[0.00004581841,0.00006420215,0.000298663,0.0001333546,0.0001593327,0.0003366754,0.0001601999,0.3846144,0.004380779,0.5688387,0.04090939,0.00005833059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006849632,0.000397964,0.9897581,0.0002111324,0.00005420592,0.00005413856,0.0001112528,0.0006023777,0.001961084],"genre_scores_gemma":[0.1603875,0.001170127,0.8353927,0.0002338171,0.0001240936,0.0001303265,0.0006181472,0.0001454979,0.001797818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004622918,"threshold_uncertainty_score":0.02075952,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145352743","doi":"10.1002/jcc.20484","title":"An algorithm for three‐dimensional Voronoi S‐network","year":2006,"lang":"en","type":"article","venue":"Journal of Computational Chemistry","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"Alexander von Humboldt-Stiftung","keywords":"Voronoi diagram; Delaunay triangulation; SPHERES; Algorithm; Realization (probability); Centroidal Voronoi tessellation; Computer science; Bowyer–Watson algorithm; Computational geometry; Mathematics; Geometry; Physics","authors":[{"name":"N. N. Medvedev","is_ca":false},{"name":"V. P. Voloshin","is_ca":false},{"name":"Valériy Luchnikov","is_ca":false},{"name":"Marina L. Gavrilova","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008499045044182228,"gpt":0.2404819980159642,"spread":0.231982952971782,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001037366,0.0009400151,0.00104086,0.002298193,0.001470125,0.002394066,0.002883641,0.001259348,0.009642623],"category_scores_gemma":[0.004286685,0.0006126331,0.001288579,0.002165709,0.001062792,0.002858518,0.003441139,0.0014409,0.003112451],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00188447,"about_ca_system_score_gemma":0.002452627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007255905,"about_ca_topic_score_gemma":0.006604469,"domain_scores_codex":[0.9986246,0.0002540261,0.0001141322,0.0002700434,0.0006009148,0.0001363134],"domain_scores_gemma":[0.9985983,0.0005565764,0.00006768461,0.0002855507,0.0004180821,0.00007375836],"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":[0.0001732511,0.0000873577,0.0009810962,0.000235548,0.00008422181,0.0001594449,0.0002694828,0.2368872,0.00382892,0.2438453,0.01347863,0.4999696],"study_design_scores_gemma":[0.00005586312,0.00003571845,0.0001142568,0.00003009072,0.00001505115,0.0001521065,0.00005582601,0.8523157,0.002873472,0.1173491,0.02697217,0.00003071193],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001142407,0.00007505781,0.9961391,0.00007473682,0.00003190167,0.00008434414,0.000111819,0.0009644257,0.001376129],"genre_scores_gemma":[0.0272559,0.0001239532,0.9694822,0.00003699274,0.00002427594,0.0002713661,0.0005224121,0.0002587421,0.002024175],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009642623,"threshold_uncertainty_score":0.0322578,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2076172709","doi":"10.1145/765568.765571","title":"The height of a random binary search tree","year":2003,"lang":"en","type":"article","venue":"Journal of the ACM","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":100,"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":"Binary search tree; Combinatorics; Binary number; Random binary tree; Mathematics; Binary tree; Tree (set theory); Self-balancing binary search tree; Optimal binary search tree; Discrete mathematics; K-ary tree; Arithmetic; Tree structure","authors":[{"name":"Bruce Reed","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02206708586160027,"gpt":0.2553730957915877,"spread":0.2333060099299874,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00127681,0.0001883287,0.0004930252,0.0007928117,0.0005069122,0.001213927,0.0008555268,0.0007686891,0.003734874],"category_scores_gemma":[0.01513907,0.0003615063,0.0002285816,0.0008379942,0.0007660544,0.002322009,0.001053945,0.0006897877,0.0008418041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001076261,"about_ca_system_score_gemma":0.0008490996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001207216,"about_ca_topic_score_gemma":0.001666323,"domain_scores_codex":[0.9990163,0.000246831,0.0000362747,0.0001788484,0.0002953572,0.0002263256],"domain_scores_gemma":[0.9939693,0.003959205,0.0005176853,0.0006426409,0.0004805434,0.0004305405],"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":[0.001591807,0.0001882792,0.0319655,0.0006123677,0.0001922649,0.0005293419,0.0005745748,0.3476055,0.04613889,0.359686,0.02747069,0.1834448],"study_design_scores_gemma":[0.0001299445,0.0002817945,0.01065106,0.00008914727,0.00007075324,0.0007613657,0.0002307066,0.758586,0.008502944,0.2113518,0.009274228,0.00007031875],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6811479,0.002899147,0.2848557,0.003506045,0.0002390943,0.0001159136,0.002195911,0.001040865,0.02399931],"genre_scores_gemma":[0.9622296,0.0007103921,0.03211674,0.000300273,0.00009915618,0.0000716391,0.0007049791,0.0001319106,0.003635389],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003734874,"threshold_uncertainty_score":0.01249444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2010342401","doi":"10.1080/13658810601079759","title":"A shortest path algorithm with novel heuristics for dynamic transportation networks","year":2007,"lang":"en","type":"article","venue":"International Journal of Geographical Information Systems","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"MRF Geosystems (Canada)","funders":"","keywords":"Heuristics; Computer science; Shortest path problem; Path (computing); Process (computing); Yen's algorithm; Algorithm; Object (grammar); Mathematical optimization; Dijkstra's algorithm; K shortest path routing; Artificial intelligence; Theoretical computer science; Mathematics","authors":[{"name":"Bo Huang","is_ca":false},{"name":"Qiang Wu","is_ca":true},{"name":"F. Benjamin Zhan","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.007295755120132437,"gpt":0.2433534698424764,"spread":0.236057714722344,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004788022,0.0006469418,0.0005995896,0.001218075,0.0006556151,0.0008414704,0.001235188,0.0008185811,0.001196219],"category_scores_gemma":[0.002080025,0.0004055237,0.0005412901,0.001864277,0.0004167093,0.001399057,0.000715455,0.0007839253,0.0003807579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005923217,"about_ca_system_score_gemma":0.001585383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006446355,"about_ca_topic_score_gemma":0.005641946,"domain_scores_codex":[0.9997136,0.00008851903,0.00002182491,0.00006607311,0.00007619183,0.00003378059],"domain_scores_gemma":[0.9993275,0.0003905765,0.00006876639,0.00006872988,0.0001008387,0.00004365184],"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":[0.0001497724,0.0002066849,0.0009393942,0.0001727966,0.00009183611,0.0001609587,0.000101693,0.6148089,0.00541565,0.02738705,0.00778287,0.3427824],"study_design_scores_gemma":[0.00004297613,0.00008587218,0.0001817335,0.000009031254,0.00001859374,0.0001288543,0.00002848367,0.9841766,0.001351494,0.008791404,0.005164773,0.0000200579],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01351696,0.0003993588,0.9828759,0.0001146499,0.00007879775,0.00009378594,0.00009550153,0.001091134,0.001733852],"genre_scores_gemma":[0.1269031,0.0003182457,0.8707378,0.00006708779,0.00003822226,0.0001797812,0.0003078808,0.00008823739,0.001359685],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006446355,"threshold_uncertainty_score":0.01281768,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005048938","doi":"10.1145/1516360.1516459","title":"Interactive query refinement","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":99,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Query optimization; Information retrieval; Query language","authors":[{"name":"Chaitanya Mishra","is_ca":true},{"name":"Nick Koudas","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.009324530882337508,"gpt":0.2442648592033287,"spread":0.2349403283209912,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03868237,0.002557668,0.002923774,0.002847639,0.002190692,0.004121261,0.008799552,0.002852608,0.006620697],"category_scores_gemma":[0.1135076,0.001933135,0.004275256,0.003226136,0.005938482,0.01362104,0.01151789,0.005406121,0.001922598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002068057,"about_ca_system_score_gemma":0.002819454,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005710116,"about_ca_topic_score_gemma":0.004926736,"domain_scores_codex":[0.9376021,0.02335069,0.004313617,0.0090054,0.02244334,0.003284867],"domain_scores_gemma":[0.8489628,0.09540972,0.005590187,0.03701202,0.01143248,0.001592753],"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":[0.002082543,0.0009065036,0.0139163,0.001833272,0.0007573516,0.001533898,0.009874343,0.1127844,0.04798695,0.3122905,0.01808467,0.4779494],"study_design_scores_gemma":[0.0003258687,0.0007731167,0.001668568,0.0003066681,0.0004125725,0.001634192,0.001728806,0.5814421,0.04348477,0.3087793,0.05918868,0.0002553399],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01037705,0.0004101935,0.9842047,0.0005243094,0.00004193621,0.0003009211,0.0001366022,0.001923381,0.002080955],"genre_scores_gemma":[0.2509477,0.000536281,0.7407108,0.0008243979,0.0002108246,0.0004731111,0.001096577,0.001192289,0.004008032],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03868237,"threshold_uncertainty_score":0.2045744,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100235843","doi":"10.5555/1182635.1164146","title":"Relaxing join and selection queries","year":2006,"lang":"en","type":"article","venue":"National University of Singapore","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":95,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Joins; Computer science; Traverse; Query optimization; Theoretical computer science; Relaxation (psychology); Join (topology); Lattice (music); Selection (genetic algorithm); Information retrieval; Data mining; Mathematics; Combinatorics; Machine learning","authors":[{"name":"Nick Koudas","is_ca":true},{"name":"Chen Li","is_ca":false},{"name":"Anthony K. H. Tung","is_ca":false},{"name":"Rares Vernica","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.008028305870935474,"gpt":0.1763056307184854,"spread":0.1682773248475499,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02788503,0.001640484,0.003273107,0.001914578,0.002777103,0.004769934,0.004623576,0.002985838,0.00451375],"category_scores_gemma":[0.07891474,0.001599754,0.002297412,0.002500439,0.005597466,0.01253821,0.007681623,0.006531983,0.001218554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001840661,"about_ca_system_score_gemma":0.004221964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003048762,"about_ca_topic_score_gemma":0.003861067,"domain_scores_codex":[0.957993,0.01938277,0.003407837,0.004505541,0.01200962,0.002701133],"domain_scores_gemma":[0.9269903,0.04330549,0.005231238,0.01733148,0.005060997,0.002080508],"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":[0.003563708,0.0009286675,0.01387275,0.001238474,0.0004635395,0.001157233,0.006749473,0.3544259,0.07775334,0.2203816,0.01191552,0.3075498],"study_design_scores_gemma":[0.0004117861,0.001148666,0.00147764,0.0001169526,0.0001683905,0.001030719,0.0021959,0.7705643,0.02525665,0.1727974,0.02464984,0.000181777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09177588,0.0006240854,0.8990702,0.001689976,0.00009170002,0.0005337836,0.0005674012,0.002073649,0.003573376],"genre_scores_gemma":[0.3560306,0.000273283,0.6386673,0.0006250377,0.000203687,0.0004397433,0.001214203,0.0004599202,0.002086168],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02788503,"threshold_uncertainty_score":0.1474719,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162148987","doi":"","title":"Clusterability: A Theoretical Study","year":2009,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Cluster analysis; Generality; Computer science; Pairwise comparison; Set (abstract data type); Property (philosophy); Data mining; Theoretical computer science; Artificial intelligence","authors":[{"name":"Margareta Ackerman","is_ca":true},{"name":"Shai Ben-David","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.00920970011625449,"gpt":0.2564770682758922,"spread":0.2472673681596377,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01566457,0.001668136,0.00216494,0.009332836,0.005197671,0.01032295,0.005587206,0.003927781,0.01232882],"category_scores_gemma":[0.09896776,0.001490636,0.002944825,0.01379428,0.01632383,0.02372874,0.007530558,0.008217606,0.001694533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008427003,"about_ca_system_score_gemma":0.0019131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002845092,"about_ca_topic_score_gemma":0.001225878,"domain_scores_codex":[0.9814672,0.007583987,0.0009465778,0.003879882,0.004926989,0.001195417],"domain_scores_gemma":[0.8356991,0.1328838,0.007660625,0.01122135,0.009336126,0.003199073],"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":[0.00003055042,0.00003963295,0.001674197,0.0001962515,0.00003856892,0.00006452246,0.0004427217,0.008198379,0.0001825689,0.9763166,0.002412858,0.01040307],"study_design_scores_gemma":[0.00001578832,0.0000378486,0.0007189725,0.0001247487,0.00003054215,0.0002251886,0.0004268925,0.04438914,0.0005388469,0.9438255,0.009641402,0.00002523346],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04371805,0.009104131,0.8719686,0.0156654,0.0003264577,0.0002638858,0.0007135654,0.0002979003,0.05794201],"genre_scores_gemma":[0.8299276,0.008393838,0.1459786,0.001654726,0.002532156,0.0006952099,0.001550227,0.0004410938,0.008826506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01566457,"threshold_uncertainty_score":0.08284312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2020493833","doi":"10.1145/1989323.1989390","title":"BE-tree","year":2011,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Tree (set theory); Mathematics; Combinatorics","authors":[{"name":"Mohammad Sadoghi","is_ca":true},{"name":"Hans‐Arno Jacobsen","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.06173774393611898,"gpt":0.2255523000344625,"spread":0.1638145560983435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006699249,0.0004393962,0.0008402566,0.001374189,0.000818374,0.002325094,0.001698167,0.0006648306,0.009170614],"category_scores_gemma":[0.005154752,0.0003031549,0.0005140625,0.002659546,0.0005041593,0.004894018,0.00207004,0.0009394282,0.003015116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008087946,"about_ca_system_score_gemma":0.001346812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001692364,"about_ca_topic_score_gemma":0.003646183,"domain_scores_codex":[0.9992114,0.00009628768,0.0001092997,0.0001142947,0.0003774909,0.00009113457],"domain_scores_gemma":[0.998133,0.0005026085,0.000147366,0.000596703,0.0004844892,0.0001357148],"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":[0.000860126,0.0003174185,0.003149053,0.0009455333,0.00009691859,0.0002338835,0.0003997395,0.02219578,0.02172319,0.2645791,0.1264818,0.5590175],"study_design_scores_gemma":[0.0001601426,0.0005219334,0.001155332,0.0002064129,0.00007756992,0.0007873094,0.0002478148,0.2811845,0.03498944,0.2758189,0.4047272,0.0001234345],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0312921,0.002199559,0.9004377,0.001043251,0.0004021327,0.0005088284,0.01084746,0.01872109,0.03454788],"genre_scores_gemma":[0.2824111,0.001758345,0.6615787,0.00111089,0.0001821425,0.0008876346,0.02655372,0.002239995,0.02327763],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009170614,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2001088180","doi":"10.5555/338219.338659","title":"Computing contour trees in all dimensions","year":2000,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":90,"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":"Simple (philosophy); Computer science; Contour line; Algorithm; Artificial intelligence; Cartography; Geography","authors":[{"name":"Hamish Carr","is_ca":true},{"name":"Jack Snoeyink","is_ca":false},{"name":"Ulrike Axen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.02725043140270391,"gpt":0.2643550684760672,"spread":0.2371046370733632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007823548,0.001025038,0.001362323,0.002564674,0.001419963,0.003567486,0.001585013,0.001330829,0.008127303],"category_scores_gemma":[0.009273987,0.0008414043,0.001328764,0.003932793,0.001249417,0.007595608,0.00367719,0.001931726,0.003031484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006658987,"about_ca_system_score_gemma":0.0008701975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00237828,"about_ca_topic_score_gemma":0.003563682,"domain_scores_codex":[0.9987624,0.0001221386,0.0001568208,0.0002905429,0.0005061661,0.0001620349],"domain_scores_gemma":[0.9965463,0.001168017,0.0002980516,0.001153858,0.00068663,0.0001471295],"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":[0.0004192408,0.0001383671,0.005069087,0.0004929052,0.0001219926,0.0005938507,0.0008670875,0.1284083,0.02397908,0.2731954,0.01922727,0.5474874],"study_design_scores_gemma":[0.00006356046,0.00009415663,0.001090622,0.00008009433,0.00006712919,0.0004490651,0.0001923893,0.5227549,0.01569329,0.4307282,0.02871815,0.00006836955],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0168929,0.0002837254,0.9765013,0.0001121389,0.00006990969,0.00004626771,0.0003673683,0.002021732,0.003704567],"genre_scores_gemma":[0.1030761,0.0003344296,0.8926978,0.0000627118,0.00005353379,0.00009375272,0.001113428,0.0004170005,0.002151248],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008127303,"threshold_uncertainty_score":0.02718854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}