{"meta":{"query_hash":"3a9fca90f174","filters":{"venue":"IEEE Transactions on Knowledge and Data Engineering"},"cohort_total":120,"direct_labels_cover":0,"predictions_cover":120,"exported":120,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/3a9fca90f174","api":"https://metacan.xera.ac/api/v1/cohort?venue=IEEE+Transactions+on+Knowledge+and+Data+Engineering"},"results":[{"id":"W1616993132","doi":"10.1109/tkde.2015.2448541","title":"A Family of Rank Similarity Measures Based on Maximized Effectiveness Difference","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Chinese Academy of Sciences; Google","keywords":"Relevance (law); Measure (data warehouse); Metric (unit); Similarity (geometry); Rank (graph theory); Computer science; Similarity measure; Learning to rank; Maximization; Context (archaeology); Ranking (information retrieval); Data mining; Information retrieval; Mathematics; Artificial intelligence; Mathematical optimization","score_opus":0.07556383053037817,"score_gpt":0.29334646976984136,"score_spread":0.21778263923946317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1616993132","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02533409,0.000061836305,0.97370154,0.000018838586,0.00034222862,0.00016803606,0.000085513864,0.000097945136,0.00019000072],"genre_scores_gemma":[0.9957936,0.0000140846,0.004117541,0.000019171717,0.000010170557,0.000016796681,0.000008355867,0.0000062605363,0.000014029958],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991194,0.000062968,0.00017362222,0.00023512379,0.0002530983,0.00015577264],"domain_scores_gemma":[0.99882686,0.00024497233,0.00002561158,0.0006265047,0.00014245765,0.00013357763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005728825,0.00013159792,0.00018752167,0.00019563493,0.00006096488,0.000057397094,0.0005138473,0.000055905577,0.0000021276194],"category_scores_gemma":[0.000034050612,0.00011323416,0.000035897923,0.0003069698,0.000024301073,0.0004189875,0.00001080105,0.0001848422,0.000010260192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017842875,0.0027448179,0.0003183552,0.0014515274,0.0002091804,0.000034623623,0.0031598967,0.24133632,0.038810816,0.0028263808,0.0004962571,0.7068275],"study_design_scores_gemma":[0.0014056317,0.00018899435,0.0026467894,0.00010161503,0.000015421943,0.0000020929697,0.000008524449,0.97194207,0.023172837,0.000019119963,0.0003418208,0.00015505604],"about_ca_topic_score_codex":0.000016817088,"about_ca_topic_score_gemma":0.0000028516909,"teacher_disagreement_score":0.9704595,"about_ca_system_score_codex":0.000032604574,"about_ca_system_score_gemma":0.00009292023,"threshold_uncertainty_score":0.4617555},"labels":[],"label_agreement":null},{"id":"W1903488793","doi":"10.1109/tkde.2015.2453952","title":"A Cooperative Coevolution Framework for Parallel Learning to Rank","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Evolutionary Algorithms and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Science Foundation of Shandong Province; Academy of Finland; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Benchmark (surveying); Rank (graph theory); Coevolution; Context (archaeology); Learning to rank; Artificial intelligence; Divide and conquer algorithms; Machine learning; Evolutionary algorithm; Function (biology); Theoretical computer science; Algorithm; Ranking (information retrieval); Mathematics","score_opus":0.04245486072800539,"score_gpt":0.3010015428149192,"score_spread":0.2585466820869138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1903488793","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034731583,0.0002902785,0.99804926,0.00040595434,0.00032601386,0.00028223702,0.0000564966,0.00018665829,0.000055763136],"genre_scores_gemma":[0.40165687,0.0000495786,0.59757715,0.000048496782,0.00012660692,0.00023619572,0.000027939444,0.00001550963,0.0002616546],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992255,0.000015708285,0.00013240722,0.00036695783,0.0000796946,0.00017973766],"domain_scores_gemma":[0.9990847,0.0001798882,0.000016701482,0.00043670216,0.000102424776,0.0001795725],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019768465,0.00011699357,0.00011276936,0.00010200036,0.00020364986,0.0000692002,0.0003838449,0.000056438963,0.0000019485576],"category_scores_gemma":[0.0000313116,0.000119791606,0.000022263874,0.00034150874,0.00001224223,0.0004422978,0.000013603342,0.00017792944,0.00004380043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000350104,0.00027796143,0.000005276499,0.00004096758,0.00006426608,0.0000013750993,0.0027747718,0.873185,0.0004935424,0.061732028,0.0036700177,0.05771983],"study_design_scores_gemma":[0.00033424754,0.00013934875,0.000032669745,0.000038373062,0.00001070206,0.0000072349835,0.00006150585,0.96183693,0.00025827726,0.0004653873,0.036647227,0.00016811176],"about_ca_topic_score_codex":0.0000063326083,"about_ca_topic_score_gemma":0.000005948708,"teacher_disagreement_score":0.40130955,"about_ca_system_score_codex":0.00004257848,"about_ca_system_score_gemma":0.00005732877,"threshold_uncertainty_score":0.488496},"labels":[],"label_agreement":null},{"id":"W1969381345","doi":"10.1109/tkde.2014.2320725","title":"Malware Propagation in Large-Scale Networks","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Network Security and Intrusion Detection","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"National Natural Science Foundation of China","keywords":"Malware; Computer science; Pareto distribution; Scale (ratio); Scale-free network; Network security; Exponential function; Computer security; Exponential distribution; Complex network; Theoretical computer science; Data mining; Mathematics; Statistics","score_opus":0.011726118781379809,"score_gpt":0.22815498637143758,"score_spread":0.21642886759005778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969381345","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047469023,0.00015799074,0.9939108,0.000050284576,0.0007211432,0.00009626423,0.0000067811206,0.00015284629,0.00015702168],"genre_scores_gemma":[0.9952744,0.00011956282,0.0043907505,0.000031321844,0.00010807097,0.000015062975,0.00000888811,0.000009306713,0.000042615757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992097,0.00003213925,0.00015360447,0.00033548474,0.00007139743,0.00019764587],"domain_scores_gemma":[0.9993138,0.00006526827,0.000018789107,0.0005193247,0.000020360694,0.000062464955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031672404,0.000106748084,0.00010685691,0.00015125051,0.000101856895,0.00006943711,0.00033868797,0.00007458323,0.000008375896],"category_scores_gemma":[0.0000043312207,0.00010918443,0.00001793972,0.00037172658,0.000008089294,0.00065246434,0.000013571616,0.00024505085,0.000017705916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002157431,0.00032472127,0.000065190055,0.00010661993,0.000018739336,0.000003490922,0.0011169084,0.44712636,0.0005276478,0.0023582622,0.00044014995,0.5478903],"study_design_scores_gemma":[0.00024962393,0.000047523816,0.0003158597,0.000058982918,0.0000038199178,0.000006826274,0.0000056592726,0.99078286,0.00081919966,0.000028322269,0.007556307,0.00012504104],"about_ca_topic_score_codex":0.000005984046,"about_ca_topic_score_gemma":0.00013939658,"teacher_disagreement_score":0.9905275,"about_ca_system_score_codex":0.000021125536,"about_ca_system_score_gemma":0.000008946151,"threshold_uncertainty_score":0.4452412},"labels":[],"label_agreement":null},{"id":"W1969742982","doi":"10.1109/69.979978","title":"A comprehensive analytical performance model for disk devices under random workloads","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Waterloo; University of Toronto","keywords":"Optical disc; Computer science; Disk array; Magnetic storage; Server; Computer data storage; Optical storage; Constant (computer programming); Hard disk drive performance characteristics; Computer hardware; Computer network; Operating system","score_opus":0.06566339483825503,"score_gpt":0.28485298537923814,"score_spread":0.2191895905409831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969742982","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021604316,0.001247209,0.9954811,0.00011416532,0.00019733568,0.00018662462,0.00012938616,0.0004442514,0.000039551465],"genre_scores_gemma":[0.90097076,0.0005143831,0.098252684,0.00003800412,0.000023222565,0.00004786324,0.000010710032,0.000016111804,0.00012627832],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99896836,0.0000067018864,0.00018131142,0.00047962056,0.00009247612,0.00027149834],"domain_scores_gemma":[0.9986171,0.0002539734,0.00002525805,0.0009841353,0.00004490026,0.000074603005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006862899,0.00018842456,0.00020684973,0.00017186803,0.00016127645,0.00007883846,0.00083676924,0.000075835356,0.0000038765884],"category_scores_gemma":[0.00000786153,0.00017650923,0.000037115246,0.00030463643,0.000048465652,0.001168474,0.00003218074,0.00020321562,0.000018684173],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025998796,0.00014567135,0.000003946306,0.00015409371,0.00007852583,0.000002582754,0.0002496,0.79483235,0.00019580664,0.0023393012,0.0006164752,0.20135565],"study_design_scores_gemma":[0.0006901464,0.00004509256,0.000015533229,0.000049388636,0.000025330237,0.000009700158,0.00001441826,0.9957642,0.0005609631,0.00006891644,0.0025456434,0.0002106478],"about_ca_topic_score_codex":7.453552e-7,"about_ca_topic_score_gemma":0.0000054808056,"teacher_disagreement_score":0.8988103,"about_ca_system_score_codex":0.00003202083,"about_ca_system_score_gemma":0.000010477686,"threshold_uncertainty_score":0.7197838},"labels":[],"label_agreement":null},{"id":"W1969972789","doi":"10.1109/tkde.2011.260","title":"The Minimum Consistent Subset Cover Problem: A Minimization View of Data Mining","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complexity and Algorithms in Graphs","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Cluster analysis; Bipartite graph; Cardinality (data modeling); Clique; Set cover problem; Set (abstract data type); Theoretical computer science; Artificial intelligence; Graph; Mathematics; Data mining; Combinatorics","score_opus":0.08975363559799747,"score_gpt":0.27409211179744,"score_spread":0.1843384761994425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969972789","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00055260013,0.0011453227,0.9970045,0.000043088094,0.0004467821,0.00014502893,0.00021700688,0.000072365925,0.0003732739],"genre_scores_gemma":[0.71447915,0.0016182964,0.28346995,0.00003583193,0.000061683495,0.000030888907,0.000094925694,0.000028448478,0.00018084567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99900955,0.00003068845,0.00027031012,0.00039592717,0.00011403355,0.00017947552],"domain_scores_gemma":[0.9979887,0.00024847296,0.00005312383,0.0015938274,0.000052721083,0.000063154956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032773544,0.00013268145,0.00014958423,0.00009470849,0.00017814897,0.00006491318,0.0014630466,0.00004046924,0.000010252039],"category_scores_gemma":[0.000009032425,0.000108625914,0.000027108155,0.00033303368,0.000064942484,0.0007431464,0.00006977437,0.00011654631,0.000007420953],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005626401,0.0008037898,0.00004511808,0.00058261293,0.00042064177,0.0000136135695,0.00601497,0.0021627604,0.00066004775,0.0076936013,0.0044267764,0.9771198],"study_design_scores_gemma":[0.00033360862,0.000082272396,0.00010245806,0.00016298144,0.000049569317,0.00002418338,0.00005463477,0.9746625,0.0013874413,0.000096190364,0.022833755,0.00021045026],"about_ca_topic_score_codex":0.000012628344,"about_ca_topic_score_gemma":0.00004076039,"teacher_disagreement_score":0.97690934,"about_ca_system_score_codex":0.000008238702,"about_ca_system_score_gemma":0.00004544194,"threshold_uncertainty_score":0.44296363},"labels":[],"label_agreement":null},{"id":"W1978421404","doi":"10.1109/tkde.2014.3","title":"Editorial [State of the Transactions]","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Dalhousie University; University of Ottawa","keywords":"Computer science; Library science; Reputation; Operations research; Political science; Mathematics; Law","score_opus":0.008794747565106346,"score_gpt":0.21763764702363603,"score_spread":0.20884289945852968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978421404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0043855137,0.00013600531,0.9739922,0.00015137761,0.020922652,0.0001585382,0.00004308538,0.00009913593,0.000111492634],"genre_scores_gemma":[0.9941966,0.00006548741,0.004108173,0.00005635302,0.0014265592,0.000029300916,0.0000026826613,0.00001526862,0.00009957256],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920017,0.000021572809,0.0001776396,0.00028138122,0.00014871689,0.00017053021],"domain_scores_gemma":[0.9988233,0.00011088746,0.00003103863,0.0008978463,0.00006520263,0.00007171479],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009147876,0.00013253948,0.00012000957,0.0001004004,0.00012235739,0.00006410103,0.0009655181,0.000045025623,0.000014249902],"category_scores_gemma":[0.0000010536265,0.00009747183,0.000045056993,0.00040227926,0.000020511307,0.0006219624,0.000011305023,0.00022835855,0.000025004683],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003060885,0.00066917215,0.000016308555,0.000566738,0.00033407073,0.0000015030913,0.008781675,0.12199878,0.034044545,0.00053335464,0.0069750496,0.8260482],"study_design_scores_gemma":[0.0010200905,0.0001451042,0.0005431786,0.00021705907,0.0000759991,0.000023280878,0.000068585265,0.8095722,0.090327114,0.0003575977,0.0970917,0.00055808],"about_ca_topic_score_codex":0.000108110486,"about_ca_topic_score_gemma":0.00009351087,"teacher_disagreement_score":0.98981106,"about_ca_system_score_codex":0.0000093577255,"about_ca_system_score_gemma":0.000032782278,"threshold_uncertainty_score":0.39747858},"labels":[],"label_agreement":null},{"id":"W1992440927","doi":"10.1109/tkde.2014.2359672","title":"Incorporating Social Role Theory into Topic Models for Social Media Content Analysis","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; Engineering and Physical Sciences Research Council; National Natural Science Foundation of China","keywords":"Social media; Computer science; Microblogging; Generative model; Focus (optics); Topic model; Regularization (linguistics); Data science; Process (computing); World Wide Web; Information retrieval; Generative grammar; Artificial intelligence","score_opus":0.06034266008053929,"score_gpt":0.27600291463329624,"score_spread":0.21566025455275695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1992440927","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031462016,0.00016579477,0.9957112,0.00006782438,0.00049935613,0.00008682329,0.00003930881,0.00014121394,0.00014224382],"genre_scores_gemma":[0.9894822,0.000004553241,0.010069218,0.000014239748,0.0003020756,0.000040713898,0.000022926783,0.000011786155,0.000052246967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99909633,0.000047767066,0.00021539693,0.00035794018,0.00010124219,0.00018129332],"domain_scores_gemma":[0.99918354,0.00032020337,0.00004521238,0.000337905,0.000051147636,0.00006199816],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051609136,0.00013765042,0.00024377974,0.00021347117,0.0003523603,0.000106948784,0.00047258486,0.00008252395,0.0000012749194],"category_scores_gemma":[0.000013691601,0.00013253663,0.00008825614,0.00032333712,0.00001976593,0.00042870035,0.000013595928,0.00012062588,0.0000032964826],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044468692,0.00033305227,0.00003704409,0.00033041104,0.001285972,0.0000017866495,0.057875287,0.056757677,0.009690684,0.23850538,0.00042433693,0.6347139],"study_design_scores_gemma":[0.00027897337,0.000023073357,0.00004101272,0.00001462423,0.00008705148,9.76832e-7,0.00017662492,0.99625057,0.0009428223,0.0013582427,0.0006535567,0.00017244274],"about_ca_topic_score_codex":0.000018565988,"about_ca_topic_score_gemma":0.00011469204,"teacher_disagreement_score":0.98633605,"about_ca_system_score_codex":0.00003186954,"about_ca_system_score_gemma":0.000019997402,"threshold_uncertainty_score":0.5404687},"labels":[],"label_agreement":null},{"id":"W1997668352","doi":"10.1109/tkde.2012.190","title":"Efficient Cluster Labeling for Support Vector Clustering","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Cluster analysis; Disjoint sets; Interconnection; Cluster (spacecraft); Process (computing); Algorithm; Point (geometry); Function (biology); Data mining; Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.03179128225384418,"score_gpt":0.3012782757759483,"score_spread":0.2694869935221041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997668352","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018861995,0.00013514112,0.9961647,0.00016063215,0.0008012874,0.00047023536,0.000055256867,0.00027363823,0.0000529123],"genre_scores_gemma":[0.6742138,0.000045924502,0.32454228,0.00006200105,0.00016700722,0.00031074707,0.000016139154,0.00006135875,0.00058071903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99853677,0.000015714946,0.00023701151,0.00059457356,0.00015663153,0.00045929142],"domain_scores_gemma":[0.99846786,0.0002896977,0.000025350855,0.0009369754,0.00009816365,0.0001819236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025910293,0.00020181386,0.00018192695,0.00021245386,0.00019275174,0.00020341546,0.00082550675,0.00006817145,0.000017511544],"category_scores_gemma":[0.00001838526,0.00020094996,0.000041302406,0.00026453706,0.000021446775,0.00049665425,0.000060933766,0.000229735,0.00009714188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012830913,0.0001480305,9.831209e-7,0.00029378332,0.000058002715,0.0000037518253,0.0006233214,0.72303885,0.0077558216,0.00009692434,0.00039859803,0.26756912],"study_design_scores_gemma":[0.00049598893,0.00009092091,0.000018839393,0.000055120792,0.000007833664,0.000021120566,0.00001239109,0.99337006,0.0031099853,0.000009696324,0.0025802653,0.00022776137],"about_ca_topic_score_codex":0.000011262733,"about_ca_topic_score_gemma":0.000008030062,"teacher_disagreement_score":0.67232764,"about_ca_system_score_codex":0.00006352431,"about_ca_system_score_gemma":0.00003841933,"threshold_uncertainty_score":0.81945014},"labels":[],"label_agreement":null},{"id":"W2003787915","doi":"10.1109/tkde.2014.2310219","title":"Discovery of Temporal Associations in Multivariate Time Series","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data mining; Multivariate statistics; Time series; Pruning; Scalability; Redundancy (engineering); Series (stratigraphy); Artificial intelligence; Machine learning","score_opus":0.015994662512468352,"score_gpt":0.23679044876291291,"score_spread":0.22079578625044455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2003787915","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0072914674,0.00005240763,0.992117,0.000042548072,0.00012642224,0.000040138922,0.000073821335,0.000046504316,0.00020968704],"genre_scores_gemma":[0.98439,0.000013609996,0.015292116,0.0000034126579,0.000022622728,0.0000034155114,0.000017731674,0.000007205678,0.0002498859],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935114,0.00002182126,0.00020621445,0.00022571853,0.00006620343,0.00012892278],"domain_scores_gemma":[0.99937755,0.00010846077,0.000042456013,0.0004142422,0.000027950471,0.000029333456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024488993,0.000092571914,0.00017408017,0.00014872018,0.00005595934,0.000062460764,0.00030746657,0.00003683161,0.000003294489],"category_scores_gemma":[0.000018368308,0.000089453766,0.000027834676,0.00038749378,0.000013257804,0.0011420602,0.000014334381,0.00009906918,0.000007929561],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008725067,0.001997831,0.002567084,0.0006163179,0.0008239264,0.000016130778,0.00893539,0.45376864,0.07590658,0.034361918,0.0007387589,0.42018017],"study_design_scores_gemma":[0.00019140531,0.000041781463,0.0014648101,0.000045517452,0.000013796639,0.0000018536441,0.000010137998,0.99468845,0.0026868824,0.000033530636,0.00069951214,0.00012232545],"about_ca_topic_score_codex":0.00006817064,"about_ca_topic_score_gemma":0.000089150984,"teacher_disagreement_score":0.9770985,"about_ca_system_score_codex":0.000015558007,"about_ca_system_score_gemma":0.000017227405,"threshold_uncertainty_score":0.36478186},"labels":[],"label_agreement":null},{"id":"W2026060326","doi":"10.1109/tkde.2012.151","title":"NHOP: A Nested Associative Pattern for Analysis of Consensus Sequence Ensembles","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Associative property; Computer science; Sequence (biology); Tree (set theory); Theoretical computer science; Tree structure; Pattern recognition (psychology); Core (optical fiber); Artificial intelligence; Algorithm; Data mining; Computational biology; Mathematics; Combinatorics; Biology; Binary tree","score_opus":0.03855882831999959,"score_gpt":0.2947681018071184,"score_spread":0.2562092734871188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026060326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11965935,0.0006443176,0.87820774,0.000012258469,0.00017103963,0.00011139187,0.001142238,0.000008764941,0.00004290664],"genre_scores_gemma":[0.9981168,0.00011132312,0.0013622093,0.000018442817,0.000058845515,0.000012507373,0.00026194612,0.00000972885,0.000048218462],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995021,0.000009732212,0.00016318918,0.00013240137,0.000033375796,0.000159188],"domain_scores_gemma":[0.99951243,0.00006315369,0.000047136116,0.0002752618,0.00004345593,0.000058578204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016805474,0.00009673585,0.00015509602,0.000081083366,0.000041679712,0.000008057676,0.00009950094,0.00008421428,0.0000029835403],"category_scores_gemma":[0.000008163556,0.00009480254,0.00006018289,0.00013269838,0.00001931988,0.000007161093,0.0000054118436,0.000053476157,9.4866215e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002939531,0.0009800531,0.003163287,0.00088233396,0.013283846,0.000001575903,0.0044815177,0.08711105,0.47795665,0.00026128642,0.0038439508,0.4077405],"study_design_scores_gemma":[0.00093810697,0.00021268526,0.0016822979,0.000058239628,0.0015811762,0.000008011699,0.00022751586,0.9186438,0.06576114,0.000005748914,0.010389854,0.000491471],"about_ca_topic_score_codex":0.0000082343,"about_ca_topic_score_gemma":0.000048039896,"teacher_disagreement_score":0.8784574,"about_ca_system_score_codex":0.000008286624,"about_ca_system_score_gemma":0.000016513635,"threshold_uncertainty_score":0.38659355},"labels":[],"label_agreement":null},{"id":"W2030978449","doi":"10.1109/tkde.2014.2357012","title":"ISC: An Iterative Social Based Classifier for Adult Account Detection on Twitter","year":2014,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Classifier (UML); Social graph; Graph; Machine learning; Social media; Artificial intelligence; Data mining; Information retrieval; World Wide Web; Theoretical computer science","score_opus":0.03642803597983174,"score_gpt":0.27845537529562386,"score_spread":0.24202733931579212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2030978449","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007605626,0.0000064682717,0.9905701,0.00014673012,0.0012006697,0.00014439711,0.000041247025,0.000196064,0.00008867109],"genre_scores_gemma":[0.99434537,0.000002397504,0.0049528913,0.00022590236,0.0003382449,0.000058090704,0.000015548841,0.000018193317,0.000043344382],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912244,0.000034578483,0.00013236266,0.00043602756,0.00009740959,0.00017715666],"domain_scores_gemma":[0.99920696,0.00015041616,0.000027579717,0.0004536534,0.000093405106,0.00006795846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020907677,0.00015501067,0.00011926629,0.00017317063,0.00028785685,0.00019192204,0.00031078627,0.00009485159,0.0000037601872],"category_scores_gemma":[0.0000136614035,0.00015076238,0.00004040464,0.00017752871,0.000012815559,0.0007753131,0.0000037860666,0.00019047254,0.000014423208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002004195,0.0004847528,0.0000046347545,0.00018550694,0.0000846173,0.0000013135636,0.003025391,0.019340638,0.026769895,0.0014237155,0.0012528561,0.9472263],"study_design_scores_gemma":[0.00051702396,0.00031623806,0.000114666516,0.000028800016,0.000016974467,0.0000023046373,0.000011573781,0.9527159,0.037919745,0.0000509183,0.008113056,0.00019281117],"about_ca_topic_score_codex":0.0000087768685,"about_ca_topic_score_gemma":0.00006606185,"teacher_disagreement_score":0.98673975,"about_ca_system_score_codex":0.000041427054,"about_ca_system_score_gemma":0.000016164726,"threshold_uncertainty_score":0.61479115},"labels":[],"label_agreement":null},{"id":"W2051664277","doi":"10.1109/tkde.2011.100","title":"Discovery of Delta Closed Patterns and Noninduced Patterns from Sequences","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Substring; Computer science; Set (abstract data type); Sequence (biology); Data mining; Suffix tree; Pattern recognition (psychology); Artificial intelligence; Data structure","score_opus":0.04450856788129964,"score_gpt":0.2576284759502814,"score_spread":0.21311990806898173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2051664277","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21294737,0.000092417205,0.78518575,0.000014101319,0.00016424306,0.00005760756,0.0014599231,0.000051750674,0.00002679902],"genre_scores_gemma":[0.9726999,0.00019597157,0.026966684,0.000010686461,0.000027651768,0.000015118706,0.000059748923,0.000009466268,0.000014803591],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921966,0.0000107921815,0.00017368246,0.0003918775,0.000070701884,0.00013328837],"domain_scores_gemma":[0.9990593,0.000084898056,0.00003512103,0.0007328745,0.000024841576,0.00006294543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000082200226,0.00012621337,0.00014012282,0.00008788722,0.00006611582,0.00007266929,0.00056529936,0.00004339957,0.000005742747],"category_scores_gemma":[0.000002830996,0.00011865254,0.00001856895,0.00011105419,0.000021948592,0.0009402006,0.000028144792,0.00011358203,0.0000035438736],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016029982,0.000660152,0.0012638138,0.00022685269,0.00027354844,0.00001880547,0.0063498663,0.00016364297,0.01894037,0.0019816298,0.00012015768,0.9699851],"study_design_scores_gemma":[0.0007972752,0.00019536527,0.024033811,0.00042180324,0.000104744446,0.000024419467,0.00022230175,0.8538889,0.11902941,0.00016486984,0.00045214497,0.00066490535],"about_ca_topic_score_codex":0.0006231207,"about_ca_topic_score_gemma":0.0001251101,"teacher_disagreement_score":0.96932024,"about_ca_system_score_codex":0.000007019673,"about_ca_system_score_gemma":0.000020526792,"threshold_uncertainty_score":0.48385102},"labels":[],"label_agreement":null},{"id":"W2059054797","doi":"10.1109/tkde.2013.88","title":"Mining Statistically Significant Co-location and Segregation Patterns","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Data mining; Correlation; Artificial intelligence; Pattern recognition (psychology); Mathematics","score_opus":0.02346222270620061,"score_gpt":0.2662764905445469,"score_spread":0.24281426783834628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059054797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007077262,0.000051338873,0.9921492,0.00011648136,0.0001131526,0.00014682638,0.00016049613,0.00012389067,0.00006138504],"genre_scores_gemma":[0.8807807,0.00007153591,0.1188743,0.000022714064,0.000027521746,0.000069964684,0.00008167647,0.000011368979,0.000060195838],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992233,0.000012224949,0.00015937124,0.00037636838,0.00008048425,0.00014824641],"domain_scores_gemma":[0.9991368,0.00015517845,0.000024930017,0.00052364334,0.000051179246,0.000108255874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011727288,0.000114962895,0.00009376403,0.00009814605,0.00013033334,0.00022394022,0.00030636482,0.00003731944,0.000011627266],"category_scores_gemma":[0.000008127247,0.00011407876,0.000007502587,0.0001695901,0.000019341596,0.0008171042,0.000011441905,0.0000997757,0.00003845317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[9.605554e-7,0.00008008433,0.000034210585,0.00008493797,0.000020791433,0.0000011765535,0.0005016862,0.00062279555,0.0016212736,0.0026253646,0.0005480857,0.99385864],"study_design_scores_gemma":[0.00014625283,0.000037917078,0.0019614056,0.000047600268,0.000011971602,0.0000072552252,0.000039687326,0.99557483,0.0011556799,0.000042123687,0.00082246534,0.00015280042],"about_ca_topic_score_codex":0.000049297883,"about_ca_topic_score_gemma":0.000009099314,"teacher_disagreement_score":0.994952,"about_ca_system_score_codex":0.000013878166,"about_ca_system_score_gemma":0.000022228054,"threshold_uncertainty_score":0.46519968},"labels":[],"label_agreement":null},{"id":"W2076039115","doi":"10.1109/tkde.2009.25","title":"Evaluating the Generation of Domain Ontologies in the Knowledge Puzzle Project","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":69,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Ontology; Computer science; Ontology learning; Upper ontology; Information retrieval; Domain (mathematical analysis); Ontology-based data integration; Domain knowledge; Process ontology; Suggested Upper Merged Ontology; Set (abstract data type); Ontology alignment; Natural language processing; Data science; Artificial intelligence; Semantic Web","score_opus":0.1546157879818343,"score_gpt":0.36613754980686486,"score_spread":0.21152176182503055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076039115","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.038914345,0.00085513736,0.95917803,0.00025720094,0.00024911753,0.00022029907,0.0000064006736,0.000049890645,0.00026955243],"genre_scores_gemma":[0.9748093,0.000056327524,0.025002342,0.00002070326,0.00006293332,0.000021271127,0.0000027100382,0.000003847534,0.000020599677],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99919033,0.00008628238,0.00020697918,0.00026345684,0.00010699531,0.00014594],"domain_scores_gemma":[0.9989139,0.00020569593,0.000028363334,0.0008096169,0.000028793778,0.000013633193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087136327,0.00010186845,0.00010760288,0.00011297474,0.00012573537,0.00006575783,0.0008079504,0.000039123046,8.327247e-7],"category_scores_gemma":[0.000019380479,0.00006537016,0.000022530365,0.00033145634,0.00001537259,0.00035586962,0.000009762877,0.00018301983,0.0000020313819],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001085026,0.00033255445,0.000008578974,0.000074903204,0.000027867203,0.0000033015904,0.018746296,0.13484462,0.017179964,0.009188426,0.0002256692,0.819357],"study_design_scores_gemma":[0.00018238409,0.000090589885,0.00014136956,0.000035379355,0.000008155248,0.000009739869,0.000109841654,0.99709904,0.0015904013,0.00010438216,0.00054684945,0.000081853614],"about_ca_topic_score_codex":0.000017010112,"about_ca_topic_score_gemma":0.00014907208,"teacher_disagreement_score":0.9358949,"about_ca_system_score_codex":0.000020413361,"about_ca_system_score_gemma":0.000045857818,"threshold_uncertainty_score":0.2665718},"labels":[],"label_agreement":null},{"id":"W2085909071","doi":"10.1109/tkde.2010.226","title":"Privacy Preserving Decision Tree Learning Using Unrealized Data Sets","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Decision tree; Incremental decision tree; Tree (set theory); Decision tree learning; Information privacy; Data mining; Artificial intelligence; Machine learning; Computer security; Mathematics","score_opus":0.06209211290478007,"score_gpt":0.32537221592102517,"score_spread":0.2632801030162451,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085909071","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02380718,0.0002919365,0.972679,0.00033079175,0.001293812,0.00018135957,0.00021051762,0.0010991001,0.0001063124],"genre_scores_gemma":[0.42407173,0.00019868101,0.5754898,0.000009711624,0.00006308425,0.000008161234,0.00009955382,0.00003910035,0.000020163405],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768,0.000042441996,0.00036273763,0.001190877,0.00026449113,0.0004594159],"domain_scores_gemma":[0.981989,0.00064854877,0.00007308756,0.017077237,0.000057887213,0.00015422193],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00082893646,0.0003004261,0.0002733222,0.00039139533,0.00034738219,0.00036058834,0.028658045,0.00020561337,0.000020487274],"category_scores_gemma":[0.0026941523,0.0003052232,0.000032239637,0.0006806769,0.000052975003,0.0032334616,0.009679719,0.0011157548,0.000023969968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003694793,0.00031119346,0.0001264041,0.00020163476,0.00015681649,0.000046236855,0.0002980576,0.011948046,0.042964563,0.0002320826,0.014875396,0.9288026],"study_design_scores_gemma":[0.0004479336,0.00002872208,0.00011168351,0.00013530544,0.000029425122,0.000059057158,0.000008965685,0.9823125,0.0037172306,0.00061688595,0.012203631,0.0003286486],"about_ca_topic_score_codex":0.000059237267,"about_ca_topic_score_gemma":0.00012754322,"teacher_disagreement_score":0.97036445,"about_ca_system_score_codex":0.00003693302,"about_ca_system_score_gemma":0.00008046273,"threshold_uncertainty_score":0.99994},"labels":[],"label_agreement":null},{"id":"W2091214390","doi":"10.1109/tkde.2012.220","title":"Bias Correction in a Small Sample from Big Data","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":71,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Estimator; Sample size determination; Computer science; Sampling bias; Big data; Sample (material); Simple random sample; Population size; Sampling (signal processing); Statistics; Reciprocal; Population; Point estimation; Data mining; Mathematics; Telecommunications","score_opus":0.10547437860269274,"score_gpt":0.291973674795889,"score_spread":0.18649929619319625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091214390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02976199,0.00031587214,0.9678766,0.000007196609,0.00079259113,0.00008691838,0.000843008,0.000090901405,0.00022490259],"genre_scores_gemma":[0.9943161,0.000037062564,0.004241915,0.000004113786,0.00046392943,0.000016686821,0.00085270085,0.000020412133,0.000047072077],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921894,0.00002390862,0.00018510895,0.00031131005,0.000043518634,0.00021719444],"domain_scores_gemma":[0.9986143,0.00028442778,0.000026760728,0.0009817338,0.000012374025,0.00008040761],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020174023,0.00014408729,0.00017150523,0.0001596882,0.000059420283,0.00003768162,0.00034559765,0.000034882567,0.000084223604],"category_scores_gemma":[0.0000046288033,0.00015162403,0.000026389589,0.00027964858,0.000010504908,0.00033799934,0.000024289306,0.00021906346,0.000017820212],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016830129,0.0005624874,0.008457338,0.000016600681,0.00018508578,4.823119e-7,0.0005007351,0.0031869484,0.00084081735,0.00011105943,0.002225028,0.9838966],"study_design_scores_gemma":[0.00057161984,0.00003060772,0.0057300157,0.00016622027,0.00022164064,0.0000015229909,0.00017140097,0.9165331,0.0041234945,0.00013899432,0.07173528,0.00057609536],"about_ca_topic_score_codex":0.0017711378,"about_ca_topic_score_gemma":0.000915329,"teacher_disagreement_score":0.9833205,"about_ca_system_score_codex":0.000020320658,"about_ca_system_score_gemma":0.00001469365,"threshold_uncertainty_score":0.61830485},"labels":[],"label_agreement":null},{"id":"W2096451472","doi":"10.1109/tkde.2005.50","title":"Using AUC and accuracy in evaluating learning algorithms","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":2141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Machine learning; Computer science; Artificial intelligence; Naive Bayes classifier; Decision tree; Measure (data warehouse); Receiver operating characteristic; Algorithm; Bayes' theorem; Data mining; Support vector machine; Bayesian probability","score_opus":0.09066818198011457,"score_gpt":0.36427771998820674,"score_spread":0.2736095380080922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2096451472","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00894332,0.00035339608,0.99011266,0.000068032634,0.000105427396,0.000108614746,0.000016149323,0.00024273459,0.00004968545],"genre_scores_gemma":[0.68607575,0.000179386,0.31363192,0.000013854731,0.00004045405,0.00001263597,0.0000078499515,0.000012049299,0.000026105074],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999059,0.000033897497,0.00020603418,0.0004149186,0.00009663967,0.0001895097],"domain_scores_gemma":[0.99914235,0.00019877493,0.000036044283,0.00053367537,0.000028324797,0.000060829843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004324713,0.00012765932,0.00012357759,0.00024086074,0.000115293966,0.00011566273,0.00040132855,0.00005380643,0.0000035803712],"category_scores_gemma":[0.000038647686,0.00013922688,0.000010970224,0.00030868992,0.000016768903,0.0014475895,0.000025576199,0.00028808718,0.00000661875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028092593,0.00006130484,0.00002767492,0.000040366176,0.000010287849,0.0000019830834,0.0006082497,0.031069074,0.015809016,0.00030831047,0.000025598727,0.9520353],"study_design_scores_gemma":[0.00020956731,0.000025590862,0.00018452054,0.000074669726,0.0000060417347,0.00001956216,0.000015250223,0.9869223,0.010098672,0.000011923785,0.0022801047,0.00015179551],"about_ca_topic_score_codex":0.000013082415,"about_ca_topic_score_gemma":0.00001194664,"teacher_disagreement_score":0.9558532,"about_ca_system_score_codex":0.000054579756,"about_ca_system_score_gemma":0.000032820048,"threshold_uncertainty_score":0.5677507},"labels":[],"label_agreement":null},{"id":"W2109468254","doi":"10.1109/tkde.2012.86","title":"Achieving Data Privacy through Secrecy Views and Null-Based Virtual Updates","year":2012,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada; Technische Universität Wien","keywords":"Computer science; Null (SQL); Secrecy; Tuple; SQL; Semantics (computer science); Relational database; Information retrieval; Theoretical computer science; Database; Data mining; Programming language; Computer security; Mathematics","score_opus":0.06739210014020883,"score_gpt":0.3002273917608937,"score_spread":0.23283529162068486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109468254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007637916,0.004485798,0.98570937,0.00010421032,0.0010324065,0.00016921439,0.00014912615,0.00028645725,0.000425478],"genre_scores_gemma":[0.97104436,0.0005481895,0.027876306,0.000069067144,0.00023618339,0.000014959956,0.00010642942,0.000029795785,0.000074705466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983616,0.000055595698,0.00026746324,0.0007102315,0.0001354865,0.00046961536],"domain_scores_gemma":[0.9973345,0.00029898048,0.00004801573,0.0020647119,0.000023419147,0.000230394],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005086358,0.00030144607,0.00028122414,0.00013090434,0.00027063713,0.00020512457,0.0015249249,0.00010397867,0.000018224167],"category_scores_gemma":[0.000034759898,0.00027139636,0.000034115863,0.00032739437,0.000047695303,0.0030185257,0.00013937833,0.00031986035,0.000054663582],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009376629,0.0031112314,0.001394221,0.0012932247,0.0006397944,0.000034124874,0.025900735,0.007223397,0.011888772,0.0289523,0.012311156,0.9071573],"study_design_scores_gemma":[0.001034534,0.0001571321,0.0008436706,0.00021668943,0.00011657397,0.00006887887,0.000074943826,0.7572511,0.0045200656,0.000035713238,0.23483032,0.0008503931],"about_ca_topic_score_codex":0.000012692464,"about_ca_topic_score_gemma":0.000012631066,"teacher_disagreement_score":0.96340644,"about_ca_system_score_codex":0.000027623728,"about_ca_system_score_gemma":0.000053413503,"threshold_uncertainty_score":0.99997383},"labels":[],"label_agreement":null},{"id":"W2110420974","doi":"10.1109/tkde.2010.186","title":"Exact Top-K Queries in Wireless Sensor Networks","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Energy Efficient Wireless Sensor Networks","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Network topology; Wireless sensor network; Context (archaeology); Tree (set theory); Topology (electrical circuits); Algorithm; Set (abstract data type); Logical topology; Theoretical computer science; Computer network; Mathematics","score_opus":0.012046588402308779,"score_gpt":0.23622373699697677,"score_spread":0.224177148594668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2110420974","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08187029,0.00013623573,0.9156399,0.000054217657,0.001756459,0.000085837404,0.000011557004,0.00024685913,0.00019865825],"genre_scores_gemma":[0.98461205,0.00015592734,0.014930924,0.000021500498,0.00013227157,0.0000139807435,0.000008697975,0.000024327173,0.00010031951],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987251,0.00002543694,0.0002286491,0.000548284,0.000108319895,0.0003641957],"domain_scores_gemma":[0.9984711,0.00023007226,0.00002756387,0.0011139667,0.00002967239,0.00012762292],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022448918,0.0002133824,0.00020120696,0.00022673969,0.00010391261,0.00012629718,0.0007380766,0.00014729478,0.000008736735],"category_scores_gemma":[0.000005816469,0.00021850014,0.000031497722,0.00049886026,0.00003875292,0.00055775756,0.00002304328,0.0006539801,0.000012048922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008637493,0.00016152569,0.00009349635,0.00003053315,0.000020183135,0.000024875257,0.0002779141,0.92812306,0.00398115,0.0019526761,0.00008631392,0.06523965],"study_design_scores_gemma":[0.0002469513,0.000022929013,0.00029061805,0.000052828796,0.000005909207,0.000026267651,0.000009486736,0.9929169,0.0037143067,0.000002324551,0.0024608674,0.00025062065],"about_ca_topic_score_codex":0.000029308589,"about_ca_topic_score_gemma":0.00030454298,"teacher_disagreement_score":0.90274173,"about_ca_system_score_codex":0.000019907022,"about_ca_system_score_gemma":0.000025274205,"threshold_uncertainty_score":0.89101774},"labels":[],"label_agreement":null},{"id":"W2111680152","doi":"10.1109/tkde.2005.111","title":"Integration and efficient lookup of compressed XML accessibility maps","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Simon Fraser University; Chinese University of Hong Kong; University of Hong Kong","keywords":"Computer science; XML; XML database; Efficient XML Interchange; Streaming XML; Document Structure Description; XML framework; XML Signature; Representation (politics); Database; Information retrieval; World Wide Web","score_opus":0.029268377672019983,"score_gpt":0.3110997126736295,"score_spread":0.2818313350016095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2111680152","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17831911,0.0011047423,0.8174432,0.00018044836,0.0003354212,0.00023142564,0.0001874925,0.0000947516,0.002103431],"genre_scores_gemma":[0.99893486,0.0001549689,0.00073187845,0.0000071654354,0.00007646344,0.000006914632,0.000009160653,0.000005779839,0.00007283003],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999388,0.00002806809,0.00015609084,0.00020867481,0.00009499589,0.00012419916],"domain_scores_gemma":[0.99949783,0.00012782901,0.000027605634,0.00022874029,0.000043705986,0.000074299474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002685894,0.00008382046,0.0001268919,0.00007935461,0.00016748432,0.000047031226,0.00017996541,0.000054631426,0.000029821313],"category_scores_gemma":[0.000015441508,0.000076891025,0.00001828484,0.00013419517,0.00007686615,0.0003376744,0.0000053135345,0.00011182129,0.000004508686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011266602,0.0008635381,0.0003156998,0.0002373026,0.000115787196,0.0000016786942,0.010760465,0.032695778,0.010007411,0.004577698,0.00027671244,0.9400353],"study_design_scores_gemma":[0.0014585516,0.000069020556,0.0043624258,0.00018450379,0.00013210959,0.0000020113855,0.0008316991,0.95667166,0.013697281,0.00006381642,0.022116678,0.00041027128],"about_ca_topic_score_codex":0.0001406371,"about_ca_topic_score_gemma":0.00072586804,"teacher_disagreement_score":0.93962497,"about_ca_system_score_codex":0.000021891392,"about_ca_system_score_gemma":0.000027722204,"threshold_uncertainty_score":0.3135525},"labels":[],"label_agreement":null},{"id":"W2112154958","doi":"10.1109/tkde.2009.59","title":"Discovering Transitional Patterns and Their Significant Milestones in Transaction Databases","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Database; Database transaction; Transaction processing; Transaction log; Distributed database; Information retrieval; Data science","score_opus":0.02862650924382022,"score_gpt":0.26474186092001395,"score_spread":0.23611535167619374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112154958","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03409625,0.00019978362,0.964288,0.00019245023,0.00011755768,0.0001054973,0.0008850886,0.00009924736,0.00001610507],"genre_scores_gemma":[0.9857031,0.0004192302,0.01366876,0.000026865091,0.000033989698,0.000020043142,0.000110551635,0.000008794475,0.000008666798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990932,0.00001323644,0.0001789564,0.000465786,0.00006761655,0.00018121781],"domain_scores_gemma":[0.9992834,0.0000954758,0.000016879583,0.0005093845,0.000010804383,0.00008410362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013033832,0.00016332288,0.00014235888,0.00017078308,0.00010687142,0.000091707305,0.00031101218,0.00003239031,0.000003842977],"category_scores_gemma":[0.0000014863026,0.0001522026,0.000017730936,0.00021497921,0.000017230182,0.0010835021,0.000005098458,0.00017035849,0.0000027075228],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013704219,0.00047813874,0.000031588846,0.000085124186,0.000029747995,0.000010539873,0.0016846261,0.008581818,0.011482766,0.0016804059,0.000049232534,0.9758723],"study_design_scores_gemma":[0.00042999483,0.00006536283,0.0044833324,0.00016344138,0.000013157374,0.000042028976,0.00010597953,0.98644996,0.006322247,0.000038522714,0.0015759134,0.00031004264],"about_ca_topic_score_codex":0.000057808036,"about_ca_topic_score_gemma":0.00008358562,"teacher_disagreement_score":0.97786814,"about_ca_system_score_codex":0.00001707544,"about_ca_system_score_gemma":0.000019457706,"threshold_uncertainty_score":0.62066424},"labels":[],"label_agreement":null},{"id":"W2114175725","doi":"10.1109/tkde.2009.49","title":"Enhancing Learning Objects with an Ontology-Based Memory","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Reusability; Learning object; Ontology; Semantic Web; Process (computing); Knowledge base; Artificial intelligence; Natural language processing; World Wide Web; Programming language","score_opus":0.01977965045427822,"score_gpt":0.2566786341254655,"score_spread":0.23689898367118728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2114175725","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.024797268,0.00029884194,0.9737415,0.00008705628,0.00024639806,0.00007608286,0.0000029111047,0.00045205158,0.00029792346],"genre_scores_gemma":[0.95276225,0.00001894879,0.04703993,0.000070929455,0.00003733833,0.0000051279812,0.0000053169997,0.000008827369,0.00005134684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990444,0.00002832367,0.00013298492,0.0004452377,0.00009201658,0.00025700813],"domain_scores_gemma":[0.9990389,0.00012483406,0.000024438126,0.00068267935,0.00003035665,0.00009880445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017631777,0.00016609511,0.0001741435,0.00016983326,0.00016479848,0.00009123346,0.00051323755,0.00006520085,0.000003835032],"category_scores_gemma":[0.000009193711,0.00014520966,0.000019758858,0.00022561436,0.000020115116,0.0007008697,0.0000045466227,0.00025801844,0.000010475551],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014032796,0.0008538159,0.00008614992,0.00024910213,0.00013493799,0.0001917087,0.0054207207,0.30960035,0.04109005,0.0013473245,0.000080900034,0.6408046],"study_design_scores_gemma":[0.00070776744,0.000808735,0.0009464563,0.00014062494,0.000034076813,0.000061208426,0.00014309185,0.9427091,0.053495936,0.000027962818,0.00053381675,0.00039123866],"about_ca_topic_score_codex":0.000013854805,"about_ca_topic_score_gemma":0.00020294334,"teacher_disagreement_score":0.927965,"about_ca_system_score_codex":0.00001944985,"about_ca_system_score_gemma":0.000060303082,"threshold_uncertainty_score":0.59214777},"labels":[],"label_agreement":null},{"id":"W2117287993","doi":"10.1109/tkde.2008.94","title":"Detecting Word Substitutions in Text","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Sentence; Word (group theory); Natural language processing; Set (abstract data type); Artificial intelligence; Linguistics","score_opus":0.06066739218277305,"score_gpt":0.31280192462405365,"score_spread":0.2521345324412806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2117287993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41101897,0.00048025558,0.564066,0.00020601109,0.0011006279,0.0002967356,0.000074183656,0.00033171568,0.02242551],"genre_scores_gemma":[0.9985502,0.00049702555,0.0004589167,0.000017336182,0.00005424544,0.000002705215,0.000004082472,0.0000059435556,0.0004095752],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994247,0.00001857455,0.00014154296,0.00012720517,0.00009271912,0.00019528723],"domain_scores_gemma":[0.9995549,0.00010038391,0.000014617851,0.00020083277,0.000020122112,0.000109142595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024788777,0.00007416542,0.00008150951,0.0002029129,0.00040950836,0.000031913918,0.0001499505,0.0000553642,0.000077173],"category_scores_gemma":[0.000045577985,0.000079196725,0.0000158373,0.00039769177,0.00005167466,0.0006896861,0.000002178723,0.00017014537,0.000064067644],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069816546,0.0007746851,0.00041967464,0.00020372271,0.000104545674,0.000049841798,0.2680244,0.06859999,0.0019953386,0.0057703606,0.0035786098,0.65040904],"study_design_scores_gemma":[0.0042524324,0.00016558086,0.018156325,0.0008042565,0.000094753836,0.00015907161,0.01941351,0.3497768,0.009016208,0.000077864155,0.59582955,0.0022536844],"about_ca_topic_score_codex":0.00019046088,"about_ca_topic_score_gemma":0.0014271823,"teacher_disagreement_score":0.64815533,"about_ca_system_score_codex":0.00005130095,"about_ca_system_score_gemma":0.000086602755,"threshold_uncertainty_score":0.3229549},"labels":[],"label_agreement":null},{"id":"W2118532575","doi":"10.1109/tkde.2005.201","title":"Localization site prediction for membrane proteins by integrating rule and SVM classification","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Support vector machine; Computer science; Subsequence; Artificial intelligence; Machine learning; Precision and recall; Data mining; Curse of dimensionality; Kernel (algebra); Feature vector","score_opus":0.01169135818690139,"score_gpt":0.2569569636183845,"score_spread":0.2452656054314831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118532575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022597538,0.000286768,0.97621983,0.000053606473,0.00008453918,0.0002492404,0.00037191878,0.00004192688,0.00009462565],"genre_scores_gemma":[0.9805459,0.00030025883,0.017350344,0.00003189204,0.00014324741,0.000064419706,0.0013117471,0.000024408464,0.00022777934],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994695,0.000010316137,0.00016276167,0.00020987837,0.000043393986,0.00010412361],"domain_scores_gemma":[0.99962837,0.000019162006,0.000034048488,0.0002354954,0.000035883597,0.000047018366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014139767,0.0001081956,0.00007328372,0.000049329712,0.00011209891,0.00003475426,0.00007417921,0.00009269423,0.0000030744948],"category_scores_gemma":[0.000023627255,0.000108504915,0.000014789418,0.000054887663,0.000017002028,0.000033080643,0.0000046974365,0.000094156545,0.0000025107845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008474584,0.00017577823,0.00016204592,0.0005312181,0.00009227239,8.278479e-8,0.00059101224,0.046774387,0.7753748,0.0000896467,0.0027593544,0.17336462],"study_design_scores_gemma":[0.0003374516,0.000095328855,0.000039761337,0.0000336085,0.000023950446,0.000005459881,0.0000247194,0.8649211,0.07259946,8.61469e-7,0.061809994,0.00010829601],"about_ca_topic_score_codex":0.0000036063982,"about_ca_topic_score_gemma":0.00002307442,"teacher_disagreement_score":0.9588695,"about_ca_system_score_codex":0.000012218722,"about_ca_system_score_gemma":0.000012381977,"threshold_uncertainty_score":0.44247022},"labels":[],"label_agreement":null},{"id":"W2119387217","doi":"10.1109/tkde.2008.77","title":"Bias and Controversy in Evaluation Systems","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Set (abstract data type); Object (grammar); Feature (linguistics); Information retrieval; Data set; Data science; Artificial intelligence; Data mining; Machine learning","score_opus":0.09300923597913141,"score_gpt":0.29509245422620883,"score_spread":0.20208321824707742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119387217","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00989875,0.0015335893,0.9874365,0.000035175803,0.00048432947,0.0002168658,0.000013722823,0.00011898887,0.00026209888],"genre_scores_gemma":[0.9974378,0.0003758326,0.0020680004,0.0000065247336,0.000025781204,0.000037691872,0.0000029924756,0.0000063117527,0.00003911849],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99932134,0.000038667265,0.00016012466,0.00027037424,0.000094161995,0.000115304516],"domain_scores_gemma":[0.99937916,0.00010361326,0.000020281199,0.00041978736,0.000027623399,0.000049549944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042600208,0.000094344156,0.00013232947,0.00017530554,0.00006557798,0.000056400655,0.00020767194,0.000045418106,0.0000010827596],"category_scores_gemma":[0.000006061748,0.00008996967,0.000010998017,0.00016074361,0.000009806508,0.0005437281,0.0000073723777,0.000102945145,0.0000031165043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052523952,0.0011439755,0.0019188045,0.0012444486,0.00038060517,0.00013905493,0.01304843,0.055056464,0.0066126687,0.016736036,0.009736879,0.89393014],"study_design_scores_gemma":[0.00040567885,0.000038590737,0.00046028668,0.000079905025,0.0000064528904,0.00007472407,0.000017154103,0.9936774,0.0005807853,0.0000101971955,0.0045275223,0.00012135441],"about_ca_topic_score_codex":0.00008641124,"about_ca_topic_score_gemma":0.00003406583,"teacher_disagreement_score":0.987539,"about_ca_system_score_codex":0.000030873976,"about_ca_system_score_gemma":0.000024712514,"threshold_uncertainty_score":0.36688566},"labels":[],"label_agreement":null},{"id":"W2122115541","doi":"10.1109/tkde.2003.1232279","title":"Reasoning about uniqueness constraints in object relational databases","year":2003,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Relational database; Uniqueness; Generalization; Functional dependency; Theoretical computer science; Relational model; Object (grammar); Simple (philosophy); Relational calculus; Representation (politics); Core (optical fiber); Database; Artificial intelligence; Mathematics","score_opus":0.03363073257960945,"score_gpt":0.27978618866793326,"score_spread":0.24615545608832382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122115541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018493928,0.0006934349,0.99592316,0.000009989182,0.00043275114,0.00010447824,0.00027484592,0.000111224865,0.000600722],"genre_scores_gemma":[0.78258675,0.00021254587,0.21692139,0.000017555156,0.000029507286,0.000029688264,0.00007477177,0.000018077646,0.00010970595],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989988,0.000045006498,0.0002188565,0.00043069443,0.00009606243,0.00021055876],"domain_scores_gemma":[0.9989429,0.0001974243,0.0000288507,0.0007225881,0.00002847024,0.00007974446],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032398672,0.00015115038,0.00015542629,0.0001846894,0.00011054392,0.000029740462,0.00021639201,0.000037822396,0.000015031638],"category_scores_gemma":[0.000037522554,0.00015445094,0.000017695584,0.00033864798,0.00003985319,0.0013306921,0.000010861236,0.00020141329,0.00001228939],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020821064,0.00035871108,0.0004978266,0.0003366191,0.000090535614,0.000108416374,0.0012767616,0.07564534,0.0031438647,0.82724017,0.00025805327,0.09102286],"study_design_scores_gemma":[0.0024919913,0.000110675326,0.0025338256,0.0020358968,0.000040314506,0.0005466562,0.00026959128,0.7313642,0.024535812,0.00015586572,0.23425463,0.0016605604],"about_ca_topic_score_codex":0.000024306839,"about_ca_topic_score_gemma":0.00010315009,"teacher_disagreement_score":0.8270843,"about_ca_system_score_codex":0.00003319182,"about_ca_system_score_gemma":0.00008628162,"threshold_uncertainty_score":0.6298327},"labels":[],"label_agreement":null},{"id":"W2124070832","doi":"10.1109/tkde.2002.1033784","title":"The presumed-either two-phase commit protocol","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Distributed systems and fault tolerance","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; IBM (Canada)","funders":"","keywords":"Commit; Abort; Computer science; Two-phase commit protocol; Exploit; Compensating transaction; Protocol (science); Computer security; Distributed transaction; Transaction processing; Operating system; Database; Medicine; Database transaction","score_opus":0.03674964714283385,"score_gpt":0.3081144308505624,"score_spread":0.27136478370772854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124070832","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000064105254,0.00023150853,0.9934172,0.00013187923,0.0004010174,0.0043894523,0.000099490986,0.000179992,0.0010853647],"genre_scores_gemma":[0.9736303,0.0000716404,0.0044905473,0.00005710881,0.00023799867,0.018628182,0.000010093242,0.000045207362,0.0028289128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991013,0.00002687023,0.00020131802,0.0003224207,0.00011480919,0.00023331658],"domain_scores_gemma":[0.99859506,0.00011700254,0.00002908425,0.0011292573,0.000032925444,0.00009668437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020159093,0.00014558507,0.00011793545,0.000046485246,0.0002851718,0.00023274423,0.0009033067,0.00003857355,0.000015584768],"category_scores_gemma":[0.000004409744,0.0001067272,0.000029277026,0.00023398576,0.000025223571,0.00049843563,0.000013436213,0.00019372487,0.000085814565],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002387572,0.0007990733,0.000004557031,0.00015293379,0.000115453615,0.000018536357,0.0008244284,0.008416039,0.0007480368,0.0032795651,0.019265579,0.9663519],"study_design_scores_gemma":[0.0007640615,0.000041370058,0.0000054242814,0.000039348775,0.000004666821,0.000012084777,0.000004781085,0.65413123,0.00052696635,0.000005665541,0.34435233,0.00011205707],"about_ca_topic_score_codex":0.00000767771,"about_ca_topic_score_gemma":0.000022582422,"teacher_disagreement_score":0.98892665,"about_ca_system_score_codex":0.000015925129,"about_ca_system_score_gemma":0.0000097359125,"threshold_uncertainty_score":0.4352209},"labels":[],"label_agreement":null},{"id":"W2127426313","doi":"10.1109/69.929898","title":"Constructing the dependency structure of a multiagent probabilistic network","year":2001,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Dependency (UML); Probabilistic logic; Computer science; Cover (algebra); Graphical model; Representation (politics); Theoretical computer science; Domain (mathematical analysis); Dependency graph; Conditional probability; Artificial intelligence; Data mining; Mathematics; Graph","score_opus":0.0310304745145064,"score_gpt":0.2611466064437121,"score_spread":0.23011613192920571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127426313","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01197128,0.0003896591,0.98686475,0.000044645243,0.00044079145,0.00009753496,0.000030446803,0.00007776269,0.00008311037],"genre_scores_gemma":[0.97761506,0.00007011861,0.02222091,0.000010587769,0.000053778458,0.000003689825,0.0000030006559,0.0000070910473,0.00001575361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992467,0.000022840015,0.00018217362,0.00027738907,0.00008849594,0.00018238727],"domain_scores_gemma":[0.9990463,0.00015658022,0.00003337226,0.0006642294,0.000043010667,0.000056468314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013078951,0.00011772655,0.00012167134,0.00004474395,0.000116701645,0.000052477702,0.0006049273,0.000047528792,0.000008143611],"category_scores_gemma":[0.000010160034,0.00008940815,0.000022857894,0.00027033442,0.00003234433,0.00023522264,0.000016251768,0.0002183403,0.0000026296086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013840686,0.00010995088,0.00012401979,0.00015684046,0.00010162419,0.000010399448,0.0010863763,0.4699442,0.0023115342,0.015248355,0.000118290955,0.51077455],"study_design_scores_gemma":[0.00012873719,0.0000273814,0.000049990176,0.000077527926,0.00001970278,0.000069735244,0.000023342716,0.9977737,0.001068552,0.00045074217,0.00019341786,0.00011714472],"about_ca_topic_score_codex":0.000014004241,"about_ca_topic_score_gemma":0.00007123351,"teacher_disagreement_score":0.96564376,"about_ca_system_score_codex":0.00001456524,"about_ca_system_score_gemma":0.00003652559,"threshold_uncertainty_score":0.36459586},"labels":[],"label_agreement":null},{"id":"W2128933128","doi":"10.1109/tkde.2008.38","title":"Simultaneous Pattern and Data Clustering for Pattern Cluster Analysis","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining; Cluster analysis; Categorical variable; Relation (database); Cluster (spacecraft); Data set; Set (abstract data type); Pattern recognition (psychology); Consensus clustering; Measure (data warehouse); Artificial intelligence; Fuzzy clustering; CURE data clustering algorithm; Machine learning","score_opus":0.039446023589009414,"score_gpt":0.28539766762821617,"score_spread":0.24595164403920675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128933128","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020798147,0.00021023849,0.9953512,0.00013354354,0.00018881865,0.00017145654,0.0017138355,0.00014019184,0.00001088752],"genre_scores_gemma":[0.9283933,0.00030451486,0.07050336,0.00008659467,0.00009904372,0.00004571191,0.00043478076,0.000024410429,0.000108303226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986657,0.000011471756,0.00021942046,0.00077847816,0.000091374844,0.00023353862],"domain_scores_gemma":[0.99757725,0.00035158463,0.000033320066,0.0018794677,0.000035221397,0.00012313416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018134233,0.00017931913,0.00021265313,0.00020712042,0.0002621051,0.00013441547,0.0011308993,0.00005526418,0.0000035248922],"category_scores_gemma":[0.0000103523425,0.00017971887,0.000031471467,0.00036461806,0.000027709164,0.0007536913,0.00010607194,0.00013422537,0.000008439316],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036529127,0.00011536796,0.000046014407,0.000084700616,0.0002774402,0.0000098750625,0.00056669256,0.023443501,0.00010466826,0.000006353896,0.0006013871,0.9747403],"study_design_scores_gemma":[0.00029606148,0.000032708955,0.00012208981,0.000022819833,0.00013061448,0.000043003176,0.0000101362275,0.99127257,0.00010186599,0.0000014679041,0.0077554216,0.00021121552],"about_ca_topic_score_codex":0.0000531368,"about_ca_topic_score_gemma":0.00017374902,"teacher_disagreement_score":0.97452915,"about_ca_system_score_codex":0.000013373277,"about_ca_system_score_gemma":0.000018373763,"threshold_uncertainty_score":0.7328723},"labels":[],"label_agreement":null},{"id":"W2129500661","doi":"10.1109/tkde.2008.162","title":"Mining Projected Clusters in High-Dimensional Spaces","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Cluster analysis; Computer science; Curse of dimensionality; Linear subspace; Outlier; Clustering high-dimensional data; Data mining; CURE data clustering algorithm; Data point; Correlation clustering; Computation; Pattern recognition (psychology); Canopy clustering algorithm; Single-linkage clustering; Algorithm; Artificial intelligence; Mathematics","score_opus":0.03923416376241975,"score_gpt":0.2902071390881266,"score_spread":0.2509729753257069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129500661","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.078350835,0.00016864784,0.92071116,0.00007827223,0.00035839542,0.000118287775,0.00001671544,0.00016877997,0.000028896402],"genre_scores_gemma":[0.86483985,0.00007677724,0.1347946,0.0000128572465,0.00003863903,0.000024136294,0.000008119606,0.00001836168,0.00018665669],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988579,0.000025108617,0.00016783019,0.00047709525,0.00017202593,0.00030005295],"domain_scores_gemma":[0.9990692,0.00016970372,0.000017036058,0.000610294,0.00003472555,0.00009900614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014709024,0.00014903606,0.00015295281,0.00036157656,0.00013051172,0.000044512766,0.0005477946,0.000054011,0.0000037087975],"category_scores_gemma":[0.00001167857,0.00015192889,0.00001649736,0.00056374643,0.000034427132,0.0007464144,0.00003680541,0.00025896032,0.00001544827],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052059346,0.0004295947,0.00007480193,0.00017402534,0.00007519741,0.00030747306,0.0030339607,0.82337093,0.0050621238,0.00012366245,0.0004251665,0.166871],"study_design_scores_gemma":[0.00050530396,0.000056586734,0.00035238947,0.00007545039,0.0000024845833,0.00009525517,0.000015176133,0.996149,0.0021019115,0.0000030423028,0.00046135043,0.00018203264],"about_ca_topic_score_codex":0.00003081904,"about_ca_topic_score_gemma":0.000040483894,"teacher_disagreement_score":0.786489,"about_ca_system_score_codex":0.00005529967,"about_ca_system_score_gemma":0.00006496651,"threshold_uncertainty_score":0.619548},"labels":[],"label_agreement":null},{"id":"W2129546202","doi":"10.1109/tkde.2009.174","title":"An Efficient Concept-Based Mining Model for Enhancing Text Clustering","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":131,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Sentence; Natural language processing; Phrase; Term (time); Similarity (geometry); Semantics (computer science); Cluster analysis; Artificial intelligence; Document clustering; Meaning (existential); Word (group theory); Measure (data warehouse); Information retrieval; Similarity measure; Semantic similarity; Data mining; Linguistics","score_opus":0.02779020595604768,"score_gpt":0.2810140212831417,"score_spread":0.253223815327094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129546202","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038914531,0.000129599,0.99524313,0.0000561388,0.00018949165,0.00009320914,0.00013028401,0.00023800282,0.000028693345],"genre_scores_gemma":[0.8403625,0.000004060427,0.15941556,0.000069465415,0.00004538479,0.000009794446,0.00004544479,0.000011796637,0.000035976598],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99882114,0.000013398264,0.00021986094,0.0005637287,0.00010045373,0.0002814317],"domain_scores_gemma":[0.9987236,0.000112298185,0.000032149066,0.00095333986,0.000039459752,0.00013915467],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026282496,0.00018033855,0.00019050873,0.00021982058,0.00020980359,0.00017055635,0.0007010057,0.000056144705,0.0000016678579],"category_scores_gemma":[0.000006700024,0.00018569181,0.000048533424,0.0002611228,0.000012513271,0.0005065864,0.000007252913,0.00011522635,0.0000033027802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000045309016,0.00008491378,1.7795706e-7,0.000015852973,0.000012147522,9.798123e-7,0.0005523343,0.92688125,0.0038567113,0.000055127162,0.000052283565,0.06848367],"study_design_scores_gemma":[0.0003545949,0.000101774844,0.0000049681535,0.00007302899,0.00003392881,0.0000026159892,0.00003324074,0.99215823,0.0068274387,0.0000027201797,0.00018357408,0.00022387263],"about_ca_topic_score_codex":0.0000027180104,"about_ca_topic_score_gemma":0.000022738306,"teacher_disagreement_score":0.8364711,"about_ca_system_score_codex":0.000027696598,"about_ca_system_score_gemma":0.00005162087,"threshold_uncertainty_score":0.75722927},"labels":[],"label_agreement":null},{"id":"W2131967083","doi":"10.1109/tkde.2010.262","title":"Resilient Identity Crime Detection","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":68,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Advantage Forensics (Canada)","funders":"Australian Research Council; University of Warwick","keywords":"Computer science; Identity (music); Computer security","score_opus":0.03861372655258806,"score_gpt":0.271454297643489,"score_spread":0.23284057109090095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131967083","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019796735,0.000100119585,0.9960957,0.000009815875,0.00029854133,0.000109141656,0.000014723442,0.0004789632,0.00091332564],"genre_scores_gemma":[0.9766067,0.00008955969,0.023092115,0.000013414907,0.000027864013,0.00004050105,0.0000014885076,0.000009695036,0.00011866219],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928826,0.0000106185835,0.00014119594,0.00035299172,0.000070898306,0.0001360549],"domain_scores_gemma":[0.999044,0.00002297818,0.00002246993,0.0007990946,0.00003204959,0.00007938431],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013022251,0.00010495356,0.00008112096,0.00015373089,0.00016281924,0.000056087745,0.00051871414,0.000053010463,0.000016961694],"category_scores_gemma":[0.0000023332575,0.00010927106,0.000028100423,0.0003197784,0.00001597481,0.0009551146,0.00001648774,0.00014884358,0.00005900265],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029567365,0.0009117267,0.000018310642,0.00014656028,0.00012138459,0.000010847765,0.001756719,0.0008294694,0.045830663,0.032735284,0.00063993933,0.91696954],"study_design_scores_gemma":[0.00030866274,0.00021724099,0.0020929978,0.000047751848,0.000045396057,0.00006636703,0.000030231295,0.4991866,0.4824637,0.0007846566,0.0142455185,0.00051086606],"about_ca_topic_score_codex":0.000035660163,"about_ca_topic_score_gemma":0.000030152729,"teacher_disagreement_score":0.974627,"about_ca_system_score_codex":0.000023963157,"about_ca_system_score_gemma":0.000011873614,"threshold_uncertainty_score":0.44559446},"labels":[],"label_agreement":null},{"id":"W2134465446","doi":"10.1109/tkde.2006.11","title":"Input variable selection: mutual information and linear mixing measures","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Blind Source Separation Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Independent component analysis; Mutual information; Computer science; Preprocessor; Dependency (UML); Data pre-processing; Data mining; Mixing (physics); Feature selection; Pattern recognition (psychology); Blind signal separation; Algorithm; Gaussian; Artificial intelligence; Channel (broadcasting)","score_opus":0.01617825178139467,"score_gpt":0.24222236436313338,"score_spread":0.2260441125817387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134465446","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012446691,0.00014285624,0.9973345,0.000057750003,0.00015623977,0.00009129879,0.000017783863,0.00041555485,0.000539362],"genre_scores_gemma":[0.81058663,0.00006501328,0.18904713,0.00006088649,0.000083028586,0.00001984734,0.000023817129,0.000010608243,0.00010305196],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99938285,0.00001886475,0.00018036808,0.00019638857,0.000095783755,0.0001257362],"domain_scores_gemma":[0.999519,0.000062173254,0.000026367321,0.00028838258,0.000058321024,0.000045756893],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026167146,0.00011049381,0.000092918235,0.00021026896,0.00013799111,0.00017590557,0.00021450901,0.00006634773,0.0000025845848],"category_scores_gemma":[0.000006413752,0.00011582846,0.000011493642,0.0003172442,0.000012108218,0.00204226,0.000010618731,0.00016897933,0.000010145314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000059908332,0.0006279327,0.00017869443,0.0005660611,0.00021470424,0.0000053916583,0.005714644,0.34522015,0.021432966,0.11568069,0.009177054,0.5011218],"study_design_scores_gemma":[0.00021263625,0.000046176818,0.000085835796,0.000032738037,0.000010462538,0.00002927102,0.000007494524,0.93826234,0.014012734,0.000118804164,0.047010418,0.00017109438],"about_ca_topic_score_codex":0.00004024157,"about_ca_topic_score_gemma":0.000026373544,"teacher_disagreement_score":0.80934197,"about_ca_system_score_codex":0.000019772435,"about_ca_system_score_gemma":0.00003757452,"threshold_uncertainty_score":0.47233474},"labels":[],"label_agreement":null},{"id":"W2137420824","doi":"10.1109/tkde.2002.1047768","title":"Efficient queries over Web views","year":2002,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Relational database; Information retrieval; Redundancy (engineering); Materialized view; Data redundancy; Set (abstract data type); SQL; Data mining; World Wide Web; Theoretical computer science; Database; View; Database design; Programming language","score_opus":0.036669561203935296,"score_gpt":0.2640088886651401,"score_spread":0.2273393274612048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137420824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018731988,0.0019300714,0.9943665,0.000048936072,0.00079165935,0.00010374057,0.00018927609,0.00023417335,0.000462401],"genre_scores_gemma":[0.94624674,0.00058770296,0.052046437,0.000051034684,0.00013896941,0.00004394084,0.000014112514,0.000030848412,0.00084020785],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990359,0.000015907546,0.00019501173,0.00043223132,0.00010482265,0.00021611659],"domain_scores_gemma":[0.9987221,0.00007444004,0.000025417736,0.0010558835,0.00002119616,0.00010099322],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000120958284,0.00016831806,0.00016667847,0.00012534928,0.0001457329,0.000052534604,0.00035206636,0.000040954026,0.000054822696],"category_scores_gemma":[0.0000057286957,0.00015151907,0.000030806797,0.00026398367,0.000025576745,0.00048608243,0.00001974176,0.00015227014,0.00009806028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032243355,0.001616005,0.000031590243,0.0011833446,0.0003222,0.00012316323,0.007796524,0.30605078,0.024649197,0.07979585,0.020494994,0.5579041],"study_design_scores_gemma":[0.00017828922,0.00002559309,0.000014173322,0.000060437247,0.0000064587316,0.000019111025,0.000009236555,0.7892792,0.0011149385,0.00000219366,0.20911542,0.00017492565],"about_ca_topic_score_codex":0.000006250372,"about_ca_topic_score_gemma":0.000027869692,"teacher_disagreement_score":0.94437355,"about_ca_system_score_codex":0.000020660886,"about_ca_system_score_gemma":0.000010881138,"threshold_uncertainty_score":0.6178768},"labels":[],"label_agreement":null},{"id":"W2137525015","doi":"10.1109/tkde.2006.80","title":"Pattern discovery of fuzzy time series for financial prediction","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":179,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Research Council Canada; University of Illinois at Urbana-Champaign; National Science Council","keywords":"Fuzzy logic; Investment (military); Computer science; Fuzzy set; Time series; Data mining; Finance; Process (computing); Representation (politics); Artificial intelligence; Machine learning; Economics","score_opus":0.050218342144370126,"score_gpt":0.32520649560718534,"score_spread":0.27498815346281524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137525015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029648308,0.000110400826,0.9670722,0.000023558263,0.00086467474,0.00017430088,0.0016691411,0.00005658152,0.00038081736],"genre_scores_gemma":[0.982339,0.0000131856295,0.0150882285,0.0000050249905,0.000270364,0.00003656173,0.000050498373,0.000024524297,0.0021725663],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987673,0.000040825224,0.00041726782,0.00038638915,0.00022116963,0.0001670277],"domain_scores_gemma":[0.9980663,0.0011543595,0.000070553324,0.00057466375,0.00009727045,0.000036874695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011049791,0.00013594462,0.00023118153,0.00025252084,0.00010399064,0.000077895165,0.00034069692,0.000073468385,0.00001739768],"category_scores_gemma":[0.0002523719,0.00011904442,0.00006439662,0.0003284275,0.000039087277,0.0007846606,0.000009209162,0.00010028919,0.000010636022],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035321616,0.00043037315,0.00062790763,0.00024358362,0.000072325565,0.0000032059245,0.00041182857,0.04702095,0.025074681,0.00036584103,0.01628241,0.9091137],"study_design_scores_gemma":[0.002577515,0.0009116956,0.024498552,0.0004271707,0.00026471328,0.000073374074,0.00009555326,0.8256016,0.08448612,0.0048240186,0.0552382,0.0010015207],"about_ca_topic_score_codex":0.000014863467,"about_ca_topic_score_gemma":0.000038686543,"teacher_disagreement_score":0.9526907,"about_ca_system_score_codex":0.00001739807,"about_ca_system_score_gemma":0.000039603117,"threshold_uncertainty_score":0.48544905},"labels":[],"label_agreement":null},{"id":"W2137763598","doi":"10.1109/tkde.2004.58","title":"Efficient phrase-based document indexing for Web document clustering","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":320,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Document clustering; Computer science; Cluster analysis; Vector space model; Search engine indexing; Phrase; Information retrieval; Document classification; Data mining; tf–idf; Artificial intelligence; Term (time)","score_opus":0.020283882135440662,"score_gpt":0.2679597706680517,"score_spread":0.24767588853261105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137763598","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007419664,0.00019505926,0.9911999,0.00018202553,0.00047957455,0.0001662769,0.00010755438,0.0002164863,0.000033429245],"genre_scores_gemma":[0.9234667,0.00001709425,0.07628253,0.000039947772,0.000059072034,0.000052343978,0.000030981166,0.00001778425,0.000033575147],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986981,0.00001259748,0.00024721236,0.00057928456,0.00015078778,0.0003120013],"domain_scores_gemma":[0.99875206,0.00010449054,0.000036797675,0.00093418703,0.000033746528,0.00013871319],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034198232,0.00020499488,0.00019265142,0.00028553634,0.00021337986,0.00021772845,0.0006802019,0.000052851567,0.000004958067],"category_scores_gemma":[0.000008043313,0.00020214051,0.0000673313,0.00034310337,0.000016144857,0.0003144251,0.000025183228,0.00014462964,0.000017627119],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000821009,0.00010556598,0.0000010275191,0.000088697794,0.00005468107,0.000003846004,0.00022966682,0.9700858,0.0019204194,0.00032008253,0.00003901521,0.027143003],"study_design_scores_gemma":[0.0010648075,0.00007637138,0.000009209919,0.00017407483,0.000050165218,0.0000056994504,0.000018829312,0.98858494,0.006719325,0.00001931992,0.0030210137,0.00025623225],"about_ca_topic_score_codex":0.000018678602,"about_ca_topic_score_gemma":0.00003339825,"teacher_disagreement_score":0.91604704,"about_ca_system_score_codex":0.00010094115,"about_ca_system_score_gemma":0.00008974737,"threshold_uncertainty_score":0.82430506},"labels":[],"label_agreement":null},{"id":"W2140849876","doi":"10.1109/tkde.2010.223","title":"Effective and Efficient Shape-Based Pattern Detection over Streaming Time Series","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Euclidean distance; Series (stratigraphy); Time series; Measure (data warehouse); Distance measures; Scaling; Data mining; Pattern recognition (psychology); Artificial intelligence; Algorithm; Machine learning; Mathematics","score_opus":0.006535432479670956,"score_gpt":0.21111493770867348,"score_spread":0.20457950522900253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140849876","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1928887,0.000058817215,0.80650085,0.000015991141,0.00026800405,0.00008775923,0.00003120589,0.00011689402,0.000031774307],"genre_scores_gemma":[0.99679595,0.000006247585,0.0030766486,0.000007548756,0.00005280697,0.000013097247,0.000005517941,0.000013124917,0.000029063809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99918926,0.000014251949,0.00013309695,0.00040160256,0.000083197425,0.00017860823],"domain_scores_gemma":[0.9992752,0.0001255606,0.000029013812,0.00045381254,0.000029217312,0.00008715895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016901632,0.00015681797,0.00014491347,0.00015754862,0.00019794345,0.00015406558,0.00022326206,0.0000603292,0.00001908538],"category_scores_gemma":[0.0000074849977,0.00014827818,0.000032196738,0.00023018444,0.00002761633,0.0004326763,0.000016880917,0.00023632518,0.000012256555],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010732521,0.00008498345,0.00004037261,0.000070212554,0.00005551701,0.0000047270673,0.00031158802,0.020211233,0.050835643,0.00003295455,0.0000066956372,0.92833537],"study_design_scores_gemma":[0.00020971561,0.00007277443,0.0012442701,0.000034131135,0.000028275519,0.000014263206,0.0000065793415,0.9784135,0.019312954,0.000001708884,0.0004974255,0.00016436385],"about_ca_topic_score_codex":0.000022107273,"about_ca_topic_score_gemma":0.000088688765,"teacher_disagreement_score":0.9582023,"about_ca_system_score_codex":0.000013397473,"about_ca_system_score_gemma":0.000011067694,"threshold_uncertainty_score":0.60466087},"labels":[],"label_agreement":null},{"id":"W2141277572","doi":"10.1109/tkde.2013.53","title":"Extended Subtree: A New Similarity Function for Tree Structured Data","year":2013,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Similarity (geometry); Edit distance; Cluster analysis; Data mining; Tree (set theory); Function (biology); Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.058334273774491116,"score_gpt":0.3147285319055442,"score_spread":0.25639425813105304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2141277572","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002911379,0.0002965762,0.9975629,0.00017524858,0.0007290294,0.00040630126,0.00023193871,0.0002726035,0.000034257257],"genre_scores_gemma":[0.48982087,0.00016227135,0.50792813,0.000058365902,0.00035730787,0.00013187822,0.00028171198,0.000072716204,0.0011867181],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848485,0.000017771565,0.0001994576,0.0007802632,0.00016218526,0.00035545244],"domain_scores_gemma":[0.99718904,0.00021041633,0.000026773636,0.0022794886,0.00007526279,0.00021903691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018178154,0.00019893702,0.00017697942,0.00017593334,0.00016747482,0.00021780928,0.0016271911,0.000084755426,0.000021011994],"category_scores_gemma":[0.000029631288,0.00019577288,0.000027693482,0.00032515696,0.000020760657,0.002130516,0.00008591426,0.00026954163,0.000025828556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001999081,0.000073653515,0.0000010966638,0.00008858158,0.00006453335,0.0000015722787,0.00011196876,0.006567033,0.004280792,0.00013930873,0.0027702635,0.9858812],"study_design_scores_gemma":[0.00062829914,0.00010226514,0.00043963388,0.000026652842,0.000020346835,0.000012209596,0.000009937925,0.9872869,0.001693562,0.0003292407,0.009231338,0.00021958107],"about_ca_topic_score_codex":0.000048858095,"about_ca_topic_score_gemma":0.00010802828,"teacher_disagreement_score":0.9856616,"about_ca_system_score_codex":0.000040776547,"about_ca_system_score_gemma":0.00008051616,"threshold_uncertainty_score":0.79833865},"labels":[],"label_agreement":null},{"id":"W2142103633","doi":"10.1109/tkde.2006.172","title":"Discovering Frequent Closed Partial Orders from Strings","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Multiset; Data mining; String (physics); Pruning; Set (abstract data type); Knowledge extraction; Order (exchange); Theoretical computer science; Mathematics","score_opus":0.017260913842518027,"score_gpt":0.24542276892658657,"score_spread":0.22816185508406855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142103633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017741697,0.000153687,0.980753,0.00007641144,0.00037223156,0.00008412961,0.00045488245,0.0002235896,0.00014034957],"genre_scores_gemma":[0.9338047,0.000048795893,0.06574257,0.000013678674,0.00015303153,0.000031232736,0.00012639558,0.000017349366,0.0000622417],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901813,0.000007836794,0.00018360539,0.0004833777,0.00009854178,0.00020852646],"domain_scores_gemma":[0.9989446,0.00008500744,0.000025273775,0.00085375406,0.000015968068,0.00007543514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008104604,0.00014927115,0.00012272604,0.000085922795,0.00014200454,0.0001899458,0.0006378362,0.000044134737,0.000008920797],"category_scores_gemma":[0.000002348714,0.00015277008,0.00002621944,0.00023401238,0.000018329114,0.00075769064,0.00002214874,0.00015324057,0.000033062373],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016345017,0.0009825596,0.00007444298,0.00009596853,0.00020832183,0.000028960529,0.0008142356,0.081900135,0.028141517,0.01764404,0.003848367,0.8662451],"study_design_scores_gemma":[0.00034118982,0.000023228968,0.00033394966,0.000045815377,0.000021774817,0.0000038865983,0.000010910364,0.96266085,0.011925659,0.00008028219,0.024301598,0.00025083145],"about_ca_topic_score_codex":0.00048478117,"about_ca_topic_score_gemma":0.00008797783,"teacher_disagreement_score":0.916063,"about_ca_system_score_codex":0.00002516229,"about_ca_system_score_gemma":0.000025703483,"threshold_uncertainty_score":0.6229783},"labels":[],"label_agreement":null},{"id":"W2142407957","doi":"10.1109/tkde.2010.152","title":"A Machine Learning Approach for Identifying Disease-Treatment Relations in Short Texts","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Domain (mathematical analysis); Field (mathematics); Set (abstract data type); Health care; Machine learning; Artificial intelligence; Dissemination; Information extraction; Data science","score_opus":0.036150843997362125,"score_gpt":0.3036804357149973,"score_spread":0.2675295917176352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142407957","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08613843,0.0013646991,0.9117308,0.000026353388,0.00023653347,0.00018114284,0.00018082444,0.00004446999,0.00009674636],"genre_scores_gemma":[0.9873821,0.00019342193,0.011558905,0.0000042151196,0.00007739292,0.00007907087,0.0003724264,0.00001688701,0.000315589],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937934,0.000010012254,0.00011686541,0.0003087133,0.00003591632,0.00014918498],"domain_scores_gemma":[0.99957734,0.000037452348,0.000007672468,0.0002800116,0.000012931529,0.00008457683],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011415457,0.00011410679,0.000097277836,0.00007957437,0.00009414869,0.000019937483,0.00011590609,0.00009597624,0.000003992708],"category_scores_gemma":[0.00002888675,0.00010437175,0.000034365217,0.00007109288,0.000028523908,0.000008167922,0.0000062548947,0.00016546821,0.0000017519875],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031683475,0.0015271866,0.004219961,0.00039363463,0.0003562684,0.000011638056,0.0007099883,0.057342343,0.37839052,0.00012626064,0.00040592722,0.55619943],"study_design_scores_gemma":[0.0014984963,0.0003678424,0.0028926823,0.00006796973,0.00013482972,0.000021986081,0.000079156176,0.865657,0.022655213,0.00001457635,0.10607005,0.00054024224],"about_ca_topic_score_codex":0.000008721762,"about_ca_topic_score_gemma":0.0001094285,"teacher_disagreement_score":0.9012437,"about_ca_system_score_codex":0.000009098444,"about_ca_system_score_gemma":0.000026677302,"threshold_uncertainty_score":0.42561564},"labels":[],"label_agreement":null},{"id":"W2142595897","doi":"10.1109/tkde.2006.146","title":"On the Signature Tree Construction and Analysis","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Signature (topology); Tree (set theory); Set (abstract data type); Digital signature; Data structure; Data mining; File format; Information retrieval; Theoretical computer science; Database; Programming language; Hash function; Mathematics","score_opus":0.011715846144598278,"score_gpt":0.2185866327377866,"score_spread":0.20687078659318833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142595897","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016816572,0.0001793226,0.9968415,0.00022782023,0.00024533257,0.00006917769,0.00008185748,0.00009805433,0.00057530747],"genre_scores_gemma":[0.9823975,0.00011987724,0.016911492,0.000058759808,0.000077680845,0.000011961316,0.000063676,0.000009691909,0.0003493808],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993747,0.000013416087,0.000097344506,0.00031447664,0.00008247857,0.00011756974],"domain_scores_gemma":[0.9992066,0.0001251743,0.000017143995,0.00060689804,0.000012672296,0.00003149718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013132248,0.000109377936,0.00009733934,0.00021483631,0.00013903782,0.00017384934,0.00038218198,0.00003353002,0.000007955077],"category_scores_gemma":[0.0000023139992,0.00008180596,0.000026229827,0.0005554708,0.000024562702,0.0004900537,0.00001364415,0.0001410446,0.000008149302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014533351,0.00028572071,0.000051998566,0.00007804209,0.000778729,0.000016788796,0.00024236616,0.03876492,0.0010697014,0.11773752,0.008692375,0.8322673],"study_design_scores_gemma":[0.00018920495,0.000031945325,0.00052481226,0.000016935564,0.00015129126,0.0000046488617,0.000012400486,0.98881423,0.0009803746,0.00026448898,0.0088425195,0.00016711601],"about_ca_topic_score_codex":0.000011665867,"about_ca_topic_score_gemma":0.000037436308,"teacher_disagreement_score":0.9807158,"about_ca_system_score_codex":0.000008256931,"about_ca_system_score_gemma":0.0000047632197,"threshold_uncertainty_score":0.33359504},"labels":[],"label_agreement":null},{"id":"W2142804492","doi":"10.1109/tkde.2011.138","title":"A Lightweight Algorithm for Message Type Extraction in System Application Logs","year":2011,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Message passing; Partition (number theory); Event (particle physics); Algorithm; Data type; Web log analysis software; Task (project management); Data mining; Theoretical computer science; Distributed computing; Programming language; Operating system; The Internet","score_opus":0.026532542095579034,"score_gpt":0.26306770202565416,"score_spread":0.23653515993007512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142804492","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018691134,0.00036284357,0.99615264,0.000006940484,0.00090984174,0.00032744522,0.000027927861,0.0002309558,0.000112299866],"genre_scores_gemma":[0.9460119,0.00007745639,0.05366471,0.0000038206294,0.000058260302,0.00012752735,0.000011325615,0.000012644976,0.00003237456],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991672,0.000014182534,0.00020979503,0.00038295024,0.000064089436,0.00016179486],"domain_scores_gemma":[0.9991283,0.00007463609,0.000031269865,0.0006606614,0.000050394035,0.000054763463],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030717728,0.00011909277,0.00013923748,0.00016001843,0.000077404904,0.000027363278,0.00036125706,0.0000873321,0.0000015997247],"category_scores_gemma":[0.0000026959024,0.00010853082,0.000024063618,0.00031232796,0.000009232072,0.0006585125,0.0000066696557,0.0001184824,0.000025501424],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027733966,0.00037861994,0.000087102046,0.00068033935,0.000048631206,0.0000038536386,0.0015805988,0.0015145947,0.0008519981,0.0013983994,0.00012411305,0.993304],"study_design_scores_gemma":[0.0003295193,0.0000722859,0.00045999588,0.000108220505,0.000014254701,0.000021404994,0.000029063667,0.9893338,0.0070516,0.000011757813,0.002400467,0.00016762159],"about_ca_topic_score_codex":0.00003086907,"about_ca_topic_score_gemma":0.000018382585,"teacher_disagreement_score":0.9931364,"about_ca_system_score_codex":0.00005841538,"about_ca_system_score_gemma":0.000027466735,"threshold_uncertainty_score":0.4425758},"labels":[],"label_agreement":null},{"id":"W2147312192","doi":"10.1109/tkde.2006.73","title":"Approximate processing of massive continuous quantile queries over high-speed data streams","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"China Academy of Space Technology; University of New South Wales","keywords":"Computer science; Data stream mining; STREAMS; Quantile; Data mining; Parallel computing; Computer network; Statistics; Mathematics","score_opus":0.020542173346513697,"score_gpt":0.2531488894735193,"score_spread":0.23260671612700562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147312192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0045466716,0.00042738352,0.99323213,0.000034154662,0.0003738261,0.00013659979,0.0008634742,0.00018289709,0.00020284079],"genre_scores_gemma":[0.95709425,0.00009609415,0.041925237,0.0000069014486,0.000092239825,0.000006523728,0.0004843466,0.000022505428,0.0002719117],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988175,0.000012469209,0.00025438092,0.0005469033,0.00014434825,0.00022440772],"domain_scores_gemma":[0.9983445,0.000053552212,0.000067129455,0.0014502899,0.00003809379,0.00004646311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017564607,0.00017950805,0.00021916971,0.00016425026,0.00009856889,0.0001997664,0.0013252309,0.000043473974,0.000008281096],"category_scores_gemma":[0.0000041187095,0.00017172452,0.000018771805,0.00032360517,0.000040351217,0.0023382246,0.0000908865,0.000120526034,0.00000661238],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004830552,0.001348965,0.000106611806,0.001475528,0.00027309568,0.00005982704,0.00062941725,0.02520861,0.009699464,0.01511087,0.0075297537,0.9385095],"study_design_scores_gemma":[0.00042440637,0.000038520586,0.00016707051,0.00011155094,0.000041516807,0.0000035405797,0.000029654742,0.98854834,0.00545237,0.000047616075,0.0049022273,0.00023317686],"about_ca_topic_score_codex":0.00012682541,"about_ca_topic_score_gemma":0.000044518085,"teacher_disagreement_score":0.96333975,"about_ca_system_score_codex":0.000011380185,"about_ca_system_score_gemma":0.000026094154,"threshold_uncertainty_score":0.70027226},"labels":[],"label_agreement":null},{"id":"W2147876569","doi":"10.1109/tkde.2015.2453171","title":"RankRC: Large-Scale Nonlinear Rare Class Ranking","year":2015,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Robustness (evolution); Kernel (algebra); Machine learning; Artificial intelligence; Focus (optics); Class (philosophy); Nonlinear system; Rare events; Algorithm; Computational complexity theory; Mathematics","score_opus":0.03825382451170466,"score_gpt":0.27483103722904034,"score_spread":0.23657721271733567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147876569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013179198,0.00047207173,0.9955508,0.00012108717,0.0009526185,0.00009991909,0.000046558675,0.0003447604,0.0010942697],"genre_scores_gemma":[0.88163626,0.00010733975,0.11700837,0.00014749388,0.00021035945,0.000019422807,0.000047788293,0.00004183437,0.0007811129],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885494,0.000036371774,0.0002022812,0.0004402709,0.00017870958,0.00028742405],"domain_scores_gemma":[0.99884015,0.00010321664,0.000029808998,0.000737384,0.00006705767,0.00022235668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000444063,0.00017071255,0.00017169549,0.00018727283,0.0001549248,0.00016091378,0.00062368705,0.000073456875,0.000013419238],"category_scores_gemma":[0.0000157876,0.00017429293,0.00003781856,0.00037581334,0.000016220632,0.00086553174,0.00002269912,0.00029926523,0.00011415796],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014514978,0.0012119411,0.00011105335,0.00036921081,0.00031466567,0.00011658827,0.0265561,0.36529723,0.003536103,0.0049127256,0.0070480895,0.59038115],"study_design_scores_gemma":[0.00087383523,0.000036842466,0.000024679523,0.000043370645,0.000012296618,0.000020696656,0.00013356718,0.87215334,0.00063082285,0.000012900716,0.12586088,0.00019675201],"about_ca_topic_score_codex":0.0000042260012,"about_ca_topic_score_gemma":0.000022629589,"teacher_disagreement_score":0.88031834,"about_ca_system_score_codex":0.000033788485,"about_ca_system_score_gemma":0.000062949475,"threshold_uncertainty_score":0.71074593},"labels":[],"label_agreement":null},{"id":"W2149473201","doi":"10.1109/tkde.2009.17","title":"Learning Heuristics for the Superblock Instruction Scheduling Problem","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Parallel Computing and Optimization Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Heuristics; Compiler; Parallel computing; Scheduling (production processes); Instruction scheduling; Benchmark (surveying); Register allocation; Schedule; Dynamic priority scheduling; Two-level scheduling; Programming language; Mathematical optimization; Operating system; Mathematics","score_opus":0.02210105566365551,"score_gpt":0.2659790234019478,"score_spread":0.2438779677382923,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149473201","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005228202,0.00029951704,0.99807215,0.00016853648,0.00025509982,0.00015320082,0.000005708517,0.0004604799,0.00006247804],"genre_scores_gemma":[0.66991985,0.00020514798,0.32969674,0.000023004775,0.00006537479,0.00001125658,0.0000054147617,0.0000077953755,0.0000654308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993636,0.000014333437,0.0001432109,0.00026528694,0.0000622002,0.0001513558],"domain_scores_gemma":[0.9993281,0.00016480687,0.000023912331,0.00038946033,0.000052029944,0.00004172378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023790725,0.00010783934,0.00008994491,0.000091573296,0.00032477744,0.0001282715,0.00044318844,0.000045668952,6.2858044e-7],"category_scores_gemma":[0.0000140431475,0.00009082105,0.000025382797,0.00021207353,0.0000102215,0.00030376876,0.0000072331472,0.00020574048,0.0000021149115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003872642,0.000031523992,0.0000015281679,0.00002022291,0.000013106848,2.9826188e-7,0.00027502907,0.7898314,0.00021579734,0.0012774387,0.000103102466,0.2082267],"study_design_scores_gemma":[0.00018401173,0.00009582275,0.00001809439,0.000036907804,0.0000121170515,0.000011804316,0.000009468348,0.9931852,0.0017132973,0.00009674441,0.004524262,0.0001122625],"about_ca_topic_score_codex":0.0000019430215,"about_ca_topic_score_gemma":0.0000010448778,"teacher_disagreement_score":0.669397,"about_ca_system_score_codex":0.000015151457,"about_ca_system_score_gemma":0.000020183581,"threshold_uncertainty_score":0.37035748},"labels":[],"label_agreement":null},{"id":"W2151953639","doi":"10.1109/tkde.2005.166","title":"Fast algorithms for frequent itemset mining using FP-trees","year":2005,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":552,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Data mining; Traverse; Association rule learning; Algorithm; Tree (set theory); Data structure; Tree structure; Trie; Prefix; Binary tree; Mathematics","score_opus":0.05517782314487753,"score_gpt":0.3067297556925058,"score_spread":0.2515519325476283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2151953639","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001680434,0.00037454136,0.9963653,0.000120376586,0.00036585686,0.00017036188,0.00068258034,0.0001945859,0.000045965302],"genre_scores_gemma":[0.113305464,0.000077640856,0.8859453,0.000038752416,0.0002993993,0.00007474193,0.00008503442,0.00002955934,0.00014406312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887556,0.000007874056,0.00023049324,0.0005226892,0.000092846494,0.00027051504],"domain_scores_gemma":[0.99880457,0.00013908636,0.000035479443,0.00085615873,0.0000432712,0.00012141129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019418773,0.00017738853,0.00015783079,0.0001621162,0.00023775583,0.00017684295,0.0007163907,0.000057334855,0.0000045271636],"category_scores_gemma":[0.0000057078573,0.00018363188,0.000037947695,0.00026580834,0.000019417168,0.00093230326,0.000021108925,0.000119306635,0.00001428661],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000229816,0.00015324554,0.0000022708077,0.000037940168,0.00005037117,0.0000012349291,0.0005487343,0.032777097,0.0026304203,0.00047592132,0.0008216894,0.9624988],"study_design_scores_gemma":[0.0002649273,0.00003324448,0.00001543196,0.000058726837,0.000023687266,0.000020602605,0.000029523873,0.9620176,0.003079309,0.0000067978613,0.03423934,0.00021078663],"about_ca_topic_score_codex":0.000015379796,"about_ca_topic_score_gemma":0.000033065317,"teacher_disagreement_score":0.96228796,"about_ca_system_score_codex":0.000041748186,"about_ca_system_score_gemma":0.000038670823,"threshold_uncertainty_score":0.7488291},"labels":[],"label_agreement":null},{"id":"W2152225808","doi":"10.1109/tkde.2010.33","title":"Asking Generalized Queries to Domain Experts to Improve Learning","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"China University of Geosciences; Shanghai Jiao Tong University; University of Pennsylvania","keywords":"Computer science; Oracle; Construct (python library); Classifier (UML); Ask price; Domain (mathematical analysis); Set (abstract data type); Machine learning; Class (philosophy); Labeled data; Active learning (machine learning); Artificial intelligence; Theoretical computer science; Mathematics","score_opus":0.010832096937412392,"score_gpt":0.265796040034446,"score_spread":0.25496394309703363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152225808","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.044468276,0.000048387174,0.95288897,0.00032323372,0.0016222626,0.00012163457,0.000012801311,0.00034412558,0.0001703345],"genre_scores_gemma":[0.76683354,0.00001127286,0.23208939,0.00010190934,0.00025840726,0.00004708506,0.00000572267,0.000029174356,0.00062352535],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988756,0.000025923942,0.00016182166,0.00053353986,0.000114085,0.00028899076],"domain_scores_gemma":[0.99888444,0.00009229813,0.00001803489,0.0007313287,0.000031876978,0.00024203163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027320956,0.00018395473,0.00016413389,0.00022566992,0.00023914041,0.00020765419,0.0006227248,0.00006061877,0.000015430456],"category_scores_gemma":[0.00002760398,0.0001796962,0.00003054804,0.00032413402,0.000009896495,0.0003938798,0.00003720854,0.00041467563,0.000047677917],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001824053,0.00011510889,0.000020112666,0.000059787217,0.000052049647,0.000017439248,0.00635638,0.079611614,0.27814087,0.002155364,0.00059999846,0.63285303],"study_design_scores_gemma":[0.0004547292,0.00018918968,0.000083379164,0.00006748383,0.00001040173,0.000034086963,0.00006715989,0.78954816,0.028707217,0.000027469076,0.18025629,0.00055441755],"about_ca_topic_score_codex":0.00004357141,"about_ca_topic_score_gemma":0.000059474594,"teacher_disagreement_score":0.72236526,"about_ca_system_score_codex":0.0000141305745,"about_ca_system_score_gemma":0.000024282968,"threshold_uncertainty_score":0.7327798},"labels":[],"label_agreement":null},{"id":"W2155826795","doi":"10.1109/tkde.2010.205","title":"Static and Dynamic Delegation in the Role Graph Model","year":2010,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Shandong University","keywords":"Delegation; Computer science; Static analysis; Role-based access control; Graph; Distributed computing; Session (web analytics); Access control; Context (archaeology); Computer security; Theoretical computer science; Programming language; World Wide Web","score_opus":0.01446956893650409,"score_gpt":0.2885935015401711,"score_spread":0.274123932603667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155826795","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2445355,0.00033465342,0.7526782,0.00038660664,0.00027661017,0.00022140949,0.00008163195,0.00006183084,0.0014235321],"genre_scores_gemma":[0.9991764,0.00018380764,0.000537134,0.000018276804,0.00002209792,0.000016671827,0.000005775633,0.000005379337,0.000034454013],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995741,0.00001865383,0.000079390455,0.00013747507,0.00007023286,0.00012012415],"domain_scores_gemma":[0.9996493,0.00011612335,0.000010306558,0.00017183064,0.00001320385,0.00003924106],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028129824,0.00006163128,0.00006112894,0.000082920626,0.00019035982,0.00006891834,0.00017394204,0.000044173925,0.0000055763026],"category_scores_gemma":[0.000009504278,0.00005006312,0.000009542383,0.0001469373,0.000043161388,0.00039465792,0.0000018674356,0.00020452833,0.000002588026],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005017273,0.00051793735,0.00048673613,0.00012951711,0.00008521336,0.000007818529,0.04993245,0.08590173,0.0062737116,0.03038387,0.00011529276,0.82611555],"study_design_scores_gemma":[0.00019826286,0.000008101658,0.0004451124,0.000009774879,0.000018508752,0.000001221571,0.00059044675,0.99610347,0.00003793353,0.00084257394,0.0016610106,0.00008356742],"about_ca_topic_score_codex":0.000219747,"about_ca_topic_score_gemma":0.00939618,"teacher_disagreement_score":0.9102017,"about_ca_system_score_codex":0.0000067528704,"about_ca_system_score_gemma":0.000025268204,"threshold_uncertainty_score":0.5243289},"labels":[],"label_agreement":null},{"id":"W2157751754","doi":"10.1109/tkde.2006.131","title":"Test strategies for cost-sensitive decision trees","year":2006,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":145,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Hong Kong University of Science and Technology","keywords":"Computer science; Medical diagnosis; Decision tree; Machine learning; Test (biology); Artificial intelligence; Test case; Process (computing); Medical costs; Data mining; Health care; Medicine","score_opus":0.02750885075641095,"score_gpt":0.28599389310441553,"score_spread":0.25848504234800457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157751754","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028739797,0.000094605995,0.99788266,0.00005465498,0.0002334535,0.00026481578,0.0005355648,0.00042545458,0.00022141302],"genre_scores_gemma":[0.8282907,0.00005557546,0.17131777,0.000014743953,0.000060246664,0.000082398845,0.0000799073,0.00001518114,0.00008349338],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991253,0.0000074766863,0.00018871849,0.00041697023,0.00008169304,0.00017983203],"domain_scores_gemma":[0.9985084,0.0005348213,0.000029861496,0.00080936705,0.00007151535,0.000046011588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015070196,0.00014147181,0.00012662551,0.00016562785,0.00012389073,0.00018648166,0.00051708176,0.00005941732,0.0000014955782],"category_scores_gemma":[0.000013784951,0.0001397748,0.000025509857,0.00022488147,0.000023060671,0.0011184709,0.000010455095,0.00010338512,0.000011965863],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040690036,0.0007419148,0.000015922058,0.00013747849,0.000049831953,0.000009757272,0.0003729459,0.019060306,0.07036135,0.0450838,0.015596396,0.84852964],"study_design_scores_gemma":[0.00044267642,0.00010399996,0.00054725446,0.000082876395,0.000016948257,0.000016934597,0.00003084982,0.8973285,0.073375024,0.00082447776,0.026925048,0.0003054193],"about_ca_topic_score_codex":0.000012786102,"about_ca_topic_score_gemma":0.00007561653,"teacher_disagreement_score":0.8782682,"about_ca_system_score_codex":0.000030966457,"about_ca_system_score_gemma":0.00004309484,"threshold_uncertainty_score":0.5699851},"labels":[],"label_agreement":null},{"id":"W2160172686","doi":"10.1109/tkde.2009.138","title":"Credibility: How Agents Can Handle Unfair Third-Party Testimonies in Computational Trust Models","year":2009,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Access Control and Trust","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Credibility; Computer science; Computer security; Work (physics); Computational trust; Empirical evidence; Computational model; Risk analysis (engineering); Artificial intelligence; Reputation; Business; Political science; Law","score_opus":0.057837470981609185,"score_gpt":0.3104771853336928,"score_spread":0.2526397143520836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160172686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09402299,0.0007891028,0.89701885,0.0027358753,0.0006427778,0.0004474031,0.00048949337,0.0003202429,0.0035332527],"genre_scores_gemma":[0.9985486,0.00010022981,0.0009795846,0.000040332074,0.00008120397,0.00001102341,0.000027964808,0.000008155201,0.00020287251],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990965,0.000034317563,0.00014650058,0.00031123887,0.0001610127,0.00025040712],"domain_scores_gemma":[0.99943644,0.00013808224,0.000021932106,0.00023790248,0.000045302193,0.00012037249],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002606901,0.0001320807,0.00016906562,0.00014372951,0.00028367806,0.00012755852,0.00026288937,0.00007826867,0.000015379312],"category_scores_gemma":[0.000021168715,0.0001327873,0.000028782919,0.00028250265,0.00006043889,0.00073294656,0.000003832331,0.0001945632,0.000004671284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000056179993,0.0006797077,0.00066905975,0.000062260704,0.000073530544,0.000018197645,0.010043806,0.89237326,0.00010126329,0.0044137896,0.0009623975,0.09054657],"study_design_scores_gemma":[0.0006606218,0.000046868798,0.003816734,0.000057271536,0.000028024415,0.0000015409179,0.00040210248,0.99119234,0.00006364615,0.0013033687,0.0022037174,0.00022378002],"about_ca_topic_score_codex":0.0003024363,"about_ca_topic_score_gemma":0.0021437912,"teacher_disagreement_score":0.90452564,"about_ca_system_score_codex":0.000067463116,"about_ca_system_score_gemma":0.00009954358,"threshold_uncertainty_score":0.54149085},"labels":[],"label_agreement":null},{"id":"W2168616308","doi":"10.1109/tkde.2008.34","title":"Automatic Website Summarization by Image Content: A Case Study with Logo and Trademark Images","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Killam Trusts","keywords":"Automatic summarization; Computer science; Trademark; Logo (programming language); Information retrieval; Logos Bible Software; World Wide Web; Web page; Image (mathematics); Trademark infringement; Artificial intelligence; Process (computing); Abstraction","score_opus":0.034974161712979936,"score_gpt":0.2577001686089124,"score_spread":0.2227260068959325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2168616308","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060502667,0.0003335742,0.9383507,0.00004707485,0.000052431238,0.00027602166,0.00005976743,0.00035196822,0.000025805362],"genre_scores_gemma":[0.98576266,0.00021535797,0.013803627,0.000011339458,0.000010698839,0.000033157554,0.000009890039,0.000014318816,0.0001389344],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991489,0.000031207248,0.00017909495,0.00038921225,0.00010534557,0.00014620616],"domain_scores_gemma":[0.9992323,0.00008682307,0.000033662902,0.0005062779,0.000051122144,0.00008984849],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013853399,0.00016167814,0.00015808837,0.00013131171,0.00022059625,0.00010881282,0.0002454754,0.000039231647,0.0000039784927],"category_scores_gemma":[0.0000051996167,0.00013730873,0.000013769637,0.00030640105,0.00005367822,0.0010118271,0.000010570598,0.00014540515,0.0000042771053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015837836,0.007244309,0.0029310407,0.0015250251,0.0009818659,0.0052800123,0.018605001,0.0002505688,0.1492615,0.00040290545,0.005437952,0.80792147],"study_design_scores_gemma":[0.0018200151,0.00088222197,0.0016344731,0.00013600106,0.00012552395,0.0055176113,0.0006432281,0.9326578,0.055002075,0.0000058803626,0.00082907063,0.000746111],"about_ca_topic_score_codex":0.00004239965,"about_ca_topic_score_gemma":0.000012282028,"teacher_disagreement_score":0.9324072,"about_ca_system_score_codex":0.000017570022,"about_ca_system_score_gemma":0.00002295022,"threshold_uncertainty_score":0.5599288},"labels":[],"label_agreement":null},{"id":"W2170595610","doi":"10.1109/tkde.2004.1269594","title":"CAIM discretization algorithm","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":449,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Discretization; Discretization of continuous features; Algorithm; Computer science; Decision tree; Class (philosophy); Tree (set theory); ID3 algorithm; Decision tree learning; Artificial intelligence; Incremental decision tree; Mathematics; Discretization error","score_opus":0.01997980423624899,"score_gpt":0.24933739576293726,"score_spread":0.22935759152668828,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170595610","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020594284,0.0002697047,0.9982048,0.00013406674,0.0005470757,0.00006929399,0.00004589841,0.00018799807,0.00033519597],"genre_scores_gemma":[0.7816358,0.00029810786,0.21780258,0.000048978593,0.00009864548,0.000013246519,0.000029474912,0.000016766246,0.000056385055],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993352,0.0000064629735,0.00011118666,0.00031372553,0.00007646952,0.00015690312],"domain_scores_gemma":[0.99929345,0.00002634264,0.000012755626,0.0005708373,0.000017957376,0.00007865595],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008238421,0.00011103884,0.00008980783,0.00009643594,0.000109587774,0.00009593235,0.00043051504,0.00004379451,0.0000037410723],"category_scores_gemma":[0.0000020607768,0.000100845515,0.000019069352,0.00025141635,0.0000125017505,0.00060935895,0.000010126958,0.00011771655,0.00003622699],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000027319297,0.00022913399,0.0000021301269,0.00004578897,0.00004125589,0.00001803307,0.00090463087,0.107079454,0.00044707383,0.0061676614,0.00018170953,0.8848804],"study_design_scores_gemma":[0.0004442349,0.00007185344,0.00009079916,0.000047811827,0.000013264324,0.000031142474,0.000011157081,0.98998845,0.001983302,0.00030010738,0.006777542,0.00024035826],"about_ca_topic_score_codex":0.000016081218,"about_ca_topic_score_gemma":0.000010766997,"teacher_disagreement_score":0.88464004,"about_ca_system_score_codex":0.000025680047,"about_ca_system_score_gemma":0.000025141626,"threshold_uncertainty_score":0.41123608},"labels":[],"label_agreement":null},{"id":"W2342411541","doi":"10.1109/tkde.2016.2527003","title":"Conflict-Aware Weighted Bipartite B-Matching and Its Application to E-Commerce","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Bipartite graph; Computer science; Scalability; Matching (statistics); Scheduling (production processes); The Internet; Time complexity; Approximation algorithm; Blossom algorithm; Context (archaeology); Theoretical computer science; Data mining; Graph; Combinatorics; Algorithm; Mathematics; World Wide Web; Mathematical optimization; Database","score_opus":0.030657586213925878,"score_gpt":0.28427757784468977,"score_spread":0.2536199916307639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342411541","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025410517,0.00014416012,0.9959306,0.0007453961,0.00013001781,0.00019197345,0.000052742238,0.00018751118,0.000076526776],"genre_scores_gemma":[0.98792285,0.00035973106,0.011159675,0.000106549414,0.00003176548,0.00004904829,0.000006958998,0.000015526546,0.00034786813],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992251,0.000018009949,0.0001368488,0.00036585671,0.00008075119,0.00017344083],"domain_scores_gemma":[0.99918765,0.00011164772,0.000015411988,0.00046407196,0.0000473919,0.00017385506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000155416,0.0001116036,0.000100475736,0.0001607541,0.00011827398,0.00007300693,0.0003511543,0.000041314317,0.000008947444],"category_scores_gemma":[0.000003999195,0.00008972786,0.000011566997,0.00025132348,0.000008907464,0.0006697907,0.00002203906,0.00008518409,0.000078747384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024703173,0.00024000599,0.000021854536,0.00020954738,0.00009532113,0.00000388224,0.0033171629,0.023289166,0.07247821,0.015084025,0.0007280586,0.8845081],"study_design_scores_gemma":[0.00042036062,0.00004913561,0.00007621282,0.00010801941,0.000007879756,0.000008720339,0.000008687533,0.9459383,0.009311027,0.00003180513,0.043811772,0.00022810043],"about_ca_topic_score_codex":0.000004447699,"about_ca_topic_score_gemma":0.000010155222,"teacher_disagreement_score":0.98538184,"about_ca_system_score_codex":0.000016094873,"about_ca_system_score_gemma":0.000014968351,"threshold_uncertainty_score":0.3658996},"labels":[],"label_agreement":null},{"id":"W2342671210","doi":"10.1109/tkde.2016.2525993","title":"Clearing Contamination in Large Networks","year":2016,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Computer science; Clearing; Graph; Mathematical optimization; Theoretical computer science; Algorithm; Mathematics","score_opus":0.014555985345564236,"score_gpt":0.2634419975948157,"score_spread":0.24888601224925144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2342671210","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01841407,0.000077771765,0.98082787,0.000016688615,0.00009217781,0.000070859576,0.000040202005,0.00007079214,0.0003895967],"genre_scores_gemma":[0.99926037,0.000035348166,0.0004299923,0.0000032250753,0.00009645808,0.000017157685,0.000016796874,0.00001453145,0.00012609633],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993988,0.000013741275,0.00014499741,0.00022572403,0.00003993278,0.00017679716],"domain_scores_gemma":[0.99950945,0.000098438366,0.000018262148,0.00031797038,0.000015066336,0.00004078149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015889126,0.000102090125,0.00012317176,0.00013214689,0.000048854323,0.000021072177,0.00014069646,0.00002836794,0.00008448507],"category_scores_gemma":[9.637107e-7,0.00008645706,0.000026448597,0.00016919729,0.00000827747,0.00023964753,0.000007326276,0.000116164454,0.000009892194],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022896242,0.0003963704,0.008249252,0.000024549743,0.00014492651,0.000002522794,0.00022594647,0.015610766,0.0019748753,0.005240167,0.0004813315,0.9676264],"study_design_scores_gemma":[0.0009128187,0.00003297266,0.0057540527,0.00024440902,0.00004834311,9.559981e-7,0.000037581172,0.9813463,0.002689136,0.00010853225,0.008496715,0.0003281516],"about_ca_topic_score_codex":0.000018911132,"about_ca_topic_score_gemma":0.000062314735,"teacher_disagreement_score":0.98084635,"about_ca_system_score_codex":0.000022674245,"about_ca_system_score_gemma":0.000006393158,"threshold_uncertainty_score":0.35256168},"labels":[],"label_agreement":null},{"id":"W2543722153","doi":"10.1109/tkde.2017.2740284","title":"Activity Maximization by Effective Information Diffusion in Social Networks","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":63,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Submodular set function; Scalability; Maximization; Polling; Approximation algorithm; Heuristic; Upper and lower bounds; Social network (sociolinguistics); Mathematical optimization; Algorithm; Artificial intelligence; Social media; Mathematics","score_opus":0.010554535711334448,"score_gpt":0.26786463651132125,"score_spread":0.2573101007999868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2543722153","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.048489593,0.00001799199,0.9505302,0.000018388006,0.000100609,0.00016076834,0.00008438587,0.00004809547,0.0005499705],"genre_scores_gemma":[0.9995152,0.000018308463,0.00018404369,0.0000025724023,0.00010124886,0.000038638194,0.00011036499,0.000008816063,0.000020848935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9995274,0.000017573173,0.000116900694,0.00015731623,0.000050913844,0.00012987285],"domain_scores_gemma":[0.9994955,0.00004334796,0.000059111506,0.0003506387,0.000019975481,0.000031403666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011615361,0.0001159583,0.00013850044,0.00009488957,0.00033196597,0.00012057767,0.00019735069,0.000045266817,0.000018016799],"category_scores_gemma":[0.0000016899659,0.00012361616,0.000029598763,0.00008641387,0.0000171352,0.00095553586,0.000013262201,0.00019497261,0.0000037027653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003726341,0.00022048294,0.0014160625,0.000027209646,0.0000726942,2.304941e-7,0.0002702161,0.02203332,0.0007527949,0.00029872963,0.00095280726,0.9739182],"study_design_scores_gemma":[0.0003804956,0.000016092552,0.0077978508,0.000034398556,0.00003062632,1.631856e-7,0.0000106149055,0.9885112,0.001205033,0.00003789301,0.0018192647,0.00015638031],"about_ca_topic_score_codex":0.0001263162,"about_ca_topic_score_gemma":0.000027516366,"teacher_disagreement_score":0.9737618,"about_ca_system_score_codex":0.00002781328,"about_ca_system_score_gemma":0.000006110868,"threshold_uncertainty_score":0.5040921},"labels":[],"label_agreement":null},{"id":"W2610350176","doi":"10.1109/tkde.2017.2699965","title":"Finding Related Forum Posts through Content Similarity over Intention-Based Segmentation","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"European Research Council; Université Paris-Saclay; European Cooperation in Science and Technology","keywords":"Segmentation; Similarity (geometry); Computer science; Set (abstract data type); Point (geometry); Information retrieval; Contrast (vision); Content (measure theory); Artificial intelligence; Image (mathematics); Mathematics","score_opus":0.0766944298027059,"score_gpt":0.3090613877724966,"score_spread":0.23236695796979068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610350176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019392796,0.000107165724,0.97856206,0.00031365082,0.0011533117,0.00014238011,0.00004201914,0.00014776064,0.00013884013],"genre_scores_gemma":[0.9760288,0.000031524367,0.02374676,0.00004485886,0.000019048595,0.000011669531,0.000017228012,0.000011483579,0.00008863272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999066,0.000014667374,0.0002045094,0.00040458376,0.00011191596,0.00019830822],"domain_scores_gemma":[0.99862945,0.00007327894,0.00006166118,0.0011316754,0.000042683725,0.00006122659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000169933,0.00013781953,0.0001250682,0.0000865303,0.00040854284,0.00024618936,0.0006821073,0.000071159404,0.000010279027],"category_scores_gemma":[0.000019009733,0.00014160367,0.000040525283,0.00006964125,0.000020532625,0.0015071076,0.000023796081,0.00020454894,0.0000119462975],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010964013,0.0013742913,0.0040453263,0.0008410945,0.00075593876,0.00009380039,0.0059386077,0.2699319,0.06875214,0.020755276,0.0012421134,0.62615985],"study_design_scores_gemma":[0.0006140955,0.000030470443,0.0010152592,0.00011659581,0.000019489595,0.000004700669,0.000024240557,0.98900515,0.008546203,0.00007567133,0.0003791565,0.00016899154],"about_ca_topic_score_codex":0.000069137204,"about_ca_topic_score_gemma":0.000063064595,"teacher_disagreement_score":0.956636,"about_ca_system_score_codex":0.0000518121,"about_ca_system_score_gemma":0.0000280843,"threshold_uncertainty_score":0.577443},"labels":[],"label_agreement":null},{"id":"W2766449686","doi":"10.1109/tkde.2017.2766059","title":"A Location-Query-Browse Graph for Contextual Recommendation","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Australian Research Council","keywords":"Computer science; Graph; Bipartite graph; Information retrieval; Graph database; Web search query; Web query classification; Homogeneous; Theoretical computer science; World Wide Web; Search engine; Mathematics; Combinatorics","score_opus":0.0619002510906548,"score_gpt":0.3532966062404341,"score_spread":0.2913963551497793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766449686","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030571835,0.00009582618,0.9947436,0.0006640108,0.0003971272,0.00023915847,0.00014692171,0.000073611336,0.00058256247],"genre_scores_gemma":[0.99845266,0.00013649398,0.0005384065,0.000024673109,0.00015697951,0.000068855894,0.00007853625,0.000010067278,0.0005333262],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931246,0.000030986113,0.00015522288,0.0002726325,0.00006975516,0.00015895495],"domain_scores_gemma":[0.99895144,0.00025308912,0.00004890709,0.00053113594,0.0001222417,0.000093193674],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0005916502,0.000092123315,0.000117321775,0.00011626915,0.0014635001,0.00018369814,0.000329561,0.00006978256,0.00007681379],"category_scores_gemma":[0.00011217708,0.00010144489,0.000042398722,0.00010313391,0.00009595812,0.0005558295,0.0000030430824,0.000100496174,0.000019065397],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087705856,0.00065290544,0.00017943876,0.0003774284,0.00033621996,8.210013e-7,0.013830941,0.009816675,0.00044456575,0.00832794,0.0029708645,0.9629745],"study_design_scores_gemma":[0.0026974103,0.0002246404,0.0016703922,0.00039744074,0.00057778455,0.0000017440469,0.005068279,0.6309093,0.0023347877,0.0008611495,0.35405776,0.0011992886],"about_ca_topic_score_codex":0.0011239585,"about_ca_topic_score_gemma":0.013806432,"teacher_disagreement_score":0.9953955,"about_ca_system_score_codex":0.00004194381,"about_ca_system_score_gemma":0.00009147827,"threshold_uncertainty_score":0.99983644},"labels":[],"label_agreement":null},{"id":"W2766474394","doi":"10.1109/tkde.2017.2767044","title":"Workload Management in Database Management Systems: A Taxonomy","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Workload; Computer science; Database; Process (computing); Data management; Operating system","score_opus":0.03969699418589224,"score_gpt":0.26058751751532017,"score_spread":0.22089052332942793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766474394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021625382,0.0006647317,0.98884374,0.00007471817,0.0010444752,0.00045146802,0.000016395956,0.00017011803,0.006571825],"genre_scores_gemma":[0.9748536,0.0003635584,0.023103163,0.000019525247,0.000070398535,0.00015695041,0.0000043143627,0.000018358705,0.0014101603],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986668,0.000020289051,0.00022738513,0.0006401619,0.00014206652,0.0003032595],"domain_scores_gemma":[0.9972236,0.00003800407,0.000050741808,0.0025815691,0.0000110964575,0.0000949855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003754388,0.00019545226,0.00016971877,0.00031292447,0.00030616572,0.00044302427,0.0018203921,0.00003502719,0.00000245424],"category_scores_gemma":[0.000001592674,0.0001960621,0.000028450306,0.00016911086,0.000021750604,0.00019749018,0.00018981475,0.00017974932,0.000045163586],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013619018,0.0004243064,0.00003143849,0.0008176469,0.00028543896,0.00031884672,0.00019919322,0.17467244,0.000014031867,0.0071004494,0.001391552,0.814731],"study_design_scores_gemma":[0.00069507014,0.000020155594,0.00043970963,0.0006313131,0.000034752127,0.000009009657,0.00006447052,0.94468695,0.000035963094,0.000007844645,0.053095825,0.00027895812],"about_ca_topic_score_codex":0.00003669415,"about_ca_topic_score_gemma":0.000016287207,"teacher_disagreement_score":0.97269106,"about_ca_system_score_codex":0.000051410876,"about_ca_system_score_gemma":0.0000057818606,"threshold_uncertainty_score":0.79951805},"labels":[],"label_agreement":null},{"id":"W2784105835","doi":"10.1109/tkde.2018.2793862","title":"A Two-Phase Algorithm for Differentially Private Frequent Subgraph Mining","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"International Development Research Centre","funders":"National Institutes of Health; National Institute of General Medical Sciences; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Differential privacy; Support vector machine; Pruning; Data mining; Graph; Algorithm; Theoretical computer science; Artificial intelligence","score_opus":0.038717565892846036,"score_gpt":0.30775679803649514,"score_spread":0.2690392321436491,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784105835","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005779073,0.00021017637,0.9910123,0.00027264265,0.001195009,0.0002459557,0.0004753407,0.0007758553,0.000033654425],"genre_scores_gemma":[0.22629948,0.00008532456,0.77330494,0.000021325453,0.00013114486,0.000064985674,0.000046787613,0.000027336795,0.000018688412],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854517,0.000015562811,0.00024315646,0.0006957363,0.0001214101,0.00037894578],"domain_scores_gemma":[0.9945644,0.00018230018,0.00004222077,0.005043653,0.00006342562,0.0001039912],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00024920088,0.00022525253,0.00019866288,0.00029871677,0.00021711375,0.00015560142,0.00818061,0.0000884539,0.000007188075],"category_scores_gemma":[0.00019147813,0.00022575817,0.000045545617,0.00039251315,0.00007264027,0.0008154448,0.0009905339,0.00018736016,0.000013016862],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013030291,0.0003007593,0.0000028814022,0.00006889689,0.00012554196,0.0000071986706,0.0001689998,0.00005493711,0.007956475,0.000580879,0.0048466893,0.9858737],"study_design_scores_gemma":[0.001111142,0.00021895608,0.00000949943,0.00008308337,0.000028986402,0.000014954023,0.0000070354577,0.9548575,0.03768294,0.00088947697,0.0048257895,0.0002705946],"about_ca_topic_score_codex":0.000008176911,"about_ca_topic_score_gemma":0.000024833435,"teacher_disagreement_score":0.9856031,"about_ca_system_score_codex":0.000034109693,"about_ca_system_score_gemma":0.000032122178,"threshold_uncertainty_score":0.9971856},"labels":[],"label_agreement":null},{"id":"W2792179143","doi":"10.1109/tkde.2018.2810873","title":"Supervised Search Result Diversification via Subtopic Attention","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China; Natural Science Foundation of Beijing Municipality; Microsoft Research","keywords":"Computer science; Pooling; Diversification (marketing strategy); Machine learning; Artificial intelligence; Ranking (information retrieval); Relevance (law); Information retrieval; Data mining","score_opus":0.04992458604131879,"score_gpt":0.2878324295515918,"score_spread":0.237907843510273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792179143","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037713524,0.00002579887,0.9612956,0.00009199412,0.00044261364,0.000111378155,0.000034917943,0.00013501008,0.00014918376],"genre_scores_gemma":[0.9937066,0.00004215591,0.0058580185,0.000016431597,0.00006774066,0.0000061116843,0.000031835305,0.000005580934,0.00026554437],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992467,0.000019543877,0.00014893591,0.000252209,0.00015468812,0.0001779302],"domain_scores_gemma":[0.9991461,0.00003987726,0.0000133043395,0.00058829604,0.00012287624,0.000089536945],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024651698,0.00008968916,0.0000726778,0.00018791785,0.00021993254,0.000106786654,0.00049564656,0.00004896921,0.000022270473],"category_scores_gemma":[0.0000038360945,0.00008672344,0.000021624699,0.00035981313,0.000030604246,0.0010943409,0.000017124079,0.00013931893,0.00023078168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007606999,0.00037365954,0.00014919098,0.0001944747,0.00006849388,0.000006722385,0.004233565,0.0009047017,0.04996723,0.0020537358,0.00083168125,0.9411405],"study_design_scores_gemma":[0.00041384515,0.000122622,0.0037451866,0.000027018812,0.000011472347,0.000008697156,0.000027671478,0.9720718,0.01961758,0.000006008313,0.003786098,0.00016197117],"about_ca_topic_score_codex":0.000017149014,"about_ca_topic_score_gemma":0.0000074641416,"teacher_disagreement_score":0.97116715,"about_ca_system_score_codex":0.000030014413,"about_ca_system_score_gemma":0.000024904995,"threshold_uncertainty_score":0.35364795},"labels":[],"label_agreement":null},{"id":"W2796213239","doi":"10.1109/tkde.2018.2821671","title":"Characterizing and Predicting Early Reviewers for Effective Product Marketing on E-Commerce Websites","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Digital Marketing and Social Media","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"National Key Research and Development Program of China; Innovate UK; Natural Science Foundation of Beijing Municipality; Renmin University of China; National Natural Science Foundation of China","keywords":"Helpfulness; Popularity; Product (mathematics); Computer science; New product development; Information retrieval; Artificial intelligence; World Wide Web; Psychology; Marketing; Mathematics; Business; Social psychology","score_opus":0.023891853591576025,"score_gpt":0.3001767249798764,"score_spread":0.2762848713883004,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796213239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9484434,0.0014106921,0.028374227,0.00058422796,0.0036243843,0.0019354379,0.0002868291,0.0005348343,0.014805942],"genre_scores_gemma":[0.9977687,0.00039068845,0.0005486156,0.00003483989,0.00081638095,0.000068668356,0.000008362794,0.000025145764,0.00033862522],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99893063,0.00011586865,0.00015970292,0.00039128927,0.000115217015,0.00028728438],"domain_scores_gemma":[0.9980558,0.0014744838,0.000042359734,0.00022446743,0.000078750665,0.00012409584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017882325,0.00014710745,0.00018840781,0.000095989264,0.00063552364,0.00014338641,0.00016189796,0.00006180073,0.000006823417],"category_scores_gemma":[0.0008170356,0.0001502987,0.000032798678,0.00018704322,0.000112400216,0.00042666978,0.000007008889,0.00017137767,0.000010832287],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019254394,0.00012888713,0.0008824397,0.0005160551,0.000112490125,0.0000012424591,0.01571827,0.000008987198,0.0017901566,0.00015918899,0.0005790615,0.9799107],"study_design_scores_gemma":[0.0041977083,0.0023681326,0.07435237,0.013469569,0.00084635086,0.000015976477,0.009126152,0.030587818,0.012196762,0.00012313084,0.8490614,0.0036546013],"about_ca_topic_score_codex":0.00003749277,"about_ca_topic_score_gemma":0.00009723568,"teacher_disagreement_score":0.9762561,"about_ca_system_score_codex":0.000038380356,"about_ca_system_score_gemma":0.000027189953,"threshold_uncertainty_score":0.6129003},"labels":[],"label_agreement":null},{"id":"W2796436043","doi":"10.1109/tkde.2020.2981311","title":"HyperMinHash: MinHash in LogLog space","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Cancer Institute; National Human Genome Research Institute; National Institutes of Health","keywords":"Jaccard index; Cardinality (data modeling); Combinatorics; Mathematics; Discrete mathematics; Computer science; Data mining; Statistics","score_opus":0.04477670225587619,"score_gpt":0.28229477497768213,"score_spread":0.23751807272180595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796436043","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009919672,0.0013891148,0.9944337,0.00030464932,0.0017399346,0.00022547125,0.00043502086,0.00027031568,0.00020979658],"genre_scores_gemma":[0.88697964,0.0014307714,0.11058173,0.00008390812,0.0003419995,0.00008061206,0.0002495703,0.00007001224,0.00018175294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980478,0.00003339448,0.0003162533,0.0011294341,0.00016592999,0.00030712967],"domain_scores_gemma":[0.99775255,0.00013735698,0.000052945074,0.0018348816,0.000030417132,0.00019182367],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00018104662,0.00036108616,0.00040285432,0.00029075495,0.00007622432,0.00020502556,0.0016232971,0.0002381995,0.000009897413],"category_scores_gemma":[0.000011104327,0.00036968765,0.000055537064,0.00032088094,0.000023260587,0.00044747867,0.00028249095,0.00097181834,0.00005668348],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000074556585,0.0012717184,0.000053767322,0.002733442,0.00034258296,0.0006693196,0.004159573,0.21153057,0.0061079953,0.00371217,0.014397336,0.754947],"study_design_scores_gemma":[0.00035372548,0.000040980918,0.00013063489,0.00040620234,0.000022238619,0.000021696647,0.00000792215,0.9866337,0.0014029713,0.00013113307,0.010395793,0.0004529745],"about_ca_topic_score_codex":0.000046787743,"about_ca_topic_score_gemma":0.000036474972,"teacher_disagreement_score":0.8859877,"about_ca_system_score_codex":0.000052760766,"about_ca_system_score_gemma":0.00011478901,"threshold_uncertainty_score":0.9998755},"labels":[],"label_agreement":null},{"id":"W2797819729","doi":"10.1109/tkde.2018.2828095","title":"Fast Cosine Similarity Search in Binary Space with Angular Multi-Index Hashing","year":2018,"lang":"en","type":"preprint","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hamming distance; Nearest neighbor search; Binary code; Hash function; Hash table; Cosine similarity; Dynamic perfect hashing; Hamming space; Binary number; Computer science; Locality-sensitive hashing; Similarity (geometry); Linear search; Algorithm; Binary search algorithm; Hamming code; Search algorithm; Mathematics; Theoretical computer science; Double hashing; Data mining; Pattern recognition (psychology); Block code; Artificial intelligence; Decoding methods","score_opus":0.04571143733524703,"score_gpt":0.31959227247375244,"score_spread":0.2738808351385054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797819729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0033376897,0.00077637803,0.99447584,0.00008759024,0.000280687,0.0003915504,0.00015643192,0.0004501836,0.000043636384],"genre_scores_gemma":[0.75188833,0.00059416896,0.24716166,0.000020339368,0.00009312478,0.000040520135,0.000046629517,0.000053497213,0.000101752215],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980417,0.000047803707,0.00026819692,0.0010318112,0.00021286738,0.00039763207],"domain_scores_gemma":[0.9978503,0.00011273602,0.00004910166,0.0017264469,0.000115979026,0.00014541643],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040356495,0.00038922278,0.0003771805,0.00050459645,0.00013027771,0.00022539383,0.0012835669,0.00023558977,0.000004813353],"category_scores_gemma":[0.0000123748905,0.00037452995,0.00004454037,0.000546904,0.000072373616,0.0009881258,0.00018784203,0.0012284919,0.000007764197],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042861205,0.003713286,0.0009849581,0.00499854,0.0006356263,0.0010787331,0.006967257,0.53501856,0.01871399,0.0003990919,0.0011449023,0.42591643],"study_design_scores_gemma":[0.0005018711,0.00015866873,0.00044697043,0.0010654535,0.000019968702,0.000024551426,0.00001877791,0.95957315,0.0367051,0.000025034697,0.00093730766,0.00052314467],"about_ca_topic_score_codex":0.00006888327,"about_ca_topic_score_gemma":0.00011739329,"teacher_disagreement_score":0.74855065,"about_ca_system_score_codex":0.00010942544,"about_ca_system_score_gemma":0.00012717981,"threshold_uncertainty_score":0.99987066},"labels":[],"label_agreement":null},{"id":"W2807633791","doi":"10.1109/tkde.2018.2857471","title":"Secure and Efficient Skyline Queries on Encrypted Data","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Cryptography and Data Security","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Institutes of Health; National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Patient-Centered Outcomes Research Institute","keywords":"Computer science; Encryption; Cloud computing; Skyline; Scalability; Database; Outsourcing; Computer network; Data mining; Operating system","score_opus":0.02885223219186742,"score_gpt":0.2747359068435998,"score_spread":0.24588367465173236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807633791","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010802965,0.0006507462,0.9861723,0.000097429205,0.0007115857,0.00011343609,0.0010742289,0.00021994085,0.00015735005],"genre_scores_gemma":[0.97821707,0.00032169672,0.021090755,0.000053166885,0.00013234529,0.000006455839,0.00015640569,0.000014589703,0.0000075264775],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871176,0.000022609976,0.00017350184,0.0007312957,0.00012749726,0.00023334668],"domain_scores_gemma":[0.99756473,0.00014294923,0.000024047113,0.0020772445,0.00005100508,0.00014001435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002694349,0.00019441487,0.00015718755,0.00020342963,0.00023404953,0.00015235398,0.0010672646,0.000070432514,0.00001367119],"category_scores_gemma":[0.000017543583,0.00018114662,0.00001594622,0.0004954873,0.000089075686,0.0006743341,0.00009002592,0.00022624277,0.000026203674],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036950005,0.0031725548,0.00007025102,0.00094475166,0.0006581213,0.00008471085,0.01237388,0.0070393397,0.010007941,0.12172872,0.02039197,0.82315826],"study_design_scores_gemma":[0.00049131276,0.0002286566,0.00027891967,0.00011284873,0.000032199678,0.000028757515,0.000034327582,0.936373,0.0031119976,0.00006824882,0.05889122,0.00034854232],"about_ca_topic_score_codex":0.00001616767,"about_ca_topic_score_gemma":0.0000831423,"teacher_disagreement_score":0.9674141,"about_ca_system_score_codex":0.000009107695,"about_ca_system_score_gemma":0.00002923531,"threshold_uncertainty_score":0.7386945},"labels":[],"label_agreement":null},{"id":"W2820145021","doi":"10.1109/tkde.2018.2854797","title":"Introducing Cuts Into a Top-Down Process for Checking Tree Inclusion","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Tree (set theory); Matching (statistics); Bounded function; Computer science; Set (abstract data type); Combinatorics; Order (exchange); Space (punctuation); Theoretical computer science; Algorithm; Discrete mathematics; Mathematics; Programming language; Statistics","score_opus":0.021276819399349816,"score_gpt":0.2953921537667026,"score_spread":0.27411533436735275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2820145021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037677342,0.00029715817,0.9943265,0.00011316315,0.0009711499,0.00018978784,0.000042086016,0.00020736932,0.000085067135],"genre_scores_gemma":[0.8997635,0.000051288956,0.09946004,0.000039473118,0.0005206884,0.000042772503,0.000031584448,0.000023021707,0.0000675967],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998789,0.000011127034,0.00019921403,0.00062188687,0.00012920452,0.00024955897],"domain_scores_gemma":[0.9987339,0.00009753531,0.00003467944,0.0009291952,0.000097997996,0.00010670897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028269252,0.00017555225,0.00016309407,0.00018582595,0.00061438984,0.00011590813,0.0008979566,0.00006846456,0.0000056448694],"category_scores_gemma":[0.000018398405,0.00016033291,0.000028572093,0.00031925415,0.000026222158,0.0011601275,0.00012793484,0.00015293575,0.000011259977],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003489969,0.00018541035,0.000005410312,0.00025696773,0.000040276645,0.0000027198034,0.005691021,0.003761278,0.013651363,0.00035538853,0.00095841207,0.9750568],"study_design_scores_gemma":[0.0003888017,0.00013673524,0.00001762674,0.00016021694,0.000015426413,0.000010374968,0.000020957204,0.94720775,0.03548577,0.00016242266,0.016173506,0.00022043138],"about_ca_topic_score_codex":0.000016604727,"about_ca_topic_score_gemma":0.0000357057,"teacher_disagreement_score":0.9748364,"about_ca_system_score_codex":0.000034208442,"about_ca_system_score_gemma":0.000047687623,"threshold_uncertainty_score":0.65381867},"labels":[],"label_agreement":null},{"id":"W2894983428","doi":"10.1109/tkde.2018.2874004","title":"Precise and Fast Cryptanalysis for Bloom Filter Based Privacy-Preserving Record Linkage","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Australian Research Council; Engineering and Physical Sciences Research Council; Simons Foundation","keywords":"Bloom filter; Computer science; Cryptanalysis; Encoding (memory); Scalability; Data mining; Filter (signal processing); Information retrieval; Algorithm; Database; Cryptography; Artificial intelligence","score_opus":0.1370625278578638,"score_gpt":0.37971452956261115,"score_spread":0.24265200170474735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894983428","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008671869,0.00013832583,0.9888781,0.00027736774,0.0005128523,0.00025500573,0.0008922806,0.00007159388,0.0003026408],"genre_scores_gemma":[0.93603486,0.00016543701,0.06076394,0.00015330031,0.0003241334,0.000084471314,0.00011199194,0.00004107708,0.0023207935],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99828416,0.000055036526,0.00042596183,0.0007207556,0.00026620913,0.00024786507],"domain_scores_gemma":[0.99699545,0.0010530564,0.00006252074,0.0016079806,0.00013251322,0.00014847206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015251181,0.00018291181,0.00026672706,0.00040035925,0.00026099946,0.0003488799,0.00097805,0.00007015829,0.00025815767],"category_scores_gemma":[0.0002989434,0.00015787329,0.00006376469,0.00046415167,0.000059621078,0.00080034725,0.00006468348,0.00012731263,0.000061958744],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018535274,0.00037970082,0.00007094775,0.0002937481,0.0002929227,0.000004459372,0.0012649567,0.0035420908,0.0021193437,0.00014924143,0.0328073,0.95888996],"study_design_scores_gemma":[0.0006101198,0.00012284087,0.00016702455,0.00007932181,0.00013787835,0.0000012727509,0.00012227512,0.7403471,0.0027603114,0.00020670252,0.25520077,0.00024439336],"about_ca_topic_score_codex":0.000022244483,"about_ca_topic_score_gemma":0.0002727275,"teacher_disagreement_score":0.9586455,"about_ca_system_score_codex":0.000015836551,"about_ca_system_score_gemma":0.000021519008,"threshold_uncertainty_score":0.6437886},"labels":[],"label_agreement":null},{"id":"W2900691829","doi":"10.1109/tkde.2019.2893175","title":"Similarity Join and Similarity Self-Join Size Estimation in a Streaming Environment","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Similarity (geometry); Join (topology); Nearest neighbor search; Sublinear function; Range (aeronautics); Unary operation; Range query (database)","score_opus":0.0592414764365441,"score_gpt":0.3250866367617011,"score_spread":0.265845160325157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2900691829","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25384632,0.0002644247,0.74363446,0.00029839686,0.00041482906,0.0005004491,0.0005214073,0.000106888074,0.00041281444],"genre_scores_gemma":[0.99140227,0.0002026136,0.008068964,0.000046830944,0.000014699832,0.000013562765,0.000028466684,0.000012131092,0.00021044962],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982984,0.00008094188,0.00041774882,0.0006526922,0.00033054125,0.00021969082],"domain_scores_gemma":[0.9979545,0.0009304636,0.000052638286,0.0009423762,0.000015946101,0.000104066385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017209367,0.00017942024,0.00025737,0.00023762217,0.00009240413,0.0001761454,0.00038556414,0.0000811863,0.00012929972],"category_scores_gemma":[0.00010198143,0.00016935867,0.000027878285,0.00026213107,0.00002557398,0.0009398963,0.000047762715,0.0002486491,0.00011649519],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014129966,0.0021606265,0.0023203203,0.0007675231,0.00023536444,0.000034617675,0.005454815,0.22842643,0.0023817054,0.001429478,0.0021089786,0.75453883],"study_design_scores_gemma":[0.00086850143,0.0000803062,0.010018683,0.00007869355,0.00004257946,0.0000065059075,0.00032750107,0.96983176,0.0005538113,0.00030863765,0.01756609,0.00031692936],"about_ca_topic_score_codex":0.00004516713,"about_ca_topic_score_gemma":0.00015462279,"teacher_disagreement_score":0.7542219,"about_ca_system_score_codex":0.000056009325,"about_ca_system_score_gemma":0.000018753506,"threshold_uncertainty_score":0.6906246},"labels":[],"label_agreement":null},{"id":"W2902521181","doi":"10.1109/tkde.2019.2923914","title":"Skyline Diagram: Efficient Space Partitioning for Skyline Queries","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Skyline; Computer science; Voronoi diagram; Set (abstract data type); Scalability; Data mining; Space (punctuation); Theoretical computer science; Database; Mathematics","score_opus":0.0196882249210968,"score_gpt":0.2580137143152098,"score_spread":0.23832548939411302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902521181","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025708447,0.00029643512,0.9949624,0.00020584371,0.0011133448,0.00028331106,0.00019143862,0.0002241303,0.00015228013],"genre_scores_gemma":[0.9166816,0.00018358002,0.08110204,0.00005191485,0.00018448083,0.0000837176,0.00020037025,0.000033734836,0.0014785746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990132,0.0000088408615,0.00016587213,0.00046436058,0.000098176046,0.0002495859],"domain_scores_gemma":[0.9989148,0.00012153396,0.00002670463,0.0008236896,0.000035482106,0.00007779722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023094281,0.00015709094,0.0001533866,0.00014726058,0.00011955924,0.00018170186,0.00054781855,0.000036939786,0.000013757688],"category_scores_gemma":[0.000007601591,0.00015333355,0.00003656233,0.00025754562,0.000014397963,0.0006841073,0.000028717604,0.00011132727,0.0000705338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006104619,0.0010726505,0.00006924533,0.0011102922,0.0003365323,0.000013965876,0.0013366834,0.42679006,0.0037809173,0.04125494,0.0047380053,0.51943564],"study_design_scores_gemma":[0.0004411974,0.00007429068,0.00005250659,0.00006045029,0.000019920904,0.000002703075,0.000015890197,0.94799036,0.002570663,0.000021789772,0.04855021,0.00020001295],"about_ca_topic_score_codex":0.000005432762,"about_ca_topic_score_gemma":0.000011121091,"teacher_disagreement_score":0.9141107,"about_ca_system_score_codex":0.00001755021,"about_ca_system_score_gemma":0.000016226832,"threshold_uncertainty_score":0.625276},"labels":[],"label_agreement":null},{"id":"W2972941956","doi":"10.1109/tkde.2019.2940019","title":"Bayesian Networks for Data Integration in the Absence of Foreign Keys","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Ontario Centres of Excellence","keywords":"Computer science; Relational database; Probabilistic logic; Inference; Data integration; Bayesian network; Data mining; Cardinality (data modeling); Relation (database); Population; Theoretical computer science; Data science; Information retrieval; Machine learning; Artificial intelligence","score_opus":0.12352446206391332,"score_gpt":0.36871568932336674,"score_spread":0.24519122725945341,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2972941956","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001230318,0.000119786695,0.99680245,0.00007699007,0.0003507523,0.00035184555,0.0005194247,0.000013306358,0.0005351476],"genre_scores_gemma":[0.99663115,0.00007915783,0.0028660698,0.000037104386,0.00003175615,0.000016732634,0.00019650391,0.000006575117,0.00013495772],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998862,0.00004984558,0.00034554675,0.00040145044,0.00020827357,0.00013287285],"domain_scores_gemma":[0.99689454,0.0011261518,0.00005092088,0.0018625873,0.00003853228,0.000027294212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026728623,0.0000928476,0.00015534711,0.00016705027,0.000048184946,0.00009553989,0.0015743341,0.000041364416,0.00002824515],"category_scores_gemma":[0.00009193257,0.00006370349,0.00002292748,0.00038869915,0.000021345866,0.0008133609,0.000027598968,0.00012449347,0.000016056367],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010970451,0.00040993062,0.00016829272,0.00017808285,0.00006214937,0.0000019133624,0.0016485108,0.14296232,0.00041434178,0.016221173,0.014996892,0.8228267],"study_design_scores_gemma":[0.00024341376,0.000046821693,0.00020721633,0.00005513913,0.000011755861,0.0000011279345,0.000621536,0.9838045,0.00013181682,0.00039934384,0.01439507,0.00008225713],"about_ca_topic_score_codex":0.000027762935,"about_ca_topic_score_gemma":0.0002893638,"teacher_disagreement_score":0.99540085,"about_ca_system_score_codex":0.000007877881,"about_ca_system_score_gemma":0.000013856022,"threshold_uncertainty_score":0.29255307},"labels":[],"label_agreement":null},{"id":"W2990448760","doi":"10.1109/tkde.2019.2956520","title":"Self-Healing Event Logs","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Science Foundation of Jiangsu Province; National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft","keywords":"Computer science; Event (particle physics); Process mining; Complex event processing; Process (computing); Data mining; Business process; Rendering (computer graphics); Business process discovery; Event tree analysis; Business process management; Data science; Artificial intelligence; Business process modeling; Work in process; Reliability engineering","score_opus":0.018099234945841133,"score_gpt":0.23949345707916098,"score_spread":0.22139422213331983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990448760","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06788742,0.0008068314,0.92814815,0.00017245194,0.0010350943,0.0001614924,0.000020401867,0.0005174339,0.0012507291],"genre_scores_gemma":[0.9983685,0.00012242828,0.00081232906,0.00010012253,0.0003223216,0.000009338616,0.000037213737,0.000033382235,0.00019437385],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990632,0.0000026049945,0.0002005825,0.00039752215,0.00011351943,0.00022257972],"domain_scores_gemma":[0.99935275,0.00003367918,0.000042729273,0.00047795134,0.00007342514,0.000019449299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020524058,0.00018125272,0.0001972568,0.0003045787,0.00012192983,0.00015020161,0.00027163437,0.00006603009,0.00007174742],"category_scores_gemma":[0.0000046169075,0.00017455763,0.000048275055,0.00042931354,0.000007584684,0.0010142522,0.0000130545595,0.00018546724,0.00042230208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007877618,0.0011080188,0.000915867,0.006310128,0.00065133354,0.000014519378,0.00036481404,0.82891047,0.003275287,0.0024084277,0.0012200713,0.15474227],"study_design_scores_gemma":[0.0003176566,0.000005056283,0.000051011444,0.00011374976,0.00013078163,0.000002130011,0.000032522785,0.9702981,0.00017050037,0.00002801277,0.028607659,0.00024279206],"about_ca_topic_score_codex":0.00005690278,"about_ca_topic_score_gemma":0.000018389332,"teacher_disagreement_score":0.9304811,"about_ca_system_score_codex":0.00001682046,"about_ca_system_score_gemma":0.000015401003,"threshold_uncertainty_score":0.7118254},"labels":[],"label_agreement":null},{"id":"W2994742394","doi":"10.1109/tkde.2019.2960347","title":"Group-Based Skyline for Pareto Optimal Groups","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Air Force Office of Scientific Research; National Science Foundation","keywords":"Skyline; Computer science; Pareto principle; Dimension (graph theory); Heuristic; Group (periodic table); Point (geometry); Pareto optimal; Computation; Set (abstract data type); Theoretical computer science; Data mining; Combinatorics; Artificial intelligence; Mathematics; Algorithm; Mathematical optimization","score_opus":0.02137811809518209,"score_gpt":0.2535165900882512,"score_spread":0.23213847199306914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994742394","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019137857,0.000125877,0.9961188,0.00007737754,0.0009574051,0.00027518484,0.00023852763,0.00021291875,0.00008015729],"genre_scores_gemma":[0.81576777,0.00005180188,0.18314175,0.000085488806,0.00014753541,0.00007429668,0.00029110917,0.000033735534,0.00040652443],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990436,0.000007559012,0.00014832274,0.00047885577,0.00008995883,0.00023170644],"domain_scores_gemma":[0.9988404,0.00011684176,0.000020171427,0.0009229158,0.000022396685,0.00007725623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020342591,0.00015418313,0.00014290426,0.00015757616,0.00007631885,0.00014408393,0.0008046786,0.000040657145,0.000011442852],"category_scores_gemma":[0.000002784229,0.0001521496,0.000038941205,0.00021827365,0.000009384103,0.000996017,0.000019647263,0.00010702491,0.000059640835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118367134,0.0013225296,0.00006452247,0.0014128616,0.00037127818,0.000020332543,0.00046559214,0.16793877,0.005114954,0.024209086,0.0068372367,0.79212445],"study_design_scores_gemma":[0.00069518515,0.00012126235,0.000034988152,0.000038124348,0.000018526238,0.0000016273897,0.0000072011153,0.96552867,0.0010998956,0.000013537251,0.032239985,0.00020102081],"about_ca_topic_score_codex":0.0000030131866,"about_ca_topic_score_gemma":0.000006484724,"teacher_disagreement_score":0.813854,"about_ca_system_score_codex":0.000015540427,"about_ca_system_score_gemma":0.00001343281,"threshold_uncertainty_score":0.62044805},"labels":[],"label_agreement":null},{"id":"W3002803388","doi":"10.1109/tkde.2020.2969419","title":"Paywall Policy Learning in Digital News Media","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Toronto Metropolitan University; York University; Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Newspaper; Function (biology); Thompson sampling; Artificial intelligence; Baseline (sea); Reading (process); Machine learning","score_opus":0.035056090995382753,"score_gpt":0.2633731265782509,"score_spread":0.22831703558286814,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3002803388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00082548725,0.00019197301,0.99715734,0.0006792611,0.0001648982,0.00007206384,0.0000195164,0.00036029174,0.0005291912],"genre_scores_gemma":[0.99470806,0.00014657932,0.0049261604,0.00005806992,0.00010472988,0.00000960995,0.000007328319,0.000012439385,0.000027024429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926716,0.000010438953,0.00016786972,0.0003205188,0.000066596825,0.00016739844],"domain_scores_gemma":[0.99943644,0.00008868682,0.000017191645,0.00032651427,0.000011986941,0.00011915288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007525991,0.00011784238,0.00013933408,0.00016237515,0.000040734296,0.00015356045,0.0004783786,0.000046505862,0.0000021648482],"category_scores_gemma":[0.000017907681,0.00011492197,0.000022202554,0.00038663222,0.0000065662507,0.0008613846,0.000020304898,0.00024586997,0.00001963606],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006146486,0.00010368247,0.00017768885,0.00012077705,0.000025723422,0.000023112798,0.0045101214,0.004846237,0.00059118605,0.001981795,0.0009904284,0.9866231],"study_design_scores_gemma":[0.00050149404,0.00012724745,0.00022604209,0.00011935274,0.0000056786494,0.000023485047,0.00008167163,0.8748521,0.0021492303,0.000079484445,0.12142164,0.00041255855],"about_ca_topic_score_codex":0.000043618813,"about_ca_topic_score_gemma":0.000033455493,"teacher_disagreement_score":0.9938826,"about_ca_system_score_codex":0.000020994195,"about_ca_system_score_gemma":0.00003353239,"threshold_uncertainty_score":0.4686382},"labels":[],"label_agreement":null},{"id":"W3009808474","doi":"10.1109/tkde.2020.2978469","title":"A Framework for Anomaly Detection in Time-Driven and Event-Driven Processes using Kernel Traces","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Abstraction; Model checking; Kernel (algebra); Exploit; Probabilistic logic; Process (computing); Theoretical computer science; Distributed computing; Data mining; Programming language; Artificial intelligence","score_opus":0.033683838327205805,"score_gpt":0.2828885598886682,"score_spread":0.24920472156146237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009808474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16595161,0.00034415923,0.8331179,0.000052860418,0.00016125073,0.00022427336,0.000030803374,0.000115759496,0.0000014093082],"genre_scores_gemma":[0.9673454,0.00008281882,0.032441612,0.0000150860615,0.00006691079,0.000030180665,0.0000025031632,0.000011891015,0.0000035736202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914163,0.000014289631,0.0001895956,0.00041539493,0.000073984025,0.00016509333],"domain_scores_gemma":[0.9993895,0.0001812039,0.00003023122,0.00027527445,0.00003752961,0.00008622764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011762999,0.00013397756,0.00017098805,0.000096587464,0.00010248409,0.00008698543,0.00031097844,0.00008941118,0.0000013553091],"category_scores_gemma":[0.000031293075,0.00012792532,0.000021712778,0.00038162916,0.000016451118,0.000731319,0.0000132828645,0.0001579477,0.0000043248483],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003282702,0.00093224016,0.0051497566,0.0101153515,0.00032524287,0.000020446609,0.020527609,0.5604455,0.043495003,0.00016008022,0.00008215396,0.35841838],"study_design_scores_gemma":[0.00028854888,0.00010432039,0.00032245743,0.00018813163,0.00001660755,0.0000097879365,0.000022523029,0.9917605,0.006833685,0.000019857865,0.00027450005,0.00015908398],"about_ca_topic_score_codex":0.000008770114,"about_ca_topic_score_gemma":0.000020233765,"teacher_disagreement_score":0.8013938,"about_ca_system_score_codex":0.000024000463,"about_ca_system_score_gemma":0.00004519247,"threshold_uncertainty_score":0.5216643},"labels":[],"label_agreement":null},{"id":"W3030885106","doi":"10.1109/tkde.2020.2997938","title":"SCHAIN-IRAM: An Efficient and Effective Semi-Supervised Clustering Algorithm for Attributed Heterogeneous Information Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Cluster analysis; Computer science; Set (abstract data type); Algorithm; Theoretical computer science; Artificial intelligence; Data mining; Information retrieval; Programming language","score_opus":0.019994299086997888,"score_gpt":0.25005122190912826,"score_spread":0.23005692282213036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3030885106","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030125102,0.00032377988,0.9951977,0.00005041383,0.0004077247,0.0005600492,0.0001321647,0.00031371517,0.0000019138668],"genre_scores_gemma":[0.9190846,0.00010134277,0.080370925,0.00014413949,0.000103175065,0.00009012017,0.000080716694,0.00002359049,0.00000139571],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895513,0.000026724014,0.000214937,0.00043241706,0.000084452186,0.00028635786],"domain_scores_gemma":[0.9990735,0.00018419168,0.00003520736,0.00042245106,0.00005675366,0.00022786415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012939092,0.00021590319,0.00020112519,0.00010505765,0.00019409663,0.00014942265,0.0003847557,0.00008664087,6.365705e-7],"category_scores_gemma":[0.000007754385,0.00022268915,0.000034625817,0.00034810533,0.000020200054,0.001090777,0.000034137214,0.00022399407,0.0000020326045],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010547598,0.000016269869,4.2767635e-7,0.00003472724,0.000018884304,0.0000013531362,0.00024159983,0.6429139,0.00010195491,0.000009726532,0.000006943712,0.35664368],"study_design_scores_gemma":[0.00069473963,0.00021238599,0.000016528787,0.00004178208,0.000021366232,0.000027866254,0.000011391304,0.9970986,0.0010026647,0.00000316919,0.00063450984,0.00023495952],"about_ca_topic_score_codex":0.0000018021342,"about_ca_topic_score_gemma":0.0000027173664,"teacher_disagreement_score":0.9160721,"about_ca_system_score_codex":0.000023841969,"about_ca_system_score_gemma":0.000009308077,"threshold_uncertainty_score":0.9081},"labels":[],"label_agreement":null},{"id":"W3128735821","doi":"10.1109/tkde.2021.3054671","title":"Transfer Learning for Dynamic Feature Extraction Using Variational Bayesian Inference","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Fault Detection and Control Systems","field":"Engineering","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Inference; Bayesian inference; Weighting; Feature (linguistics); Machine learning; Transfer of learning; Artificial intelligence; Data mining; Bayesian probability; Domain (mathematical analysis); Mathematics","score_opus":0.01656466914588841,"score_gpt":0.27181164893949267,"score_spread":0.2552469797936043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128735821","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007102989,0.000703805,0.99034065,0.00002526418,0.0012196712,0.00014568078,0.00012792376,0.0002626469,0.00007134533],"genre_scores_gemma":[0.99637324,0.00013636141,0.0029733006,0.000007373388,0.00010680416,0.000038470764,0.00007939077,0.000045639255,0.00023945041],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922335,0.000019667144,0.00018113783,0.00028859073,0.00008513875,0.00020210628],"domain_scores_gemma":[0.99944407,0.00015950664,0.000009736036,0.00024812564,0.000056204626,0.000082374325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011104912,0.00018225862,0.00017810514,0.00013368341,0.0001590484,0.000075501746,0.00009332766,0.00013559293,0.000027266511],"category_scores_gemma":[0.000011834514,0.00021001307,0.00005520202,0.00021596969,0.0000074173195,0.00045360267,0.0000014869569,0.00033606004,0.0000059672843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011611664,0.000026854928,0.0000022059173,0.00016978974,0.00008832613,0.0000025182521,0.000109104585,0.8854181,0.09827728,0.000049535454,0.000022319698,0.015822338],"study_design_scores_gemma":[0.0004916388,0.000021369979,0.000040772407,0.000080414975,0.00006232372,0.00004832169,0.00005734967,0.98028004,0.00806698,0.0000054488037,0.010625783,0.00021953239],"about_ca_topic_score_codex":0.0000041533444,"about_ca_topic_score_gemma":0.000057223406,"teacher_disagreement_score":0.9892702,"about_ca_system_score_codex":0.00007444487,"about_ca_system_score_gemma":0.000036975598,"threshold_uncertainty_score":0.8564085},"labels":[],"label_agreement":null},{"id":"W3163325638","doi":"10.1109/tkde.2021.3075052","title":"Learning Hierarchical Review Graph Representations for Recommendation","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Research (Canada)","funders":"Youth Innovation Promotion Association; Youth Innovation Promotion Association of the Chinese Academy of Sciences; National Research Foundation Singapore; National Natural Science Foundation of China; Nanyang Technological University; National Research Foundation","keywords":"Computer science; Pooling; Graph; Recommender system; Artificial intelligence; Convolutional neural network; Recurrent neural network; Machine learning; Information retrieval; Theoretical computer science; Artificial neural network","score_opus":0.04649403019805645,"score_gpt":0.3242526013051148,"score_spread":0.27775857110705837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163325638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000024142768,0.0018560267,0.99579227,0.0011034294,0.00041619883,0.0001884099,0.000035210953,0.00023132886,0.00035300694],"genre_scores_gemma":[0.41669956,0.04266735,0.5361134,0.0007374038,0.000368614,0.0008602386,0.0007808705,0.00009759684,0.0016749795],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991678,0.000048612244,0.00020967603,0.00038584173,0.00005334167,0.0001347323],"domain_scores_gemma":[0.9990819,0.00022993346,0.000028846938,0.0005277234,0.00006624627,0.00006531111],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002962213,0.00010067471,0.00015033092,0.000096613265,0.00015841152,0.00008299175,0.00026330844,0.000039130184,0.000011720214],"category_scores_gemma":[0.000024863082,0.00010328337,0.00004824166,0.00029803262,0.000006442916,0.00047427157,0.000013741359,0.00018502862,0.0000043449127],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034662546,0.0001846628,0.000009909862,0.0012420233,0.00010195015,0.0000049988116,0.00033331165,0.00076386944,0.001129815,0.0048446194,0.011822789,0.9795586],"study_design_scores_gemma":[0.00055294164,0.0001584852,0.000056280107,0.0013640473,0.00007423177,0.00012277922,0.000037948237,0.5360892,0.012272496,0.00047308175,0.44831505,0.0004834521],"about_ca_topic_score_codex":0.0000043196646,"about_ca_topic_score_gemma":0.000009611988,"teacher_disagreement_score":0.97907513,"about_ca_system_score_codex":0.000014425477,"about_ca_system_score_gemma":0.000030658874,"threshold_uncertainty_score":0.42117736},"labels":[],"label_agreement":null},{"id":"W3163458230","doi":"10.1109/tkde.2021.3078099","title":"A Generalized Framework for Preserving Both Privacy and Utility in Data Outsourcing","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Division of Computer and Network Systems; National Institute of General Medical Sciences; National Institutes of Health","keywords":"Outsourcing; Computer science; Information privacy; Computer security; Data modeling; Data mining; Database; Business","score_opus":0.07632184727430395,"score_gpt":0.3213946121611277,"score_spread":0.24507276488682372,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163458230","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005176481,0.0020471972,0.98968554,0.0015533511,0.00040892776,0.00021489094,0.00053506246,0.0003605757,0.000017977689],"genre_scores_gemma":[0.28004456,0.0005457185,0.71917355,0.000030162199,0.00004033882,0.00003236515,0.00009249823,0.000021337259,0.000019454834],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981473,0.000040919196,0.00028064224,0.0010686066,0.00011383888,0.00034870702],"domain_scores_gemma":[0.9879639,0.00064031145,0.000036577814,0.011236457,0.000036009693,0.0000867221],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0005745377,0.00020062194,0.00025585984,0.00017530483,0.00013524317,0.00022865097,0.010421437,0.00014629729,0.0000063972457],"category_scores_gemma":[0.0020975436,0.0002186497,0.000020949441,0.00048429696,0.000031744163,0.0014916618,0.005952464,0.0004084691,0.0000016165811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016157166,0.0017841219,0.0012382709,0.0040325667,0.00069902116,0.00020377891,0.004051642,0.008788421,0.010736668,0.010773355,0.055221207,0.90230936],"study_design_scores_gemma":[0.00043785945,0.000014570144,0.00021951966,0.00022438387,0.000017837237,0.00001783818,0.000026237512,0.98392075,0.0027900662,0.0050975983,0.007000442,0.00023289156],"about_ca_topic_score_codex":0.000027798038,"about_ca_topic_score_gemma":0.00010732038,"teacher_disagreement_score":0.97513235,"about_ca_system_score_codex":0.000030455229,"about_ca_system_score_gemma":0.00006980385,"threshold_uncertainty_score":0.99493265},"labels":[],"label_agreement":null},{"id":"W3167049326","doi":"10.1109/tkde.2023.3328882","title":"DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Support vector machine; Artificial intelligence; Pattern recognition (psychology); Anomaly (physics); Data mining; Data modeling","score_opus":0.058018093014621526,"score_gpt":0.298694577054953,"score_spread":0.24067648404033148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167049326","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00091282884,0.000060047187,0.99620473,0.000098366676,0.00068725157,0.0003208499,0.00032819744,0.0013285967,0.000059155336],"genre_scores_gemma":[0.9505385,0.00014443627,0.048428647,0.000025674119,0.00014799401,0.00022126795,0.00014863473,0.00003493699,0.00030988464],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986665,0.000011615354,0.0002344904,0.000705694,0.00009711589,0.00028453427],"domain_scores_gemma":[0.99801856,0.0001386841,0.000038874197,0.0016426116,0.000047307014,0.000113988084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033608603,0.00017182714,0.00015092015,0.00029652193,0.00033152624,0.00014987525,0.0011836272,0.00008446008,0.000009373998],"category_scores_gemma":[0.000013974426,0.00018508438,0.000039053666,0.0007114841,0.000018027838,0.0010702515,0.00005725256,0.00016311894,0.00005968888],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026893022,0.00024747042,0.000010910898,0.0002973043,0.00014953507,0.000007874267,0.00058861304,0.0059007034,0.061463155,0.0022874982,0.006098426,0.9229216],"study_design_scores_gemma":[0.00018066049,0.000092700175,0.000108335335,0.00001765719,0.000025988149,0.00001735241,0.000016445869,0.9287847,0.023276621,0.000037578,0.047231443,0.00021049078],"about_ca_topic_score_codex":0.000013382231,"about_ca_topic_score_gemma":0.000045698747,"teacher_disagreement_score":0.9496257,"about_ca_system_score_codex":0.000040795214,"about_ca_system_score_gemma":0.00003843066,"threshold_uncertainty_score":0.7547522},"labels":[],"label_agreement":null},{"id":"W3173856251","doi":"10.1109/tkde.2021.3090664","title":"Hierarchical Multi-View Graph Pooling with Structure Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":78,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Pooling; Theoretical computer science; Graph; Upsampling; Artificial intelligence","score_opus":0.019042807564391837,"score_gpt":0.25704086656540814,"score_spread":0.2379980590010163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173856251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004413978,0.0016859199,0.99318004,0.000056160112,0.00032902218,0.00006331563,0.000021412467,0.00023520565,0.000014975863],"genre_scores_gemma":[0.84243816,0.0005158379,0.15683888,0.00003615573,0.000053130138,0.000005902796,0.000018786199,0.0000240918,0.00006908045],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989044,0.00003303893,0.00014315064,0.0005460316,0.00011133073,0.00026203363],"domain_scores_gemma":[0.9989986,0.0001429391,0.000021646827,0.00066046236,0.000047855876,0.00012854135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00006299529,0.00018441628,0.0001786393,0.0001191377,0.00018835856,0.00009779711,0.00041882048,0.00006308717,0.0000060905963],"category_scores_gemma":[0.000007490387,0.00016472119,0.00003089637,0.0006317936,0.000025725369,0.00059296185,0.00002067054,0.00063662126,0.000003522664],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012166338,0.00010800781,0.000045479475,0.00013750928,0.00010101787,0.00012893419,0.0005057104,0.7960659,0.005525045,0.0010568778,0.000025372186,0.19628796],"study_design_scores_gemma":[0.0005480915,0.00006780569,0.00023310403,0.00023411436,0.000028871747,0.00021987167,0.000014879883,0.9883364,0.006607865,0.0000669059,0.003286783,0.00035531961],"about_ca_topic_score_codex":0.000001359171,"about_ca_topic_score_gemma":0.000036126832,"teacher_disagreement_score":0.83802414,"about_ca_system_score_codex":0.000011888044,"about_ca_system_score_gemma":0.000032498694,"threshold_uncertainty_score":0.6717135},"labels":[],"label_agreement":null},{"id":"W3185277158","doi":"10.1109/tkde.2021.3100353","title":"On the Benefits of Two Dimensional Metric Learning","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Western University; Université Laval; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Boosting (machine learning); Computer science; Metric (unit); Dimension (graph theory); Benchmark (surveying); Generalization; Intrinsic dimension; Algorithm; Rank (graph theory); Data structure; Artificial intelligence; Feature learning; External Data Representation; Learning to rank; Machine learning; Curse of dimensionality; Mathematics; Ranking (information retrieval)","score_opus":0.029957211545899712,"score_gpt":0.25831982516662566,"score_spread":0.22836261362072596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185277158","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.058605354,0.000770438,0.9396226,0.00015790133,0.00044415577,0.000049143688,0.00003235325,0.00006734912,0.0002507242],"genre_scores_gemma":[0.9964219,0.000093402276,0.0032772098,0.000039981987,0.000020526295,0.0000059409917,0.000010464177,0.000006626963,0.00012399696],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994109,0.000028502536,0.00011002382,0.00023410755,0.000113046546,0.00010338496],"domain_scores_gemma":[0.999044,0.00043844522,0.000019372137,0.0004046672,0.00005214295,0.000041394505],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014251478,0.00008176027,0.00008862957,0.00011937436,0.00011248831,0.000035695255,0.0002478666,0.000027393759,0.000029697376],"category_scores_gemma":[0.000023474387,0.00006244265,0.000026581913,0.00042423565,0.000008838717,0.00022684009,0.00001511716,0.0001903585,0.000031349835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009667029,0.00028182985,0.0000069252665,0.000058851314,0.000072708,0.000007004269,0.0003689596,0.7748529,0.014981117,0.005802231,0.0009888037,0.20256901],"study_design_scores_gemma":[0.00034567362,0.00006449668,0.000095174975,0.00020478586,0.000019680056,0.000017326947,0.000017342094,0.8500909,0.14755684,0.00009530331,0.0013422893,0.00015017224],"about_ca_topic_score_codex":0.00000352163,"about_ca_topic_score_gemma":0.0000040191007,"teacher_disagreement_score":0.9378165,"about_ca_system_score_codex":0.0000069565017,"about_ca_system_score_gemma":0.000022447139,"threshold_uncertainty_score":0.25463372},"labels":[],"label_agreement":null},{"id":"W3185513611","doi":"10.1109/tkde.2022.3220948","title":"Rethinking Graph Auto-Encoder Models for Attributed Graph Clustering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Randomness; Computer science; Adjacency matrix; Correlation clustering; Feature (linguistics); Graph; Clustering coefficient; Encoder; Data mining; Pattern recognition (psychology); Theoretical computer science; Artificial intelligence; Algorithm; Mathematics; Statistics","score_opus":0.05141376820259933,"score_gpt":0.27064618378567723,"score_spread":0.2192324155830779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185513611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004127463,0.0006584151,0.99638647,0.00009538344,0.001355463,0.00031419616,0.0002332014,0.00051184866,0.00003226931],"genre_scores_gemma":[0.88582605,0.0001517802,0.1134845,0.00009370599,0.0000544348,0.00021746643,0.000054883592,0.00004628066,0.00007092352],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984136,0.000038067432,0.0002618097,0.0007018227,0.00018046677,0.00040422822],"domain_scores_gemma":[0.9985359,0.00026824782,0.000047022924,0.0009876703,0.00004439318,0.00011682222],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035285344,0.00023331102,0.00022319556,0.00035065308,0.00065290486,0.000095009775,0.0010913453,0.00005885577,0.0000046166547],"category_scores_gemma":[0.000004540154,0.00026190034,0.000086190914,0.00083213596,0.000021865411,0.0011765526,0.000079432626,0.00048627233,0.0000012397127],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013596589,0.000052543135,6.1501925e-7,0.00004043485,0.000040124807,0.000005441871,0.00049264333,0.9754489,0.00054756674,0.001219682,0.00019788388,0.021940561],"study_design_scores_gemma":[0.00044719115,0.00009033839,0.000004075422,0.00003327492,0.000023528331,0.000048218582,0.000014628697,0.9925967,0.00043269113,0.00399357,0.0020204075,0.0002953717],"about_ca_topic_score_codex":0.000005519607,"about_ca_topic_score_gemma":0.00001865789,"teacher_disagreement_score":0.8854133,"about_ca_system_score_codex":0.000047728445,"about_ca_system_score_gemma":0.00002582185,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W3190788066","doi":"10.1109/tkde.2021.3052927","title":"Discovering Structural Errors From Business Process Event Logs","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Natural Science Foundation of China; Deutsche Forschungsgemeinschaft","keywords":"Process mining; Computer science; Event (particle physics); Process (computing); Business process; Data mining; Business process discovery; Business process management; Synchronization (alternating current); Complex event processing; Business process modeling; Data science; Work in process; Engineering; Programming language","score_opus":0.021232336016666055,"score_gpt":0.25215761205603626,"score_spread":0.23092527603937021,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3190788066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54950756,0.0005594068,0.44800586,0.00018540553,0.001048004,0.00011664849,0.00022059894,0.00025863652,0.00009787857],"genre_scores_gemma":[0.99889976,0.000025669447,0.00015029876,0.00007996603,0.0003926287,0.000050322094,0.00028305614,0.00004789253,0.00007042344],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868083,0.000005829098,0.0002621841,0.0005541616,0.0002293259,0.00026767133],"domain_scores_gemma":[0.9992918,0.000033488093,0.00007799694,0.00048076996,0.00009262477,0.000023348173],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00014950773,0.0002545419,0.00025033645,0.00034402162,0.0005616712,0.00019801102,0.0005161969,0.000040640196,0.00018761412],"category_scores_gemma":[0.000010720277,0.00025441352,0.00005074991,0.00094480015,0.000022128605,0.0014560475,0.00004974662,0.00031133773,0.000021203421],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039222647,0.00010348293,0.00028443287,0.00031111453,0.00009910779,0.000008007678,0.00017874944,0.9814198,0.00043961778,0.0000636415,0.00009405633,0.01695879],"study_design_scores_gemma":[0.00044752294,0.000005491364,0.0008191133,0.00007814003,0.00021109956,0.0000048084325,0.0003287121,0.993512,0.00012809878,0.00015715102,0.0038807332,0.00042712977],"about_ca_topic_score_codex":0.0005647544,"about_ca_topic_score_gemma":0.00010196518,"teacher_disagreement_score":0.44939217,"about_ca_system_score_codex":0.00003698082,"about_ca_system_score_gemma":0.000031554497,"threshold_uncertainty_score":0.9999908},"labels":[],"label_agreement":null},{"id":"W3212438094","doi":"10.1109/tkde.2021.3126642","title":"Constrained Generative Adversarial Learning for Dimensionality Reduction","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Generative Adversarial Networks and Image Synthesis","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dimensionality reduction; Computer science; Artificial intelligence; Feature vector; Diffusion map; Big data; Pattern recognition (psychology); Data mining; Pairwise comparison; Projection (relational algebra); Curse of dimensionality; Reduction (mathematics); Transformation (genetics); Benchmark (surveying); Feature (linguistics); Machine learning; Nonlinear dimensionality reduction; Algorithm; Mathematics","score_opus":0.029209038685555043,"score_gpt":0.2658531333269815,"score_spread":0.23664409464142647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212438094","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00060335785,0.00028011808,0.9971722,0.00020456291,0.0013847426,0.000115493225,0.000049829876,0.00009159432,0.0000981228],"genre_scores_gemma":[0.8817244,0.00008770729,0.11749576,0.000018807497,0.000294209,0.000022526234,0.00005335759,0.000012345326,0.0002908883],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990528,0.000056791705,0.00015762285,0.00048004312,0.00007657201,0.00017615521],"domain_scores_gemma":[0.9991987,0.00018777912,0.000027246371,0.00038611176,0.00012170289,0.00007846877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020737287,0.00013855581,0.00015731978,0.000058632184,0.00029329842,0.00009648638,0.0001905987,0.00005682741,0.000012972701],"category_scores_gemma":[0.000030587784,0.00014235012,0.000049058923,0.00019557538,0.000025594443,0.00053726917,0.00001363803,0.00015749746,0.0000049755913],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041901345,0.00022758792,0.0000015456618,0.00006292642,0.00024738326,0.00001033301,0.0006987851,0.72383195,0.11503338,0.0038143324,0.0011488437,0.15488105],"study_design_scores_gemma":[0.00045748765,0.000049757495,0.000010455402,0.000026313735,0.000030405186,0.000022652477,0.000045026885,0.9134038,0.07856859,0.000055992885,0.007160215,0.00016929679],"about_ca_topic_score_codex":0.0000041346507,"about_ca_topic_score_gemma":0.0000069105054,"teacher_disagreement_score":0.88112104,"about_ca_system_score_codex":0.000025102347,"about_ca_system_score_gemma":0.00008530394,"threshold_uncertainty_score":0.58048695},"labels":[],"label_agreement":null},{"id":"W4210647131","doi":"10.1109/tkde.2022.3144294","title":"Low-Rank Linear Embedding for Robust Clustering","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Guangdong Province; National Natural Science Foundation of China; Natural Science Foundation of Shenzhen City","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Embedding; Robustness (evolution); Correlation clustering; Curse of dimensionality; Artificial intelligence; Pattern recognition (psychology); Algorithm","score_opus":0.03821421735241483,"score_gpt":0.27930823292496615,"score_spread":0.24109401557255133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210647131","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001852922,0.00012846528,0.99623084,0.00006975468,0.0011206443,0.00016787127,0.00017278217,0.00020218232,0.000054510183],"genre_scores_gemma":[0.8267753,0.00011129671,0.1719919,0.00009980482,0.00018267693,0.00029462215,0.0000934653,0.000046269182,0.00040465055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991416,0.000016258826,0.00015252344,0.00038439923,0.00009920085,0.00020606825],"domain_scores_gemma":[0.999265,0.00012678442,0.000022051476,0.00048811774,0.000024248466,0.000073795214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020058117,0.0001224573,0.00012096105,0.00016579704,0.00039086625,0.000064762484,0.00051139924,0.000031462743,0.00002688305],"category_scores_gemma":[0.0000050068757,0.00013335221,0.000038759816,0.00021284814,0.000006625678,0.0005273249,0.000040564748,0.0001990688,0.000011945054],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018821573,0.0001471689,4.6030124e-7,0.00012933342,0.00002736948,0.0000036867805,0.0005372553,0.90783364,0.0046953973,0.00004427224,0.0010558595,0.08550673],"study_design_scores_gemma":[0.00036774043,0.00007624173,0.000001686911,0.000047876896,0.000011011987,0.000016318218,0.000046495657,0.9828688,0.0056755138,0.0000073556157,0.010716634,0.00016434034],"about_ca_topic_score_codex":0.0000033474446,"about_ca_topic_score_gemma":0.0000051797397,"teacher_disagreement_score":0.8249224,"about_ca_system_score_codex":0.000030470328,"about_ca_system_score_gemma":0.000022978229,"threshold_uncertainty_score":0.5437945},"labels":[],"label_agreement":null},{"id":"W4312251623","doi":"10.1109/tkde.2022.3231929","title":"Multi-View Fuzzy Classification With Subspace Clustering and Information Granules","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Fuzzy Logic and Control Systems","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation for Distinguished Young Scholars of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Interpretability; Cluster analysis; Subspace topology; Data mining; Fuzzy logic; Artificial intelligence; Machine learning; Fuzzy clustering","score_opus":0.027010390069907686,"score_gpt":0.234104556318824,"score_spread":0.2070941662489163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312251623","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015220711,0.00078755594,0.9966636,0.00013544218,0.0002739479,0.00017645393,0.000045370813,0.00014669195,0.00024891912],"genre_scores_gemma":[0.98987156,0.00018649531,0.0097684935,0.000029834564,0.000018853643,0.00006703848,0.000015504,0.0000070439814,0.00003515501],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99933136,0.000028949953,0.00014997582,0.00023957794,0.00011238086,0.00013777806],"domain_scores_gemma":[0.9993734,0.00005260518,0.000036423215,0.00044897597,0.00002449389,0.000064120846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020607558,0.00011640662,0.0001188718,0.00013487774,0.0002689505,0.000119876706,0.00033357658,0.00002453636,0.0000012757391],"category_scores_gemma":[0.0000021915644,0.00010556287,0.000012907043,0.00023647108,0.000013572546,0.0014411432,0.00002324167,0.00016056722,0.000005900204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000106525644,0.00027822235,0.00011311803,0.00082002516,0.0001856553,0.000013102439,0.005916084,0.20048568,0.0029012782,0.01656665,0.00028134292,0.7723323],"study_design_scores_gemma":[0.00061681174,0.00008726033,0.000631243,0.00003379447,0.0000152342855,0.000058352834,0.00016419835,0.98756075,0.000042099393,0.000009989419,0.010607293,0.0001729575],"about_ca_topic_score_codex":0.000018766199,"about_ca_topic_score_gemma":0.0000348643,"teacher_disagreement_score":0.9883495,"about_ca_system_score_codex":0.00003169065,"about_ca_system_score_gemma":0.0000223368,"threshold_uncertainty_score":0.43047288},"labels":[],"label_agreement":null},{"id":"W4312529005","doi":"10.1109/tkde.2022.3221316","title":"DMGAN: Dynamic Multi-Hop Graph Attention Network for Traffic Forecasting","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"National Natural Science Foundation of China","keywords":"Computer science; Leverage (statistics); Data mining; Graph; Network topology; Intelligent transportation system; Theoretical computer science; Artificial intelligence; Computer network","score_opus":0.027799234583415194,"score_gpt":0.2480279719790504,"score_spread":0.22022873739563523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312529005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007822919,0.000626237,0.9858525,0.000015963784,0.001521715,0.00042534564,0.00039789287,0.0032793847,0.000058050227],"genre_scores_gemma":[0.9850779,0.00024781405,0.013892664,0.000011389629,0.00006476737,0.00034326548,0.00019886161,0.000064989064,0.000098330405],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990851,0.00001277108,0.00022226106,0.00030565323,0.000087170796,0.00028701415],"domain_scores_gemma":[0.99948215,0.00006475565,0.000019367993,0.00034863394,0.000015373,0.00006971938],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023412667,0.00019139974,0.00015782844,0.00023745699,0.00031157443,0.00003640445,0.00024441647,0.000048078655,0.000011292918],"category_scores_gemma":[0.0000023873456,0.00023286311,0.0000664336,0.00030595408,0.000012297122,0.00023312747,0.000010922121,0.00026823088,0.0000027353901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010223071,0.000065016466,9.546151e-7,0.0001391979,0.000078118246,0.0000017359625,0.000083417915,0.9081423,0.0004722016,0.000030413137,0.004875211,0.086101174],"study_design_scores_gemma":[0.0004999231,0.000065174165,0.00003479746,0.000036803583,0.00006540879,0.000012566516,0.00006192854,0.97870576,0.00007137581,0.000003156649,0.02021709,0.00022602441],"about_ca_topic_score_codex":0.000001416163,"about_ca_topic_score_gemma":0.000037645816,"teacher_disagreement_score":0.977255,"about_ca_system_score_codex":0.00007048021,"about_ca_system_score_gemma":0.0000067670608,"threshold_uncertainty_score":0.9495882},"labels":[],"label_agreement":null},{"id":"W4319459101","doi":"10.1109/tkde.2023.3243169","title":"Towards Lightweight and Automated Representation Learning System for Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Scalability; Embedding; Singular value decomposition; Parallel computing; Theoretical computer science; Algorithm; Artificial intelligence","score_opus":0.027618364107412027,"score_gpt":0.28861185003460915,"score_spread":0.2609934859271971,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319459101","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021405183,0.0003400122,0.9942969,0.000048238668,0.0008036941,0.00019290218,0.000016359112,0.002128829,0.00003255999],"genre_scores_gemma":[0.9866048,0.00030886155,0.012782275,0.0000059631625,0.00009101972,0.000057435525,0.000038638125,0.000023751792,0.00008724131],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906546,0.000021555039,0.00016329496,0.0004451717,0.00007008792,0.00023441223],"domain_scores_gemma":[0.999199,0.0002343895,0.000029253366,0.00041772384,0.00003346021,0.00008620719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016650427,0.00013651805,0.00014591376,0.00018855036,0.00021106824,0.00010092585,0.00028412454,0.00006696143,3.516908e-7],"category_scores_gemma":[0.0000076877905,0.00013507616,0.000025490106,0.00065586437,0.0000130543785,0.00060215365,0.000019146146,0.00017167113,0.000004980161],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010833907,0.00001510825,0.0000117901045,0.00014499878,0.000043436823,0.00000811538,0.0002534196,0.8830054,0.00062696356,0.00093325553,0.0004859924,0.1144607],"study_design_scores_gemma":[0.00025925852,0.00004300056,0.00015542308,0.00008372428,0.000015096191,0.000016956197,0.000019970934,0.9966074,0.0012121607,0.000012796538,0.0014307171,0.00014347713],"about_ca_topic_score_codex":0.0000027522744,"about_ca_topic_score_gemma":0.000003105867,"teacher_disagreement_score":0.9844643,"about_ca_system_score_codex":0.00001825504,"about_ca_system_score_gemma":0.000009366942,"threshold_uncertainty_score":0.5508246},"labels":[],"label_agreement":null},{"id":"W4319863485","doi":"10.1109/tkde.2023.3240431","title":"Cost-Sensitive Learning for Medical Insurance Fraud Detection With Temporal Information","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Imbalanced Data Classification Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Data mining","score_opus":0.027099778289374654,"score_gpt":0.27910290259692533,"score_spread":0.2520031243075507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319863485","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017127445,0.000011523273,0.9965991,0.00009370383,0.00023640286,0.00027667242,0.00010539868,0.0009292041,0.0000352938],"genre_scores_gemma":[0.98364985,0.00008567925,0.015859347,0.000026837528,0.00003319685,0.00014216613,0.00015985468,0.000011579977,0.000031473995],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992069,0.000018162009,0.00017765528,0.00025547258,0.00016494846,0.000176889],"domain_scores_gemma":[0.9991713,0.00018900227,0.000042776483,0.0004281383,0.000087595035,0.0000811972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003465258,0.000116252144,0.00010960978,0.0002636708,0.00017106313,0.00009541166,0.0003496463,0.00007940979,0.0000013397087],"category_scores_gemma":[0.00004432672,0.000109804656,0.000015855825,0.00054851413,0.000022383325,0.0017523174,0.000011768044,0.0002351262,0.000033095814],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004582504,0.00004791928,0.00004752927,0.00015269291,0.000042384123,0.0000039818074,0.0008909871,0.011938898,0.0016532826,0.0003964685,0.0004954418,0.9842846],"study_design_scores_gemma":[0.00036430036,0.00010057779,0.00081290345,0.00007377037,0.0000054254106,0.000018096027,0.000036381807,0.95672643,0.023777807,0.000009169043,0.017915444,0.00015967494],"about_ca_topic_score_codex":0.00000740256,"about_ca_topic_score_gemma":0.000023931398,"teacher_disagreement_score":0.9841249,"about_ca_system_score_codex":0.000031603755,"about_ca_system_score_gemma":0.000048055976,"threshold_uncertainty_score":0.4477704},"labels":[],"label_agreement":null},{"id":"W4322730971","doi":"10.1109/tkde.2023.3238993","title":"Semi-Supervised Entity Alignment With Global Alignment and Local Information Aggregation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment","keywords":"Computer science; Merge (version control); Knowledge graph; Forcing (mathematics); Data mining; Theoretical computer science; Artificial intelligence; Information retrieval; Mathematics","score_opus":0.014223436611622209,"score_gpt":0.23993458954117783,"score_spread":0.22571115292955563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322730971","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0085235275,0.000105221334,0.99046916,0.00008220686,0.00028589845,0.00015555746,0.00006305361,0.00027513533,0.000040253923],"genre_scores_gemma":[0.9895592,0.00030810613,0.009979864,0.000037098715,0.0000216504,0.000025117692,0.0000473446,0.000006792363,0.000014856474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922794,0.000012233459,0.00014932202,0.00026756292,0.00014876908,0.0001941901],"domain_scores_gemma":[0.999379,0.00004404913,0.000024154839,0.0004270239,0.000024973438,0.00010080494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000105502426,0.00013874669,0.000101371246,0.00010062514,0.000117894975,0.00009936243,0.00024553118,0.000043682594,0.0000015150358],"category_scores_gemma":[0.000001681721,0.00012756034,0.000013734815,0.0005269676,0.000025497104,0.0016758065,0.000021919775,0.00009449396,0.000019053132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022586897,0.000056372577,0.00006568229,0.00011596291,0.00006150823,0.000008942146,0.000542258,0.30855766,0.00019945033,0.0013152559,0.0004426922,0.6886116],"study_design_scores_gemma":[0.000425333,0.00007447013,0.0003909968,0.00006982615,0.00001443581,0.000019313104,0.00003442697,0.9951574,0.0013983955,0.000066988934,0.0021845608,0.0001638231],"about_ca_topic_score_codex":0.000008179705,"about_ca_topic_score_gemma":0.000024613037,"teacher_disagreement_score":0.98103565,"about_ca_system_score_codex":0.00005022096,"about_ca_system_score_gemma":0.000015304784,"threshold_uncertainty_score":0.520176},"labels":[],"label_agreement":null},{"id":"W4364321947","doi":"10.1109/tkde.2023.3265840","title":"Summarizing Provenance of Aggregate Query Results in Relational Databases","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Provenance; Relevance (law); Information retrieval; Aggregate (composite); Tuple; Database; Relational database; Data mining","score_opus":0.1898363623171656,"score_gpt":0.37494008237530535,"score_spread":0.18510372005813974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4364321947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.088084504,0.00043458075,0.9037813,0.00030982136,0.0023829262,0.00028669363,0.003201352,0.00021698038,0.0013018752],"genre_scores_gemma":[0.9954752,0.00010730925,0.0028400796,0.0000062883832,0.00003636917,0.0000073436104,0.0001964895,0.000009685254,0.0013212479],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99823177,0.00004000316,0.0005269842,0.0006411324,0.0003722214,0.00018787844],"domain_scores_gemma":[0.9972905,0.0013022862,0.000078113015,0.0012201705,0.000055185956,0.000053748245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029720385,0.000102555176,0.00016550736,0.0007302236,0.00008519148,0.00006449085,0.0005324023,0.00002595639,0.00001010859],"category_scores_gemma":[0.0005047426,0.000090839894,0.00002633513,0.0016694993,0.00003578534,0.0005894852,0.00004976313,0.00013808883,0.000092067836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015524038,0.0003311239,0.00062259304,0.00015746347,0.000055881224,0.000038643993,0.0013452213,0.43338042,0.0021585592,0.0023696409,0.032897208,0.526488],"study_design_scores_gemma":[0.0005569366,0.000023704482,0.0052353083,0.00029130184,0.000010476719,0.0000028122968,0.00015094808,0.9329841,0.0013516734,0.00012609793,0.05909461,0.00017204278],"about_ca_topic_score_codex":0.000050839863,"about_ca_topic_score_gemma":0.0001587601,"teacher_disagreement_score":0.9073907,"about_ca_system_score_codex":0.00001649136,"about_ca_system_score_gemma":0.000036897593,"threshold_uncertainty_score":0.37043434},"labels":[],"label_agreement":null},{"id":"W4366200499","doi":"10.1109/tkde.2023.3267854","title":"Hiding From Centrality Measures: A Stackelberg Game Perspective","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; National Science Foundation of Sri Lanka; Multidisciplinary University Research Initiative; Hong Kong Polytechnic University; National Natural Science Foundation of China; Narodowe Centrum Nauki; York University; New York University Abu Dhabi; National Science Foundation","keywords":"Centrality; Betweenness centrality; Computer science; Ranking (information retrieval); Stackelberg competition; Node (physics); Closeness; Social network (sociolinguistics); Theoretical computer science; Katz centrality; Mathematical optimization; Artificial intelligence; Mathematics; Mathematical economics; Social media; Statistics","score_opus":0.04118757028655001,"score_gpt":0.3047716404612869,"score_spread":0.2635840701747369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366200499","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034217063,0.00022019976,0.9634258,0.000047159676,0.00019536278,0.00012220757,0.00072824594,0.00041856407,0.00062535226],"genre_scores_gemma":[0.998729,0.00006721932,0.00066610216,0.0000034380462,0.00021497528,0.000023477502,0.00014211025,0.000025447827,0.00012825086],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905103,0.000026425321,0.00016536166,0.00041096853,0.000100406854,0.00024581453],"domain_scores_gemma":[0.9991181,0.00015175229,0.000024382016,0.0005652418,0.000045940633,0.00009461499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014393995,0.00017070619,0.00019940583,0.00015074822,0.000107547734,0.00006124346,0.00024199777,0.000032870754,0.00012052834],"category_scores_gemma":[0.000002814117,0.00017951518,0.00007068847,0.00044056028,0.000018377912,0.00022443573,0.000012060292,0.00021910419,0.000058505106],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024915056,0.0024228906,0.004954836,0.00024753122,0.007580029,0.000047324225,0.023478901,0.1681431,0.043136954,0.033166353,0.03116957,0.68540335],"study_design_scores_gemma":[0.0009476339,0.00006049977,0.0017465941,0.00025875616,0.0004696134,0.0000012617631,0.0018197822,0.9318205,0.019655693,0.0031256033,0.039072372,0.001021663],"about_ca_topic_score_codex":0.0004741513,"about_ca_topic_score_gemma":0.000079823985,"teacher_disagreement_score":0.96451193,"about_ca_system_score_codex":0.00004922046,"about_ca_system_score_gemma":0.000023199233,"threshold_uncertainty_score":0.73204166},"labels":[],"label_agreement":null},{"id":"W4382568066","doi":"10.1109/tkde.2023.3290792","title":"Individual and Structural Graph Information Bottlenecks for Out-of-Distribution Generalization","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Natural Science Foundation of China","keywords":"Spurious relationship; Computer science; Graph; Leverage (statistics); Artificial intelligence; Bottleneck; Theoretical computer science; Algorithm; Machine learning","score_opus":0.028363888784600035,"score_gpt":0.2753856377479403,"score_spread":0.24702174896334025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382568066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011754152,0.000104189254,0.9864663,0.00002916368,0.0008158382,0.00014976329,0.00051641767,0.00016144762,0.0000027256242],"genre_scores_gemma":[0.9851554,0.00022387916,0.013794596,0.00001259233,0.00004975868,0.00002551296,0.00072197354,0.000008337825,0.000007947127],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994364,0.00000781693,0.0001672375,0.00017468064,0.000075041105,0.00013882227],"domain_scores_gemma":[0.9995229,0.00008299194,0.000036909496,0.00026617743,0.000044063076,0.000046920555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010839497,0.00009695376,0.00009317548,0.00016191963,0.000105099854,0.00005533692,0.00021983533,0.00005027212,4.1670083e-7],"category_scores_gemma":[0.000007790597,0.000097776465,0.000019328232,0.00038757897,0.000017081722,0.0013432085,0.000013121393,0.00007368066,0.000001416602],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002838289,0.00002822392,0.000062229796,0.00036274863,0.0001010424,9.2975057e-7,0.0017864377,0.5224536,0.0016988303,0.008798814,0.0019746937,0.46270406],"study_design_scores_gemma":[0.00030203757,0.000051960706,0.0006949366,0.0000260945,0.00001603564,0.0000029323683,0.000010867808,0.9944752,0.0022754963,0.00032737319,0.0016950539,0.00012204409],"about_ca_topic_score_codex":0.0000014160107,"about_ca_topic_score_gemma":0.0000056398167,"teacher_disagreement_score":0.97340125,"about_ca_system_score_codex":0.000007695082,"about_ca_system_score_gemma":0.00000937909,"threshold_uncertainty_score":0.39872086},"labels":[],"label_agreement":null},{"id":"W4385732413","doi":"10.1109/tkde.2023.3303916","title":"XMQAs: Constructing Complex-Modified Question-Answering Dataset for Robust Question Understanding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Question answering; Robustness (evolution); Construct (python library); Semantics (computer science); Simple (philosophy); Artificial intelligence; Machine learning; Information retrieval; Natural language processing; Programming language","score_opus":0.15051792830781893,"score_gpt":0.3267831472600723,"score_spread":0.17626521895225336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385732413","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007091529,0.00006031447,0.9963384,0.00012809382,0.0010096423,0.00022670912,0.00093515706,0.00054680376,0.000045688474],"genre_scores_gemma":[0.8298508,0.00007972344,0.1690049,0.000023517692,0.00014864768,0.000048002636,0.0007787073,0.000033633103,0.00003209638],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986609,0.000027515836,0.000275406,0.00058802805,0.00012174721,0.00032636127],"domain_scores_gemma":[0.9986726,0.0003463136,0.000041701816,0.00079815113,0.000033823486,0.00010738912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00057562714,0.00018855318,0.00018694423,0.00030802708,0.00029946683,0.00018855336,0.0005565764,0.00007441099,0.0000030043736],"category_scores_gemma":[0.00002815739,0.00021215972,0.000031208547,0.00040086682,0.000025061929,0.00088724523,0.000030154799,0.00019177933,0.000013257374],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015879421,0.000056566652,0.000011768912,0.00040226005,0.00009192302,0.000009898971,0.0006429272,0.8938682,0.0031940157,0.038281593,0.0012880581,0.0621369],"study_design_scores_gemma":[0.0003746499,0.000026123767,0.000012945632,0.00014273732,0.000021662108,0.000021010559,0.00011059943,0.9969558,0.000531226,0.00026464398,0.0013075646,0.00023100819],"about_ca_topic_score_codex":0.000021548109,"about_ca_topic_score_gemma":0.000043906544,"teacher_disagreement_score":0.8291416,"about_ca_system_score_codex":0.00009733029,"about_ca_system_score_gemma":0.000038352668,"threshold_uncertainty_score":0.86516225},"labels":[],"label_agreement":null},{"id":"W4385863304","doi":"10.1109/tkde.2023.3305809","title":"Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Multiplex; Graph; Embedding; Graph theory; Theoretical computer science; Artificial intelligence; Mathematics; Combinatorics; Bioinformatics","score_opus":0.031247219794920875,"score_gpt":0.2927645023608479,"score_spread":0.261517282565927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385863304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0051504667,0.00017255385,0.9925979,0.00018767982,0.0009806331,0.00020141146,0.00013650216,0.0005670393,0.0000058637734],"genre_scores_gemma":[0.8678608,0.0001494179,0.13152611,0.000037326874,0.000114265546,0.000094156814,0.0000942881,0.000029075401,0.0000945438],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988946,0.000013928234,0.00017876344,0.00050167827,0.000107912376,0.0003031684],"domain_scores_gemma":[0.9986253,0.00056285894,0.000022501363,0.00062826736,0.000038576552,0.00012249134],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013859151,0.00015969579,0.00014080314,0.00032966884,0.0002707403,0.0000601921,0.0004950288,0.000062837775,0.000002463558],"category_scores_gemma":[0.000011348848,0.000161367,0.000048077123,0.00078420335,0.000028224436,0.00059648714,0.000022569535,0.00022037941,0.000020559384],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015759082,0.00008247174,0.0000025783136,0.00005139861,0.000054618442,0.000009703672,0.00017637586,0.8245169,0.004527375,0.006757981,0.0020608976,0.16174394],"study_design_scores_gemma":[0.00040376102,0.00004215704,0.00008579343,0.00005260879,0.000008945056,0.000010017818,0.0000025602506,0.9939617,0.0022119163,0.00083255774,0.0021990323,0.00018897775],"about_ca_topic_score_codex":0.000001967842,"about_ca_topic_score_gemma":0.000008210335,"teacher_disagreement_score":0.86271036,"about_ca_system_score_codex":0.000013635141,"about_ca_system_score_gemma":0.000016071763,"threshold_uncertainty_score":0.6580355},"labels":[],"label_agreement":null},{"id":"W4385863765","doi":"10.1109/tkde.2023.3303617","title":"HSMH: A Hierarchical Sequence Multi-Hop Reasoning Model With Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"State Key Laboratory of Integrated Services Networks; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Interpretability; Reinforcement learning; Reasoning system; Information retrieval; Natural language processing","score_opus":0.046428252697422394,"score_gpt":0.289260324197042,"score_spread":0.2428320714996196,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385863765","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026509438,0.000077135206,0.9961597,0.00005938718,0.00015816497,0.00012298147,0.0000091244565,0.000711831,0.000050782503],"genre_scores_gemma":[0.8903908,0.00023602517,0.10879938,0.000022167222,0.000028193735,0.000035482848,0.00001934995,0.000027364302,0.00044121256],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875987,0.00001807369,0.00016598926,0.00053864083,0.00015230665,0.00036513704],"domain_scores_gemma":[0.9989909,0.0001328846,0.000027607117,0.00067074527,0.000032381093,0.00014551793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016474261,0.00019279686,0.00015164936,0.0002221965,0.00023342682,0.00008169112,0.0005674577,0.000054473734,0.0000013915911],"category_scores_gemma":[0.000009866114,0.00017640101,0.000025924624,0.0007810598,0.000032700646,0.00082843076,0.000033138396,0.0005071625,0.000021258018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007823683,0.000015211363,0.0000032862204,0.000022443544,0.000016849654,0.000016689137,0.00032121307,0.9773555,0.0011475366,0.00048984203,0.000026146581,0.02057748],"study_design_scores_gemma":[0.00032825035,0.00007312102,0.000015850192,0.00012928223,0.0000096171,0.00002388292,0.000011483033,0.997887,0.00083683815,0.000017240201,0.00044815388,0.0002192868],"about_ca_topic_score_codex":0.0000036080344,"about_ca_topic_score_gemma":0.000011210219,"teacher_disagreement_score":0.8877399,"about_ca_system_score_codex":0.000029205878,"about_ca_system_score_gemma":0.00003558516,"threshold_uncertainty_score":0.71934247},"labels":[],"label_agreement":null},{"id":"W4387682100","doi":"10.1109/tkde.2023.3324932","title":"A Robust Database Watermarking Scheme That Preserves Statistical Characteristics","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Steganography and Watermarking Techniques","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China","keywords":"Computer science; Digital watermarking; Scheme (mathematics); Robustness (evolution); Data mining; Database; Artificial intelligence; Image (mathematics); Mathematics","score_opus":0.0642338633944093,"score_gpt":0.2844346963423049,"score_spread":0.2202008329478956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387682100","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004883551,0.000078044206,0.9928561,0.000047050307,0.00044009223,0.00011704806,0.0005143801,0.001023816,0.000039911793],"genre_scores_gemma":[0.88172036,0.00053765124,0.11724848,0.000019244384,0.000067752866,0.000043673437,0.00024536785,0.000029558347,0.00008789312],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988195,0.000020619531,0.00018555176,0.0005053506,0.00013569024,0.00033334328],"domain_scores_gemma":[0.99861497,0.00019923196,0.000027451255,0.0010132416,0.000024805982,0.00012027502],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026800492,0.00019303485,0.00017414222,0.00029035143,0.00018964575,0.00015868052,0.0008101093,0.000060465885,0.0000050065387],"category_scores_gemma":[0.000010574309,0.00018274467,0.000028514685,0.00040424737,0.000034972647,0.0010884848,0.00006720044,0.00025790214,0.000021211754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021209144,0.0012787794,0.001502962,0.0035045687,0.00076384476,0.0013660516,0.0055267205,0.012827514,0.05723582,0.018602189,0.012282657,0.8848968],"study_design_scores_gemma":[0.00022969721,0.000047817786,0.0009303421,0.00020771095,0.000015442714,0.000034404748,0.000011953767,0.9751459,0.013910088,0.00011781158,0.008977905,0.00037094732],"about_ca_topic_score_codex":0.000004608944,"about_ca_topic_score_gemma":0.00000366021,"teacher_disagreement_score":0.96231836,"about_ca_system_score_codex":0.000013292499,"about_ca_system_score_gemma":0.000016519696,"threshold_uncertainty_score":0.7452111},"labels":[],"label_agreement":null},{"id":"W4389040608","doi":"10.1109/tkde.2023.3336630","title":"Preventing Inferences Through Data Dependencies on Sensitive Data","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Defense Advanced Research Projects Agency; National Science Foundation","keywords":"Computer science; Data modeling; Data mining; Database","score_opus":0.11338065600082713,"score_gpt":0.32908617227716463,"score_spread":0.2157055162763375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389040608","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024813022,0.0002257599,0.99045515,0.001012916,0.0009391518,0.00016588012,0.0028398829,0.0016536048,0.00022635769],"genre_scores_gemma":[0.8189273,0.0017204777,0.177295,0.000049849757,0.000111721674,0.00001967755,0.0017145079,0.000044171615,0.000117320495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997699,0.000044702985,0.00026359918,0.0013260749,0.00025723779,0.00040934575],"domain_scores_gemma":[0.9786757,0.00069337554,0.00005071468,0.020478947,0.00003717717,0.00006409064],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00074491877,0.00024852483,0.00022098613,0.00026129308,0.00024661436,0.00025771925,0.029730452,0.000114620685,0.000005372161],"category_scores_gemma":[0.0014743312,0.0002427658,0.000017027822,0.0009309341,0.000059111913,0.0039127595,0.013209399,0.0004635265,0.00014612239],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003265813,0.0005736048,0.000056339628,0.0006414882,0.0006873877,0.00024491432,0.0016448329,0.010051306,0.0039037592,0.0019853646,0.27280483,0.7073735],"study_design_scores_gemma":[0.00016963598,0.000041277013,0.0001014436,0.00020414121,0.000026682485,0.000018809267,0.00008273133,0.98722214,0.0037797347,0.00093425513,0.0071257097,0.00029341993],"about_ca_topic_score_codex":0.00005316226,"about_ca_topic_score_gemma":0.00011361735,"teacher_disagreement_score":0.9771708,"about_ca_system_score_codex":0.000026528282,"about_ca_system_score_gemma":0.0000720967,"threshold_uncertainty_score":0.9947716},"labels":[],"label_agreement":null},{"id":"W4390120254","doi":"10.1109/tkde.2023.3344662","title":"ODIN: Object Density Aware Index for C$k$k NN Queries Over Moving Objects on Road Networks","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; York University","funders":"National Natural Science Foundation of China","keywords":"Notation; Object (grammar); Computer science; Index (typography); Identification (biology); Theoretical computer science; Algorithm; Data mining; Artificial intelligence; Information retrieval; Mathematics; Programming language; Arithmetic","score_opus":0.026107012340016018,"score_gpt":0.2666511080454351,"score_spread":0.2405440957054191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390120254","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029010612,0.00009834963,0.9944217,0.00004184894,0.0014931187,0.00023738174,0.00013956531,0.00056551065,0.00010147314],"genre_scores_gemma":[0.99633527,0.00023096625,0.0025305126,0.000052149484,0.0002049049,0.000051698862,0.00012238449,0.000029422008,0.00044268474],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987468,0.000015688585,0.00017069714,0.00057757995,0.00013305631,0.0003561466],"domain_scores_gemma":[0.99875283,0.0001845537,0.000028132768,0.0009105349,0.000030749186,0.00009318731],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028098084,0.00021396953,0.00018549208,0.00029139846,0.00026920284,0.00025584883,0.00069635955,0.00007261045,0.000004249906],"category_scores_gemma":[0.000011992978,0.00021625769,0.000050869912,0.0005918192,0.000017697224,0.0011186873,0.00005427465,0.0002044318,0.000029488174],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008113032,0.0002600525,0.00009420323,0.00045268124,0.0003029473,0.00005349104,0.0009160552,0.31688714,0.00026962959,0.0017860137,0.012816125,0.66608053],"study_design_scores_gemma":[0.00036034812,0.00008137461,0.0013021075,0.00008757894,0.000019269877,0.000002481183,0.000025875283,0.9924268,0.0004512751,0.000022713028,0.004962809,0.0002573366],"about_ca_topic_score_codex":0.000023728055,"about_ca_topic_score_gemma":0.00007076229,"teacher_disagreement_score":0.9934342,"about_ca_system_score_codex":0.00003155604,"about_ca_system_score_gemma":0.00002306852,"threshold_uncertainty_score":0.88187325},"labels":[],"label_agreement":null},{"id":"W4390480779","doi":"10.1109/tkde.2023.3346377","title":"A Distributed Solution for Efficient K Shortest Paths Computation Over Dynamic Road Networks","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University; University of Toronto; York University","funders":"National Natural Science Foundation of China","keywords":"Shortest path problem; Graph; Computer science; Centrality; Computation; Notation; Algorithm; Scalability; Theoretical computer science; Combinatorics; Mathematics; Database","score_opus":0.016598783254482878,"score_gpt":0.26794138589068084,"score_spread":0.25134260263619795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390480779","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00044462868,0.00086049014,0.9958399,0.00006145356,0.0016050139,0.00023579634,0.00055067625,0.00039038374,0.000011690789],"genre_scores_gemma":[0.98630214,0.000089566645,0.01276172,0.000008562737,0.0000715831,0.00004056896,0.0006566238,0.000016974944,0.000052244704],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990764,0.000009050448,0.00015940463,0.0004574551,0.00008480495,0.00021285178],"domain_scores_gemma":[0.99939156,0.00012113163,0.000013696633,0.00039071555,0.000022340033,0.000060557995],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019724676,0.00014231431,0.00010508949,0.00015708109,0.00012303295,0.0003181822,0.00035322932,0.000044434277,0.0000018559504],"category_scores_gemma":[0.0000035060002,0.00014134488,0.000037912487,0.00037657702,0.000011824766,0.00061682676,0.000020578998,0.00012458386,0.0000096450185],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000437103,0.00009084258,5.099738e-7,0.00010322655,0.000055205925,0.000006975913,0.00007012914,0.43976057,0.00012242542,0.00057974533,0.00088191195,0.5583241],"study_design_scores_gemma":[0.00017941701,0.000046388686,0.00012099933,0.000094829666,0.000036780228,0.000006125729,0.0000031780128,0.99545056,0.000028288645,0.000012354037,0.003858145,0.00016290997],"about_ca_topic_score_codex":0.000005568426,"about_ca_topic_score_gemma":0.000009564855,"teacher_disagreement_score":0.98585755,"about_ca_system_score_codex":0.000047516834,"about_ca_system_score_gemma":0.00001751166,"threshold_uncertainty_score":0.57638764},"labels":[],"label_agreement":null},{"id":"W4393144966","doi":"10.1109/tkde.2024.3381192","title":"DIBA: A Re-Configurable Stream Processor","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Alexander von Humboldt-Stiftung","keywords":"Computer science; Stream processing; Computer architecture; Parallel computing","score_opus":0.02496765267250139,"score_gpt":0.2756281570028197,"score_spread":0.2506605043303183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393144966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00028823834,0.0035254802,0.99374056,0.000075660726,0.00090900727,0.00010733974,0.00026579705,0.00050740474,0.000580484],"genre_scores_gemma":[0.95841616,0.0005501642,0.03908487,0.000025441595,0.00019185632,0.00007757002,0.000051229395,0.000039959847,0.0015627282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905896,0.0000086959935,0.00015752729,0.00048530844,0.00008773773,0.0002017965],"domain_scores_gemma":[0.9990398,0.00010052602,0.000011256914,0.00073612516,0.000023668512,0.00008861115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012770842,0.00015318433,0.00013310775,0.00014100558,0.00010379858,0.00013428433,0.00033630253,0.000041796913,0.000013984743],"category_scores_gemma":[0.0000051577686,0.00013522316,0.00002414863,0.00034903554,0.000015683547,0.0014679296,0.000011951771,0.00018185322,0.00007010785],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024852972,0.000369064,0.00000411077,0.0035007286,0.0003479934,0.00019779283,0.0039530946,0.027172701,0.011987428,0.07148411,0.009716425,0.8712417],"study_design_scores_gemma":[0.00014194004,0.000053928467,0.0000064739356,0.00040358998,0.000018442171,0.000044375607,0.000036193946,0.6813453,0.009899924,0.00003476982,0.30774847,0.00026658952],"about_ca_topic_score_codex":0.000015382631,"about_ca_topic_score_gemma":0.000035506488,"teacher_disagreement_score":0.9581279,"about_ca_system_score_codex":0.000020325011,"about_ca_system_score_gemma":0.000050864957,"threshold_uncertainty_score":0.5514241},"labels":[],"label_agreement":null},{"id":"W4394862804","doi":"10.1109/tkde.2024.3388526","title":"Feature Selection With Discernibility and Independence Criteria","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Computer science; Feature selection; Selection (genetic algorithm); Independence (probability theory); Artificial intelligence; Feature (linguistics); Data mining; Pattern recognition (psychology); Mathematics; Statistics","score_opus":0.01885862692112788,"score_gpt":0.2740728741851766,"score_spread":0.25521424726404873,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394862804","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012152373,0.0006183096,0.9862115,0.0002232416,0.00035286148,0.00007737901,0.000044551238,0.00025362952,0.00006619687],"genre_scores_gemma":[0.99053997,0.00016499133,0.009024257,0.000012099927,0.00004245159,0.000013101501,0.000008458558,0.000009424627,0.00018523676],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930674,0.000013141337,0.0000601854,0.0004214883,0.000081902865,0.0001165255],"domain_scores_gemma":[0.99956447,0.0000577741,0.0000064601495,0.0002809505,0.000022686088,0.000067661254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011647501,0.00010935529,0.00008085932,0.00010634728,0.000094355826,0.0002336154,0.00016388489,0.000061206,0.000008818361],"category_scores_gemma":[0.0000022119048,0.00008615091,0.000010502303,0.00023337116,0.000014947764,0.0010191909,0.000009088306,0.00023975472,0.000012586375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078022844,0.00027263522,0.000091081885,0.0014490539,0.00018297174,0.00005323061,0.0027278801,0.0035118894,0.05168477,0.00083165127,0.007024709,0.93209213],"study_design_scores_gemma":[0.00017086341,0.00010051481,0.0003523731,0.00035457208,0.000025266367,0.000118969896,0.000019744755,0.97441965,0.01568709,0.00004388062,0.008492736,0.00021435918],"about_ca_topic_score_codex":0.000007203945,"about_ca_topic_score_gemma":0.000034614593,"teacher_disagreement_score":0.9783876,"about_ca_system_score_codex":0.000013867135,"about_ca_system_score_gemma":0.000024750338,"threshold_uncertainty_score":0.3513132},"labels":[],"label_agreement":null},{"id":"W4396886508","doi":"10.1109/tkde.2024.3400824","title":"Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Visualization; Data visualization; Natural language; Information retrieval; Information visualization; Programming language; Database; World Wide Web; Natural language processing; Data mining","score_opus":0.042755576037026975,"score_gpt":0.33400078138952005,"score_spread":0.2912452053524931,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396886508","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017259626,0.013373461,0.98183614,0.000024669675,0.0010359202,0.00013599491,0.0016430794,0.00021858851,0.0000061588626],"genre_scores_gemma":[0.9652716,0.00037436147,0.03342944,0.000012287415,0.00010311384,0.00002073099,0.00060464384,0.000024680088,0.00015917112],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912184,0.000020209885,0.00014596648,0.0005090469,0.000060589406,0.0001423335],"domain_scores_gemma":[0.9988398,0.0002756728,0.000013005982,0.00079561694,0.000024711855,0.000051180454],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034625924,0.0001293568,0.00012760659,0.0001168375,0.000103669576,0.00017528629,0.00039413586,0.00003135126,0.000001904792],"category_scores_gemma":[0.000022883616,0.000116577874,0.000010151922,0.00022196316,0.000017261133,0.0017367491,0.000051027757,0.0001067773,0.0000037685375],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008160728,0.00022483259,0.00004619582,0.005229327,0.00065714645,0.000080661914,0.009515133,0.006462435,0.02182146,0.0294847,0.007813312,0.9185832],"study_design_scores_gemma":[0.00012213235,0.000023364744,0.000023695493,0.000212411,0.000013544681,0.000019279358,0.00005498781,0.9632909,0.002123882,0.0000030114381,0.03395004,0.00016274836],"about_ca_topic_score_codex":0.000043323675,"about_ca_topic_score_gemma":0.00027644588,"teacher_disagreement_score":0.9635456,"about_ca_system_score_codex":0.00001101872,"about_ca_system_score_gemma":0.000025800216,"threshold_uncertainty_score":0.4753908},"labels":[],"label_agreement":null},{"id":"W4400033029","doi":"10.1109/tkde.2024.3419449","title":"Hessian Aware Low-Rank Perturbation for Order-Robust Continual Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Geophysical Methods and Applications","field":"Engineering","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval; McGill University; Vector Institute; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hessian matrix; Perturbation (astronomy); Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Applied mathematics","score_opus":0.025899535669202722,"score_gpt":0.28029992811947274,"score_spread":0.25440039245027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400033029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0032467623,0.00077509216,0.993885,0.000058646463,0.0006438015,0.00021485158,0.00024059296,0.00069344544,0.00024180795],"genre_scores_gemma":[0.9854295,0.00017997938,0.013164698,0.000005667662,0.00026127318,0.00016802203,0.000115497074,0.00007137063,0.00060394336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927044,0.000009455857,0.0001625904,0.000299144,0.00005545838,0.00020289326],"domain_scores_gemma":[0.99933016,0.00028558786,0.0000072564694,0.00026132775,0.000033632856,0.00008200423],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011624138,0.00017292394,0.00015270969,0.00011299269,0.000121499375,0.000101201695,0.00013614385,0.000077645695,0.000018342302],"category_scores_gemma":[0.000010516234,0.0001734385,0.000044702978,0.00028018767,0.000014022001,0.00025974496,0.0000028997788,0.00028713097,0.000034649733],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010353378,0.000094726674,0.000001178705,0.0015610938,0.0001917303,0.0000026484731,0.0006211213,0.5898263,0.018821627,0.0016576187,0.0011569965,0.38605464],"study_design_scores_gemma":[0.00016012973,0.000030480003,0.00002494612,0.00016891811,0.00005842159,0.0000035374976,0.000041295043,0.9577826,0.0026685472,0.000046397483,0.038806163,0.00020850847],"about_ca_topic_score_codex":0.0000027690705,"about_ca_topic_score_gemma":0.0000062350164,"teacher_disagreement_score":0.9821828,"about_ca_system_score_codex":0.00002509044,"about_ca_system_score_gemma":0.000015165019,"threshold_uncertainty_score":0.7072617},"labels":[],"label_agreement":null},{"id":"W4400033057","doi":"10.1109/tkde.2024.3419215","title":"Ze-HFS: Zentropy-Based Uncertainty Measure for Heterogeneous Feature Selection and Knowledge Discovery","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Computer science; Measure (data warehouse); Feature selection; Selection (genetic algorithm); Feature (linguistics); Knowledge extraction; Data mining; Artificial intelligence","score_opus":0.018792428517041014,"score_gpt":0.2692210126805711,"score_spread":0.2504285841635301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400033057","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00097602874,0.0023049328,0.99490196,0.00019807967,0.00039825996,0.00032318506,0.00019685057,0.0006625709,0.00003813776],"genre_scores_gemma":[0.98630637,0.00013629855,0.012864007,0.00001930343,0.00012206664,0.0001871325,0.00003091596,0.000028867638,0.00030503675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989806,0.000016045911,0.00014353263,0.000586026,0.000070607784,0.00020318493],"domain_scores_gemma":[0.9992468,0.00014339463,0.000017565753,0.0004466204,0.000053212545,0.000092422175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015683149,0.00019433376,0.00014459461,0.00021105206,0.00023530447,0.00034255724,0.00029462064,0.00010713734,0.0000017322722],"category_scores_gemma":[0.000004303283,0.00018277913,0.0000615668,0.00041133558,0.000020328955,0.00058469747,0.000011671264,0.00022117552,0.000006103894],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000086264896,0.00057398644,0.0000073142232,0.0016049924,0.00039542018,0.00000961273,0.00080188416,0.10413976,0.04746437,0.0148332855,0.00623766,0.82384545],"study_design_scores_gemma":[0.00018525937,0.0001155016,0.000007127246,0.00010153555,0.000046239104,0.000036393358,0.000004735117,0.9303893,0.021426426,0.000085672844,0.04738554,0.00021625712],"about_ca_topic_score_codex":0.000007699914,"about_ca_topic_score_gemma":0.00005128375,"teacher_disagreement_score":0.98533034,"about_ca_system_score_codex":0.00006047479,"about_ca_system_score_gemma":0.00007672987,"threshold_uncertainty_score":0.7453517},"labels":[],"label_agreement":null},{"id":"W4400071817","doi":"10.1109/tkde.2024.3419698","title":"Laplacian Convolutional Representation for Traffic Time Series Imputation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Polytechnique Montréal","funders":"Centre interuniversitaire de recherche sur les reseaux d'entreprise, la logistique et le transport","keywords":"Computer science; Time series; Imputation (statistics); Series (stratigraphy); Representation (politics); Data mining; Algorithm; Machine learning; Missing data; Geology","score_opus":0.01660452875484313,"score_gpt":0.26392672422544633,"score_spread":0.2473221954706032,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400071817","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015166431,0.0006643387,0.9909197,0.000052105283,0.0009393769,0.00025496096,0.00040439406,0.0049482854,0.00030018776],"genre_scores_gemma":[0.99406385,0.00037120716,0.004640441,0.000006489375,0.00012857259,0.00011180346,0.00028588533,0.00004189759,0.00034983418],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994064,0.000005567379,0.0001531351,0.0002372265,0.00006230814,0.00013536197],"domain_scores_gemma":[0.999662,0.00007471334,0.0000057008997,0.00019063591,0.000017766992,0.00004922688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000102160026,0.00012997077,0.00009778951,0.00022641156,0.000065876506,0.00008145353,0.000095226176,0.00006114363,0.000014256727],"category_scores_gemma":[0.0000028436525,0.00014371298,0.00003527146,0.00018067195,0.000015397645,0.0005885348,0.0000021583405,0.00011000995,0.000037524387],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002767543,0.000053478514,4.1374787e-7,0.00076039525,0.0002460968,0.0000044140443,0.00043388456,0.63842416,0.004506083,0.0012982816,0.057092067,0.29715303],"study_design_scores_gemma":[0.00014928734,0.000036516125,0.000015289954,0.00007276377,0.000049412138,0.0000104939345,0.000017720675,0.95313793,0.0020639459,0.00001468077,0.044291463,0.00014048493],"about_ca_topic_score_codex":6.853356e-7,"about_ca_topic_score_gemma":0.0000059488752,"teacher_disagreement_score":0.9925472,"about_ca_system_score_codex":0.00004115258,"about_ca_system_score_gemma":0.000011701519,"threshold_uncertainty_score":0.58604455},"labels":[],"label_agreement":null},{"id":"W4400904993","doi":"10.1109/tkde.2024.3432767","title":"One Subgraph for All: Efficient Reasoning on Opening Subgraphs for Inductive Knowledge Graph Completion","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"China Postdoctoral Science Foundation; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Knowledge graph; Subgraph isomorphism problem; Induced subgraph isomorphism problem; Graph; Inductive reasoning; Theoretical computer science; Artificial intelligence; Line graph; Voltage graph","score_opus":0.0577649098250396,"score_gpt":0.3025058440658079,"score_spread":0.2447409342407683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400904993","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0034156085,0.0014526593,0.9914849,0.00011455605,0.0017927347,0.00070314715,0.00035529785,0.0004097283,0.00027137317],"genre_scores_gemma":[0.94590926,0.0001579993,0.05329009,0.000029488601,0.00016555464,0.00026355032,0.00010222663,0.000047360147,0.000034471537],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998283,0.000026731328,0.00027648697,0.00087489054,0.00012767022,0.0004111911],"domain_scores_gemma":[0.9985071,0.00054994534,0.00003173067,0.0006907959,0.00008279839,0.00013762293],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00050586736,0.00027458472,0.00027835649,0.00056519936,0.0003088888,0.00032120085,0.00064172415,0.00010685202,0.0000024222725],"category_scores_gemma":[0.000015094478,0.00027029775,0.00013361062,0.00067149504,0.000034684046,0.00044950357,0.000020166979,0.00027768651,0.000013494107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030104295,0.0020109573,0.00001059556,0.0022622098,0.0012365127,0.000016335993,0.009250427,0.10791248,0.008873831,0.19965975,0.0037715856,0.66469425],"study_design_scores_gemma":[0.0005863272,0.00038006937,0.00009111935,0.00045353026,0.00008611788,0.000009103027,0.000032622473,0.98128533,0.002138373,0.000398446,0.014143846,0.00039513336],"about_ca_topic_score_codex":0.000011917037,"about_ca_topic_score_gemma":0.000033557524,"teacher_disagreement_score":0.9424937,"about_ca_system_score_codex":0.000044701213,"about_ca_system_score_gemma":0.00004574105,"threshold_uncertainty_score":0.9999749},"labels":[],"label_agreement":null},{"id":"W4401943123","doi":"10.1109/tkde.2024.3443928","title":"PLBR: A Semi-Supervised Document Key Information Extraction via Pseudo-Labeling Bias Rectification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Rectification; Key (lock); Artificial intelligence; Information extraction; Information retrieval; Pattern recognition (psychology)","score_opus":0.02764258680815602,"score_gpt":0.2946802442361714,"score_spread":0.2670376574280154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401943123","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014307059,0.0005329027,0.9958149,0.00012147774,0.0006520353,0.00017553312,0.000020132393,0.0011372541,0.000115065646],"genre_scores_gemma":[0.8792195,0.0007122389,0.11972429,0.000023657756,0.00007130396,0.00007351507,0.000064242275,0.000020265972,0.00009099041],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988718,0.000024502333,0.00033649462,0.00041156294,0.00016696414,0.00018868769],"domain_scores_gemma":[0.998861,0.00015143515,0.00003896094,0.0007999416,0.000068312125,0.00008031613],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037443754,0.00018556317,0.00014221438,0.000518357,0.00014380844,0.00037815978,0.00043114144,0.000084730455,0.000010462047],"category_scores_gemma":[0.0000124886965,0.0001869891,0.00004757847,0.0007633236,0.000011489036,0.0051786243,0.000014393299,0.00029007057,0.00009696974],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006916057,0.00006700731,0.0000014287224,0.00022525908,0.00009383534,0.0000037154955,0.0013754164,0.0242292,0.032894284,0.001153876,0.0003465964,0.9396025],"study_design_scores_gemma":[0.00009834542,0.00003315205,0.000009359777,0.00013557402,0.000041759828,0.000026439915,0.000018366005,0.9497723,0.035216752,0.00013639651,0.014302749,0.00020878405],"about_ca_topic_score_codex":0.000019007442,"about_ca_topic_score_gemma":0.000014148469,"teacher_disagreement_score":0.9393937,"about_ca_system_score_codex":0.00012212439,"about_ca_system_score_gemma":0.00003582349,"threshold_uncertainty_score":0.76251936},"labels":[],"label_agreement":null},{"id":"W4403600950","doi":"10.1109/tkde.2024.3484009","title":"Order-2 Probabilistic Information Fusion on Random Permutation Set","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Rough Sets and Fuzzy Logic","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"China Scholarship Council; National Natural Science Foundation of China","keywords":"Computer science; Random permutation; Probabilistic logic; Permutation (music); Set (abstract data type); Fusion; Theoretical computer science; Artificial intelligence; Data mining; Mathematics; Combinatorics","score_opus":0.023837821536252177,"score_gpt":0.26031453317933057,"score_spread":0.23647671164307837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403600950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018508744,0.0002300895,0.99548286,0.00015228646,0.0010570141,0.00018626695,0.000086034706,0.00034303876,0.0006115318],"genre_scores_gemma":[0.99304867,0.00016720504,0.006519801,0.000041912735,0.000061364655,0.00002941945,0.0000858306,0.00000973062,0.000036064343],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99928033,0.000016439964,0.00017556644,0.00026862923,0.00011632339,0.00014270999],"domain_scores_gemma":[0.9992935,0.00015785852,0.000013622436,0.00044039742,0.00003452544,0.000060063147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019448137,0.000132596,0.0001021231,0.00021872521,0.00011363143,0.0002981225,0.00028983754,0.000054351854,0.000009474586],"category_scores_gemma":[0.000013115576,0.000110669986,0.000024214101,0.0003997164,0.0000105952295,0.0013668205,0.000008852032,0.00017776407,0.00014796651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003262091,0.000093414725,6.5331227e-7,0.00043802176,0.000042216652,0.000010002085,0.0028019028,0.1637644,0.00023881707,0.005231251,0.001336324,0.8260104],"study_design_scores_gemma":[0.00031476302,0.000087005945,0.000025623154,0.00011369618,0.000014639436,0.000015512387,0.0000117086465,0.9857902,0.00016054172,0.00014010485,0.0131874615,0.00013876607],"about_ca_topic_score_codex":0.0000069869134,"about_ca_topic_score_gemma":0.000006142811,"teacher_disagreement_score":0.9911978,"about_ca_system_score_codex":0.000033317086,"about_ca_system_score_gemma":0.000039037805,"threshold_uncertainty_score":0.45129913},"labels":[],"label_agreement":null},{"id":"W4404238465","doi":"10.1109/tkde.2024.3496586","title":"Finding Antagonistic Communities in Signed Uncertain Graphs","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Constraint Satisfaction and Optimization","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Computer science; Signed graph; Theoretical computer science; Graph","score_opus":0.03610903175891978,"score_gpt":0.28217160425459886,"score_spread":0.2460625724956791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404238465","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019513617,0.0004901381,0.9961789,0.000080073565,0.00071131875,0.000075024545,0.00004727628,0.00026247252,0.00020341846],"genre_scores_gemma":[0.99217755,0.00026923674,0.0074263955,0.000014367884,0.000013299218,0.0000109509065,0.000022368158,0.000009652536,0.00005620038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994027,0.000025335212,0.00014867347,0.00021633318,0.0000618699,0.00014506206],"domain_scores_gemma":[0.9992944,0.00024961625,0.000008187565,0.00038740074,0.00001222136,0.00004819132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018201255,0.00011000489,0.00009461345,0.0004076826,0.00009852534,0.00020228585,0.0002875841,0.000042149957,0.000025106912],"category_scores_gemma":[0.0000034863046,0.000114577015,0.000020050378,0.00047968558,0.00002197571,0.00062590616,0.000008954918,0.0002087203,0.000015978321],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009995444,0.00013096264,0.00006810437,0.00041827763,0.00008261091,0.000058883576,0.005906985,0.358092,0.0013159454,0.029771639,0.0002786062,0.603866],"study_design_scores_gemma":[0.00012468919,0.000019561954,0.00006837948,0.00015842025,0.000007559719,0.000020372489,0.000071802046,0.9974703,0.00028706805,0.000068856876,0.0015703515,0.00013259923],"about_ca_topic_score_codex":0.0000413872,"about_ca_topic_score_gemma":0.00018909606,"teacher_disagreement_score":0.99022615,"about_ca_system_score_codex":0.00003680332,"about_ca_system_score_gemma":0.000040088504,"threshold_uncertainty_score":0.4672315},"labels":[],"label_agreement":null},{"id":"W4405838316","doi":"10.1109/tkde.2024.3523857","title":"A Survey of Change Point Detection in Dynamic Graphs","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Gene Regulatory Network Analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Point (geometry); Mathematics","score_opus":0.027271724777452266,"score_gpt":0.268731027236579,"score_spread":0.24145930245912672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405838316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60269797,0.009176524,0.387439,0.000008405288,0.00034828606,0.00010703909,0.0001849818,0.00002551324,0.000012260085],"genre_scores_gemma":[0.9988684,0.00087582093,0.00008086284,0.000002229778,0.000021200409,0.00001511483,0.00009328954,0.000016597614,0.000026470336],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994415,0.000024811434,0.00012932147,0.0002637473,0.000037528316,0.000103114384],"domain_scores_gemma":[0.99959844,0.000019015331,0.0000100917405,0.00032027124,0.000019342104,0.00003282151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021598075,0.000093365685,0.000102172955,0.00019395031,0.000016918035,0.000010388619,0.00009407464,0.00007050147,0.0000036054273],"category_scores_gemma":[0.000003952342,0.00009707183,0.000033435917,0.00033019754,0.000013762533,0.000010812487,0.0000051711877,0.00008092994,0.0000024495566],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008084299,0.00022374306,0.00040474557,0.000581591,0.0004888382,0.000008600151,0.00030748587,0.024232915,0.49247965,0.0000089488385,0.000105014034,0.4810776],"study_design_scores_gemma":[0.00030731113,0.00016230953,0.020658758,0.00016009314,0.000094488925,0.000015233544,0.00001954299,0.8721309,0.1046075,0.0000058824317,0.0015360597,0.00030195733],"about_ca_topic_score_codex":0.000076629054,"about_ca_topic_score_gemma":0.0029695516,"teacher_disagreement_score":0.84789795,"about_ca_system_score_codex":0.000011035855,"about_ca_system_score_gemma":0.0000145560025,"threshold_uncertainty_score":0.39584744},"labels":[],"label_agreement":null},{"id":"W4406890913","doi":"10.1109/tkde.2025.3527380","title":"Computing Shapley Values for Dynamic Data","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Data mining","score_opus":0.031760860730233605,"score_gpt":0.31844716841906573,"score_spread":0.28668630768883213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406890913","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00023760526,0.0010798196,0.9959172,0.000080259044,0.0011359099,0.00019758854,0.0010354326,0.00023647667,0.000079692865],"genre_scores_gemma":[0.49735892,0.0002564106,0.5011062,0.00006888559,0.0000842222,0.000030554642,0.0004776042,0.000029223778,0.000587986],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988958,0.00001285252,0.00020973427,0.0006076311,0.0000618982,0.00021204645],"domain_scores_gemma":[0.9977828,0.0002790006,0.000025601968,0.0018204618,0.000037866022,0.00005423428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027688665,0.00015198611,0.0001766125,0.00015563902,0.000222141,0.000070385606,0.0010062548,0.000042115018,0.00000128165],"category_scores_gemma":[0.00001908856,0.00015014442,0.000021711621,0.00026497943,0.000020054104,0.0010756699,0.00008275844,0.00012419153,0.000005408412],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002919292,0.00026637505,0.000010184148,0.0012964377,0.0002887442,0.0000076035744,0.0006970023,0.04013533,0.0035960383,0.03880364,0.005035465,0.90983397],"study_design_scores_gemma":[0.0002511437,0.0000192817,0.000030742052,0.00017157596,0.00001871615,0.0000052445025,0.000022046333,0.9418297,0.00046905802,0.000045894347,0.05698754,0.00014906826],"about_ca_topic_score_codex":0.000010819561,"about_ca_topic_score_gemma":0.0000442491,"teacher_disagreement_score":0.9096849,"about_ca_system_score_codex":0.00002176875,"about_ca_system_score_gemma":0.000049648363,"threshold_uncertainty_score":0.61227113},"labels":[],"label_agreement":null},{"id":"W4408358653","doi":"10.1109/tkde.2025.3550877","title":"Correlating Time Series With Interpretable Convolutional Kernels","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"U.S. Department of Energy","keywords":"Computer science; Series (stratigraphy); Kernel (algebra); Artificial intelligence; Convolutional neural network; Time series; Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.00925635699884033,"score_gpt":0.22123404702606728,"score_spread":0.21197769002722694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408358653","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0011192365,0.00037306955,0.9966145,0.000064414606,0.00021763786,0.000055313463,0.00003137896,0.00014780943,0.0013766282],"genre_scores_gemma":[0.96019214,0.00003336025,0.035959885,0.000025896301,0.000031334363,0.000012149871,0.000016320968,0.000012183173,0.0037167477],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992479,0.00001084055,0.00015867823,0.00033620253,0.00007130081,0.0001750475],"domain_scores_gemma":[0.9993111,0.00009659442,0.000024938761,0.00047366228,0.000043918546,0.000049818456],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012850096,0.00013144239,0.00015525354,0.00014393777,0.00018341141,0.0001286775,0.00038461018,0.000038267965,0.00002726996],"category_scores_gemma":[0.000005692806,0.00011651778,0.000026061449,0.00040885096,0.000028316945,0.0008956365,0.000022383432,0.00015849224,0.00002692688],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015887871,0.00047746644,0.00034504855,0.0005071811,0.0014170714,0.0000358273,0.002358376,0.5248614,0.00877963,0.03165643,0.0026109489,0.42679176],"study_design_scores_gemma":[0.0001721849,0.000048314872,0.00009372883,0.00016735565,0.000036326917,0.0000192777,0.00002027839,0.9932309,0.0012166786,0.000025444833,0.004826204,0.0001433275],"about_ca_topic_score_codex":0.000009527855,"about_ca_topic_score_gemma":0.0000129908585,"teacher_disagreement_score":0.9606546,"about_ca_system_score_codex":0.000023982975,"about_ca_system_score_gemma":0.000046598823,"threshold_uncertainty_score":0.47514573},"labels":[],"label_agreement":null},{"id":"W4413785340","doi":"10.1109/tkde.2025.3603594","title":"Multi-View Clustering via High-Order Bipartite Graph Learning and Tensor Low-Rank Representation","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Natural Science Foundation of China","keywords":"Computer science; Cluster analysis; Bipartite graph; Representation (politics); Graph; Tensor (intrinsic definition); Rank (graph theory); Artificial intelligence; Theoretical computer science; Pattern recognition (psychology); Combinatorics; Mathematics","score_opus":0.021527688451080735,"score_gpt":0.28638668068049006,"score_spread":0.26485899222940934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413785340","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007971419,0.0007915609,0.9901909,0.00010773872,0.00054558075,0.00013642093,0.000012659027,0.00020202938,0.000041672174],"genre_scores_gemma":[0.9369175,0.0019012404,0.060488746,0.00006133416,0.00003724537,0.000051727515,0.000032518048,0.00001917571,0.00049051095],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990685,0.000034400815,0.00019173407,0.0004544896,0.00007184183,0.00017902843],"domain_scores_gemma":[0.99935853,0.00011406769,0.00002606713,0.0003786624,0.00005254455,0.00007010489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001378516,0.00014757516,0.00015350428,0.00027197943,0.0002091866,0.00012781098,0.00021861699,0.000066047556,0.000007945642],"category_scores_gemma":[0.000013034705,0.00014578851,0.000023297973,0.00047658617,0.000019031742,0.00072623166,0.000027636206,0.00021891389,0.000018430037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030849897,0.00028596143,0.000141494,0.0007634902,0.00015725949,0.000012646776,0.0009959947,0.09312504,0.0773546,0.00009511806,0.00033821378,0.8266993],"study_design_scores_gemma":[0.00058014895,0.000026890122,0.00045363017,0.00036027853,0.00002948295,0.000007638447,0.000028967059,0.9847071,0.010950504,0.000017639744,0.0026510651,0.0001866544],"about_ca_topic_score_codex":0.000028501601,"about_ca_topic_score_gemma":0.000033579094,"teacher_disagreement_score":0.92970216,"about_ca_system_score_codex":0.000011385372,"about_ca_system_score_gemma":0.000013975979,"threshold_uncertainty_score":0.5945083},"labels":[],"label_agreement":null},{"id":"W4414116777","doi":"10.1109/tkde.2025.3609302","title":"Flexible Keyword-Aware Top-$k$k Route Search","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Science Foundation of Shandong Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Process (computing); Sequence (biology); Route planning; Semantics (computer science); Point of interest","score_opus":0.028948581485631814,"score_gpt":0.29190815446982205,"score_spread":0.26295957298419026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414116777","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001955702,0.0002994586,0.9958434,0.00022474353,0.00093519967,0.000114782546,0.000098893724,0.00044787972,0.0018400656],"genre_scores_gemma":[0.91044,0.0008920927,0.06764233,0.0002474034,0.00021676409,0.00006329647,0.00016624336,0.000042809534,0.020289019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99902993,0.000013497785,0.00014281466,0.00046739634,0.000102139864,0.00024419275],"domain_scores_gemma":[0.99872655,0.00007075886,0.000009412231,0.0010943898,0.000028226548,0.00007068584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019831726,0.00014198055,0.00012700261,0.00030378983,0.00014835528,0.00024260492,0.0010844113,0.000042267402,0.000012751349],"category_scores_gemma":[0.0000025387349,0.00014308817,0.000027113068,0.0006220347,0.000015368933,0.0010594995,0.000061945975,0.00019351568,0.00006436149],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010277882,0.0002566554,0.000035458976,0.00031082498,0.00017421911,0.000018948096,0.00031746476,0.012527918,0.00028200913,0.011846078,0.00953548,0.96468467],"study_design_scores_gemma":[0.00031783863,0.000027404232,0.00012825124,0.000094286755,0.000021618245,0.0000025344548,0.00001933707,0.9221727,0.0042568115,0.000043254215,0.072721325,0.00019459403],"about_ca_topic_score_codex":0.00001888418,"about_ca_topic_score_gemma":0.00001152035,"teacher_disagreement_score":0.96449006,"about_ca_system_score_codex":0.000026191246,"about_ca_system_score_gemma":0.00003892922,"threshold_uncertainty_score":0.58349663},"labels":[],"label_agreement":null},{"id":"W4414270260","doi":"10.1109/tkde.2025.3611170","title":"A Multi-Objective Explanation Framework for Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Shandong Province; National Natural Science Foundation of China","keywords":"Focus (optics); Graph; Artificial neural network; Attribution; Graph theory; Data modeling; Pareto principle","score_opus":0.03820802667668711,"score_gpt":0.31086400128210495,"score_spread":0.27265597460541785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414270260","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004255495,0.00046807982,0.99702805,0.0001143496,0.0014124787,0.0002754677,0.0000314306,0.00020979681,0.00003481373],"genre_scores_gemma":[0.8816484,0.00008853819,0.11792479,0.00006971006,0.000059377762,0.00010843858,0.000011203786,0.000012680737,0.00007682874],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990443,0.000018791929,0.00018412464,0.00044845795,0.000058381833,0.00024592676],"domain_scores_gemma":[0.9987405,0.00046896408,0.000023686493,0.00063138775,0.000073938136,0.000061512066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019014745,0.00014759063,0.00013439603,0.0002709238,0.00021023258,0.00012904395,0.00057548296,0.00009416127,0.0000019992926],"category_scores_gemma":[0.000033545584,0.0001562859,0.000042586056,0.00060493307,0.000019289482,0.00069703936,0.0000140318225,0.0002282175,0.000004452833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039480445,0.00029886243,0.000015157056,0.00012334577,0.00012713067,0.0000043672803,0.0012827717,0.68198305,0.0007488523,0.038183395,0.00038263257,0.27681094],"study_design_scores_gemma":[0.000130812,0.000041153147,0.000045703353,0.000070103175,0.000017284241,0.000001964727,0.00005617071,0.9925686,0.005579655,0.00069356605,0.0006490982,0.00014587912],"about_ca_topic_score_codex":0.000015608488,"about_ca_topic_score_gemma":0.00005618711,"teacher_disagreement_score":0.8812229,"about_ca_system_score_codex":0.000035611673,"about_ca_system_score_gemma":0.00002448309,"threshold_uncertainty_score":0.6373154},"labels":[],"label_agreement":null},{"id":"W4414908411","doi":"10.1109/tkde.2025.3618763","title":"Breaking Information Granularity Heterogeneity: A Mutual Information-Inspired Causal Discovery Framework for Multi-Rate Time Series","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Time Series Analysis and Forecasting","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Granularity; Sampling (signal processing); Key (lock); Time series; Mutual information; Series (stratigraphy); Encoder; Information theory","score_opus":0.02118411617827084,"score_gpt":0.2668840398867101,"score_spread":0.24569992370843927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414908411","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019454795,0.00007710181,0.996644,0.00009523863,0.00046736267,0.00020089393,0.00034327965,0.0001841999,0.000042452357],"genre_scores_gemma":[0.7369964,0.00008121467,0.26201305,0.00017723495,0.000075700584,0.000098989636,0.0003390986,0.000017170447,0.00020112492],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907583,0.000018385183,0.00036044462,0.00022561835,0.000084295105,0.00023542374],"domain_scores_gemma":[0.9990626,0.00013930589,0.00006969529,0.0005808132,0.00008772483,0.0000598918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029213369,0.00018738813,0.00021149375,0.00028898648,0.0003323415,0.000624531,0.0004501197,0.000099429795,0.0000024552583],"category_scores_gemma":[0.00004310562,0.00018665884,0.00007064034,0.0004619982,0.000023651826,0.0082258405,0.000034297474,0.00017740646,0.00002001685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003179891,0.00048298083,0.00013585656,0.0020444135,0.0013649242,0.000004977562,0.008088345,0.17414226,0.0020967622,0.07104313,0.00096845796,0.7393099],"study_design_scores_gemma":[0.00034887413,0.000043720276,0.00018180048,0.00012778856,0.0000529494,0.0000049579603,0.00003453108,0.98747206,0.0021691476,0.000079803904,0.009277727,0.00020661447],"about_ca_topic_score_codex":0.00002253368,"about_ca_topic_score_gemma":0.00003977559,"teacher_disagreement_score":0.8133298,"about_ca_system_score_codex":0.000037211732,"about_ca_system_score_gemma":0.000055385884,"threshold_uncertainty_score":0.7611727},"labels":[],"label_agreement":null},{"id":"W4415221793","doi":"10.1109/tkde.2025.3621851","title":"A Causal Perspective of Stock Prediction Models","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spurious relationship; Generalizability theory; Causal model; Stock market; Predictive modelling; Mean squared prediction error; Perspective (graphical); Predictive power; Stock (firearms)","score_opus":0.12024319050058595,"score_gpt":0.3983024348601164,"score_spread":0.27805924435953044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415221793","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007374054,0.00041892976,0.9855709,0.00004888194,0.000979535,0.00016167434,0.00032769167,0.00007872652,0.005039576],"genre_scores_gemma":[0.9874963,0.00003514377,0.011389725,0.000006761075,0.000037060214,0.000017033863,0.0000033585961,0.000012055081,0.0010025224],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985833,0.00008677183,0.00038685979,0.0005113707,0.00027354885,0.0001581462],"domain_scores_gemma":[0.99722713,0.0015268876,0.00005230276,0.0008825873,0.00024570923,0.00006541007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014242377,0.00014107842,0.00024966738,0.0006283461,0.00010541402,0.00004882496,0.00049050443,0.000080105136,0.00002892245],"category_scores_gemma":[0.0003717795,0.00012558044,0.000052952764,0.0009185518,0.000047641064,0.0004612221,0.00001714311,0.00021580553,0.0000057084135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002975651,0.0005068592,0.00016626298,0.00013544987,0.000363704,0.000004304935,0.0032179358,0.3840742,0.0053234333,0.009415849,0.0053055733,0.59118885],"study_design_scores_gemma":[0.00035951124,0.00006994496,0.0005509851,0.00010514236,0.000060177757,0.0000066364764,0.00028508937,0.9909411,0.0028438284,0.0032723402,0.0013918729,0.00011333594],"about_ca_topic_score_codex":0.00003269156,"about_ca_topic_score_gemma":0.000030357416,"teacher_disagreement_score":0.98012227,"about_ca_system_score_codex":0.000059697628,"about_ca_system_score_gemma":0.00008437753,"threshold_uncertainty_score":0.5121021},"labels":[],"label_agreement":null},{"id":"W4416873169","doi":"10.1109/tkde.2025.3638821","title":"A Log-Likelihood Chain Framework for Defending Against LDP Data Poisoning Attacks","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Internet Traffic Analysis and Secure E-voting","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; Fundamental Research Funds for the Central Universities; China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Differential privacy; Categorical variable; Anomaly detection; Intrusion detection system; Skew; Data modeling; Privacy protection; Denial-of-service attack","score_opus":0.03431367048434421,"score_gpt":0.30368963994464293,"score_spread":0.26937596946029874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416873169","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001309146,0.0047774464,0.9874578,0.00026434567,0.0044599306,0.00047703573,0.00083381595,0.00025882284,0.00016163308],"genre_scores_gemma":[0.9423321,0.0007142004,0.055811785,0.00014511166,0.00040299527,0.000038510072,0.00022478301,0.000059714945,0.00027083282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956354,0.00008164571,0.00093226694,0.0020819618,0.0002501061,0.0010186333],"domain_scores_gemma":[0.9956218,0.0012137168,0.0001552612,0.0025925764,0.0001498973,0.0002667637],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013580534,0.00066445343,0.0007500796,0.00074570713,0.0007590348,0.00080705964,0.0036269221,0.00039387465,0.000017662225],"category_scores_gemma":[0.00014920972,0.0007255133,0.00020606046,0.0012454884,0.000068942136,0.0013828892,0.00022197595,0.0011297636,0.000029482288],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007802737,0.0007030299,0.000014293484,0.0013762631,0.0017942744,0.000026223599,0.0038282156,0.27903816,0.0002186151,0.047169648,0.0026729447,0.66308033],"study_design_scores_gemma":[0.0006344202,0.00008707184,0.0000075905887,0.0022259299,0.00041432856,0.000008556223,0.00019686685,0.98326015,0.0002865819,0.000025769099,0.012208508,0.0006442092],"about_ca_topic_score_codex":0.000013619401,"about_ca_topic_score_gemma":0.00012517894,"teacher_disagreement_score":0.94102293,"about_ca_system_score_codex":0.0001296267,"about_ca_system_score_gemma":0.00026654202,"threshold_uncertainty_score":0.9995196},"labels":[],"label_agreement":null},{"id":"W7084580536","doi":"10.1109/tkde.2025.3617583","title":"Adaptive Hyper-Box Granulation With Justifiable Granularity for Feature Selection","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Plant Parasitism and Resistance","field":"Agricultural and Biological Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Science Foundation of Chongqing; National Natural Science Foundation of China","keywords":"Cluster analysis; Granularity; Feature selection; CURE data clustering algorithm; Feature (linguistics); Correlation clustering; Constrained clustering; Partition (number theory); Canopy clustering algorithm","score_opus":0.018823306022998865,"score_gpt":0.23718832009148672,"score_spread":0.21836501406848785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084580536","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16320398,0.0007827663,0.8319536,0.00031727325,0.00044823566,0.0005289349,0.0021549584,0.00020904657,0.00040121318],"genre_scores_gemma":[0.9972843,0.00007330888,0.0016325613,0.000019292016,0.00006971626,0.000028309993,0.00023406715,0.0000012478718,0.0006571742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994581,0.000009717487,0.000074632866,0.0002646303,0.000046647863,0.00014631354],"domain_scores_gemma":[0.99971414,0.00012934483,0.000014813782,0.00006719471,0.00003715497,0.000037381604],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000071244336,0.00010757047,0.000120442026,0.000026329628,0.00025298513,0.000038691618,0.00011062731,0.0000765741,0.0000044484264],"category_scores_gemma":[0.0000027143196,0.00004961193,0.00002118842,0.00026851133,0.000014463555,0.00018969439,0.000001795377,0.00011725326,0.0000017084742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016778171,0.00086600584,0.0014877396,0.0005940986,0.0003717716,0.0000065963586,0.00022453579,0.036152598,0.46736655,0.0019449806,0.009842,0.4794653],"study_design_scores_gemma":[0.002935673,0.0010900162,0.09406531,0.0010366233,0.00071437325,0.000065311615,0.00021972696,0.5628991,0.12368057,0.00028687192,0.21145673,0.0015496861],"about_ca_topic_score_codex":0.00004219974,"about_ca_topic_score_gemma":0.00096088194,"teacher_disagreement_score":0.83408034,"about_ca_system_score_codex":0.00001531256,"about_ca_system_score_gemma":0.000008919556,"threshold_uncertainty_score":0.20231156},"labels":[],"label_agreement":null},{"id":"W7104533847","doi":"10.1109/tkde.2025.3631025","title":"Region Embedding With Adaptive Correlation Discovery for Predicting Urban Socioeconomic Indicators","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Knowledge and Data Engineering","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Natural Science Foundation of China; Ministry of Natural Resources","keywords":"Embedding; Feature learning; ENCODE; Representation (politics); Feature (linguistics); Graph","score_opus":0.01794958544766521,"score_gpt":0.2882866304678555,"score_spread":0.2703370450201903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104533847","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032456107,0.00013604356,0.9663609,0.000089085304,0.00021146152,0.00023450337,0.00005930668,0.000078476514,0.0003741156],"genre_scores_gemma":[0.9984247,0.0000513746,0.0004703253,0.000013450921,0.00008742994,0.000052287964,0.000037525628,0.000008870355,0.00085400697],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993376,0.000030464147,0.00014756132,0.00028151958,0.000054723154,0.00014812987],"domain_scores_gemma":[0.9992756,0.00038153876,0.00003901355,0.00021945943,0.000035803376,0.000048572354],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030647498,0.00009324984,0.000121125275,0.00024566954,0.00058904145,0.00007931558,0.00014395117,0.00007289422,0.0000068412933],"category_scores_gemma":[0.000020200847,0.000095400195,0.00003242538,0.0002581648,0.000070745074,0.0005502845,0.000002308426,0.00013380036,0.0000026530208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050899567,0.00079828367,0.012778253,0.0007237736,0.001615472,0.0000030878493,0.060939696,0.642758,0.0001988873,0.028265938,0.0023500791,0.24905954],"study_design_scores_gemma":[0.00071781554,0.000098316195,0.0008377442,0.00031527376,0.00038113442,4.632993e-7,0.006244919,0.9826339,0.00041483826,0.00008979316,0.00795019,0.00031559495],"about_ca_topic_score_codex":0.00023661547,"about_ca_topic_score_gemma":0.0018701124,"teacher_disagreement_score":0.9659686,"about_ca_system_score_codex":0.00013057695,"about_ca_system_score_gemma":0.00016712902,"threshold_uncertainty_score":0.453049},"labels":[],"label_agreement":null}]}