{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":10,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":10,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"09ce87fd00b5","filters":{"venue":"Big Data Research"}},"results":[{"id":"W2922919311","doi":"10.1016/j.bdr.2019.03.001","title":"Systematic Review of the Literature on Big Data in the Transportation Domain: Concepts and Applications","year":2019,"lang":"en","type":"article","venue":"Big Data Research","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":124,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"MacEwan University","funders":"MacEwan University; University of Otago; U.S. Department of Transportation","keywords":"Big data; Data science; Computer science; Crowdsourcing; Domain (mathematical analysis); Analytics; SAFER; Intelligent transportation system; Data analysis; Software analytics; Software; World Wide Web; Computer security; Software development; Data mining; Engineering; Transport engineering; Component-based software engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.1301934818627772,"gpt":0.365128430725414,"spread":0.2349349488626367,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001695964,0.00005128391,0.0001114694,0.00007187243,0.00003099229,0.00003402932,0.001231491,0.00002982062,0.000002213936],"category_scores_gemma":[0.00005087824,0.00002868509,0.000009457633,0.0005060316,0.0000384153,0.0001008811,0.0001028627,0.0002091602,0.000007629336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001031395,"about_ca_system_score_gemma":0.00001110098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001082991,"about_ca_topic_score_gemma":0.00006754418,"domain_scores_codex":[0.9990599,0.0001547211,0.0001876425,0.0001636685,0.0003419087,0.00009212337],"domain_scores_gemma":[0.9977551,0.0001301782,0.00002220415,0.002050425,0.00002854863,0.00001359763],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001305595,0.0001354172,0.000279581,0.756294,0.0001005172,0.000004848202,0.001392066,0.00002061244,0.0003643664,0.02747755,0.177196,0.0367221],"study_design_scores_gemma":[0.001400372,0.0001524813,0.01564924,0.4020075,0.0001958472,0.00001183394,0.002597398,0.01172729,0.0001854528,0.0006601843,0.5648906,0.0005218202],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.02110601,0.6575295,0.1085395,0.02193234,0.002391812,0.1005136,0.03259005,0.003746497,0.05165074],"genre_scores_gemma":[0.9711775,0.02679542,0.00006560924,0.0001730074,0.00005000755,0.0002510687,0.001428888,0.000009691705,0.00004886443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9500715,"threshold_uncertainty_score":0.2288437,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3113091126","doi":"10.1016/j.bdr.2020.100173","title":"Agreeing to Disagree: Choosing Among Eight Topic-Modeling Methods","year":2020,"lang":"en","type":"article","venue":"Big Data Research","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Hong Kong Polytechnic University","keywords":"Latent Dirichlet allocation; Topic model; Computer science; Data science; Artificial intelligence; Coherence (philosophical gambling strategy); Field (mathematics); Context (archaeology); Machine learning; Management science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.8645336607084751,"gpt":0.6295130273678069,"spread":0.2350206333406683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009259239,0.00009170833,0.0001949661,0.0001888215,0.001004764,0.0003741746,0.001508523,0.00006751506,0.0002103635],"category_scores_gemma":[0.006129509,0.00008455684,0.00005553034,0.002016731,0.0001575994,0.0003724009,0.001405045,0.0003608269,0.0001145059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000080818,"about_ca_system_score_gemma":0.0002620197,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006251721,"about_ca_topic_score_gemma":0.002660237,"domain_scores_codex":[0.9955417,0.001895229,0.0002518596,0.0005997883,0.001182187,0.0005292619],"domain_scores_gemma":[0.9975135,0.001157119,0.00003124427,0.0005158762,0.0002933542,0.0004888658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001801186,0.00002496227,0.003656276,0.00001653674,0.00003847262,0.000013008,0.006914508,0.000562519,0.0005418501,0.003426272,0.002598736,0.9821888],"study_design_scores_gemma":[0.0002749028,0.00005755342,0.004460173,0.00007652569,0.00003784292,4.969021e-7,0.006673796,0.5352027,0.0002549113,0.007789413,0.4447511,0.0004205507],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0312003,0.0005318184,0.9240699,0.02678004,0.0002935114,0.0003721925,0.00003846282,0.00007921696,0.01663457],"genre_scores_gemma":[0.8032299,0.0001023059,0.1918783,0.0005724387,0.002881619,0.00001486103,0.0001326033,0.00002024315,0.0011677],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9817683,"threshold_uncertainty_score":0.9450773,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901153708","doi":"10.1016/j.bdr.2018.11.001","title":"Label-Aware Distributed Ensemble Learning: A Simplified Distributed Classifier Training Model for Big Data","year":2018,"lang":"en","type":"article","venue":"Big Data Research","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"IBM (Canada); Queen's University","funders":"","keywords":"Computer science; Classifier (UML); Big data; Data mining; Machine learning; SPARK (programming language); Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.72474036327115,"gpt":0.4627651775700344,"spread":0.2619751857011156,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006154601,0.0003720792,0.0004610755,0.0004204068,0.00106911,0.001193128,0.01728046,0.0002862188,0.000008023857],"category_scores_gemma":[0.005558135,0.0003556625,0.00004436456,0.001953894,0.0005941198,0.001694246,0.01924838,0.0009477636,0.00009374799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000167606,"about_ca_system_score_gemma":0.00127327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000212479,"about_ca_topic_score_gemma":0.0004531641,"domain_scores_codex":[0.9933143,0.0004758724,0.0005982956,0.002464965,0.001417662,0.001728958],"domain_scores_gemma":[0.9867419,0.001244639,0.0001830588,0.01041267,0.0009835563,0.000434162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001271442,0.0002382074,0.00009078832,0.00006287715,0.00007747657,0.00003270503,0.0004360279,0.00001731861,0.001498988,0.002379782,0.5699521,0.4250866],"study_design_scores_gemma":[0.0006749828,0.000287997,0.00005716614,0.00007163992,0.00001257898,0.00001340512,0.0001286383,0.7455682,0.000797228,0.002101301,0.2499517,0.0003351819],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005186178,0.00005966037,0.9506995,0.001862755,0.0003666434,0.0007793141,0.04462689,0.0008155096,0.0002710951],"genre_scores_gemma":[0.7522509,0.00008633828,0.1183348,0.0001359976,0.001461657,0.0002330858,0.126477,0.0001037017,0.0009164897],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8323647,"threshold_uncertainty_score":0.9998896,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4295709232","doi":"10.1016/j.bdr.2022.100348","title":"Properties and Performance of the ABCDe Random Graph Model with Community Structure","year":2022,"lang":"en","type":"article","venue":"Big Data Research","topic":"Complex Network Analysis Techniques","field":"Physics and Astronomy","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Benchmark (surveying); Graph; Random graph; Generator (circuit theory); Community structure; Theoretical computer science; Algorithm; Power (physics); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.2926327152332855,"gpt":0.3403536589814936,"spread":0.04772094374820812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001024323,0.00006479949,0.0001243481,0.00006917853,0.0009403332,0.00003422753,0.001206806,0.000008067802,0.00004101394],"category_scores_gemma":[0.000005093945,0.00003755979,0.00001832045,0.0004334857,0.000276125,0.00008432148,0.002981962,0.0007090568,1.292377e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001086299,"about_ca_system_score_gemma":0.00009520564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001736769,"about_ca_topic_score_gemma":0.0001958725,"domain_scores_codex":[0.9986427,0.0005093995,0.0001038579,0.000137573,0.0004382165,0.0001682826],"domain_scores_gemma":[0.9984882,0.00006509013,0.00004138474,0.001298345,0.00008278622,0.00002421652],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004184498,0.001067618,0.6309915,0.0004895264,0.000994935,0.000001368472,0.005710489,0.02436589,0.02324441,0.00837888,0.02799371,0.2725772],"study_design_scores_gemma":[0.002641098,0.0005437561,0.01518576,0.000142734,0.00009741518,0.000005194352,0.003306476,0.9478521,0.01037371,0.01125017,0.008189968,0.0004116776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9981864,0.0001309338,0.000445923,0.00009348643,0.000006453258,0.0002515653,0.0004413219,0.000008816774,0.0004350746],"genre_scores_gemma":[0.9993693,0.000009366124,0.0002165478,0.000006791267,0.00002640847,0.00003396889,0.0001678029,0.000008010852,0.0001617741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9234862,"threshold_uncertainty_score":0.7232378,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3208577093","doi":"10.1016/j.bdr.2021.100275","title":"Epidemic Spreading in Trajectory Networks","year":2021,"lang":"en","type":"article","venue":"Big Data Research","topic":"COVID-19 epidemiological studies","field":"Mathematics","cited_by":17,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Outbreak; Psychological intervention; Intervention (counseling); Contact tracing; Coronavirus disease 2019 (COVID-19); Disease; Epidemic model; Infectious disease (medical specialty); Big data; Data science; Risk analysis (engineering); Computer security; Medicine; Environmental health; Virology; Data mining; Population","retraction":null,"screen_n_in":null,"score":{"opus":0.9041873969734017,"gpt":0.5915173642557057,"spread":0.312670032717696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01203354,0.0001321186,0.0004330151,0.0001412276,0.0001727893,0.00004068893,0.0010473,0.0001533474,0.0001653059],"category_scores_gemma":[0.07288726,0.0001097432,0.00004569169,0.0009775284,0.000189894,0.0001111624,0.003057638,0.0009749337,0.00008745877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002277478,"about_ca_system_score_gemma":0.000179415,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006386376,"about_ca_topic_score_gemma":0.003702982,"domain_scores_codex":[0.995724,0.001721714,0.0004712181,0.0007529414,0.0004888028,0.0008413566],"domain_scores_gemma":[0.9753993,0.0226106,0.00004862624,0.001677857,0.0001398065,0.0001238498],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001361054,0.0007211948,0.1662452,0.0006319509,0.0001692758,0.001315944,0.0004376672,0.0002387737,0.00136824,0.02954028,0.6291502,0.1700452],"study_design_scores_gemma":[0.002401518,0.0001931449,0.1293494,0.001121731,0.00005161417,0.00004809768,0.001726146,0.08445199,0.0006138409,0.2969972,0.4818243,0.001220973],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6317682,0.0956019,0.1408809,0.06290248,0.003521849,0.005360487,0.001354698,0.001285315,0.05732419],"genre_scores_gemma":[0.9863779,0.003768655,0.006670899,0.0005520498,0.0008595975,0.00008768104,0.0002168336,0.00004379663,0.001422589],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3546097,"threshold_uncertainty_score":0.9349222,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3145041349","doi":"10.1016/j.bdr.2021.100254","title":"Scaling the Growing Neural Gas for Visual Cluster Analysis","year":2021,"lang":"en","type":"article","venue":"Big Data Research","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Clutter; Visualization; Neural gas; Big data; Cluster (spacecraft); Artificial intelligence; Unsupervised learning; Graph; Scalability; Artificial neural network; Topology (electrical circuits); Machine learning; Pattern recognition (psychology); Theoretical computer science; Data mining; Recurrent neural network; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.4006687696177129,"gpt":0.4578600640552944,"spread":0.05719129443758159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001488225,0.00005956721,0.00009641835,0.0000936116,0.0005984973,0.0006189758,0.002213765,0.0000269779,0.000007335198],"category_scores_gemma":[0.0001944376,0.00004094638,0.00006624604,0.002341075,0.00005972669,0.0005298021,0.002651505,0.0002146664,0.00001745775],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001366204,"about_ca_system_score_gemma":0.00007569121,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000578513,"about_ca_topic_score_gemma":0.0001124348,"domain_scores_codex":[0.9983096,0.0002060775,0.0001438524,0.0005184473,0.0004363974,0.0003855946],"domain_scores_gemma":[0.9969748,0.001062187,0.000021143,0.001660868,0.0002064963,0.00007453722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001539434,0.0001370843,0.0004410635,0.00002421963,0.0002271862,0.00002584493,0.0001397338,0.002331297,0.003067662,0.02881406,0.05472859,0.9100479],"study_design_scores_gemma":[0.00009487398,0.000009975393,0.0003308597,0.000003707562,0.00001904462,0.000004111867,0.00003881547,0.9266783,0.0006415797,0.0006243729,0.07149839,0.00005597132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02319542,0.0006043775,0.9143955,0.06092723,0.0002054234,0.0003719337,0.00007861668,0.00005499677,0.0001664773],"genre_scores_gemma":[0.9890329,0.00008007573,0.007923074,0.001351219,0.0006672139,0.0000866863,0.0003526581,0.000009958618,0.0004962091],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9658375,"threshold_uncertainty_score":0.5968798,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3170000029","doi":"10.1016/j.bdr.2021.100239","title":"ExplorerTree: A Focus+Context Exploration Approach for 2D Embeddings","year":2021,"lang":"en","type":"article","venue":"Big Data Research","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Focus (optics); Artificial intelligence; Context (archaeology); Clutter; Convolutional neural network; Dimensionality reduction; Visualization; Machine learning; Pattern recognition (psychology); Data mining; Radar","retraction":null,"screen_n_in":null,"score":{"opus":0.6266507062173049,"gpt":0.4639213162888603,"spread":0.1627293899284446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00187767,0.0001062365,0.0001493199,0.0002162154,0.0003009423,0.000937996,0.002498379,0.00006366736,0.00001911117],"category_scores_gemma":[0.001216817,0.0001005691,0.00003690573,0.001352319,0.00006960522,0.002061503,0.002514554,0.000170795,0.00009444429],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000409598,"about_ca_system_score_gemma":0.0003892458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004051504,"about_ca_topic_score_gemma":0.00008274393,"domain_scores_codex":[0.9974739,0.0002188579,0.0002465768,0.0008325781,0.0007881587,0.0004399484],"domain_scores_gemma":[0.9965495,0.0002284187,0.00004563007,0.002329422,0.0006927383,0.0001542891],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001644493,0.0003505659,0.00003837781,0.0000862555,0.00003424666,0.00002103576,0.0009577931,0.00001413757,0.0008412002,0.1753126,0.2860791,0.5362483],"study_design_scores_gemma":[0.0004966629,0.00005322084,0.00000960238,0.00002060346,0.000004446791,0.000006754803,0.001122755,0.6370202,0.004825613,0.002974414,0.3533053,0.000160394],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00004040565,0.0003717761,0.9949464,0.002537871,0.0001406545,0.0002606941,0.0002961327,0.00008196766,0.001324161],"genre_scores_gemma":[0.4469442,0.001904235,0.4976962,0.00201436,0.001968036,0.000712995,0.03346392,0.0001340147,0.0151621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.637006,"threshold_uncertainty_score":0.9045117,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4413323615","doi":"10.1016/j.bdr.2025.100555","title":"Explainable malware detection through integrated graph reduction and learning techniques","year":2025,"lang":"en","type":"article","venue":"Big Data Research","topic":"Advanced Malware Detection Techniques","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Malware; Reduction (mathematics); Big data; Graph; Artificial intelligence; Data science; Machine learning; Deep learning; Computer security; Theoretical computer science; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1808340169138115,"gpt":0.4031757345333891,"spread":0.2223417176195776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002076346,0.0001449616,0.0001511544,0.0007764096,0.0008557141,0.0003535619,0.00131558,0.0001480313,0.000005805183],"category_scores_gemma":[0.0008303836,0.0001413322,0.00002062089,0.002765945,0.0002015903,0.001881188,0.00211766,0.001034405,0.000009574987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001587305,"about_ca_system_score_gemma":0.0001250272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008746278,"about_ca_topic_score_gemma":0.00007942537,"domain_scores_codex":[0.9975306,0.000543387,0.0002298388,0.0008692734,0.0003999871,0.0004269102],"domain_scores_gemma":[0.9978488,0.0001841163,0.00005722564,0.001398804,0.0004553805,0.00005565282],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003603465,0.00003423274,0.00003537919,0.00005917577,0.00001284151,0.000008411734,0.000138679,0.000001966738,0.04224074,0.003983034,0.002299038,0.9511505],"study_design_scores_gemma":[0.0001502331,0.0002581335,0.00008048946,0.0001369601,0.000003776366,0.00005853246,0.0006370849,0.003012876,0.6853848,0.02318755,0.2868917,0.0001978786],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001504182,0.0005263659,0.9936334,0.0005339556,0.0002251905,0.0004695443,0.000009642308,0.001143456,0.001954274],"genre_scores_gemma":[0.6792323,0.002559094,0.3124769,0.0000739488,0.000164311,0.0004375924,0.0001116378,0.00003522693,0.004908975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9509526,"threshold_uncertainty_score":0.6581548,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4405429927","doi":"10.1016/j.bdr.2024.100504","title":"Principal component analysis of multivariate spatial functional data","year":2024,"lang":"en","type":"article","venue":"Big Data Research","topic":"Soil Geostatistics and Mapping","field":"Environmental Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Principal component analysis; Multivariate statistics; Computer science; Big data; Multivariate analysis; Component (thermodynamics); Data mining; Artificial intelligence; Pattern recognition (psychology); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.4518594465811662,"gpt":0.4224598545003331,"spread":0.02939959208083309,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002159995,0.00006475172,0.0001215687,0.0002026177,0.0001037937,0.00008058574,0.001177248,0.00003143591,0.001725483],"category_scores_gemma":[0.0003310735,0.00005533285,0.00002069418,0.001111368,0.0002153369,0.0001760461,0.005834712,0.0001917018,0.000356474],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006169653,"about_ca_system_score_gemma":0.00005681053,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02043134,"about_ca_topic_score_gemma":0.004837373,"domain_scores_codex":[0.9978438,0.0001215724,0.000191927,0.0005992739,0.0009834614,0.0002599455],"domain_scores_gemma":[0.9978775,0.0003803119,0.00002121982,0.001614598,0.00001958952,0.00008676211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001836907,0.0005846265,0.04505816,0.0001689228,0.002133393,0.0002028148,0.0004797004,0.004265583,0.02828482,0.004521235,0.1183866,0.7957304],"study_design_scores_gemma":[0.00007324073,0.00001277534,0.2319472,0.000009010615,0.00007315591,7.29857e-7,0.00001691219,0.6024503,0.000030595,0.00006518262,0.1652692,0.00005173434],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3273452,0.00146262,0.5726955,0.003004605,0.003318964,0.001515726,0.06530108,0.0002215508,0.02513475],"genre_scores_gemma":[0.9875686,0.00005007272,0.001427669,0.0000102181,0.0001091781,0.0000050638,0.0102839,0.000007991657,0.0005372927],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7956787,"threshold_uncertainty_score":0.9991871,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005161541","doi":"10.1016/j.bdr.2014.08.001","title":"Special Issue on Scalable Computing for Big Data","year":2014,"lang":"en","type":"article","venue":"Big Data Research","topic":"Cloud Computing and Resource Management","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Big data; Computer science; Scalability; Data science; Distributed computing; Data mining; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.3942306666903458,"gpt":0.4020958052569457,"spread":0.007865138566599927,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.008392628,0.0001656869,0.0002206579,0.00031762,0.0007722924,0.0007932737,0.01205129,0.00007097676,0.00001071587],"category_scores_gemma":[0.001187153,0.0001436047,0.00003091847,0.0008400392,0.0001237017,0.0000716056,0.01918906,0.000396602,0.0006012522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005419643,"about_ca_system_score_gemma":0.0001048389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002258259,"about_ca_topic_score_gemma":0.00007242339,"domain_scores_codex":[0.9957447,0.0003971921,0.000294042,0.001481277,0.001171968,0.0009108004],"domain_scores_gemma":[0.9910287,0.001292883,0.00006818271,0.007262051,0.00016237,0.0001857619],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009860468,0.00007586511,0.00003081196,0.00003332608,0.00001109857,0.000004058209,0.00006368228,0.0001624828,0.000007318794,0.001458671,0.4211022,0.5770407],"study_design_scores_gemma":[0.0003057255,0.0001119117,0.0001709758,0.00004438815,0.000002103718,0.000001632043,0.00002681849,0.4241656,0.00003504746,0.0002087031,0.5748211,0.0001060016],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"editorial","genre_scores_codex":[0.01034275,0.0002141048,0.8365394,0.02189006,0.01762965,0.002231386,0.0005147207,0.000682365,0.1099556],"genre_scores_gemma":[0.3820136,0.00007219491,0.09265386,0.002897288,0.4824162,0.00004899901,0.002952557,0.0002038668,0.03674148],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7438855,"threshold_uncertainty_score":0.993294,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}