{"meta":{"query_hash":"09ce87fd00b5","filters":{"venue":"Big Data Research"},"cohort_total":10,"direct_labels_cover":0,"predictions_cover":10,"exported":10,"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/09ce87fd00b5","api":"https://metacan.xera.ac/api/v1/cohort?venue=Big+Data+Research"},"results":[{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Big data; Computer science; Scalability; Data science; Distributed computing; Data mining; Database","score_opus":0.3942306666903458,"score_gpt":0.4020958052569457,"score_spread":0.007865138566599927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005161541","genre_codex":"methods","genre_gemma":"editorial","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":[0.0103427535,0.00021410482,0.8365394,0.02189006,0.01762965,0.0022313863,0.00051472074,0.000682365,0.10995558],"genre_scores_gemma":[0.3820136,0.00007219491,0.092653856,0.0028972877,0.48241618,0.000048999013,0.0029525566,0.00020386677,0.036741477],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957447,0.0003971921,0.000294042,0.0014812773,0.0011719678,0.0009108004],"domain_scores_gemma":[0.9910287,0.0012928831,0.00006818271,0.0072620506,0.00016236998,0.00018576189],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.008392628,0.00016568688,0.00022065786,0.00031762003,0.0007722924,0.00079327374,0.012051293,0.000070976756,0.000010715875],"category_scores_gemma":[0.0011871533,0.00014360469,0.000030918465,0.0008400392,0.00012370173,0.0000716056,0.019189062,0.00039660203,0.00060125225],"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":[0.000009860468,0.00007586511,0.000030811963,0.000033326076,0.000011098567,0.0000040582086,0.00006368228,0.00016248279,0.000007318794,0.0014586706,0.42110217,0.5770407],"study_design_scores_gemma":[0.00030572547,0.00011191173,0.00017097582,0.000044388147,0.000002103718,0.0000016320433,0.000026818492,0.4241656,0.000035047462,0.00020870307,0.5748211,0.00010600157],"about_ca_topic_score_codex":0.0002258259,"about_ca_topic_score_gemma":0.00007242339,"teacher_disagreement_score":0.7438855,"about_ca_system_score_codex":0.000054196433,"about_ca_system_score_gemma":0.00010483893,"threshold_uncertainty_score":0.993294},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.72474036327115,"score_gpt":0.4627651775700344,"score_spread":0.2619751857011156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2901153708","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":[0.0005186178,0.000059660368,0.9506995,0.0018627554,0.0003666434,0.0007793141,0.044626888,0.00081550964,0.00027109508],"genre_scores_gemma":[0.7522509,0.00008633828,0.1183348,0.00013599757,0.0014616568,0.00023308581,0.12647703,0.00010370174,0.0009164897],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99331427,0.00047587242,0.0005982956,0.0024649655,0.0014176616,0.0017289578],"domain_scores_gemma":[0.9867419,0.0012446394,0.00018305877,0.010412665,0.0009835563,0.00043416198],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0061546005,0.0003720792,0.00046107545,0.0004204068,0.00106911,0.0011931281,0.017280458,0.0002862188,0.000008023857],"category_scores_gemma":[0.005558135,0.00035566252,0.00004436456,0.0019538936,0.00059411983,0.0016942457,0.019248376,0.0009477636,0.00009374799],"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":[0.00012714416,0.00023820742,0.00009078832,0.00006287715,0.00007747657,0.000032705033,0.00043602785,0.000017318605,0.0014989878,0.0023797825,0.5699521,0.42508665],"study_design_scores_gemma":[0.00067498285,0.00028799695,0.000057166137,0.00007163992,0.000012578983,0.000013405119,0.0001286383,0.7455682,0.000797228,0.002101301,0.24995166,0.00033518186],"about_ca_topic_score_codex":0.00021247899,"about_ca_topic_score_gemma":0.0004531641,"teacher_disagreement_score":0.83236474,"about_ca_system_score_codex":0.00016760596,"about_ca_system_score_gemma":0.0012732701,"threshold_uncertainty_score":0.99988955},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.13019348186277724,"score_gpt":0.36512843072541395,"score_spread":0.23493494886263672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922919311","genre_codex":"review","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":[0.021106012,0.65752953,0.10853946,0.02193234,0.0023918117,0.100513555,0.032590054,0.0037464972,0.051650744],"genre_scores_gemma":[0.97117746,0.026795425,0.00006560924,0.00017300743,0.000050007555,0.0002510687,0.0014288883,0.000009691705,0.00004886443],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990599,0.0001547211,0.00018764254,0.00016366855,0.00034190866,0.00009212337],"domain_scores_gemma":[0.99775505,0.00013017817,0.000022204153,0.0020504247,0.000028548628,0.000013597625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016959644,0.000051283914,0.00011146943,0.000071872426,0.000030992287,0.000034029323,0.001231491,0.000029820621,0.000002213936],"category_scores_gemma":[0.000050878243,0.000028685086,0.0000094576335,0.0005060316,0.000038415295,0.0001008811,0.000102862665,0.00020916024,0.000007629336],"study_design_candidate":"systematic_review","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":[0.000013055946,0.00013541724,0.00027958097,0.75629395,0.00010051715,0.000004848202,0.0013920658,0.000020612444,0.00036436637,0.027477548,0.17719595,0.036722098],"study_design_scores_gemma":[0.0014003721,0.00015248131,0.015649239,0.4020075,0.00019584718,0.000011833945,0.0025973977,0.011727291,0.00018545277,0.0006601843,0.5648906,0.0005218202],"about_ca_topic_score_codex":0.000010829915,"about_ca_topic_score_gemma":0.00006754418,"teacher_disagreement_score":0.95007145,"about_ca_system_score_codex":0.000010313948,"about_ca_system_score_gemma":0.0000111009795,"threshold_uncertainty_score":0.22884372},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.8645336607084751,"score_gpt":0.6295130273678069,"score_spread":0.23502063334066825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113091126","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":[0.031200295,0.0005318184,0.9240699,0.026780035,0.00029351143,0.00037219253,0.000038462822,0.00007921696,0.016634567],"genre_scores_gemma":[0.8032299,0.000102305916,0.19187827,0.0005724387,0.0028816191,0.000014861031,0.00013260331,0.000020243146,0.0011676998],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955417,0.0018952286,0.00025185963,0.0005997883,0.0011821869,0.0005292619],"domain_scores_gemma":[0.99751353,0.0011571193,0.000031244268,0.0005158762,0.00029335418,0.00048886583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009259239,0.00009170833,0.00019496605,0.00018882155,0.0010047645,0.0003741746,0.001508523,0.00006751506,0.00021036348],"category_scores_gemma":[0.006129509,0.00008455684,0.000055530345,0.0020167308,0.00015759937,0.00037240091,0.001405045,0.00036082693,0.00011450591],"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":[0.000018011862,0.000024962272,0.0036562758,0.00001653674,0.000038472615,0.000013007998,0.0069145076,0.00056251895,0.0005418501,0.003426272,0.0025987364,0.9821888],"study_design_scores_gemma":[0.00027490276,0.00005755342,0.004460173,0.00007652569,0.000037842925,4.9690215e-7,0.006673796,0.53520274,0.0002549113,0.0077894125,0.44475105,0.00042055073],"about_ca_topic_score_codex":0.0062517207,"about_ca_topic_score_gemma":0.0026602373,"teacher_disagreement_score":0.9817683,"about_ca_system_score_codex":0.000080818005,"about_ca_system_score_gemma":0.00026201975,"threshold_uncertainty_score":0.9450773},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.40066876961771286,"score_gpt":0.45786006405529445,"score_spread":0.057191294437581586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3145041349","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":[0.023195418,0.00060437754,0.9143955,0.06092723,0.00020542338,0.00037193365,0.00007861668,0.00005499677,0.00016647729],"genre_scores_gemma":[0.9890329,0.00008007573,0.007923074,0.0013512186,0.00066721387,0.0000866863,0.00035265807,0.000009958618,0.0004962091],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983096,0.00020607754,0.00014385245,0.00051844725,0.0004363974,0.00038559455],"domain_scores_gemma":[0.99697477,0.0010621874,0.000021142998,0.0016608682,0.00020649626,0.00007453722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014882251,0.00005956721,0.00009641835,0.000093611605,0.00059849734,0.0006189758,0.0022137652,0.000026977903,0.000007335198],"category_scores_gemma":[0.00019443761,0.000040946376,0.00006624604,0.0023410746,0.00005972669,0.0005298021,0.0026515054,0.00021466636,0.000017457747],"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":[0.000015394338,0.00013708431,0.00044106346,0.000024219633,0.00022718617,0.000025844925,0.00013973376,0.0023312967,0.0030676625,0.02881406,0.054728586,0.9100479],"study_design_scores_gemma":[0.00009487398,0.000009975393,0.0003308597,0.0000037075615,0.000019044619,0.0000041118674,0.000038815473,0.9266783,0.00064157974,0.0006243729,0.07149839,0.00005597132],"about_ca_topic_score_codex":0.0000578513,"about_ca_topic_score_gemma":0.00011243478,"teacher_disagreement_score":0.9658375,"about_ca_system_score_codex":0.000013662036,"about_ca_system_score_gemma":0.00007569121,"threshold_uncertainty_score":0.5968798},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.6266507062173049,"score_gpt":0.4639213162888603,"score_spread":0.1627293899284446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170000029","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":[0.000040405648,0.00037177608,0.99494636,0.002537871,0.00014065449,0.0002606941,0.00029613273,0.00008196766,0.0013241606],"genre_scores_gemma":[0.44694418,0.0019042348,0.49769616,0.0020143597,0.0019680364,0.000712995,0.03346392,0.00013401471,0.015162098],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974739,0.00021885788,0.00024657685,0.0008325781,0.0007881587,0.0004399484],"domain_scores_gemma":[0.9965495,0.00022841872,0.000045630066,0.0023294217,0.0006927383,0.0001542891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018776702,0.00010623651,0.00014931987,0.00021621537,0.00030094234,0.000937996,0.0024983787,0.000063667365,0.000019111167],"category_scores_gemma":[0.001216817,0.00010056906,0.000036905734,0.0013523189,0.000069605216,0.0020615035,0.0025145542,0.00017079504,0.00009444429],"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":[0.000016444934,0.00035056585,0.000038377813,0.0000862555,0.00003424666,0.000021035763,0.00095779315,0.000014137575,0.0008412002,0.1753126,0.2860791,0.53624827],"study_design_scores_gemma":[0.00049666286,0.000053220843,0.00000960238,0.000020603457,0.0000044467906,0.0000067548026,0.0011227553,0.6370202,0.0048256125,0.0029744138,0.35330534,0.00016039397],"about_ca_topic_score_codex":0.000040515042,"about_ca_topic_score_gemma":0.00008274393,"teacher_disagreement_score":0.63700604,"about_ca_system_score_codex":0.000040959796,"about_ca_system_score_gemma":0.00038924578,"threshold_uncertainty_score":0.9045117},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.9041873969734017,"score_gpt":0.5915173642557057,"score_spread":0.312670032717696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3208577093","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":[0.6317682,0.0956019,0.14088087,0.06290248,0.0035218494,0.005360487,0.0013546976,0.0012853155,0.057324186],"genre_scores_gemma":[0.9863779,0.003768655,0.0066708988,0.0005520498,0.00085959747,0.00008768104,0.0002168336,0.000043796634,0.0014225894],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99572396,0.0017217142,0.0004712181,0.0007529414,0.00048880285,0.00084135664],"domain_scores_gemma":[0.97539926,0.022610605,0.000048626243,0.0016778565,0.00013980652,0.00012384981],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.012033544,0.00013211857,0.0004330151,0.00014122756,0.00017278925,0.000040688927,0.0010473004,0.00015334737,0.00016530592],"category_scores_gemma":[0.07288726,0.00010974316,0.000045691693,0.0009775284,0.00018989401,0.00011116241,0.0030576377,0.0009749337,0.00008745877],"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":[0.00013610543,0.00072119484,0.16624519,0.0006319509,0.00016927582,0.0013159444,0.0004376672,0.00023877375,0.00136824,0.029540282,0.6291502,0.17004517],"study_design_scores_gemma":[0.0024015182,0.00019314486,0.12934943,0.0011217312,0.000051614166,0.00004809768,0.0017261462,0.08445199,0.00061384094,0.2969972,0.4818243,0.001220973],"about_ca_topic_score_codex":0.00063863763,"about_ca_topic_score_gemma":0.0037029819,"teacher_disagreement_score":0.35460967,"about_ca_system_score_codex":0.0002277478,"about_ca_system_score_gemma":0.00017941502,"threshold_uncertainty_score":0.9349222},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.2926327152332855,"score_gpt":0.3403536589814936,"score_spread":0.04772094374820812,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4295709232","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":[0.9981864,0.00013093381,0.00044592295,0.00009348643,0.0000064532583,0.0002515653,0.00044132193,0.0000088167735,0.00043507465],"genre_scores_gemma":[0.9993693,0.000009366124,0.0002165478,0.0000067912674,0.000026408467,0.00003396889,0.00016780291,0.000008010852,0.0001617741],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986427,0.0005093995,0.000103857856,0.00013757305,0.00043821655,0.0001682826],"domain_scores_gemma":[0.9984882,0.00006509013,0.000041384737,0.0012983446,0.000082786224,0.000024216519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010243226,0.00006479949,0.00012434805,0.00006917853,0.0009403332,0.00003422753,0.0012068056,0.000008067802,0.00004101394],"category_scores_gemma":[0.0000050939448,0.00003755979,0.000018320448,0.00043348566,0.00027612504,0.00008432148,0.002981962,0.0007090568,1.2923769e-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":[0.004184498,0.0010676176,0.63099146,0.0004895264,0.000994935,0.000001368472,0.0057104887,0.024365887,0.023244405,0.00837888,0.027993705,0.27257723],"study_design_scores_gemma":[0.0026410983,0.0005437561,0.015185762,0.00014273405,0.00009741518,0.0000051943516,0.0033064764,0.9478521,0.010373708,0.011250165,0.008189968,0.0004116776],"about_ca_topic_score_codex":0.001736769,"about_ca_topic_score_gemma":0.00019587249,"teacher_disagreement_score":0.9234862,"about_ca_system_score_codex":0.000010862994,"about_ca_system_score_gemma":0.000095205636,"threshold_uncertainty_score":0.72323775},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.4518594465811662,"score_gpt":0.42245985450033313,"score_spread":0.029399592080833092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405429927","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":[0.3273452,0.0014626201,0.5726955,0.0030046047,0.003318964,0.0015157259,0.06530108,0.0002215508,0.025134748],"genre_scores_gemma":[0.9875686,0.00005007272,0.0014276693,0.000010218104,0.00010917814,0.0000050638,0.010283904,0.000007991657,0.0005372927],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978438,0.0001215724,0.000191927,0.0005992739,0.0009834614,0.0002599455],"domain_scores_gemma":[0.99787754,0.00038031192,0.000021219821,0.0016145979,0.000019589523,0.000086762106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021599955,0.000064751715,0.000121568715,0.00020261768,0.000103793725,0.00008058574,0.0011772482,0.000031435906,0.001725483],"category_scores_gemma":[0.00033107348,0.000055332854,0.00002069418,0.0011113681,0.0002153369,0.00017604615,0.005834712,0.00019170181,0.00035647405],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018369067,0.0005846265,0.045058165,0.00016892275,0.0021333932,0.00020281482,0.0004797004,0.0042655827,0.028284822,0.0045212354,0.11838661,0.7957304],"study_design_scores_gemma":[0.00007324073,0.00001277534,0.23194721,0.000009010615,0.00007315591,7.29857e-7,0.000016912194,0.60245025,0.000030594998,0.00006518262,0.1652692,0.00005173434],"about_ca_topic_score_codex":0.020431342,"about_ca_topic_score_gemma":0.0048373733,"teacher_disagreement_score":0.7956787,"about_ca_system_score_codex":0.00006169653,"about_ca_system_score_gemma":0.000056810528,"threshold_uncertainty_score":0.99918705},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Malware; Reduction (mathematics); Big data; Graph; Artificial intelligence; Data science; Machine learning; Deep learning; Computer security; Theoretical computer science; Data mining; Mathematics","score_opus":0.1808340169138115,"score_gpt":0.4031757345333891,"score_spread":0.2223417176195776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413323615","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":[0.0015041821,0.0005263659,0.9936334,0.00053395564,0.00022519048,0.00046954435,0.000009642308,0.0011434562,0.0019542743],"genre_scores_gemma":[0.6792323,0.0025590942,0.3124769,0.000073948795,0.00016431099,0.00043759236,0.00011163782,0.000035226927,0.0049089747],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9975306,0.00054338697,0.00022983878,0.00086927344,0.0003999871,0.00042691024],"domain_scores_gemma":[0.9978488,0.00018411627,0.00005722564,0.0013988041,0.0004553805,0.00005565282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020763457,0.00014496161,0.00015115437,0.0007764096,0.00085571414,0.0003535619,0.0013155795,0.0001480313,0.000005805183],"category_scores_gemma":[0.0008303836,0.00014133217,0.000020620892,0.002765945,0.00020159029,0.0018811881,0.0021176601,0.0010344048,0.000009574987],"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":[0.000036034653,0.000034232737,0.00003537919,0.000059175774,0.000012841512,0.000008411734,0.00013867902,0.000001966738,0.042240743,0.0039830343,0.0022990375,0.9511505],"study_design_scores_gemma":[0.00015023309,0.00025813346,0.00008048946,0.00013696011,0.000003776366,0.000058532463,0.00063708494,0.0030128765,0.68538475,0.023187554,0.28689173,0.00019787862],"about_ca_topic_score_codex":0.00087462785,"about_ca_topic_score_gemma":0.00007942537,"teacher_disagreement_score":0.9509526,"about_ca_system_score_codex":0.00015873055,"about_ca_system_score_gemma":0.00012502717,"threshold_uncertainty_score":0.6581548},"labels":[],"label_agreement":null}]}