{"meta":{"query_hash":"183d8fa8b2bb","filters":{"venue":"IEEE Transactions on Big Data"},"cohort_total":22,"direct_labels_cover":0,"predictions_cover":22,"exported":22,"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/183d8fa8b2bb","api":"https://metacan.xera.ac/api/v1/cohort?venue=IEEE+Transactions+on+Big+Data"},"results":[{"id":"W2610514569","doi":"10.1109/tbdata.2017.2701816","title":"PPHOPCM: Privacy-Preserving High-Order Possibilistic c-Means Algorithm for Big Data Clustering with Cloud Computing","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Face and Expression Recognition","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":"St. Francis Xavier University","funders":"","keywords":"Cluster analysis; Computer science; Big data; Cloud computing; Data mining; Fuzzy clustering; Scheme (mathematics); Encryption; CURE data clustering algorithm; Clustering high-dimensional data; Algorithm; Artificial intelligence; Mathematics","score_opus":0.1454192020572554,"score_gpt":0.3165568846312504,"score_spread":0.17113768257399503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610514569","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":[0.002192679,0.00002270537,0.98856306,0.00086368667,0.0051523675,0.00047731516,0.0024360735,0.00021985744,0.00007223147],"genre_scores_gemma":[0.4211853,0.00008828789,0.57573366,0.0003274344,0.0012824939,0.00003743224,0.0009198007,0.00006723298,0.0003583461],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99737334,0.00006725853,0.00035992888,0.0013062449,0.00040259652,0.0004906368],"domain_scores_gemma":[0.99087685,0.00026819608,0.0002478844,0.008279923,0.00016265684,0.00016447254],"candidate_categories":["metaepi_narrow","sts","open_science"],"consensus_categories":[],"category_scores_codex":[0.00054184755,0.00029040838,0.00028618058,0.0001526,0.0016642434,0.0009774984,0.008118457,0.00011582423,0.0000114475515],"category_scores_gemma":[0.000076622804,0.00025230087,0.000041855415,0.0002095605,0.00010426346,0.0019666185,0.00046836128,0.00032980912,0.00004291875],"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":[0.00003578674,0.00024230184,0.0000054776815,0.00007199463,0.00008202144,0.000016856513,0.00021024434,0.0027012506,0.00087014225,0.000004255105,0.0029749773,0.9927847],"study_design_scores_gemma":[0.0012770197,0.000140553,0.00012923352,0.0003804685,0.00006794136,0.000029190396,0.000043465374,0.98847944,0.0030364192,0.000119739794,0.005889515,0.00040703206],"about_ca_topic_score_codex":0.0006949971,"about_ca_topic_score_gemma":0.0012534797,"teacher_disagreement_score":0.99237764,"about_ca_system_score_codex":0.000038793347,"about_ca_system_score_gemma":0.00015486704,"threshold_uncertainty_score":0.9999929},"labels":[],"label_agreement":null},{"id":"W2731419512","doi":"10.1109/tbdata.2017.2721444","title":"Achieving Efficient and Privacy-Preserving Cross-Domain Big Data Deduplication in Cloud","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Cloud Data Security Solutions","field":"Computer Science","cited_by":58,"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 New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Data deduplication; Computer science; Cloud computing; Big data; Homomorphic encryption; Encryption; Cloud storage; Computer security; Information privacy; Domain (mathematical analysis); Data mining; Operating system","score_opus":0.16154579015690074,"score_gpt":0.3454990075471699,"score_spread":0.18395321739026915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731419512","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":[0.14579856,0.00011211604,0.8466588,0.0028266727,0.0018031381,0.00033160878,0.0022605597,0.00011507624,0.00009345899],"genre_scores_gemma":[0.9842585,0.00013152596,0.014864514,0.00012680909,0.00023821626,0.000022794626,0.00030558673,0.00001992057,0.000032163513],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99721706,0.000114111484,0.00041542482,0.0014150089,0.00039879628,0.00043958484],"domain_scores_gemma":[0.98287296,0.00023174127,0.00019515443,0.016484775,0.000051104256,0.00016424425],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0012141626,0.00022570654,0.0002182279,0.00023490458,0.0013705048,0.0013028694,0.012429757,0.00011712635,0.0000062851705],"category_scores_gemma":[0.00024622178,0.00024404534,0.000029167255,0.00034860073,0.0002340899,0.0018305086,0.0011399415,0.00045535807,0.000052137784],"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":[0.00012548223,0.0027149597,0.005228073,0.00026211282,0.00017174265,0.000083555664,0.0032906595,0.007515894,0.009767648,0.0035985825,0.009670018,0.95757127],"study_design_scores_gemma":[0.0022997176,0.00008852491,0.06750594,0.00038340813,0.000057767986,0.00009716554,0.00008170024,0.8766843,0.0015582769,0.0010363817,0.049203202,0.0010036004],"about_ca_topic_score_codex":0.001069586,"about_ca_topic_score_gemma":0.0033228218,"teacher_disagreement_score":0.95656765,"about_ca_system_score_codex":0.00008646632,"about_ca_system_score_gemma":0.00014109889,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W2753315806","doi":"10.1109/tbdata.2017.2742530","title":"Euler Clustering on Large-Scale Dataset","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Face and Expression Recognition","field":"Computer Science","cited_by":22,"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":"National Key Research and Development Program of China; Guangdong Science and Technology Department; Sun Yat-sen University; National Natural Science Foundation of China","keywords":"Cluster analysis; Euler's formula; Kernel (algebra); Spectral clustering; Mathematics; Variable kernel density estimation; Algorithm; Pattern recognition (psychology); Computer science; Kernel method; Artificial intelligence; Discrete mathematics; Mathematical analysis; Support vector machine","score_opus":0.129188872121244,"score_gpt":0.3208625784651777,"score_spread":0.1916737063439337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753315806","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":[0.001617922,0.000004615395,0.98576826,0.0012163356,0.0025919524,0.00009827142,0.008094432,0.00009468854,0.0005135284],"genre_scores_gemma":[0.98182875,0.00013576976,0.013846095,0.0016020321,0.00026278273,0.00003265956,0.0016511207,0.000024692734,0.0006161083],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987911,0.000034878012,0.00014268012,0.0005474086,0.00024272072,0.00024118548],"domain_scores_gemma":[0.9956559,0.00005458226,0.000072028306,0.0040977267,0.000020323436,0.00009941834],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021039926,0.00012872642,0.00010926944,0.00008910146,0.00081817375,0.00039748184,0.0024915058,0.00006791327,0.000080606966],"category_scores_gemma":[0.000009758739,0.000115001414,0.00003107468,0.00006153807,0.000033475535,0.0012490274,0.00005052431,0.00021500455,0.0010856363],"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":[0.00006765366,0.00064375746,0.000008461863,0.000027475737,0.00004055828,0.000035031466,0.00019772703,0.0014076553,0.0019675635,0.00002503942,0.16542093,0.8301581],"study_design_scores_gemma":[0.0019225442,0.00022182048,0.00057120516,0.00031399104,0.000039448234,0.000028873348,0.000054293258,0.41061822,0.03837032,0.00013552488,0.54703957,0.0006841995],"about_ca_topic_score_codex":0.000058315974,"about_ca_topic_score_gemma":0.00038246944,"teacher_disagreement_score":0.98021084,"about_ca_system_score_codex":0.00001428174,"about_ca_system_score_gemma":0.00002645213,"threshold_uncertainty_score":0.99969214},"labels":[],"label_agreement":null},{"id":"W2920772632","doi":"10.1109/tbdata.2019.2903092","title":"Incremental Deep Computation Model for Wireless Big Data Feature Learning","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science; Big data; Artificial intelligence; Deep learning; Machine learning; Wireless network; Computation; Wireless; Feature (linguistics); Data modeling; Algorithm; Data mining","score_opus":0.1011934834914356,"score_gpt":0.3053111633478779,"score_spread":0.2041176798564423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920772632","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":[0.008235817,0.00002535936,0.9882921,0.00083044084,0.0015565049,0.00029354906,0.0003931623,0.00024237452,0.00013067713],"genre_scores_gemma":[0.96136963,0.000022010505,0.036179777,0.00023672928,0.00014612083,0.000011493395,0.000976306,0.000024642306,0.0010332661],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982457,0.00008682853,0.00018914934,0.0008691907,0.00031992915,0.00028921445],"domain_scores_gemma":[0.99760336,0.00015186133,0.00009525567,0.0020141483,0.00004915677,0.00008619335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004686581,0.00018472073,0.00018243922,0.00014752315,0.0003547548,0.00021227992,0.0024165066,0.00009921364,0.0000056670674],"category_scores_gemma":[0.00001040928,0.00018104141,0.000041919546,0.00028739992,0.000023251412,0.0007969756,0.00006716264,0.00040946619,0.00010069639],"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":[0.000029093282,0.00010424144,0.00002811466,0.000033020267,0.00003534155,9.606423e-7,0.00021652614,0.28454843,0.000488211,0.00004429457,0.0016211204,0.71285063],"study_design_scores_gemma":[0.00073093554,0.00009284888,0.00005853166,0.000031657186,0.000024450183,0.000009163141,0.000030512227,0.99292725,0.00025250434,0.00005400783,0.0055718045,0.00021634868],"about_ca_topic_score_codex":0.000103443024,"about_ca_topic_score_gemma":0.00021373064,"teacher_disagreement_score":0.9531338,"about_ca_system_score_codex":0.000037689213,"about_ca_system_score_gemma":0.00008701526,"threshold_uncertainty_score":0.73826545},"labels":[],"label_agreement":null},{"id":"W2923023146","doi":"10.1109/tbdata.2019.2907624","title":"Hierarchical Density-Based Clustering Using MapReduce","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","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 Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Cluster analysis; Scalability; Automatic summarization; Correlation clustering; Hierarchical clustering; CURE data clustering algorithm; Data mining; Canopy clustering algorithm; Constrained clustering; Artificial intelligence; Database","score_opus":0.1308743166587772,"score_gpt":0.3353534078399405,"score_spread":0.2044790911811633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923023146","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":[0.020743748,0.0000090006615,0.97663945,0.00037761865,0.001608636,0.00024081844,0.00008248052,0.00021964202,0.00007860237],"genre_scores_gemma":[0.7608311,0.000005505023,0.2385696,0.00021578021,0.00008346354,0.000006966994,0.000011642397,0.000025825779,0.00025007845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978163,0.000109767076,0.00022075792,0.0008498663,0.0005388349,0.00046443433],"domain_scores_gemma":[0.9966199,0.00019623208,0.000044475535,0.0029059546,0.00006183727,0.00017163814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030574144,0.00018548308,0.00018926158,0.00026992528,0.00022635177,0.00018458847,0.0023203027,0.00008562766,0.00002621226],"category_scores_gemma":[0.00000979668,0.0001913558,0.000054170214,0.00055869913,0.00006620746,0.0006934666,0.00007049834,0.0005235679,0.0002543227],"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":[0.00008229368,0.00025874423,0.000018378596,0.00008357862,0.000045292123,0.00006315371,0.00011422326,0.43440542,0.030753551,0.000037548063,0.000055793516,0.53408206],"study_design_scores_gemma":[0.00047845853,0.000077331315,0.000046474965,0.00005991929,0.000006060511,0.00004491842,0.0000066773623,0.978183,0.019963222,0.000058985166,0.0008576267,0.00021735726],"about_ca_topic_score_codex":0.00006764437,"about_ca_topic_score_gemma":0.00003557301,"teacher_disagreement_score":0.7400874,"about_ca_system_score_codex":0.0001275846,"about_ca_system_score_gemma":0.00019879956,"threshold_uncertainty_score":0.7803263},"labels":[],"label_agreement":null},{"id":"W2982169658","doi":"10.1109/tbdata.2019.2948613","title":"PES: Priority Edge Sampling in Streaming Triangle Estimation","year":2019,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","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 Windsor","funders":"","keywords":"Computer science; Sampling (signal processing); Estimator; Enhanced Data Rates for GSM Evolution; Streaming algorithm; Metric (unit); Cluster analysis; Algorithm; Variance (accounting); Clustering coefficient; Theoretical computer science; Mathematics; Statistics; Artificial intelligence; Upper and lower bounds","score_opus":0.08562440375598687,"score_gpt":0.32429078161761027,"score_spread":0.2386663778616234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2982169658","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":[0.13495086,0.00001050672,0.8635093,0.00003855489,0.00022308457,0.00023331483,0.00023147,0.00006766645,0.00073522533],"genre_scores_gemma":[0.99299276,0.0000046443574,0.006441747,0.000011070893,0.00011700238,0.000017451286,0.00026472917,0.000014364823,0.00013622665],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901575,0.000047381545,0.00025974386,0.00036122065,0.00013373222,0.00018218612],"domain_scores_gemma":[0.9987938,0.00013004184,0.00007272387,0.0009435544,0.000021462087,0.000038445178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024203763,0.00012851853,0.00021242641,0.0001778878,0.00008128691,0.000055568806,0.00036119463,0.000036050955,0.00029149294],"category_scores_gemma":[0.0000018804759,0.00013544878,0.0000676026,0.00036271964,0.000014843744,0.00028186582,0.000006629276,0.00023110808,0.000087702094],"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":[0.000025580384,0.00034230517,0.0028311398,0.000013866694,0.000065503424,4.6178977e-7,0.00011253686,0.014662533,0.0007070311,0.00020704282,0.00019086491,0.98084116],"study_design_scores_gemma":[0.00315933,0.00019671359,0.00867714,0.00051645277,0.0003263142,0.0000020592304,0.0005688474,0.94957685,0.015735857,0.0055910028,0.014427692,0.0012217119],"about_ca_topic_score_codex":0.0007105363,"about_ca_topic_score_gemma":0.00027379242,"teacher_disagreement_score":0.97961944,"about_ca_system_score_codex":0.000046593905,"about_ca_system_score_gemma":0.00004609705,"threshold_uncertainty_score":0.5523441},"labels":[],"label_agreement":null},{"id":"W3005586683","doi":"10.1109/tbdata.2020.2972887","title":"Least Squares Approximation via Sparse Subsampled Randomized Hadamard Transform","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","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 Alberta","funders":"","keywords":"Hadamard transform; Computer science; Algorithm; Subspace topology; Overdetermined system; Randomized algorithm; Embedding; Mathematics; Artificial intelligence; Applied mathematics","score_opus":0.0974922001653938,"score_gpt":0.25270262016454015,"score_spread":0.15521041999914637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3005586683","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":[0.0030123536,0.000091853326,0.9926534,0.00063744327,0.00051564624,0.00058405154,0.00029553895,0.0013959648,0.0008136895],"genre_scores_gemma":[0.9943689,0.00023577751,0.004748245,0.00021492562,0.00014905243,0.000051611638,0.00015892385,0.00005473268,0.000017799272],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878144,0.00006686094,0.00034541538,0.0003422452,0.00023089873,0.00023313414],"domain_scores_gemma":[0.9989729,0.00012331904,0.000035514648,0.00070854014,0.000036979694,0.00012272659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001584643,0.00024437197,0.0004160214,0.00010825286,0.0001043245,0.0000653896,0.0004394774,0.0001082237,0.00009208048],"category_scores_gemma":[0.0000105164,0.00023292666,0.00012741385,0.00025608478,0.00006936609,0.000307059,0.0000025712363,0.00029310264,0.00008678814],"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":[0.012849671,0.00029120568,0.0000019376673,0.00022720135,0.0008049574,0.00003623286,0.001497958,0.11241125,0.051207885,0.00010820237,0.016188357,0.8043751],"study_design_scores_gemma":[0.014821276,0.0000562773,0.0000049590767,0.000067996756,0.00018731605,0.0000114220165,0.000038654292,0.805138,0.17134754,0.00027066667,0.0076617277,0.00039414372],"about_ca_topic_score_codex":0.000086552056,"about_ca_topic_score_gemma":0.000092500966,"teacher_disagreement_score":0.99135655,"about_ca_system_score_codex":0.000027830789,"about_ca_system_score_gemma":0.000017537184,"threshold_uncertainty_score":0.94984734},"labels":[],"label_agreement":null},{"id":"W3033628195","doi":"10.1109/tbdata.2020.2998770","title":"Dynamic Entity-Based Named Entity Recognition Under Unconstrained Tagging Schemes","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Topic Modeling","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":"St. Francis Xavier University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Named-entity recognition; Natural language processing; Sentence; Artificial intelligence; Word (group theory); Entity linking; Language model; Precision and recall; Named entity; Task (project management); Knowledge base; Linguistics","score_opus":0.15396775093685824,"score_gpt":0.2866244407588694,"score_spread":0.13265668982201115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033628195","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":[0.008153108,0.000015978152,0.984243,0.0055526826,0.0010332379,0.00018337394,0.00032522346,0.00040031542,0.0000931272],"genre_scores_gemma":[0.9211032,0.000013360931,0.07670739,0.0019519259,0.00005278359,0.000012193258,0.00012123868,0.000013501325,0.000024404637],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830806,0.00008224104,0.00027197297,0.0007464079,0.00032958353,0.00026170933],"domain_scores_gemma":[0.99843776,0.000086696804,0.000076466386,0.0011855483,0.000058737784,0.0001547738],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021331411,0.00017206013,0.00016293582,0.00013531877,0.00022893201,0.00019879342,0.0012360668,0.00008201961,0.00007703616],"category_scores_gemma":[0.000020505136,0.00018862756,0.000070211136,0.00046080095,0.000057330017,0.00078982144,0.000017550119,0.00032451292,0.0001616746],"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":[0.00004670163,0.00039155784,0.000020868607,0.0001383698,0.00013523629,0.000030696832,0.00028551876,0.025312738,0.01207475,0.00042580604,0.0003674543,0.9607703],"study_design_scores_gemma":[0.0006884609,0.000043049888,0.000014784164,0.00005354308,0.00003394017,0.0000046830214,0.000031724456,0.98810405,0.008757546,0.0004152835,0.0015974523,0.00025545855],"about_ca_topic_score_codex":0.00006312966,"about_ca_topic_score_gemma":0.00019053035,"teacher_disagreement_score":0.9627913,"about_ca_system_score_codex":0.000067526234,"about_ca_system_score_gemma":0.00020519238,"threshold_uncertainty_score":0.76920086},"labels":[],"label_agreement":null},{"id":"W3089041741","doi":"10.1109/tbdata.2020.3026318","title":"On Security of an Identity-Based Dynamic Data Auditing Protocol for Big Data Storage","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Cloud Data Security Solutions","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 New Brunswick","funders":"Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Computer science; Big data; Protocol (science); Audit; Computer security; Cryptographic protocol; Cryptography; Data mining","score_opus":0.22039325091568981,"score_gpt":0.37304155498988695,"score_spread":0.15264830407419713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089041741","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":[0.00029305476,0.0000028039597,0.863451,0.0018403068,0.0008347701,0.021977285,0.11132127,0.0002651957,0.000014316418],"genre_scores_gemma":[0.76578903,0.000010064534,0.15002975,0.0032958433,0.0013340032,0.027507588,0.051822495,0.00019050571,0.000020737489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99588937,0.00022781489,0.0006336056,0.002054318,0.0007482921,0.0004466129],"domain_scores_gemma":[0.98465496,0.000468603,0.00031049157,0.01415564,0.00011908028,0.00029123342],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0010739929,0.00031826535,0.0003615681,0.00022247787,0.0004816174,0.0003366483,0.015617368,0.00013135199,0.000022754344],"category_scores_gemma":[0.0002662168,0.00034727808,0.00006230083,0.0010353347,0.00015479089,0.004056707,0.00044436866,0.0005287198,0.000049616643],"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":[0.002424071,0.019954182,0.00002321469,0.005375701,0.0010574013,0.00022222749,0.0030485874,0.031803846,0.01083901,0.008364852,0.20183484,0.71505207],"study_design_scores_gemma":[0.0017442845,0.00039498834,0.00001956652,0.00012503825,0.0000644206,0.000005528988,0.000028964405,0.96453786,0.0010376391,0.0005708126,0.03110195,0.00036894815],"about_ca_topic_score_codex":0.00027559814,"about_ca_topic_score_gemma":0.004382768,"teacher_disagreement_score":0.932734,"about_ca_system_score_codex":0.00007839046,"about_ca_system_score_gemma":0.0005366212,"threshold_uncertainty_score":0.9998979},"labels":[],"label_agreement":null},{"id":"W3173588045","doi":"10.1109/tbdata.2021.3089986","title":"SOREL: Efficient and Secure ORE-based Range Query over Outsourced Data","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Cryptography and Data Security","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":"University of New Brunswick","funders":"","keywords":"Computer science; Scalability; Encryption; Cloud computing; Range query (database); Outsourcing; Scheme (mathematics); Big data; Query optimization; Sargable; Database; Distributed computing; Computer security; Data mining; Web search query; Operating system; Information retrieval; Search engine","score_opus":0.08136779334271013,"score_gpt":0.27963554450835715,"score_spread":0.19826775116564702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173588045","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":[0.010070864,0.000338219,0.9783247,0.00093754166,0.001063779,0.00015432782,0.008849569,0.000198034,0.00006296048],"genre_scores_gemma":[0.97756404,0.0001657501,0.019411866,0.001093712,0.000119781755,0.000010868186,0.0015960562,0.000022985443,0.000014946217],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976444,0.00013322399,0.00025220492,0.0012355617,0.0004198329,0.0003147761],"domain_scores_gemma":[0.9934558,0.00021535835,0.00006179743,0.006027484,0.000057749436,0.00018180643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039782087,0.00022077844,0.0002153528,0.00017231535,0.0003072637,0.0003160151,0.0024226645,0.00011392585,0.00005897815],"category_scores_gemma":[0.000020354224,0.0002126214,0.000058461992,0.00079031783,0.000114532086,0.0006330253,0.00011861057,0.00035902258,0.000028213293],"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":[0.00065087236,0.008391512,0.0009699792,0.0007196152,0.00088482734,0.0010845484,0.0035918946,0.01353427,0.0062691164,0.01200194,0.07826928,0.87363213],"study_design_scores_gemma":[0.0038359086,0.00014166413,0.0023538885,0.00019246037,0.00020543432,0.0000981932,0.00012917981,0.84361696,0.008072784,0.00041452853,0.13984743,0.0010915959],"about_ca_topic_score_codex":0.00013502793,"about_ca_topic_score_gemma":0.0007201346,"teacher_disagreement_score":0.9674932,"about_ca_system_score_codex":0.000016943506,"about_ca_system_score_gemma":0.00018222295,"threshold_uncertainty_score":0.86704487},"labels":[],"label_agreement":null},{"id":"W4286656147","doi":"10.1109/tbdata.2022.3186857","title":"Efficient Learned Spatial Index With Interpolation Function Based Learned Model","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Data Management and Algorithms","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 New Brunswick","funders":"","keywords":"Computer science; Leverage (statistics); Spatial database; Data mining; Spatial analysis; Spatial query; Index (typography); Overhead (engineering); Interpolation (computer graphics); Multivariate interpolation; Function (biology); Machine learning; Artificial intelligence; Information retrieval; Sargable; Web search query; Bilinear interpolation; Mathematics","score_opus":0.08700016958677916,"score_gpt":0.2643861053845783,"score_spread":0.17738593579779915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286656147","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":[0.0010904518,0.0000043887794,0.99602586,0.0007989803,0.0010370304,0.00025567968,0.00032086344,0.00024321735,0.0002235016],"genre_scores_gemma":[0.99064463,0.0000019624733,0.008099445,0.0003956991,0.000044688746,0.000055588764,0.0003045861,0.00001726506,0.00043615745],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814326,0.00010149906,0.00019108532,0.0007193324,0.0006105567,0.00023424646],"domain_scores_gemma":[0.99808806,0.00003930411,0.0000892185,0.0016837904,0.000033346125,0.00006625238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003821409,0.00016214089,0.00011897707,0.0003277408,0.00053364574,0.00019218579,0.0014443456,0.000029277937,0.0000983257],"category_scores_gemma":[0.0000027539238,0.00015476672,0.000037594327,0.0006447109,0.000033701708,0.00044711248,0.00005811228,0.0003449027,0.000040121377],"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":[0.00016084127,0.00026099308,0.000006865684,0.000005193311,0.000024258963,0.0000037928335,0.000044870136,0.76185906,0.00008138117,0.00008490954,0.00039873034,0.23706909],"study_design_scores_gemma":[0.0009015304,0.00030304358,0.000059432947,0.000008457155,0.00003164753,0.0000025002655,0.0000351815,0.99554753,0.00011256208,0.00007362397,0.0027296145,0.00019488354],"about_ca_topic_score_codex":0.00018027029,"about_ca_topic_score_gemma":0.00014090518,"teacher_disagreement_score":0.98955417,"about_ca_system_score_codex":0.00007237039,"about_ca_system_score_gemma":0.00010825682,"threshold_uncertainty_score":0.6311203},"labels":[],"label_agreement":null},{"id":"W4323896842","doi":"10.1109/tbdata.2023.3255003","title":"Approximate Clustering Ensemble Method for Big Data","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Advanced Clustering Algorithms Research","field":"Computer Science","cited_by":31,"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":"National Natural Science Foundation of China","keywords":"Cluster analysis; Computer science; Disjoint sets; Big data; Correlation clustering; Data mining; Component (thermodynamics); Cluster (spacecraft); Artificial intelligence; Mathematics; Combinatorics","score_opus":0.3223194882196442,"score_gpt":0.40855782386772044,"score_spread":0.08623833564807626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323896842","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":[0.000027131908,0.00002267105,0.9919521,0.0010292026,0.0034740928,0.00050481904,0.0021749793,0.00072843005,0.00008653119],"genre_scores_gemma":[0.012512303,0.00021687409,0.98350835,0.00019174349,0.00061895564,0.00020418725,0.00060568424,0.000085204396,0.0020567265],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968954,0.00011629894,0.00032595257,0.0014279581,0.00052342797,0.0007109929],"domain_scores_gemma":[0.9923183,0.0006626186,0.000067871035,0.0066926153,0.00008279897,0.00017582893],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0014296513,0.00023312964,0.00025445168,0.00040706282,0.00045593447,0.00028688493,0.0064266487,0.000095419186,0.0000036500642],"category_scores_gemma":[0.00006414986,0.00023470646,0.000051869913,0.0013412362,0.000049327806,0.0011139091,0.00037285726,0.0003228488,0.00017148569],"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":[0.000027028322,0.00006260298,1.3618165e-7,0.00007701516,0.000044798955,0.000016329592,0.00009016671,0.019021807,0.003919291,0.00002023402,0.002516015,0.9742046],"study_design_scores_gemma":[0.0005331994,0.00007432282,0.000004529643,0.000039797535,0.00001456356,0.000030896474,0.000026228246,0.9536978,0.007975087,0.0003906713,0.036959633,0.00025329704],"about_ca_topic_score_codex":0.00007104708,"about_ca_topic_score_gemma":0.00023800308,"teacher_disagreement_score":0.9739513,"about_ca_system_score_codex":0.000064243446,"about_ca_system_score_gemma":0.00013509406,"threshold_uncertainty_score":0.99894905},"labels":[],"label_agreement":null},{"id":"W4387757671","doi":"10.1109/tbdata.2023.3325746","title":"A Federated Convolution Transformer for Fake News Detection","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Misinformation and Its Impacts","field":"Social Sciences","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":"Brandon University","funders":"","keywords":"Computer science; Cluster analysis; Federated learning; Embedding; Data mining; The Internet; World Wide Web; Machine learning; Artificial intelligence","score_opus":0.2312254761613512,"score_gpt":0.37149474252581516,"score_spread":0.14026926636446396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387757671","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":[0.011989252,0.0000054469565,0.97850186,0.0018747832,0.002004799,0.0006537409,0.00084850943,0.00042915787,0.0036924826],"genre_scores_gemma":[0.99583095,0.00027972853,0.00007609684,0.00034624373,0.00017605122,0.00002451929,0.00022402577,0.000013146817,0.00302923],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988979,0.000064043474,0.0002222828,0.00021003913,0.0002878672,0.00031786092],"domain_scores_gemma":[0.99937046,0.000111149115,0.00004903731,0.0002493184,0.00008349158,0.00013656533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005439092,0.00010078275,0.00010457276,0.00021476868,0.0011870454,0.00015474389,0.00021631576,0.00012612811,0.00014345488],"category_scores_gemma":[0.000052265503,0.000100109646,0.000057642,0.0007570861,0.000072621726,0.00082178036,6.180496e-7,0.000119020144,0.00041011735],"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":[0.0001271625,0.000067139335,0.0000010718461,0.000024289504,0.000036888247,4.2015338e-7,0.005315059,0.00029328358,0.0019738912,0.000093617804,0.011453915,0.9806133],"study_design_scores_gemma":[0.0026216567,0.00029176698,0.00035032132,0.0000675049,0.00010818656,0.000003982272,0.017601788,0.047890678,0.027261265,0.0003112047,0.90291125,0.0005804142],"about_ca_topic_score_codex":0.0010714107,"about_ca_topic_score_gemma":0.017479442,"teacher_disagreement_score":0.9838417,"about_ca_system_score_codex":0.000084607884,"about_ca_system_score_gemma":0.00018615396,"threshold_uncertainty_score":0.97539395},"labels":[],"label_agreement":null},{"id":"W4390738572","doi":"10.1109/tbdata.2024.3352978","title":"GAT-COBO: Cost-Sensitive Graph Neural Network for Telecom Fraud Detection","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Imbalanced Data Classification Techniques","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 Toronto","funders":"National Natural Science Foundation of China","keywords":"Computer science; Graph; Artificial intelligence; Machine learning; Classifier (UML); Theoretical computer science","score_opus":0.08922606455742202,"score_gpt":0.3055968200315244,"score_spread":0.21637075547410237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390738572","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":[0.00013984472,0.00007453575,0.99083674,0.0010334967,0.0040587783,0.00072403136,0.0016905622,0.0013709664,0.000071025424],"genre_scores_gemma":[0.93236893,0.00015852267,0.06554344,0.0005824468,0.0004305242,0.0003317015,0.00034065603,0.0000419979,0.0002018037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980821,0.000083485196,0.0002994683,0.00091206364,0.00024485966,0.00037805055],"domain_scores_gemma":[0.99739546,0.00036165555,0.0000631058,0.0019892994,0.00009511315,0.00009535787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039150164,0.00021436614,0.00017531682,0.00026460807,0.00034903933,0.00038562992,0.0013082653,0.00012674142,0.0000064620567],"category_scores_gemma":[0.000014480257,0.00021307981,0.00009437205,0.0010131405,0.000072558876,0.001173625,0.000016261678,0.00037337997,0.00007310741],"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":[0.00002979533,0.0000626462,8.7725334e-7,0.000027846661,0.000051297375,0.000007832376,0.000055504494,0.0013364337,0.0038180992,0.0007271854,0.015238149,0.9786443],"study_design_scores_gemma":[0.00030000083,0.00023207901,0.00014031724,0.000095305455,0.000058983678,0.00006940705,0.000015156913,0.74925333,0.14018454,0.00229992,0.10689627,0.0004546994],"about_ca_topic_score_codex":0.000046164198,"about_ca_topic_score_gemma":0.00021348729,"teacher_disagreement_score":0.97818965,"about_ca_system_score_codex":0.00008280561,"about_ca_system_score_gemma":0.00007886802,"threshold_uncertainty_score":0.86891425},"labels":[],"label_agreement":null},{"id":"W4398152538","doi":"10.1109/tbdata.2024.3403390","title":"Accelerating Blockchain-Enabled Federated Learning With Clustered Clients","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Privacy-Preserving Technologies in Data","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":"Simon Fraser University","funders":"Basic and Applied Basic Research Foundation of Guangdong Province; National Natural Science Foundation of China","keywords":"Computer science; Single point of failure; Blockchain; Asynchronous communication; Distributed computing; Enhanced Data Rates for GSM Evolution; Cluster analysis; Distributed learning; Edge device; Convergence (economics); Artificial intelligence; Machine learning; Data mining; Computer security; Computer network","score_opus":0.10089906378633208,"score_gpt":0.2952834803242316,"score_spread":0.1943844165378995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398152538","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":[0.010330534,0.00008362926,0.97917044,0.005281218,0.0013744228,0.00025647954,0.00017308735,0.0029072324,0.0004229754],"genre_scores_gemma":[0.91744953,0.00005288792,0.08172763,0.00014629822,0.00006840205,0.00003535999,0.00007828986,0.000039337123,0.00040226476],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973691,0.00011899816,0.0003186164,0.0012356495,0.00046307791,0.0004945262],"domain_scores_gemma":[0.9915516,0.0002699408,0.000067661,0.007951479,0.00006653909,0.00009281684],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00049267197,0.00027791,0.0002142125,0.00035065503,0.00064377295,0.0012859183,0.017303785,0.00015209393,0.000029673029],"category_scores_gemma":[0.00046120796,0.00023690648,0.000037744285,0.0013981167,0.00008245416,0.0010102503,0.0019197352,0.0009999512,0.00015565367],"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":[0.00007405982,0.00029966413,0.000039514587,0.00015962547,0.00037305304,0.0003511407,0.00022928059,0.009209457,0.004348203,0.00013097901,0.04572377,0.9390612],"study_design_scores_gemma":[0.0004022888,0.0001684505,0.000012663871,0.0002741168,0.000027737042,0.00007134259,0.000048401056,0.9796901,0.012879564,0.00044109675,0.0056482726,0.00033598483],"about_ca_topic_score_codex":0.00008059701,"about_ca_topic_score_gemma":0.00014944225,"teacher_disagreement_score":0.9704806,"about_ca_system_score_codex":0.00010140609,"about_ca_system_score_gemma":0.00016837455,"threshold_uncertainty_score":0.99975085},"labels":[],"label_agreement":null},{"id":"W4398152819","doi":"10.1109/tbdata.2024.3403383","title":"Harnessing the Power of Local Supervision in Federated Learning","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Educational Curriculum and Learning Methods","field":"Social Sciences","cited_by":1,"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; Power (physics); Data science","score_opus":0.1214020775678456,"score_gpt":0.39488234107125697,"score_spread":0.27348026350341137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398152819","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":[0.12233025,0.000626613,0.8665369,0.0041395053,0.0029596388,0.0001496647,0.00003195249,0.00010379496,0.0031216498],"genre_scores_gemma":[0.9986584,0.000103726314,0.0002960387,0.000043070962,0.00008786799,0.0000048596057,0.000013668467,0.0000086390055,0.00078371586],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985819,0.0006384138,0.00015517623,0.00021737398,0.00026360844,0.00014354594],"domain_scores_gemma":[0.99904186,0.00065376033,0.000021752276,0.00020550891,0.000041129682,0.000036016514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017179634,0.000063278225,0.000080946775,0.00011128588,0.0004989462,0.00012336411,0.00029626672,0.000066068766,0.00026973255],"category_scores_gemma":[0.0000702881,0.000046832727,0.000031196872,0.0007098579,0.00017615908,0.00023180954,0.0000027032634,0.00044219906,0.000034655426],"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":[0.000021376627,0.00019198294,0.0002800621,0.000033120836,0.000028598446,0.000005749128,0.019876115,0.008585251,0.00069273205,0.00072018726,0.00081514876,0.9687497],"study_design_scores_gemma":[0.0007106685,0.00026537132,0.011812066,0.0022306633,0.00014761106,0.000015339796,0.1518958,0.06602019,0.005418623,0.0008930152,0.759752,0.0008387081],"about_ca_topic_score_codex":0.0025209698,"about_ca_topic_score_gemma":0.0017021049,"teacher_disagreement_score":0.96791095,"about_ca_system_score_codex":0.000049476166,"about_ca_system_score_gemma":0.00029896823,"threshold_uncertainty_score":0.3837541},"labels":[],"label_agreement":null},{"id":"W4405907170","doi":"10.1109/tbdata.2024.3524105","title":"Data Reconstruction and Protection in Federated Learning for Fine-Tuning Large Language Models","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Privacy-Preserving Technologies in Data","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 Toronto","funders":"","keywords":"Computer science","score_opus":0.13940838244706683,"score_gpt":0.3164687905736269,"score_spread":0.1770604081265601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405907170","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":[0.0038110386,0.00025948693,0.9890424,0.0030796854,0.0010117601,0.00042125268,0.0013569013,0.0009837119,0.000033744964],"genre_scores_gemma":[0.90031713,0.00018815519,0.09880587,0.000026693559,0.000060874598,0.00008115815,0.00042899742,0.0000253457,0.00006577233],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982369,0.00007811147,0.0002403467,0.0010104029,0.0001536466,0.0002805927],"domain_scores_gemma":[0.9943577,0.00016400093,0.000044908593,0.005371486,0.000025323672,0.00003659121],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00082733744,0.00015227638,0.00014208499,0.0003846398,0.0002840781,0.00046124292,0.0071090995,0.00013890394,0.000004423011],"category_scores_gemma":[0.0006915885,0.00015528734,0.000016363845,0.0006817625,0.000041392155,0.0029720925,0.0015213006,0.00060260436,0.000007715513],"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":[0.000018740073,0.000043667023,0.0000029331243,0.00008996377,0.000030980096,0.000012822574,0.00009605926,0.0010864564,0.002357146,0.000087271816,0.0024878904,0.9936861],"study_design_scores_gemma":[0.00029917908,0.00004937504,0.000005657585,0.0002021324,0.000011824939,0.00006012686,0.000086955086,0.99080664,0.0020546303,0.004101853,0.0021556923,0.00016594237],"about_ca_topic_score_codex":0.00014923188,"about_ca_topic_score_gemma":0.0010242923,"teacher_disagreement_score":0.99352014,"about_ca_system_score_codex":0.000062603,"about_ca_system_score_gemma":0.000077162455,"threshold_uncertainty_score":0.99826294},"labels":[],"label_agreement":null},{"id":"W4405907376","doi":"10.1109/tbdata.2024.3524101","title":"Is Split Learning Privacy-Preserving for Fine-Tuning Large Language Models?","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Privacy-Preserving Technologies in Data","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":"University of Toronto","funders":"","keywords":"Computer science; Theoretical computer science; Artificial intelligence","score_opus":0.11959491806294341,"score_gpt":0.32876354956127773,"score_spread":0.2091686314983343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405907376","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":[0.0013011575,0.00068841147,0.9786224,0.012720851,0.0015866476,0.00035293135,0.0018320788,0.002591894,0.00030366442],"genre_scores_gemma":[0.6640074,0.0002276071,0.33385867,0.00031397573,0.00018663383,0.0001093069,0.00027128684,0.00008026487,0.000944862],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99706763,0.0000732767,0.00036123657,0.0013823133,0.00043622,0.00067929947],"domain_scores_gemma":[0.98436546,0.0005474673,0.00006822328,0.014860384,0.00005671483,0.0001017554],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.00087796163,0.00030309023,0.00025278179,0.0004440884,0.00047231384,0.0007231233,0.034436915,0.00020201463,0.000058985017],"category_scores_gemma":[0.001245792,0.00030321765,0.00011775253,0.0009500045,0.000053859512,0.0027715927,0.0056929714,0.0008826884,0.00011657876],"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":[0.00003323573,0.0002228141,0.0000090506755,0.0004747637,0.0002740813,0.00010076437,0.0015791139,0.0034482633,0.0031192289,0.002003732,0.30463102,0.6841039],"study_design_scores_gemma":[0.00028130886,0.00006141958,0.0000030781032,0.00024156841,0.000033621094,0.000017821014,0.00008889732,0.93693674,0.006216363,0.015920352,0.039873324,0.00032549392],"about_ca_topic_score_codex":0.00008683578,"about_ca_topic_score_gemma":0.00007675761,"teacher_disagreement_score":0.9334885,"about_ca_system_score_codex":0.00009680548,"about_ca_system_score_gemma":0.00012724323,"threshold_uncertainty_score":0.999942},"labels":[],"label_agreement":null},{"id":"W4409077140","doi":"10.1109/tbdata.2025.3556615","title":"Utility-Driven Data Analytics Algorithm for Transaction Modifications Using Pre-Large Concept With Single Database Scan","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Software Testing and Debugging Techniques","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":"","keywords":"Computer science; Database transaction; Analytics; Database; Transaction processing; Data mining; Transaction data; Algorithm; Transaction log; Distributed transaction","score_opus":0.2046491776236223,"score_gpt":0.3506634177596448,"score_spread":0.14601424013602252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409077140","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":[0.000107626234,0.00005022339,0.98497474,0.00031057774,0.00058976223,0.0005964316,0.010885365,0.0024531959,0.00003209601],"genre_scores_gemma":[0.3086544,0.0000186274,0.6898686,0.00016071938,0.00005059634,0.000035601326,0.0010758628,0.000022267399,0.000113328584],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997641,0.000090264984,0.00037233654,0.0012057582,0.0003068527,0.00038377795],"domain_scores_gemma":[0.99332064,0.00046729975,0.00012413802,0.0057920762,0.0001869223,0.000108919274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044247496,0.00025536335,0.0002582278,0.00034249408,0.00070319884,0.00025700594,0.0030513944,0.00010435013,0.0000053397102],"category_scores_gemma":[0.00004692887,0.0002489482,0.00004835842,0.0010456811,0.00013696804,0.001323324,0.000044268607,0.0002852978,0.0000021073427],"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":[0.00005056488,0.0013643601,0.000028020726,0.0000733205,0.00021296713,0.00000517989,0.0002023866,0.004781262,0.00061803684,0.00016836644,0.009364096,0.9831314],"study_design_scores_gemma":[0.0005851764,0.00010330808,0.00003625224,0.00018233147,0.00019681585,0.000015423024,0.00001572079,0.99014896,0.0045056236,0.0003057851,0.0036404673,0.00026412762],"about_ca_topic_score_codex":0.00034771542,"about_ca_topic_score_gemma":0.00030613848,"teacher_disagreement_score":0.9853677,"about_ca_system_score_codex":0.00008550451,"about_ca_system_score_gemma":0.00041483247,"threshold_uncertainty_score":0.9999963},"labels":[],"label_agreement":null},{"id":"W4413822057","doi":"10.1109/tbdata.2025.3604171","title":"Optimizing Deduplication Parameters via a Change-Estimation Analytical Model","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Big Data","topic":"Innovation Diffusion and Forecasting","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 Alberta","funders":"","keywords":"Computer science; Data deduplication; Database","score_opus":0.44762231411228676,"score_gpt":0.4268905043208662,"score_spread":0.02073180979142053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413822057","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":[0.0077712187,0.000010511548,0.98719376,0.0023985493,0.00075846864,0.00027363512,0.00014539521,0.00009387067,0.0013545994],"genre_scores_gemma":[0.95603997,0.00000934485,0.040905263,0.0019155316,0.00003232507,0.00005161007,0.00007216373,0.0000105513345,0.0009632309],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976404,0.00007727741,0.0006630519,0.00068436004,0.0007089798,0.00022593765],"domain_scores_gemma":[0.99741894,0.0004675943,0.00016174608,0.001612119,0.00026352477,0.00007604848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013545561,0.00015596602,0.00020768616,0.00088329025,0.0003811737,0.00025052682,0.0009893752,0.00011546704,0.00007514007],"category_scores_gemma":[0.00028704014,0.00013414318,0.00006977136,0.0021679075,0.00008494111,0.0007057516,0.00001658114,0.00024397604,0.00019677692],"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":[0.00004141173,0.00012825905,0.0000116393785,0.0000043279506,0.000017753626,6.6097243e-7,0.00015326728,0.11652926,0.00028610684,0.0006486933,0.002225855,0.8799528],"study_design_scores_gemma":[0.00027504523,0.00001793653,0.00008795336,0.000032566742,0.00003254213,0.0000028194486,0.00007173175,0.99415743,0.001138407,0.0030393647,0.0010184873,0.00012569639],"about_ca_topic_score_codex":0.00003545482,"about_ca_topic_score_gemma":0.000049013157,"teacher_disagreement_score":0.9482688,"about_ca_system_score_codex":0.00006677178,"about_ca_system_score_gemma":0.00008963251,"threshold_uncertainty_score":0.54702},"labels":[],"label_agreement":null},{"id":"W4417002497","doi":"10.1109/tbdata.2025.3639977","title":"TrustChain: A Blockchain Framework for Auditing and Verifying Aggregators in Decentralized Federated Learning","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Big Data","topic":"Privacy-Preserving Technologies in Data","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":"University of New Brunswick; University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"News aggregator; Node (physics); Trust management (information system); Audit; Independence (probability theory); Federated learning; Anomaly detection; Scheme (mathematics)","score_opus":0.08314352619012509,"score_gpt":0.3241899130853899,"score_spread":0.2410463868952648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417002497","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":[0.016663123,0.0013146575,0.95813704,0.017796272,0.003551343,0.001097974,0.0007438478,0.0006676079,0.000028141016],"genre_scores_gemma":[0.79595876,0.0021505267,0.20116173,0.000362859,0.000060808754,0.000133156,0.000057366447,0.000048251433,0.000066569104],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.994582,0.00042482186,0.001021249,0.002307969,0.00042836345,0.0012356121],"domain_scores_gemma":[0.9876431,0.0024524657,0.00037242976,0.009238048,0.00011851803,0.00017544067],"candidate_categories":["metaresearch","metaepi_narrow","sts","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0017611608,0.0006234743,0.00072882156,0.0010601797,0.0015026064,0.0010318398,0.018082442,0.0007739084,0.000021453405],"category_scores_gemma":[0.015351194,0.0007340793,0.00010833694,0.0030322496,0.000349779,0.0007420806,0.00339392,0.0023558787,0.000007911974],"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":[0.0002633409,0.00032172736,0.00021836165,0.00036301633,0.00023898217,0.000042334857,0.00029027727,0.0029626363,0.0002903505,0.00063376635,0.002799342,0.99157584],"study_design_scores_gemma":[0.002237435,0.00016087823,0.000077896104,0.0030182377,0.000103640705,0.000015301493,0.0003882642,0.9578,0.0064893872,0.025145443,0.0038904306,0.00067310786],"about_ca_topic_score_codex":0.00024243702,"about_ca_topic_score_gemma":0.0004913508,"teacher_disagreement_score":0.9909028,"about_ca_system_score_codex":0.00033460034,"about_ca_system_score_gemma":0.00049227016,"threshold_uncertainty_score":0.9999457},"labels":[],"label_agreement":null},{"id":"W4417002646","doi":"10.1109/tbdata.2025.3639954","title":"Dual-Channel Learning Framework for miRNA-Drug Interaction Prediction Based on Structural Features and Signed Bipartite Graph Neural Network","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Big Data","topic":"Computational Drug Discovery Methods","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 Saskatchewan","funders":"Fundamental Research Funds for the Central Universities; Shaanxi Normal University; National Natural Science Foundation of China","keywords":"Bipartite graph; Graph isomorphism; Graph; Artificial neural network; Biological network; Convolutional neural network; Complex network; Matching (statistics); Sequence (biology)","score_opus":0.06206073388846581,"score_gpt":0.3363125870963738,"score_spread":0.274251853207908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417002646","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":[0.011687749,0.0003257011,0.96284866,0.0034210228,0.019154258,0.001142359,0.0011246566,0.00026005536,0.00003552314],"genre_scores_gemma":[0.9597771,0.00010019842,0.037642583,0.0009738683,0.0007665976,0.0001232518,0.00030757923,0.00004990766,0.0002589064],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9948777,0.0010214986,0.0007928578,0.0019081732,0.00066021294,0.00073953456],"domain_scores_gemma":[0.9932493,0.004279797,0.0003574958,0.0016599882,0.00022497913,0.00022845162],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0011370543,0.00065776496,0.00052905944,0.0008501476,0.0017289971,0.0010015441,0.0010143549,0.00031161815,0.000019300542],"category_scores_gemma":[0.00019338487,0.0006953419,0.00025962444,0.0018272789,0.00020936286,0.0015625833,0.000054478758,0.00162908,0.000005680626],"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":[0.00097085745,0.00014499814,0.000023964829,0.0001132117,0.00016266048,0.0000048593706,0.00028171472,0.8151636,0.000060668084,0.0007991281,0.0015659168,0.18070842],"study_design_scores_gemma":[0.0012384935,0.0005248897,0.002085977,0.0008589408,0.00025807746,0.000022677446,0.00008108432,0.98191506,0.0010044212,0.01063393,0.00088269974,0.00049374055],"about_ca_topic_score_codex":0.00009973151,"about_ca_topic_score_gemma":0.0001346083,"teacher_disagreement_score":0.94808936,"about_ca_system_score_codex":0.0001736208,"about_ca_system_score_gemma":0.00027628828,"threshold_uncertainty_score":0.9995706},"labels":[],"label_agreement":null}]}