{"meta":{"query_hash":"b933c51cc8d0","filters":{"venue":"Journal Of Big Data"},"cohort_total":29,"direct_labels_cover":0,"predictions_cover":29,"exported":29,"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/b933c51cc8d0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Journal+Of+Big+Data"},"results":[{"id":"W1623534659","doi":"10.1186/s40537-015-0021-4","title":"Meta-MapReduce for scalable data mining","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Machine Learning and Data Classification","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 Ottawa; Dalhousie University","funders":"","keywords":"Computer science; Scalability; Big data; AdaBoost; Machine learning; Node (physics); Programming paradigm; Cloud computing; Artificial intelligence; Data mining; Database; Programming language; Operating system; Support vector machine","score_opus":0.6436468009513665,"score_gpt":0.3948568341215879,"score_spread":0.2487899668297786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1623534659","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":[0.00064095034,0.0013962283,0.9891389,0.0067795245,0.0011390737,0.000065528155,0.00033874984,0.000024147079,0.000476882],"genre_scores_gemma":[0.09742723,0.00006890715,0.8990729,0.00037807095,0.0013848353,0.000002344654,0.0010993093,0.000015064154,0.00055136933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987145,0.00009397454,0.0003736098,0.00030873032,0.00035942343,0.00014972982],"domain_scores_gemma":[0.9959646,0.000196579,0.00046057635,0.0030052331,0.00021268181,0.00016033613],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0037175529,0.000083217135,0.00023165019,0.00010149809,0.00006249354,0.000255979,0.006078374,0.00003282447,0.000004188959],"category_scores_gemma":[0.0015733702,0.000060435952,0.000036078898,0.00019607916,0.000015541416,0.0022884936,0.0016116712,0.00014108088,0.0000137457355],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029612029,0.00009486675,0.00030786364,0.00001900053,0.00039894143,0.000010414199,0.00017387293,0.00010305227,0.00019261532,0.00072811765,0.6457739,0.35216776],"study_design_scores_gemma":[0.00049293274,0.00010814917,0.00021247288,0.000016751876,0.0003094492,0.00012481534,0.00005063772,0.21550053,0.00007421103,0.00046065362,0.78254974,0.00009965597],"about_ca_topic_score_codex":0.000019128816,"about_ca_topic_score_gemma":0.000008452446,"teacher_disagreement_score":0.3520681,"about_ca_system_score_codex":0.000016109721,"about_ca_system_score_gemma":0.000311215,"threshold_uncertainty_score":0.9992992},"labels":[],"label_agreement":null},{"id":"W2132987460","doi":"10.1186/s40537-014-0011-y","title":"Contextual anomaly detection framework for big sensor data","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Anomaly Detection Techniques and Applications","field":"Computer Science","cited_by":141,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Anomaly detection; Context (archaeology); Toolbox; Data mining; Detector; Cluster analysis; Task (project management); False positive paradox; Anomaly (physics); Volume (thermodynamics); Big data; Process (computing); Content (measure theory); Artificial intelligence; Machine learning; Pattern recognition (psychology)","score_opus":0.2992592294446529,"score_gpt":0.3639286034466015,"score_spread":0.06466937400194861,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2132987460","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":[0.0018064053,0.00016941299,0.9949761,0.0013932035,0.0011647812,0.00014703354,0.00019545968,0.000062293,0.00008528905],"genre_scores_gemma":[0.5638476,0.000055612392,0.43325475,0.00034477064,0.0023403766,0.0000060823504,0.000042849733,0.000013224968,0.000094739546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998812,0.00004149844,0.00041279875,0.00031028708,0.00026704965,0.00015636208],"domain_scores_gemma":[0.9966733,0.00015341755,0.00045581278,0.002237383,0.00031591207,0.00016416825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010827829,0.00009640427,0.00017771042,0.00012903556,0.00010679373,0.00017686811,0.0032898379,0.00009120114,0.0000014790382],"category_scores_gemma":[0.0005621223,0.00008166174,0.000043587923,0.00031398048,0.00003579898,0.00088165235,0.0009480381,0.00022551793,0.0000121269595],"study_design_candidate":"not_applicable","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":[0.0000596751,0.00011507964,0.00009564529,0.000009381334,0.00005352578,0.000009450145,0.000086048894,0.000008339404,0.0013619355,0.0042735925,0.038577374,0.9553499],"study_design_scores_gemma":[0.0007531003,0.000668313,0.00037809362,0.00005234512,0.00005685269,0.00056889903,0.00018206604,0.03737661,0.00660379,0.019777065,0.9333214,0.00026144797],"about_ca_topic_score_codex":0.000024262356,"about_ca_topic_score_gemma":0.00002729499,"teacher_disagreement_score":0.9550885,"about_ca_system_score_codex":0.000038641476,"about_ca_system_score_gemma":0.00017972337,"threshold_uncertainty_score":0.6113392},"labels":[],"label_agreement":null},{"id":"W2772611570","doi":"10.1186/s40537-017-0106-3","title":"A computing platform for pairs-trading online implementation via a blended Kalman-HMM filtering approach","year":2017,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Complex Systems and Time Series Analysis","field":"Economics, Econometrics and Finance","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":"Western University; TD Bank Group","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Trading strategy; Kalman filter; Hidden Markov model; Pairs trade; Algorithmic trading; Analytics; High-frequency trading; Big data; Herding; Algorithm; Machine learning; Data mining; Artificial intelligence; Econometrics; Finance; Economics","score_opus":0.27014718466711596,"score_gpt":0.3335862340197416,"score_spread":0.06343904935262562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2772611570","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":[0.18125822,0.001213818,0.8108064,0.0005690284,0.0013609015,0.00036470848,0.0022642403,0.000015933003,0.0021467607],"genre_scores_gemma":[0.97032577,0.000050100156,0.028119542,0.00003139781,0.0010943663,0.0000013789326,0.00028228262,0.000018065804,0.00007711853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99846506,0.000005865154,0.0010063673,0.00024482518,0.00005774358,0.00022014098],"domain_scores_gemma":[0.99697506,0.000041776362,0.0020883502,0.0007648104,0.000058619975,0.000071388415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011620586,0.00011705886,0.00048548836,0.00020804505,0.00040004536,0.00029343698,0.0009197896,0.000039314113,0.00007701941],"category_scores_gemma":[0.00009964001,0.00011856983,0.00016236406,0.00006654785,0.00002131602,0.00076932774,0.00031141395,0.00011665435,0.000004141941],"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":[0.00028600442,0.00065842376,0.062052663,0.0008117637,0.002993648,0.00003829732,0.0020744728,0.00058323296,0.0006777697,0.021527966,0.020039147,0.8882566],"study_design_scores_gemma":[0.0036393257,0.00033795307,0.03146231,0.0001393957,0.00015003463,0.00018124859,0.0017047955,0.7893321,0.00006195786,0.007866446,0.16457786,0.00054657],"about_ca_topic_score_codex":0.00044732046,"about_ca_topic_score_gemma":0.00021346592,"teacher_disagreement_score":0.88771003,"about_ca_system_score_codex":0.00006436256,"about_ca_system_score_gemma":0.000025735946,"threshold_uncertainty_score":0.4835137},"labels":[],"label_agreement":null},{"id":"W2806417635","doi":"10.1186/s40537-018-0128-5","title":"A non-parametric maximum for number of selected features: objective optima for FDR and significance threshold with application to ordinal survey analysis","year":2018,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Advanced Statistical Methods and Models","field":"Mathematics","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":"Capilano University; Simon Fraser University","funders":"","keywords":"False discovery rate; Statistical hypothesis testing; Mathematics; False positives and false negatives; Statistics; Multiple comparisons problem; Parametric statistics; Ordinal data; False positive paradox; Computer science; Nonparametric statistics; Set (abstract data type); Data mining; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.16021114342389361,"score_gpt":0.44617616919924197,"score_spread":0.2859650257753483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806417635","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":[0.029768813,0.00002140995,0.9679906,0.00003776098,0.000032806707,0.0005629644,0.0015467142,0.000003600187,0.00003536273],"genre_scores_gemma":[0.35016906,0.000006719081,0.64960825,0.0000174213,0.00009274998,0.000019414034,0.000044109303,0.0000128050615,0.000029479947],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988946,0.000046085595,0.00040473932,0.00026654845,0.00021580009,0.00017225856],"domain_scores_gemma":[0.995625,0.0019000806,0.00052417244,0.0004257991,0.001413987,0.00011095179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012937769,0.000121785204,0.00051454426,0.0001974823,0.00006273317,0.000025153882,0.00030413084,0.000054943,0.0000032473156],"category_scores_gemma":[0.0026712725,0.00008662682,0.000045961457,0.0011963159,0.00006837662,0.00013427714,0.00006238055,0.00010128356,2.8167062e-7],"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":[0.077546656,0.0055066915,0.08509144,0.003740457,0.023726279,0.000033140765,0.0036761456,0.004047901,0.029820472,0.048390903,0.0778136,0.64060634],"study_design_scores_gemma":[0.010455052,0.010370361,0.12808764,0.00050466886,0.009742493,0.00021017515,0.0006484392,0.18942414,0.015170138,0.631594,0.002210553,0.0015823669],"about_ca_topic_score_codex":0.00003569887,"about_ca_topic_score_gemma":0.0002474695,"teacher_disagreement_score":0.63902396,"about_ca_system_score_codex":0.00003106191,"about_ca_system_score_gemma":0.00009884604,"threshold_uncertainty_score":0.3532539},"labels":[],"label_agreement":null},{"id":"W2947950257","doi":"10.1186/s40537-019-0203-6","title":"Detecting taxi movements using Random Swap clustering and sequential pattern mining","year":2019,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Management and Algorithms","field":"Computer Science","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":"Carleton University","funders":"Carleton University","keywords":"Cluster analysis; Computer science; Swap (finance); Silhouette; Data mining; Hierarchical clustering; k-means clustering; Artificial intelligence","score_opus":0.11508057947702388,"score_gpt":0.29573302343564384,"score_spread":0.18065244395861996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947950257","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":[0.2708989,0.0000849652,0.72735035,0.00007053907,0.001439163,0.00006114107,0.000014072827,0.0000089458135,0.000071899005],"genre_scores_gemma":[0.92748106,0.00006223134,0.07140731,0.00025774213,0.0006802068,2.4333292e-7,0.000012569195,0.000012948288,0.00008570193],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988453,0.000047207763,0.00035384594,0.00023874498,0.00032227527,0.00019267043],"domain_scores_gemma":[0.9988481,0.00004857783,0.0003928476,0.0006069253,0.00003873906,0.00006482734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010196017,0.00009883478,0.000188282,0.00015216506,0.000078183264,0.00048096292,0.0014032668,0.00002297217,0.000007898645],"category_scores_gemma":[0.000042460437,0.000085810236,0.000029316592,0.00012915203,0.000011682218,0.0022392706,0.0024856876,0.00012558844,0.0000048757133],"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":[0.000023189643,0.000024190422,0.0056693503,0.00005767358,0.00011385714,0.000120335404,0.0002571719,0.00027823643,0.0062273038,0.0000044795556,0.0002517714,0.98697245],"study_design_scores_gemma":[0.0031672013,0.000096570315,0.00099652,0.00029499453,0.000037152866,0.0001578616,0.00018174884,0.989181,0.0004930212,0.00006328124,0.0051181586,0.00021251325],"about_ca_topic_score_codex":0.00003367235,"about_ca_topic_score_gemma":0.000008340235,"teacher_disagreement_score":0.98890275,"about_ca_system_score_codex":0.000021019156,"about_ca_system_score_gemma":0.000026390584,"threshold_uncertainty_score":0.46379364},"labels":[],"label_agreement":null},{"id":"W2952066860","doi":"10.1186/s40537-019-0218-z","title":"STVG: an evolutionary graph framework for analyzing fast-evolving networks","year":2019,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":12,"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; Tertiary Education Trust Fund; Cisco Systems","keywords":"Computer science; Theoretical computer science; Graph; Snapshot (computer storage); Graph database; Database","score_opus":0.0752406044275541,"score_gpt":0.3422732496091298,"score_spread":0.2670326451815757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952066860","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":[0.024601365,0.0009017043,0.9714366,0.0006795396,0.0018232219,0.00013120851,0.00008274918,0.000023505467,0.00032007345],"genre_scores_gemma":[0.91752076,0.00024493845,0.08044328,0.00008616572,0.0013277322,6.5263106e-7,0.00025330854,0.000009633359,0.00011353162],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990853,0.000075254306,0.00028027184,0.00012827196,0.00026701705,0.00016388886],"domain_scores_gemma":[0.99887395,0.00022851264,0.00032780558,0.00023170617,0.0002368114,0.00010124334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010446877,0.000057293582,0.00013166512,0.00011945174,0.0002466196,0.00008437791,0.00047910013,0.00009844081,0.00005838626],"category_scores_gemma":[0.00024835984,0.000053829106,0.000051398903,0.0002814386,0.000036145608,0.00096724596,0.000014264556,0.00018223783,0.0000022529202],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031491034,0.0002561891,0.49368018,0.000050338243,0.0002532807,0.000017592396,0.01155723,0.36862954,0.000045314886,0.024182092,0.026793066,0.074220255],"study_design_scores_gemma":[0.0031343428,0.0010011684,0.4360406,0.0016290649,0.0006579864,0.000027818109,0.023168007,0.29133865,0.000009872745,0.035936344,0.20580019,0.0012559306],"about_ca_topic_score_codex":0.000047159778,"about_ca_topic_score_gemma":0.00012944837,"teacher_disagreement_score":0.8929194,"about_ca_system_score_codex":0.000027289972,"about_ca_system_score_gemma":0.0001516346,"threshold_uncertainty_score":0.21950872},"labels":[],"label_agreement":null},{"id":"W3022470673","doi":"10.1186/s40537-020-00302-z","title":"Leveraging machine learning and big data for optimizing medication prescriptions in complex diseases: a case study in diabetes management","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Diabetes, Cardiovascular Risks, and Lipoproteins","field":"Medicine","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":"McMaster University; Toronto Metropolitan University","funders":"","keywords":"Computer science; Bayesian network; Big data; Machine learning; Medical prescription; Variable (mathematics); Artificial intelligence; Bayesian probability; Data mining; Medicine; Mathematics","score_opus":0.2050337070575335,"score_gpt":0.3363276992871178,"score_spread":0.13129399222958432,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022470673","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":[0.9747171,0.008536033,0.011545872,0.002707196,0.0002610031,0.0016170384,0.0005516615,0.000023807519,0.000040326806],"genre_scores_gemma":[0.99323994,0.0006394335,0.0044189207,0.00020472604,0.0005493708,0.000014532716,0.0009054556,0.000020619325,0.000007007467],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99843335,0.00015476026,0.0005257669,0.00034406493,0.0003473512,0.00019470567],"domain_scores_gemma":[0.9987989,0.000085965265,0.00020225835,0.0006750652,0.000045970217,0.00019184477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00141531,0.00012363776,0.00047138566,0.00026704994,0.00007466472,0.00006214757,0.00039739805,0.00002644478,0.0000064377964],"category_scores_gemma":[0.0006516185,0.00010796629,0.000051019008,0.00023971709,0.00003269713,0.00033262448,0.00068613526,0.00030539584,4.6942426e-7],"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":[0.0001744823,0.00064612756,0.13639145,0.0006564864,0.00084823725,0.0027704614,0.0016144013,0.00028771354,0.00006160369,0.0000010111887,0.0017557624,0.8547923],"study_design_scores_gemma":[0.03309386,0.0018058169,0.43923813,0.0017767971,0.0046988125,0.0009509247,0.034466576,0.3481633,0.00001663446,0.000051745177,0.13508715,0.0006502432],"about_ca_topic_score_codex":0.00074188435,"about_ca_topic_score_gemma":0.0005468224,"teacher_disagreement_score":0.854142,"about_ca_system_score_codex":0.000041446354,"about_ca_system_score_gemma":0.000056966655,"threshold_uncertainty_score":0.44027376},"labels":[],"label_agreement":null},{"id":"W3044719873","doi":"10.1186/s40537-020-00329-2","title":"Predictive big data analytics for supply chain demand forecasting: methods, applications, and research opportunities","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":469,"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":"Supply chain; Computer science; Predictive analytics; Demand forecasting; Supply chain management; Big data; Time series; Data science; Cluster analysis; Analytics; Support vector machine; Data mining; Machine learning; Operations research; Business; Engineering; Marketing","score_opus":0.9012087118397553,"score_gpt":0.5583508521736629,"score_spread":0.3428578596660924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044719873","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":[0.000530767,0.00093895034,0.9774029,0.015919656,0.0001128644,0.000574723,0.0041509075,0.000020911653,0.0003482964],"genre_scores_gemma":[0.18184099,0.0019636753,0.8101884,0.00069101853,0.0038243567,0.00007495681,0.000920751,0.000049444647,0.0004463969],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99668,0.0003475473,0.001050819,0.0005856419,0.001069129,0.0002668403],"domain_scores_gemma":[0.9908983,0.0044870437,0.0008129843,0.0021118831,0.0013217188,0.00036806465],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019598832,0.0001278355,0.00037815783,0.0003718391,0.00036350838,0.00040990635,0.004382971,0.00008413363,0.000011676727],"category_scores_gemma":[0.01322569,0.00009391445,0.000049643204,0.000928517,0.0003030689,0.00055718306,0.0026057328,0.0003937353,0.0000025664858],"study_design_candidate":"not_applicable","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":[0.00007591935,0.000043176908,0.00034520516,0.00002215181,0.00004262139,0.0000047839344,0.00017826614,0.000012068309,0.00014902146,0.0012421723,0.31750533,0.6803793],"study_design_scores_gemma":[0.0002673469,0.00029019846,0.00012359966,0.000042403815,0.00006646565,0.00007803121,0.0016543969,0.1779857,0.00018626895,0.036042374,0.78315914,0.00010409101],"about_ca_topic_score_codex":0.000012551626,"about_ca_topic_score_gemma":0.000013948242,"teacher_disagreement_score":0.6802752,"about_ca_system_score_codex":0.000021378879,"about_ca_system_score_gemma":0.0003787256,"threshold_uncertainty_score":0.9950863},"labels":[],"label_agreement":null},{"id":"W3081491601","doi":"10.1186/s40537-020-00345-2","title":"Prediction of probable backorder scenarios in the supply chain using Distributed Random Forest and Gradient Boosting Machine learning techniques","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":160,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Gradient boosting; Random forest; Computer science; Boosting (machine learning); Decision tree; Machine learning; CLARITY; Artificial intelligence; Flexibility (engineering); Metric (unit); Supply chain; Tree (set theory); Business process; Process (computing); Data mining; Work in process; Statistics; Mathematics; Operations management; Engineering","score_opus":0.30504179187817343,"score_gpt":0.3606107987158744,"score_spread":0.055569006837700996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081491601","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":[0.561535,0.00065572205,0.4282517,0.008192865,0.000071181625,0.00066968764,0.0005062061,0.00003812973,0.000079504054],"genre_scores_gemma":[0.97504187,0.00007963185,0.024637122,0.00007014467,0.0001107169,0.000002617494,0.00004949805,0.0000058305714,0.0000025427814],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998268,0.00016833308,0.0007583998,0.00018264768,0.00050469127,0.000117905205],"domain_scores_gemma":[0.9982546,0.0004549752,0.0007086334,0.00035683985,0.00017794356,0.000047019083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041824095,0.00007924357,0.00023379805,0.00012140561,0.00012468919,0.00011117926,0.0009860735,0.0000397294,0.000005303412],"category_scores_gemma":[0.004246899,0.00004668433,0.000037433103,0.0006400753,0.0000718886,0.0002817745,0.00041323606,0.00030922896,2.8523473e-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":[0.0007029925,0.00035446422,0.76888615,0.000088925604,0.000060013765,0.00004855553,0.0032786077,0.0077063274,0.013536491,0.00045016987,0.024156997,0.18073031],"study_design_scores_gemma":[0.0015969429,0.00068135466,0.013614653,0.000581023,0.00007774661,0.00040612114,0.0013762822,0.9230399,0.001002193,0.0059757945,0.051469445,0.00017850856],"about_ca_topic_score_codex":0.000049564587,"about_ca_topic_score_gemma":0.00008504075,"teacher_disagreement_score":0.9153336,"about_ca_system_score_codex":0.000017949764,"about_ca_system_score_gemma":0.000051366562,"threshold_uncertainty_score":0.50842416},"labels":[],"label_agreement":null},{"id":"W3081799531","doi":"10.1186/s40537-020-00333-6","title":"Short-term stock market price trend prediction using a comprehensive deep learning system","year":2020,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":370,"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; Carleton University","keywords":"Feature engineering; Computer science; Stock market; Stock (firearms); Artificial intelligence; Deep learning; Machine learning; Big data; Personalization; Stock market prediction; Econometrics; Data mining; Economics; World Wide Web","score_opus":0.4401202832170943,"score_gpt":0.4249298837676808,"score_spread":0.015190399449413472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081799531","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":[0.4757818,0.00083596027,0.5160824,0.0003225169,0.0031835278,0.0002608979,0.00019376352,0.00007026929,0.0032688517],"genre_scores_gemma":[0.95920694,0.00002389375,0.038670514,0.00007690216,0.0018850494,7.604288e-7,0.000015013566,0.000030376492,0.0000905307],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99411565,0.0015606388,0.0015089887,0.0005179005,0.0020041713,0.00029267572],"domain_scores_gemma":[0.99407643,0.0028049962,0.001385511,0.00081562105,0.0005627522,0.00035469636],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0063652643,0.00020156655,0.0006193729,0.00038195547,0.00023907585,0.00035965908,0.002067556,0.00010218031,0.00010814701],"category_scores_gemma":[0.009888594,0.0001526508,0.00014924456,0.0010860615,0.000066671055,0.00088958064,0.0009625956,0.000651199,0.000011887475],"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":[0.00097015186,0.000057436555,0.06892932,0.00011641566,0.00024104354,0.00039757407,0.0012769096,0.0034755445,0.00474613,0.000007092907,0.022146415,0.897636],"study_design_scores_gemma":[0.0010200324,0.00052499666,0.1422325,0.00040701267,0.000267209,0.0026627064,0.0037513417,0.8005726,0.00006941627,0.0000536754,0.04812706,0.00031147714],"about_ca_topic_score_codex":0.0000030705446,"about_ca_topic_score_gemma":0.0000030090723,"teacher_disagreement_score":0.8973245,"about_ca_system_score_codex":0.00012651112,"about_ca_system_score_gemma":0.00012472447,"threshold_uncertainty_score":0.99845153},"labels":[],"label_agreement":null},{"id":"W3124386847","doi":"10.1186/s40537-021-00418-w","title":"CaReAl: capturing read alignments in a BAM file rapidly and conveniently","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","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":"Princess Margaret Cancer Centre; University Health Network","funders":"National Institute of Food and Drug Safety Evaluation; Ministry of Food and Drug Safety","keywords":"Computer science; Snapshot (computer storage); Visualization; Multithreading; Data mining; Database; Operating system; Thread (computing)","score_opus":0.053662873558947666,"score_gpt":0.26752129902605437,"score_spread":0.2138584254671067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124386847","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":[0.9886786,0.00966638,0.000037647656,0.00019104962,0.0002810096,0.000033183267,0.0007031975,2.8923117e-7,0.00040866254],"genre_scores_gemma":[0.9955238,0.0029922754,0.00072514324,0.00014691889,0.00025739524,8.1153956e-7,0.00021426045,0.0000073949973,0.00013199127],"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994155,0.000032101536,0.00020811961,0.00015724186,0.0000792935,0.00010774823],"domain_scores_gemma":[0.9994773,0.000013684212,0.000106604784,0.00029000832,0.00006221776,0.000050139915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015947287,0.00006744526,0.00013189061,0.00002649234,0.000022804406,0.000017302651,0.00017767341,0.000042499058,0.000018910092],"category_scores_gemma":[0.00010525865,0.000061085935,0.000024891975,0.000036262714,0.000025264342,0.0000013987988,0.0003785183,0.000057625643,6.139813e-7],"study_design_candidate":"bench_or_experimental","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":[0.00013092904,0.00016005732,0.037585203,0.000055521556,0.00038534284,0.00032218237,0.00046197578,0.000034934666,0.8627143,0.0000096434105,0.0518727,0.046267238],"study_design_scores_gemma":[0.0031302506,0.00044314028,0.14273691,0.00017895967,0.000102473576,0.00084270973,0.0016263822,0.000053241773,0.09826853,0.00021997806,0.75199634,0.00040110812],"about_ca_topic_score_codex":0.000028808694,"about_ca_topic_score_gemma":0.00013139368,"teacher_disagreement_score":0.7644457,"about_ca_system_score_codex":0.000006799028,"about_ca_system_score_gemma":0.000081822,"threshold_uncertainty_score":0.24910122},"labels":[],"label_agreement":null},{"id":"W3155713909","doi":"10.1186/s40537-021-00455-5","title":"Domain randomization for neural network classification","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":26,"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":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Classifier (UML); Convolutional neural network; Artificial intelligence; Artificial neural network; Task (project management); Domain (mathematical analysis); Machine learning; Pattern recognition (psychology); Randomization; Transfer of learning; Contextual image classification; Data mining; Image (mathematics); Clinical trial; Mathematics","score_opus":0.1690613487970136,"score_gpt":0.3181836121059016,"score_spread":0.14912226330888803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155713909","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":[0.0013892449,0.00036247764,0.9932162,0.0033050154,0.0013348574,0.00006267464,0.00000498754,0.0000119197875,0.00031261166],"genre_scores_gemma":[0.33018556,0.00018069558,0.6652441,0.001406144,0.0024164228,0.0000032746243,0.00018525918,0.000014722759,0.00036381226],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901307,0.00014565061,0.0003527363,0.00015175552,0.00021589804,0.000120905366],"domain_scores_gemma":[0.9986113,0.00022835728,0.00038415665,0.0004685621,0.0002446559,0.00006302131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011716736,0.000054728112,0.00013899856,0.00004913981,0.00010324691,0.000199287,0.0007284728,0.000031161864,0.000007225144],"category_scores_gemma":[0.00030851306,0.00004779249,0.000052403186,0.00028022027,0.000012258525,0.00068952667,0.00014371471,0.000107256776,0.0000037914338],"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":[0.00043662498,0.00013088566,0.0007098176,0.0000301809,0.00010639542,0.00006532065,0.0006522614,0.023371305,0.0039631226,0.06726897,0.08308787,0.82017726],"study_design_scores_gemma":[0.0050313286,0.00006874519,0.0034015898,0.000043621174,0.000025332594,0.00019988812,0.00014474503,0.49871987,0.00008972841,0.0066623227,0.4854831,0.00012969956],"about_ca_topic_score_codex":3.6046234e-7,"about_ca_topic_score_gemma":0.0000032054854,"teacher_disagreement_score":0.82004756,"about_ca_system_score_codex":0.000018104718,"about_ca_system_score_gemma":0.00014267428,"threshold_uncertainty_score":0.19489212},"labels":[],"label_agreement":null},{"id":"W3162192441","doi":"10.1186/s40537-021-00539-2","title":"Integration of image segmentation and fuzzy theory to improve the accuracy of damage detection areas in traffic accidents","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Industrial Vision Systems and Defect Detection","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 Calgary","funders":"","keywords":"Machine vision; Computer science; Process (computing); Field (mathematics); Artificial intelligence; Fuzzy logic; Segmentation; Image processing; Computer vision; Machine learning; Image (mathematics)","score_opus":0.04525610434908552,"score_gpt":0.29229943292188365,"score_spread":0.24704332857279812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162192441","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":[0.98118705,0.00013774798,0.01769603,0.000021690012,0.0007562448,0.000121859666,0.0000310109,0.000004435761,0.000043962373],"genre_scores_gemma":[0.99949133,0.00007237541,0.00024221452,0.0000062025874,0.00016369512,0.0000013183005,0.000008941298,0.0000072886464,0.0000066117145],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991015,0.00011724193,0.0004744474,0.000075523705,0.0001719561,0.00005930476],"domain_scores_gemma":[0.9992156,0.00015552323,0.00023393372,0.00023635068,0.00013150914,0.00002706752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009911434,0.000062662926,0.00015741179,0.00015403728,0.000028541415,0.000030493957,0.0001272222,0.00005250784,0.0000050732338],"category_scores_gemma":[0.0006186928,0.000045120705,0.000029820678,0.00026583718,0.000010583487,0.00042043402,0.00006348621,0.00016446461,6.7423923e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078223384,0.000014709469,0.000050620845,0.000027944136,0.000021691312,0.0000037923055,0.0005151375,0.0009081808,0.669711,0.0000032767705,0.0000778398,0.32858762],"study_design_scores_gemma":[0.0015275507,0.0002828808,0.025145393,0.00045084226,0.00007751134,0.00011327742,0.00516154,0.008226726,0.95832604,0.00019252411,0.00036739337,0.00012830048],"about_ca_topic_score_codex":0.000026502776,"about_ca_topic_score_gemma":0.00016318334,"teacher_disagreement_score":0.3284593,"about_ca_system_score_codex":0.000038075104,"about_ca_system_score_gemma":0.00002849735,"threshold_uncertainty_score":0.18399689},"labels":[],"label_agreement":null},{"id":"W3169194364","doi":"10.1186/s40537-021-00504-z","title":"The LRA Workbench: an IDE for efficient REST API composition through linked metadata","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","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":"Athabasca University; University of Alberta","funders":"","keywords":"Computer science; Workbench; Algorithm; Metadata; Database; Data mining; World Wide Web","score_opus":0.11870621425021255,"score_gpt":0.32371307929150894,"score_spread":0.2050068650412964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169194364","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":[0.038335524,0.0036318828,0.94104046,0.013656078,0.0027108185,0.00018712525,0.0001664755,0.000033420733,0.00023824102],"genre_scores_gemma":[0.6893101,0.0008349589,0.29609206,0.008859466,0.0039012602,0.000008131931,0.00087035727,0.000040239694,0.00008349084],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982012,0.00018561218,0.00050258473,0.0003505888,0.0004947088,0.00026529282],"domain_scores_gemma":[0.99655145,0.00048390313,0.0004175555,0.0020631813,0.0003700505,0.00011385247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00100118,0.00013452231,0.00021839388,0.000057719815,0.00039531675,0.00072406424,0.0039424635,0.000050708983,0.0000023859207],"category_scores_gemma":[0.000052739084,0.00008594119,0.000084891864,0.0004811646,0.000033205833,0.0013823643,0.0010916909,0.00026555776,0.000003819845],"study_design_candidate":"not_applicable","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":[0.0010705406,0.0029535661,0.00037882983,0.00040239337,0.0016957197,0.0010101679,0.015285598,0.012907648,0.07668114,0.16018797,0.03481932,0.6926071],"study_design_scores_gemma":[0.003412014,0.0008679042,0.004275101,0.0006277585,0.00040520166,0.0015238682,0.0021163893,0.13707246,0.019856192,0.024257632,0.8048335,0.0007519784],"about_ca_topic_score_codex":0.000028658613,"about_ca_topic_score_gemma":0.0002598479,"teacher_disagreement_score":0.77001417,"about_ca_system_score_codex":0.000020678279,"about_ca_system_score_gemma":0.00021233033,"threshold_uncertainty_score":0.7326144},"labels":[],"label_agreement":null},{"id":"W3181834696","doi":"10.1186/s40537-021-00489-9","title":"Examining the impact of cross-domain learning on crime prediction","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Crime Patterns and Interventions","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Memorial University of Newfoundland; Dalhousie University","keywords":"Computer science; Generalization; Perspective (graphical); Domain (mathematical analysis); Transfer of learning; Data science; Domain knowledge; Task (project management); Machine learning; Baseline (sea); Crime analysis; Demographics; Artificial intelligence; Subject-matter expert; Data mining; Expert system","score_opus":0.34207003076943,"score_gpt":0.4718022365358112,"score_spread":0.12973220576638123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3181834696","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":[0.9875492,0.0002296683,0.0009099895,0.00028044565,0.00053520413,0.000025847496,0.00008560921,0.000003960343,0.010380094],"genre_scores_gemma":[0.99851424,0.00010105775,0.00005706086,0.000014915528,0.0006879074,1.6834993e-7,0.000015082075,0.0000038584963,0.0006057372],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989937,0.00025103963,0.0002833169,0.00007678652,0.00029277435,0.000102373335],"domain_scores_gemma":[0.9990803,0.0001418248,0.00030393334,0.00023433824,0.00019375069,0.000045881872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016540538,0.000040853814,0.00010012236,0.0000462985,0.00024545743,0.000119209166,0.00037325415,0.000030212233,0.0006675819],"category_scores_gemma":[0.00088961615,0.00002645536,0.00010969391,0.00013810702,0.000092624694,0.00030477263,0.00010374369,0.00022731154,0.0000055141254],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015853935,0.00077406707,0.7584571,0.00003448391,0.00061234436,0.00010699011,0.018408889,0.0012385891,0.016301485,0.0012510731,0.084936805,0.1177196],"study_design_scores_gemma":[0.00049525726,0.00067890954,0.9398753,0.00036375658,0.000052702773,0.00004677548,0.011879674,0.00016618699,0.0005898556,0.00047260596,0.045302726,0.00007624715],"about_ca_topic_score_codex":0.00049710146,"about_ca_topic_score_gemma":0.00009236884,"teacher_disagreement_score":0.18141817,"about_ca_system_score_codex":0.000051320778,"about_ca_system_score_gemma":0.00018581533,"threshold_uncertainty_score":0.7309554},"labels":[],"label_agreement":null},{"id":"W4200412035","doi":"10.1186/s40537-021-00547-2","title":"Dynamic order Markov model for categorical sequence clustering","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Algorithms and Data Compression","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":false,"ca_institutions":"Université de Sherbrooke","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Hidden Markov model; Cluster analysis; Pattern recognition (psychology); Markov chain; Markov model; Sequence (biology); Categorical variable; Suffix tree; Data mining; Artificial intelligence; Algorithm; Data structure; Machine learning","score_opus":0.13437511965790933,"score_gpt":0.3358048966184071,"score_spread":0.2014297769604978,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200412035","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":[0.00045655415,0.00037551078,0.99693507,0.001210313,0.0008296912,0.00003603932,0.00010820095,0.0000105579675,0.000038078266],"genre_scores_gemma":[0.060923513,0.0002183138,0.93803006,0.00029559864,0.00020094664,0.0000010413233,0.00009264482,0.000008896141,0.0002289825],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893975,0.00002923724,0.00031963064,0.00025503774,0.00027950024,0.00017685455],"domain_scores_gemma":[0.9983215,0.000076598175,0.00019350526,0.0010145148,0.0002919176,0.00010199278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004107699,0.000084679246,0.00017008655,0.00005498738,0.000084580184,0.00017445079,0.0019140843,0.00004279893,0.0000038340745],"category_scores_gemma":[0.00016408965,0.000066882196,0.00004084378,0.00020525606,0.000014990829,0.0011344253,0.0016814591,0.00016230988,0.0000025016739],"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":[0.000044588687,0.00016818407,0.000034479894,0.00006609669,0.000058350186,0.00047497658,0.00018987327,0.010453339,0.0062742685,0.00088290666,0.02727417,0.9540788],"study_design_scores_gemma":[0.0003053111,0.000029643134,0.00003534748,0.000034036704,0.000009977809,0.00052451243,0.0000096958,0.99038047,0.00007298675,0.0018282988,0.0066829934,0.000086740176],"about_ca_topic_score_codex":0.0000052308264,"about_ca_topic_score_gemma":0.000015875301,"teacher_disagreement_score":0.9799271,"about_ca_system_score_codex":0.000042651216,"about_ca_system_score_gemma":0.00039477387,"threshold_uncertainty_score":0.35568768},"labels":[],"label_agreement":null},{"id":"W4210862833","doi":"10.1186/s40537-021-00468-0","title":"Big data quality framework: a holistic approach to continuous quality management","year":2021,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":141,"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":"Big data; Computer science; Data quality; Profiling (computer programming); Data science; Data mining; Quality (philosophy); Data management; Exploratory data analysis; Engineering; Operations management","score_opus":0.7948772270531455,"score_gpt":0.5341265486844159,"score_spread":0.26075067836872956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210862833","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":[0.0051803603,0.00066493574,0.9570451,0.008075943,0.0047591478,0.0003519765,0.006621786,0.00002873136,0.017272016],"genre_scores_gemma":[0.6252039,0.0011314885,0.3299585,0.018971471,0.0061247917,0.0000145405065,0.0051567936,0.00008357462,0.013354921],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98893905,0.0019356688,0.0030110741,0.0014158335,0.004177032,0.0005213502],"domain_scores_gemma":[0.9817297,0.0021597894,0.0017153798,0.013071508,0.00079468807,0.00052894617],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.040043317,0.00027553967,0.0010198185,0.0004144787,0.00020622801,0.0014006472,0.012576649,0.0001231949,0.00015494459],"category_scores_gemma":[0.026830984,0.00021256179,0.00015011702,0.0016588402,0.0001337335,0.0013288544,0.015088393,0.0005726027,0.00029152958],"study_design_candidate":"not_applicable","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":[0.0001520835,0.0009380399,0.00045112928,0.000107609914,0.00029874028,0.00022944418,0.00031074195,0.00003254838,0.000023777813,0.026836554,0.3750104,0.5956089],"study_design_scores_gemma":[0.00076544966,0.00005569167,0.01954164,0.0001260307,0.00017023509,0.000062544255,0.007386626,0.00016722253,0.000015897142,0.029006477,0.94234633,0.0003558746],"about_ca_topic_score_codex":0.00015622175,"about_ca_topic_score_gemma":0.00021521508,"teacher_disagreement_score":0.62708664,"about_ca_system_score_codex":0.00007502545,"about_ca_system_score_gemma":0.0002600313,"threshold_uncertainty_score":0.999636},"labels":[],"label_agreement":null},{"id":"W4302614395","doi":"10.1186/s40537-022-00608-0","title":"Adaptive multiple imputations of missing values using the class center","year":2022,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":21,"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 Manitoba","funders":"Thailand Research Fund; Natural Sciences and Engineering Research Council of Canada; Khon Kaen University","keywords":"Imputation (statistics); Missing data; Categorical variable; Computer science; Data mining; Artificial intelligence; Machine learning","score_opus":0.19522271418559686,"score_gpt":0.33417412123125606,"score_spread":0.1389514070456592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4302614395","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":[0.00732005,0.00016567574,0.98981285,0.001646024,0.00039870053,0.000050274368,0.0005435426,0.000006031073,0.000056863923],"genre_scores_gemma":[0.6129434,0.000010794549,0.38660127,0.00017661207,0.00020676987,0.0000013402812,0.000038741004,0.0000062907798,0.000014801824],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991197,0.00008649743,0.0002866445,0.000120976445,0.00029508295,0.00009112215],"domain_scores_gemma":[0.9985976,0.00018148308,0.0004101214,0.0006779286,0.00009638965,0.000036468435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064956944,0.000048274243,0.000099899094,0.000071305214,0.00031322334,0.00007495211,0.0020001067,0.000008574424,0.00000441755],"category_scores_gemma":[0.00007388121,0.000034630226,0.00003658468,0.00029626235,0.00004032668,0.0004606111,0.0012364844,0.00017085928,5.6294977e-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":[0.0000211902,0.00051398436,0.0007461506,0.000009719886,0.00017547478,0.000037697795,0.0032259533,0.008379313,0.0032431446,0.0021819652,0.030579805,0.9508856],"study_design_scores_gemma":[0.00026384924,0.000065085995,0.00059148617,0.00002147033,0.000022308159,0.00028675422,0.0007602313,0.9752642,0.00015853213,0.0011799613,0.021328598,0.00005755514],"about_ca_topic_score_codex":0.00003449182,"about_ca_topic_score_gemma":0.000002411026,"teacher_disagreement_score":0.96688485,"about_ca_system_score_codex":0.00003008649,"about_ca_system_score_gemma":0.00015456889,"threshold_uncertainty_score":0.3716729},"labels":[],"label_agreement":null},{"id":"W4311824268","doi":"10.1186/s40537-022-00667-3","title":"Chromatin state distribution of residue-specific histone acetylation in early myoblast differentiation","year":2022,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Genomics and Chromatin Dynamics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":4,"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 Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Southeast University","keywords":"Epigenetics; Chromatin; Histone; Histone acetyltransferase; Acetylation; Computational biology; Biology; Regulation of gene expression; Histone Acetyltransferases; Histone methyltransferase; Cell biology; Genetics; Gene","score_opus":0.025726578740153612,"score_gpt":0.2479546704509838,"score_spread":0.2222280917108302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311824268","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":[0.993067,0.00043847333,0.0053458316,0.00009233099,0.000253742,0.000062286206,0.0007240633,0.0000010585115,0.0000152058155],"genre_scores_gemma":[0.99684465,0.00028198672,0.00027228685,0.000009376086,0.000110465655,0.0000013049506,0.002431931,0.000008818521,0.000039202987],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990368,0.00008180231,0.00045353736,0.00013029683,0.0002025785,0.00009498986],"domain_scores_gemma":[0.9989723,0.0000086211785,0.00054636743,0.0003556564,0.000088996974,0.000028043425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042627667,0.00006893593,0.00013334659,0.00006191557,0.00004837739,0.000012919226,0.0003564229,0.000033531076,0.00001098837],"category_scores_gemma":[0.00004671273,0.00007078018,0.00003786014,0.00010470849,0.000022353472,0.000010167178,0.00030460852,0.00012208069,5.0600903e-7],"study_design_candidate":"bench_or_experimental","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":[0.00032657813,0.00026756525,0.009220301,0.00003205394,0.00005429571,0.000007403998,0.00021771005,0.0026181869,0.97000974,0.000044945074,0.006119636,0.011081591],"study_design_scores_gemma":[0.003228193,0.0014547013,0.8991333,0.000066854605,0.000049840146,0.000098311786,0.00037886907,0.005184841,0.065132536,0.0006808653,0.024233991,0.00035766946],"about_ca_topic_score_codex":0.000022794698,"about_ca_topic_score_gemma":0.000058103542,"teacher_disagreement_score":0.9048772,"about_ca_system_score_codex":0.00007608011,"about_ca_system_score_gemma":0.00007329936,"threshold_uncertainty_score":0.2886332},"labels":[],"label_agreement":null},{"id":"W4324378562","doi":"10.1186/s40537-023-00710-x","title":"A semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Sentiment Analysis and Opinion Mining","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":"Concordia University","funders":"","keywords":"Computer science; Bottleneck; Sentiment analysis; Artificial intelligence; Semi-supervised learning; Machine learning; Big data; Supervised learning; Language model; Function (biology); Natural language processing; Data mining; Artificial neural network","score_opus":0.2707046506402733,"score_gpt":0.37505771781517383,"score_spread":0.1043530671749005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4324378562","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":[0.0054035983,0.0000953535,0.98905957,0.004123608,0.00067860866,0.00012094969,0.00028969816,0.00004960662,0.00017902983],"genre_scores_gemma":[0.3206645,0.0003397558,0.67006433,0.0015338986,0.0010504008,0.0000056386966,0.005749079,0.00004904103,0.00054338435],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99722654,0.00019769967,0.00077272695,0.0007002352,0.0008455376,0.0002572666],"domain_scores_gemma":[0.99521667,0.00034837745,0.00040322563,0.0037194095,0.00014839157,0.00016392385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026359488,0.00018526531,0.0003774836,0.00040932593,0.00013190783,0.00031479535,0.0048246896,0.00007587069,0.000033928172],"category_scores_gemma":[0.00016440051,0.00015011762,0.00010603849,0.00086599553,0.00001703539,0.000997876,0.0015828735,0.00025076544,0.00005409565],"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":[0.00019128875,0.0007470266,0.0013584225,0.000024883007,0.0008952962,0.000074436866,0.00054357084,0.02976087,0.08138376,0.00023264282,0.19578725,0.68900055],"study_design_scores_gemma":[0.0007380558,0.000052735053,0.00082273025,0.00006817859,0.0001190565,0.0000024581132,0.000068750975,0.9925551,0.00087346055,0.000116100615,0.004421271,0.00016212645],"about_ca_topic_score_codex":0.00002473267,"about_ca_topic_score_gemma":0.000008648751,"teacher_disagreement_score":0.9627942,"about_ca_system_score_codex":0.000051930536,"about_ca_system_score_gemma":0.00024323625,"threshold_uncertainty_score":0.89655536},"labels":[],"label_agreement":null},{"id":"W4360827072","doi":"10.1186/s40537-023-00711-w","title":"Deep learning based deep-sea automatic image enhancement and animal species classification","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Ichthyology and Marine Biology","field":"Environmental Science","cited_by":41,"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":"Centro para el Desarrollo Tecnológico Industrial; Ministerio de Ciencia, Innovación y Universidades","keywords":"Computer science; Artificial intelligence; Residual; Deep learning; Pipeline (software); Pattern recognition (psychology); Data set; Set (abstract data type); Convolutional neural network; Algorithm","score_opus":0.06251843455730097,"score_gpt":0.2822145933443102,"score_spread":0.21969615878700924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4360827072","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":[0.9834175,0.00007005299,0.012035372,0.0017560121,0.00030958647,0.000074116026,0.000006815417,0.00002429774,0.0023062322],"genre_scores_gemma":[0.9968026,0.00014454473,0.0024808377,0.000101758575,0.00011137671,0.0000010718812,0.000076018885,0.0000048430857,0.00027692714],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9992818,0.00008919636,0.00021725436,0.00013424207,0.00013522088,0.00014226607],"domain_scores_gemma":[0.9995019,0.00008148792,0.00016628267,0.00019118996,0.000008741476,0.000050436895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065912266,0.00006305272,0.00011152926,0.000053242147,0.000093561415,0.000018759918,0.0002929341,0.00004307379,0.0008172327],"category_scores_gemma":[0.00020597795,0.00005025005,0.00001684627,0.000122017846,0.00014675404,0.00020523164,0.00035535925,0.00014885045,0.00029604067],"study_design_candidate":"observational","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":[0.00020989699,0.00018311568,0.2632594,0.000050560117,0.00007550615,0.0001505208,0.0003893409,0.00028327008,0.43277684,0.000074549076,0.020077432,0.28246957],"study_design_scores_gemma":[0.00035610338,0.00028195398,0.860217,0.000009875523,0.000030355319,0.000043945463,0.0001689931,0.111687556,0.0008751736,0.00007392238,0.026170347,0.00008479315],"about_ca_topic_score_codex":0.000011705264,"about_ca_topic_score_gemma":0.00005787033,"teacher_disagreement_score":0.59695756,"about_ca_system_score_codex":0.00003775703,"about_ca_system_score_gemma":0.000011659317,"threshold_uncertainty_score":0.8948125},"labels":[],"label_agreement":null},{"id":"W4384821779","doi":"10.1186/s40537-023-00796-3","title":"Detecting bots in social-networks using node and structural embeddings","year":2023,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Broadcom (Canada); Toronto Metropolitan University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metadata; Embedding; Class (philosophy); Node (physics); Machine learning; Social network (sociolinguistics); Feature (linguistics); Artificial intelligence; Anonymity; Focus (optics); Information retrieval; Data mining; Social media; World Wide Web","score_opus":0.1361918284243414,"score_gpt":0.33335033520205176,"score_spread":0.19715850677771035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384821779","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":[0.9085861,0.00012997186,0.08971458,0.00026609332,0.0012396171,0.000022214093,0.00000249492,0.00002388877,0.000015037316],"genre_scores_gemma":[0.9943591,0.000023207309,0.0048317905,0.000051701118,0.0007245359,7.313924e-8,0.0000012869933,0.0000049767445,0.0000033769393],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992413,0.00004767716,0.00023302219,0.00014287658,0.00017719103,0.00015791782],"domain_scores_gemma":[0.9994296,0.000079635494,0.00021295337,0.000201717,0.000035692156,0.000040424075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089156005,0.00006040858,0.00012206882,0.00019718829,0.00015064713,0.00021040686,0.0006125477,0.000048952737,7.424968e-7],"category_scores_gemma":[0.00013332484,0.000054264627,0.000019710353,0.000566077,0.000015341975,0.00087827625,0.00047196652,0.0002532635,7.3492924e-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":[0.0000595198,0.00001705318,0.038264263,0.000053636366,0.0000760317,0.00039099887,0.0041419165,0.013763583,0.013237817,0.000183855,0.0032682954,0.926543],"study_design_scores_gemma":[0.0002866891,0.000025361052,0.038981825,0.00006444661,0.00000797247,0.00027356486,0.00007862464,0.95861846,0.00016886383,0.0011368527,0.00026534483,0.00009201881],"about_ca_topic_score_codex":0.000043837186,"about_ca_topic_score_gemma":0.000026595555,"teacher_disagreement_score":0.94485486,"about_ca_system_score_codex":0.00003324679,"about_ca_system_score_gemma":0.000031839016,"threshold_uncertainty_score":0.22128472},"labels":[],"label_agreement":null},{"id":"W4390759017","doi":"10.1186/s40537-023-00866-6","title":"RPf-GCNs: reciprocal perspective driven fused GCNs for rumor detection on social media","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Misinformation and Its Impacts","field":"Social Sciences","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 Alberta","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Reciprocal; Computer science; Rumor; Perspective (graphical); Graph; Social media; Convolutional neural network; Profiling (computer programming); Artificial intelligence; Machine learning; Data science; World Wide Web; Theoretical computer science","score_opus":0.29748346181366003,"score_gpt":0.42489555319564437,"score_spread":0.12741209138198434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390759017","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":[0.63806003,0.0018470045,0.04800692,0.11839926,0.05221674,0.0025527745,0.0038195776,0.0005808007,0.13451688],"genre_scores_gemma":[0.99388444,0.00017331258,0.00022766663,0.00024951342,0.0052108793,8.189626e-7,0.000021211816,0.000010149887,0.0002220006],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987834,0.00008119752,0.00029146156,0.0001146936,0.00053476216,0.00019448917],"domain_scores_gemma":[0.99900913,0.00031337826,0.00018818569,0.00012963024,0.0002242144,0.00013547373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012765443,0.00007629584,0.00014582368,0.0001956316,0.00033987578,0.0002510063,0.00041140092,0.000092180395,0.00009422374],"category_scores_gemma":[0.002131863,0.00006109343,0.00008999366,0.0002642381,0.000083852996,0.0009213607,0.00004211767,0.00024287656,0.000044983306],"study_design_candidate":"not_applicable","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":[0.00046868858,0.00013379854,0.000009741714,0.000047035403,0.00018810187,0.000022899165,0.21022913,0.000007020857,0.00077821244,0.02175819,0.18536752,0.58098966],"study_design_scores_gemma":[0.0015802844,0.0005291864,0.0017231621,0.00027944671,0.00016485149,0.000036250487,0.19536981,0.0020566124,0.0010073332,0.009005213,0.78790355,0.00034431918],"about_ca_topic_score_codex":0.000054826578,"about_ca_topic_score_gemma":0.0009629489,"teacher_disagreement_score":0.602536,"about_ca_system_score_codex":0.0003042135,"about_ca_system_score_gemma":0.000514932,"threshold_uncertainty_score":0.2614084},"labels":[],"label_agreement":null},{"id":"W4391520039","doi":"10.1186/s40537-023-00842-0","title":"Survey of transformers and towards ensemble learning using transformers for natural language processing","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Topic Modeling","field":"Computer Science","cited_by":112,"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; Carleton University","keywords":"Computer science; Transformer; Automatic summarization; Artificial intelligence; Language model; Question answering; Natural language processing; Classifier (UML); Natural language; Machine learning; Sentiment analysis; Natural language understanding; Ensemble forecasting","score_opus":0.14319068897057724,"score_gpt":0.35099681994531884,"score_spread":0.2078061309747416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391520039","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":[0.14496748,0.008952916,0.845322,0.00017691623,0.00045098635,0.000060013463,0.000022845288,0.000012156138,0.00003470244],"genre_scores_gemma":[0.9702448,0.000100382385,0.029499343,0.000018060126,0.00010203207,2.1566692e-7,0.0000091450975,0.000008755023,0.0000172565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989973,0.00004910258,0.00036108005,0.00018437301,0.00024364343,0.00016453268],"domain_scores_gemma":[0.9995009,0.00010016112,0.00011555142,0.00012101702,0.00010609606,0.0000562802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016280136,0.00008617007,0.00020161469,0.00015744792,0.00005972106,0.00015012671,0.0004681423,0.00003961099,7.932728e-7],"category_scores_gemma":[0.00010966711,0.00006821084,0.000046158784,0.00023094835,0.000026079131,0.0011138701,0.000060349157,0.00024420978,8.879871e-8],"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":[0.000018324032,0.0000066201765,0.00009466807,0.000237742,0.000031323994,0.000011784159,0.0017778325,0.00015396932,0.006455829,0.000012110627,0.00002173545,0.99117804],"study_design_scores_gemma":[0.00032602286,0.00007820863,0.0004886768,0.00034047855,0.000035967074,0.0001487607,0.00033400528,0.9957077,0.0018136763,0.000030553652,0.0005966764,0.000099263896],"about_ca_topic_score_codex":0.0001358799,"about_ca_topic_score_gemma":0.00006473976,"teacher_disagreement_score":0.99555373,"about_ca_system_score_codex":0.000025334151,"about_ca_system_score_gemma":0.00032901086,"threshold_uncertainty_score":0.2781557},"labels":[],"label_agreement":null},{"id":"W4393112045","doi":"10.1186/s40537-024-00898-6","title":"Multi-sample $$\\zeta $$-mixup: richer, more realistic synthetic samples from a p-series interpolant","year":2024,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Domain Adaptation and Few-Shot Learning","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":false,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Compute Canada; Simon Fraser University; Nvidia","keywords":"Algorithm; Computer science; Machine learning; Artificial intelligence; Series (stratigraphy)","score_opus":0.18171046952873535,"score_gpt":0.33451089087990676,"score_spread":0.15280042135117142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393112045","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":[0.0019120127,0.0032485425,0.98989546,0.00223624,0.0020163613,0.000052862997,0.00046104076,0.00008114592,0.00009633015],"genre_scores_gemma":[0.58598447,0.0007112929,0.4114087,0.000505156,0.0008444877,0.0000021005253,0.0001999347,0.000034433197,0.00030941857],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834776,0.00013421943,0.00052539865,0.00035759326,0.00041545203,0.00021958222],"domain_scores_gemma":[0.9977788,0.0007614201,0.0002451088,0.0009665096,0.00009366071,0.00015450186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007541192,0.00015546894,0.00026700125,0.00021128872,0.00009160002,0.0006868809,0.0021106382,0.00005384419,0.000056971516],"category_scores_gemma":[0.0011937533,0.00012052302,0.00008641571,0.00031757116,0.00007606616,0.0011373934,0.00069047965,0.00037668046,0.00005045704],"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":[0.00020119974,0.0004666362,0.0014186418,0.00024471473,0.000961406,0.0026466013,0.016758721,0.0005487728,0.009023111,0.02764556,0.05536313,0.8847215],"study_design_scores_gemma":[0.0006876604,0.00019552991,0.006126833,0.00094687124,0.00012983472,0.00074589846,0.0012193158,0.47486225,0.00016809783,0.0050134105,0.50946254,0.00044175918],"about_ca_topic_score_codex":0.00038481888,"about_ca_topic_score_gemma":0.00011632285,"teacher_disagreement_score":0.8842797,"about_ca_system_score_codex":0.000047901194,"about_ca_system_score_gemma":0.00019629377,"threshold_uncertainty_score":0.66236085},"labels":[],"label_agreement":null},{"id":"W4409069510","doi":"10.1186/s40537-025-01122-9","title":"SPINEX-anomaly: similarity-based predictions with explainable neighbors exploration for anomaly and outlier detection","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Anomaly Detection Techniques and Applications","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 Manitoba","funders":"Clemson University","keywords":"Anomaly detection; Anomaly (physics); Outlier; Computer science; Similarity (geometry); Data mining; Computational Science and Engineering; Artificial intelligence; Pattern recognition (psychology); Machine learning; Image (mathematics)","score_opus":0.06406157203631375,"score_gpt":0.29009704088610744,"score_spread":0.2260354688497937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409069510","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":[0.0044153086,0.00008387558,0.9918205,0.0028925142,0.0002070479,0.00029307633,0.000038410602,0.00007294071,0.0001763305],"genre_scores_gemma":[0.85527724,0.00004076646,0.14397982,0.00030044606,0.00016724107,0.00005804913,0.000019225961,0.000008680406,0.00014852264],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990622,0.000030519936,0.00034484421,0.00027016713,0.0001556646,0.00013660571],"domain_scores_gemma":[0.9986086,0.000073542775,0.0002952071,0.0006711386,0.00028265882,0.00006884602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043128972,0.000108459615,0.00016183795,0.00031632165,0.0003125457,0.00019768869,0.0006045735,0.00006681051,0.0000015924217],"category_scores_gemma":[0.00006548352,0.000090104084,0.00004155068,0.00054338604,0.00004260776,0.0013305403,0.00014212808,0.00014649026,5.3327165e-7],"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":[0.0009473196,0.0014739402,0.0068554305,0.00047874678,0.0006145846,0.000035800564,0.000506711,0.0049242214,0.020154402,0.056307312,0.041502476,0.8661991],"study_design_scores_gemma":[0.0032618293,0.0025846106,0.008819968,0.0002623007,0.00033182607,0.00015407187,0.00033071145,0.5778081,0.051746752,0.020002814,0.33414915,0.0005478757],"about_ca_topic_score_codex":0.000021260881,"about_ca_topic_score_gemma":0.0000594053,"teacher_disagreement_score":0.8656512,"about_ca_system_score_codex":0.000052004867,"about_ca_system_score_gemma":0.00018879985,"threshold_uncertainty_score":0.3674338},"labels":[],"label_agreement":null},{"id":"W4410234140","doi":"10.1186/s40537-025-01141-6","title":"FunDa: scalable serverless data analytics and in situ query processing","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Cloud Computing and Resource Management","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 New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs; New Brunswick Innovation Foundation","keywords":"Computer science; Scalability; Analytics; Database; SQL; Data science","score_opus":0.10645358447112441,"score_gpt":0.30749756790749044,"score_spread":0.20104398343636604,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410234140","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":[0.42036778,0.0078042503,0.554845,0.011844053,0.0015015942,0.00016228862,0.00003184899,0.000054280325,0.0033889592],"genre_scores_gemma":[0.9872948,0.000086035056,0.011693497,0.00036515453,0.0001819543,1.13008085e-7,0.000008828777,0.000004190912,0.00036541684],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998815,0.00005680575,0.0003917495,0.00031026377,0.0002538919,0.00017230303],"domain_scores_gemma":[0.9981832,0.00007261376,0.00021977705,0.0014037295,0.000065322725,0.00005537532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015399281,0.00008627311,0.00020528842,0.00026758507,0.0000841517,0.0003705563,0.003526324,0.000033819382,4.7684415e-7],"category_scores_gemma":[0.00010756876,0.0000699689,0.000014697761,0.0006559904,0.000032518576,0.00024159063,0.00533659,0.00022470253,0.0000010270721],"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":[0.000022108563,0.00019488,0.01069926,0.0002736864,0.00008015262,0.00021613113,0.00019567319,0.0026341083,0.0001287681,0.0003390359,0.02150936,0.96370685],"study_design_scores_gemma":[0.0007820956,0.00003441746,0.02426467,0.00091921247,0.000051426177,0.00007330112,0.00017922596,0.90609944,0.00004004388,0.00076595915,0.066623695,0.00016652599],"about_ca_topic_score_codex":0.000033217624,"about_ca_topic_score_gemma":0.00012876047,"teacher_disagreement_score":0.9635403,"about_ca_system_score_codex":0.00003314971,"about_ca_system_score_gemma":0.00018031122,"threshold_uncertainty_score":0.6651678},"labels":[],"label_agreement":null},{"id":"W4415383695","doi":"10.1186/s40537-025-01280-w","title":"Digital twins in healthcare: a review of AI-powered practical applications across health domains","year":2025,"lang":"en","type":"review","venue":"Journal Of Big Data","topic":"Digital Transformation in Industry","field":"Engineering","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 Calgary","funders":"","keywords":"Health care; Digital health; Mental healthcare; Selection (genetic algorithm); Mental health; Virtual patient","score_opus":0.16700421305543162,"score_gpt":0.4465265295323191,"score_spread":0.27952231647688747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415383695","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.974381e-8,0.9780898,0.007918846,0.0021252139,0.00046254025,0.0008401735,0.007894289,0.00002460067,0.002644492],"genre_scores_gemma":[0.000009510645,0.99774957,0.000498738,0.0002546964,0.00022156865,0.000033244007,0.0011632025,0.00003553644,0.000033961842],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9959701,0.00009211269,0.0029311804,0.00020344768,0.00047013862,0.00033307547],"domain_scores_gemma":[0.99721193,0.0003716654,0.00094872515,0.0010972556,0.00015737911,0.00021302665],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011653205,0.00029841062,0.0019955994,0.0002869175,0.000030549785,0.00010694342,0.0011260174,0.00025096475,0.0000074363347],"category_scores_gemma":[0.00040920623,0.00025971103,0.0002788204,0.0010801046,0.000054726326,0.0011459487,0.00019241385,0.0015760117,0.000016963117],"study_design_candidate":"not_applicable","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":[0.000001515859,0.00006691862,0.0000021787732,0.2110796,0.000086915126,0.000008302125,0.0000101551705,0.0000020788943,4.2477617e-9,0.00021409971,0.016661862,0.7718664],"study_design_scores_gemma":[0.00014058258,0.000029968798,0.0000013762071,0.16651936,0.000072129675,0.0002821286,0.00001473505,0.0000035293879,5.6003834e-8,0.000048170987,0.8327554,0.0001325861],"about_ca_topic_score_codex":0.0000051085663,"about_ca_topic_score_gemma":0.000012247916,"teacher_disagreement_score":0.8160935,"about_ca_system_score_codex":0.0003571859,"about_ca_system_score_gemma":0.0022668915,"threshold_uncertainty_score":0.9999855},"labels":[],"label_agreement":null},{"id":"W4416285692","doi":"10.1186/s40537-025-01307-2","title":"UniqueNOSD: a novel framework for NoSQL over SQL databases","year":2025,"lang":"en","type":"article","venue":"Journal Of Big Data","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":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada; University of Windsor","keywords":"NoSQL; SQL; Scalability; Relational database; Relational database management system; Redundancy (engineering); Consistency (knowledge bases); View; Query by Example","score_opus":0.1547059754666002,"score_gpt":0.37866323701805993,"score_spread":0.22395726155145973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416285692","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":[0.00025549254,0.0008840111,0.99353236,0.0013980631,0.0021145595,0.0001323162,0.0015178348,0.0000231434,0.00014221398],"genre_scores_gemma":[0.0050779376,0.00014243883,0.9926579,0.001139213,0.0006426268,0.000004029383,0.000115697265,0.0000095740015,0.0002105617],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986674,0.000030477871,0.0005179127,0.0003009611,0.00026386417,0.00021934234],"domain_scores_gemma":[0.99694794,0.0005208136,0.00041413397,0.0018347553,0.00019518207,0.00008717781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069637736,0.00013377084,0.0002938411,0.00018306916,0.00011652324,0.000083716535,0.0018148855,0.000047105757,0.000007422972],"category_scores_gemma":[0.0010280092,0.00010484547,0.00006722007,0.0003815147,0.000044964137,0.0019029176,0.0012271913,0.00022500005,0.0000030446085],"study_design_candidate":"not_applicable","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":[0.000050603092,0.00011851894,0.0002464501,0.00009036137,0.00008477334,0.000025190904,0.000053082866,0.000022098931,0.0010693352,0.8945347,0.067270584,0.036434274],"study_design_scores_gemma":[0.0005712867,0.00006919015,0.00037265976,0.00060704263,0.000027154896,0.000066111614,0.00004233074,0.0026814102,0.0009837,0.0070857317,0.98734933,0.00014406831],"about_ca_topic_score_codex":0.000035304893,"about_ca_topic_score_gemma":0.000031100877,"teacher_disagreement_score":0.92007875,"about_ca_system_score_codex":0.000033905937,"about_ca_system_score_gemma":0.00034024467,"threshold_uncertainty_score":0.42754743},"labels":[],"label_agreement":null}]}