{"meta":{"query_hash":"a02047a22732","filters":{"topic":"Big Data Technologies and Applications"},"cohort_total":167,"direct_labels_cover":4,"predictions_cover":167,"exported":167,"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/a02047a22732","api":"https://metacan.xera.ac/api/v1/cohort?topic=Big+Data+Technologies+and+Applications"},"results":[{"id":"W1486792363","doi":"10.3968/5186","title":"Is the Digital Revolution Driven by an Ideology","year":2014,"lang":"en","type":"article","venue":"Studies in sociology of science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ideology; Futurist; Sociology; Enlightenment; Diversity (politics); Aesthetics; Cliché; Face (sociological concept); Philosophy of technology; Epistemology; Social science; Law; Politics; Political science; Linguistics; Philosophy of science; Philosophy; Anthropology","score_opus":0.2583378344107343,"score_gpt":0.45624415763801324,"score_spread":0.1979063232272789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1486792363","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":[0.98131233,0.0005199206,0.001339477,0.015287348,0.00020294874,0.00010231085,0.000037861864,0.000020722768,0.0011770705],"genre_scores_gemma":[0.9986636,0.00015954906,0.0005439584,0.00050336274,0.000018517558,0.000019476634,0.0000015395636,0.0000015013914,0.0000884704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984931,0.00008211807,0.00035280123,0.00045586316,0.00036287613,0.0002532368],"domain_scores_gemma":[0.9976472,0.0011695632,0.00019971844,0.00073158613,0.00022847822,0.000023418224],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0031004546,0.000070690156,0.00021397173,0.000105196676,0.00048164747,0.000014221411,0.0021440652,0.00007881304,0.000010588341],"category_scores_gemma":[0.0063625774,0.00003970255,0.000031711774,0.00080595654,0.07953224,0.00031695154,0.00078376016,0.00014425383,0.000038260867],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017245025,0.00021061888,0.23252851,0.000007534621,0.000034774883,6.994464e-7,0.057095066,0.00010684633,0.009989424,0.32356295,0.23450531,0.14194104],"study_design_scores_gemma":[0.0001898781,0.00026179067,0.060623206,0.000007955843,0.0000047449403,0.0000049952623,0.14394538,0.0018900204,0.00064157,0.7553895,0.03689224,0.00014871122],"about_ca_topic_score_codex":0.000011069891,"about_ca_topic_score_gemma":0.000017435295,"teacher_disagreement_score":0.43182656,"about_ca_system_score_codex":0.000035220906,"about_ca_system_score_gemma":0.0000354483,"threshold_uncertainty_score":0.92297274},"labels":[],"label_agreement":null},{"id":"W1496518399","doi":"","title":"Proceedings of the 2001 workshop on Multimedia and security: new challenges","year":2001,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Multimedia; Computer science; Software; Library science; Telecommunications; World Wide Web","score_opus":0.27735875866211795,"score_gpt":0.3742508454132318,"score_spread":0.09689208675111383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496518399","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":[0.6645984,0.0010429525,0.0001514939,0.19478549,0.000110495144,0.00047439412,0.000014551814,0.00016209071,0.13866012],"genre_scores_gemma":[0.9870119,0.00369962,0.0022483142,0.00033678065,0.000051859108,0.000011528928,3.5045605e-7,0.000004878722,0.006634763],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905914,0.0000036717768,0.00018318596,0.00025342064,0.00037308707,0.00012749407],"domain_scores_gemma":[0.9991459,0.00030037476,0.000090844966,0.0003320482,0.00007945632,0.000051326748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003728008,0.00006469087,0.0001059048,0.000060485367,0.00006686968,0.00005455132,0.00069945806,0.00007808476,0.00018016595],"category_scores_gemma":[0.00094617344,0.000032022006,0.000028136144,0.00048121042,0.00012761202,0.000108588574,0.00027441594,0.000103844905,0.00004316784],"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":[0.0000066351654,0.00004848254,0.0019342154,0.0000013951791,0.0000037460886,1.4011607e-7,0.00029913275,3.447401e-7,0.0002560229,0.062075417,0.21821687,0.7171576],"study_design_scores_gemma":[0.00028577863,0.00004128827,0.026658943,0.000031991196,0.000006653104,0.000009433116,0.0073913676,0.0009494463,0.002287569,0.2701865,0.692022,0.00012898508],"about_ca_topic_score_codex":0.000023140576,"about_ca_topic_score_gemma":0.00012142056,"teacher_disagreement_score":0.7170286,"about_ca_system_score_codex":0.000004618435,"about_ca_system_score_gemma":0.000012239282,"threshold_uncertainty_score":0.19726908},"labels":[],"label_agreement":null},{"id":"W1508161314","doi":"10.1177/1536867x0800800406","title":"A Shortcut through Long Loops: An Illustration of Two Alternatives to Looping over Observations","year":2008,"lang":"en","type":"article","venue":"The Stata Journal Promoting communications on statistics and Stata","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Traffic Injury Research Foundation","funders":"","keywords":"Computer science; Search engine indexing; Key (lock); Mathematical optimization; Identifier; Data mining; Operations research; Information retrieval; Mathematics","score_opus":0.5569936812276851,"score_gpt":0.48027112868617966,"score_spread":0.07672255254150545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1508161314","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":[0.33965778,0.0002520564,0.65078145,0.0061392356,0.000063902036,0.000461139,0.0023045356,0.000039786384,0.00030009888],"genre_scores_gemma":[0.8022426,0.0015622058,0.19558756,0.00028057137,0.000035796118,0.000023452792,0.00014804726,0.000016992002,0.0001028154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970868,0.00042476528,0.0010571802,0.00033850173,0.00082344323,0.0002693041],"domain_scores_gemma":[0.9933288,0.0023273078,0.0007381004,0.002727944,0.0007450552,0.0001327731],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021836427,0.00018051174,0.00028441174,0.00018565348,0.0019794423,0.00038146417,0.0030186158,0.00004255505,0.00003980142],"category_scores_gemma":[0.0025065783,0.00012383042,0.000042474814,0.0007911866,0.000667194,0.0007186542,0.0008382631,0.0005437444,0.000010993668],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006175563,0.0007577156,0.012813098,0.000017612785,0.0001393008,0.000015356112,0.017349865,0.0011771343,0.0014686384,0.77585655,0.013303757,0.17703918],"study_design_scores_gemma":[0.0016130253,0.0013978274,0.13961276,0.00033879813,0.00013761253,0.0004509469,0.013006908,0.10678811,0.00082372513,0.6995824,0.035350084,0.00089781266],"about_ca_topic_score_codex":0.00019468134,"about_ca_topic_score_gemma":0.0004192762,"teacher_disagreement_score":0.4625848,"about_ca_system_score_codex":0.000039874583,"about_ca_system_score_gemma":0.00014371234,"threshold_uncertainty_score":0.99931985},"labels":[],"label_agreement":null},{"id":"W1622445028","doi":"10.5703/1288284315628","title":"The Punishment for Dreamers: Big Data, Retention, and Academic Libraries","year":2015,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Purdue Pharma (Canada)","funders":"","keywords":"Punishment (psychology); Data retention; Computer science; Big data; Internet privacy; Computer security; Psychology; Operating system; Social psychology","score_opus":0.7045384724497639,"score_gpt":0.44020883294422797,"score_spread":0.2643296395055359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1622445028","genre_codex":"commentary","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":[0.045031738,0.007807333,0.43942595,0.48755416,0.0015514103,0.0022972047,0.0014116031,0.00074181135,0.014178768],"genre_scores_gemma":[0.9015845,0.0027809967,0.067715354,0.002520963,0.00057465315,0.00041429792,0.0004161529,0.000026492438,0.023966588],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989176,0.000019115145,0.00026153965,0.00032800468,0.00033522048,0.00013856123],"domain_scores_gemma":[0.99767655,0.00076730346,0.00009227763,0.0012905073,0.000107707536,0.00006567807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018637811,0.00005600686,0.000076804194,0.000037981572,0.00029026897,0.00046303263,0.0018054683,0.00007105396,0.000007023017],"category_scores_gemma":[0.0026030382,0.000027429227,0.000014473203,0.00027649535,0.00029796376,0.00047946564,0.001087104,0.000088464665,0.00004187523],"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":[0.0000039338456,0.0000028828154,0.00045183644,2.680606e-7,0.0000026639773,2.4733811e-8,0.00001914521,1.2654849e-7,0.000019138151,0.11063172,0.5612181,0.32765016],"study_design_scores_gemma":[0.00008418105,0.000015978576,0.00038535945,9.786664e-7,0.0000033510687,0.000001095112,0.003055348,0.0005237452,0.00019297583,0.2979951,0.69770795,0.00003396504],"about_ca_topic_score_codex":0.000018587923,"about_ca_topic_score_gemma":0.000037097347,"teacher_disagreement_score":0.8565528,"about_ca_system_score_codex":0.000005710752,"about_ca_system_score_gemma":0.000052113282,"threshold_uncertainty_score":0.44650343},"labels":[],"label_agreement":null},{"id":"W163543987","doi":"","title":"Advancing Geoinformation Science for a Changing World ed. by Stan Geertman, Wolfgang Reinhardt, Fred Toppen (review)","year":2013,"lang":"en","type":"article","venue":"Cartographica The International Journal for Geographic Information and Geovisualization","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Environmental ethics; History; Philosophy","score_opus":0.03422490018015934,"score_gpt":0.36065340669428153,"score_spread":0.3264285065141222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W163543987","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":[0.04969478,0.006687339,0.8786934,0.052693512,0.0029936824,0.0066114217,0.0008441558,0.00033784827,0.0014438446],"genre_scores_gemma":[0.8978612,0.051525638,0.0105667,0.031381123,0.0007938405,0.0034543453,0.0031845719,0.00006808532,0.0011645057],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99620676,0.000041019477,0.0013628948,0.0002761013,0.0015578847,0.0005553189],"domain_scores_gemma":[0.9938008,0.00048762577,0.0011480482,0.0004313275,0.003959289,0.00017290011],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005625808,0.00022294694,0.00024680127,0.0027728193,0.001847131,0.0020349978,0.0016721783,0.00008775893,0.00011883778],"category_scores_gemma":[0.00251562,0.0001532592,0.00023592102,0.0030599055,0.00035141432,0.0055765873,0.000291423,0.00021980639,0.000024100062],"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":[0.000057782094,0.000050468007,0.0024271559,0.000113623544,0.000117356714,1.7355738e-7,0.0006564571,0.00019331246,0.00090074394,0.10679331,0.5482101,0.34047952],"study_design_scores_gemma":[0.0008610879,0.00010040881,0.0014477572,0.00026187318,0.00005067061,0.00005600439,0.0026711076,0.03871291,0.00049200427,0.022187356,0.9328353,0.0003235308],"about_ca_topic_score_codex":0.00002754477,"about_ca_topic_score_gemma":0.00002663655,"teacher_disagreement_score":0.8681267,"about_ca_system_score_codex":0.00006950608,"about_ca_system_score_gemma":0.00010948784,"threshold_uncertainty_score":0.99945235},"labels":[],"label_agreement":null},{"id":"W1724277128","doi":"10.3968/6594","title":"Socio-Economy Plans & Growth Features","year":2015,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Continuance; CLARITY; Sustainability; Civilization; Quality (philosophy); Competition (biology); Business; Economic system; Political economy; Economics; Political science; Ecology; Law","score_opus":0.18178657641399315,"score_gpt":0.4156774503240427,"score_spread":0.23389087391004953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1724277128","genre_codex":"other","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":[0.07175636,0.0001547728,0.0004131193,0.027978681,0.0013439311,0.00024671538,0.000055729313,0.0001210876,0.8979296],"genre_scores_gemma":[0.9901632,0.0000026569928,0.0010882594,0.0005127201,0.00017906606,0.000028460903,0.0000051713278,0.0000031654356,0.0080172885],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984368,0.000024414237,0.00027494662,0.00034875303,0.0007248024,0.00019025462],"domain_scores_gemma":[0.9983565,0.000101676436,0.00023667343,0.0003572457,0.00083279033,0.00011512112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001247088,0.00007194595,0.00012746394,0.0001890074,0.00033637718,0.00018843623,0.0015917029,0.000073640156,0.00019659406],"category_scores_gemma":[0.0004495374,0.00005654952,0.00004168626,0.001644676,0.0011080195,0.0005686696,0.00019036337,0.00008969638,0.00018562583],"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":[0.0000014028038,0.00005617449,0.002957193,7.583702e-7,9.3234326e-7,2.3093893e-8,0.00054101646,2.2189663e-7,0.00023395554,0.81000644,0.17800377,0.008198095],"study_design_scores_gemma":[0.000073286385,0.000016638123,0.20343208,0.0000019867164,0.0000031733248,9.0414017e-7,0.0049827574,0.0000019364047,0.0008947012,0.3225471,0.46795285,0.00009258075],"about_ca_topic_score_codex":0.00008851212,"about_ca_topic_score_gemma":0.0000017194634,"teacher_disagreement_score":0.91840684,"about_ca_system_score_codex":0.0000978307,"about_ca_system_score_gemma":0.00086033414,"threshold_uncertainty_score":0.4082544},"labels":[],"label_agreement":null},{"id":"W1746751216","doi":"","title":"Four Changes of Modern Universities From the Perspective of “4V” of Big Data","year":2015,"lang":"en","type":"article","venue":"Canadian social science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Variety (cybernetics); Perspective (graphical); Value (mathematics); Discipline; Balance (ability); Independence (probability theory); Volume (thermodynamics); Data science; Sociology; Political science; Public relations; Computer science; Social science; Psychology; Data mining","score_opus":0.5205431722637939,"score_gpt":0.3891481667219264,"score_spread":0.13139500554186745,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1746751216","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":[0.80997616,0.0008818389,0.0035513602,0.044207405,0.00054927834,0.0004348125,0.018685285,0.000032966214,0.12168086],"genre_scores_gemma":[0.9995307,0.000007740636,0.0002726384,0.00006949761,0.000043577944,7.614342e-7,0.0000049757978,0.0000014101987,0.00006874704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9988051,0.0000265724,0.00012871798,0.00025000263,0.0006386314,0.000150966],"domain_scores_gemma":[0.9981247,0.0001906227,0.00017198709,0.0007892887,0.00062316534,0.0001002148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010757429,0.00004234007,0.00012305917,0.00013798752,0.00019397584,0.000030071902,0.0037437559,0.00004223398,0.000015227128],"category_scores_gemma":[0.00096257264,0.00002942485,0.000018350389,0.0014373304,0.0023487278,0.00019610269,0.00047793557,0.00005351705,0.0000032079513],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011708789,0.000029806108,0.011723756,0.0000021884664,0.000023698138,0.0000023389966,0.027307296,0.000008415789,0.0037100222,0.62031394,0.050021563,0.28684524],"study_design_scores_gemma":[0.00019882325,0.000052434993,0.02102668,0.000013232257,0.000021799042,6.744212e-7,0.6606896,0.0010208901,0.002142895,0.26150495,0.053172827,0.0001552299],"about_ca_topic_score_codex":0.13853553,"about_ca_topic_score_gemma":0.21165799,"teacher_disagreement_score":0.63338226,"about_ca_system_score_codex":0.00015154645,"about_ca_system_score_gemma":0.0016381294,"threshold_uncertainty_score":0.86720103},"labels":[],"label_agreement":null},{"id":"W1986663507","doi":"10.1002/bult.2007.1720340104","title":"Folksonomies: Introduction: Folksonomies and image tagging: Seeing the future?","year":2007,"lang":"en","type":"article","venue":"Bulletin of the American Society for Information Science and Technology","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":20,"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":"","keywords":"Folksonomy; Bookmarking; World Wide Web; Computer science; The Internet; Information retrieval; Multimedia","score_opus":0.027997836696210702,"score_gpt":0.30930805775715353,"score_spread":0.28131022106094283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986663507","genre_codex":"commentary","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":[0.37748775,0.00025774486,0.01748326,0.60258955,0.00027489424,0.0007340564,0.000047622187,0.0001600492,0.00096507877],"genre_scores_gemma":[0.9583711,0.00039051325,0.037406392,0.0034742528,0.00015225948,0.00007110286,0.0000021218148,0.000005540834,0.00012668496],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9984854,0.000008417146,0.0004918008,0.0002597866,0.0004695019,0.00028509618],"domain_scores_gemma":[0.99740946,0.00041264892,0.0007345114,0.0007840791,0.00062504143,0.000034249042],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0045350106,0.00010544279,0.0001976996,0.00021638398,0.0011372357,0.00022495163,0.0014758704,0.00006645253,0.000008235218],"category_scores_gemma":[0.0018017906,0.00005802179,0.00009370518,0.0025345725,0.0076994295,0.00043803413,0.00078917306,0.00016942082,0.000010059191],"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":[0.000016712944,0.000012445101,0.0011256313,0.00000906872,0.000017864786,2.1099321e-8,0.0007045872,0.000003607382,0.0019035641,0.16743563,0.19886339,0.6299075],"study_design_scores_gemma":[0.00011583647,0.000047391946,0.003295943,0.0000024991616,0.000008399303,0.000015518062,0.047677606,0.00019335575,0.0030333763,0.00640172,0.9391318,0.000076537006],"about_ca_topic_score_codex":0.00002389975,"about_ca_topic_score_gemma":0.0000050365597,"teacher_disagreement_score":0.7402684,"about_ca_system_score_codex":0.000043425654,"about_ca_system_score_gemma":0.00007417425,"threshold_uncertainty_score":0.995001},"labels":[],"label_agreement":null},{"id":"W1991222875","doi":"10.1109/iembs.2010.5625982","title":"Intelligent Clinical Decision Support Systems based on SNOMED CT","year":2010,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"SNOMED CT; Computer science; Decision support system; Clinical decision support system; Systematized Nomenclature of Medicine; Artificial intelligence; Data mining; Intelligent decision support system; Process (computing); Information retrieval; Terminology","score_opus":0.3280054473452616,"score_gpt":0.4708973819526968,"score_spread":0.1428919346074352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1991222875","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":[0.46716282,0.000013184904,0.45967796,0.008044789,0.004960896,0.0010027142,0.0001518981,0.0007242969,0.058261443],"genre_scores_gemma":[0.9882426,0.000012097458,0.009152052,0.00069941854,0.00009844331,0.000042568146,0.000016259915,0.0000084635,0.0017280697],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969928,0.00005419204,0.0010451019,0.0006600961,0.0010137543,0.00023400711],"domain_scores_gemma":[0.99355686,0.0035869367,0.00020146414,0.0022998925,0.00018718398,0.000167675],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004400928,0.00012777337,0.00027437575,0.00022921566,0.00013857838,0.0003032423,0.0017803278,0.00014120761,0.0025441416],"category_scores_gemma":[0.0053864853,0.000075044445,0.0001478228,0.0006491694,0.00019198668,0.000106657964,0.00025767338,0.00044946244,0.0064588487],"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":[0.000022238311,0.00023788885,0.009557418,8.360403e-7,0.0000035976097,0.000007334787,0.0000025733764,0.00007005099,0.00013094669,0.042064756,0.2252739,0.7226285],"study_design_scores_gemma":[0.00020740024,0.00014534334,0.007349082,0.0000054093407,0.0000039526212,0.0000073926844,0.00017349594,0.030837798,0.000778997,0.0076815644,0.95267177,0.00013779251],"about_ca_topic_score_codex":0.000032359745,"about_ca_topic_score_gemma":0.00008011416,"teacher_disagreement_score":0.72739786,"about_ca_system_score_codex":0.0000126835885,"about_ca_system_score_gemma":0.000081381084,"threshold_uncertainty_score":0.99836767},"labels":[],"label_agreement":null},{"id":"W2016395525","doi":"10.3109/0142159x.2014.917761","title":"Better data ≫ Bigger data","year":2014,"lang":"en","type":"letter","venue":"Medical Teacher","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Computer science; Data science","score_opus":0.6124631028625367,"score_gpt":0.4637355412884244,"score_spread":0.14872756157411227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2016395525","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042517382,0.0002527689,0.01499268,0.9731428,0.00059705746,0.00020450221,0.0012885751,0.00028100552,0.009198095],"genre_scores_gemma":[0.0001818745,0.00007978036,0.0022213573,0.93929386,0.0107882125,0.000037873997,0.022069018,0.00006586461,0.025262175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9900721,0.00038587966,0.0010659739,0.0026346592,0.005192975,0.00064843585],"domain_scores_gemma":[0.97278595,0.0011288963,0.00039598678,0.025388168,0.00009834479,0.00020263257],"candidate_categories":["metaresearch","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science","research_integrity","insufficient_payload"],"category_scores_codex":[0.007971082,0.00038305297,0.0007212393,0.00023658645,0.00016496406,0.0004325746,0.039429266,0.0024748717,0.028270844],"category_scores_gemma":[0.020124817,0.00023940849,0.000085837295,0.0006342185,0.00078492204,0.000409083,0.016090311,0.0049287537,0.011259397],"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":[5.480368e-7,0.000023194518,0.00022854422,0.0000049179453,0.000022963844,0.00006456047,0.000003377476,7.082468e-9,2.4455386e-7,0.000034459586,0.811084,0.18853322],"study_design_scores_gemma":[0.00013490782,0.000008908958,0.000038124763,0.000031459524,0.00003991825,0.000030394724,0.0000138202995,0.0054107993,4.8105454e-7,0.005482778,0.98849297,0.000315417],"about_ca_topic_score_codex":0.000103807426,"about_ca_topic_score_gemma":0.000036490925,"teacher_disagreement_score":0.18821779,"about_ca_system_score_codex":0.000025357596,"about_ca_system_score_gemma":0.00020161568,"threshold_uncertainty_score":0.9988201},"labels":[],"label_agreement":null},{"id":"W2069440547","doi":"10.1109/mdso.2004.1270710","title":"Guest editors' introduction [Data-intensive computing]","year":2004,"lang":"en","type":"article","venue":"IEEE Distributed Systems Online","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Computer science","score_opus":0.18926746312373835,"score_gpt":0.38889982800576756,"score_spread":0.1996323648820292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2069440547","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":[0.13585877,0.00047701356,0.6716802,0.057866838,0.06905731,0.0011379662,0.062627845,0.0012478236,0.00004619846],"genre_scores_gemma":[0.9483584,0.000016628013,0.0009941179,0.0001191816,0.03709457,0.000013383372,0.013299512,0.000017206045,0.00008700219],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663186,0.000074286094,0.0009827177,0.0009971744,0.00094888284,0.00036508922],"domain_scores_gemma":[0.99457777,0.00026090947,0.00048795188,0.0029765232,0.0015735441,0.00012329772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011717574,0.00021515197,0.00042880705,0.00015328647,0.00027870986,0.00033973792,0.0024109373,0.0002193708,0.000015059918],"category_scores_gemma":[0.0038888112,0.00016308046,0.00007079203,0.0012248135,0.00020143093,0.00038147107,0.0004448194,0.0003385656,0.00068446406],"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":[0.000008917933,0.00017308668,0.00016508558,0.0000066780085,0.00002624682,0.000009288385,0.00002178984,0.003989321,0.0008296537,0.0017740722,0.9908777,0.0021181633],"study_design_scores_gemma":[0.00047987758,0.000060810915,0.0007293142,0.0000324478,0.00002435348,0.00008758222,0.0030553688,0.006971734,0.00054561056,0.0013660303,0.9863901,0.0002567775],"about_ca_topic_score_codex":0.0004013454,"about_ca_topic_score_gemma":0.00007635288,"teacher_disagreement_score":0.81249964,"about_ca_system_score_codex":0.00013907046,"about_ca_system_score_gemma":0.00008844852,"threshold_uncertainty_score":0.87976295},"labels":[],"label_agreement":null},{"id":"W207420180","doi":"","title":"Using Kerberos to provide secure authentication for DB2","year":2011,"lang":"en","type":"article","venue":"Conference of the Centre for Advanced Studies on Collaborative Research","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada)","funders":"","keywords":"Kerberos; Computer security; Computer science; Authentication (law); Authentication protocol; Single sign-on; Password","score_opus":0.7905099832838044,"score_gpt":0.5572253473335264,"score_spread":0.23328463595027804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W207420180","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":[0.73277456,0.0013068346,0.14039946,0.07807224,0.0020640579,0.033966865,0.008194146,0.00020793467,0.003013888],"genre_scores_gemma":[0.9632363,0.00006525354,0.034215212,0.00004083176,0.000027138243,0.00085714145,0.0000046781347,0.000013377173,0.0015401202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99757165,0.0001682403,0.00047699764,0.0005719934,0.00079717144,0.00041395062],"domain_scores_gemma":[0.98705,0.0025179295,0.0003037367,0.0010480968,0.009004624,0.000075592456],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001822892,0.00014559971,0.00032085725,0.00019552646,0.0007482612,0.00007697589,0.001502172,0.00006886757,0.00001609602],"category_scores_gemma":[0.024169568,0.00008728509,0.00008308067,0.0020788587,0.00058055524,0.00018443949,0.00059429073,0.00015125037,0.0000149702355],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012002514,0.00041526306,0.00046693895,0.00011264329,0.00018076203,2.9645088e-7,0.018061299,0.00030806792,0.063739315,0.8145729,0.032067176,0.06887509],"study_design_scores_gemma":[0.00091610645,0.00071739696,0.00037959308,0.000270086,0.000027418093,2.4868186e-7,0.11155416,0.0020621666,0.36790323,0.3898037,0.12609886,0.00026699866],"about_ca_topic_score_codex":0.0000047377152,"about_ca_topic_score_gemma":0.00020634285,"teacher_disagreement_score":0.42476916,"about_ca_system_score_codex":0.0001368834,"about_ca_system_score_gemma":0.0003067656,"threshold_uncertainty_score":0.9840503},"labels":[],"label_agreement":null},{"id":"W2145090263","doi":"10.1109/igarss.1989.577763","title":"Specifications For Gis And Image Analysis Data A Government Perspective","year":2005,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Government of British Columbia","funders":"","keywords":"Perspective (graphical); Computer science; Government (linguistics); Image (mathematics); Data science; Information retrieval; Computer vision; Artificial intelligence","score_opus":0.47357637904697797,"score_gpt":0.4478742357616225,"score_spread":0.025702143285355472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2145090263","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":[0.004697002,0.00018432985,0.87748635,0.0911867,0.000013683501,0.00039527705,0.0042723618,0.00009812756,0.021666178],"genre_scores_gemma":[0.6278192,0.000116476906,0.36723396,0.00024295533,0.00006113822,0.000075181604,0.000090240035,0.000004742249,0.0043561],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986632,0.000009611234,0.00023319492,0.0005740539,0.00040821958,0.00011175415],"domain_scores_gemma":[0.997258,0.0005186462,0.00008754566,0.0019572244,0.00013461408,0.000043975695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005985107,0.00006224731,0.00013070955,0.00008585126,0.00016822726,0.00022524875,0.0011949447,0.000033217715,0.00047417267],"category_scores_gemma":[0.0011449142,0.000043019285,0.000046915975,0.0009199917,0.00011885221,0.00037244143,0.00053149555,0.000040984047,0.00009800801],"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":[0.0000065066515,0.00012813289,0.0010794643,4.8649406e-7,0.00014897037,1.2139806e-7,0.00012099106,0.000009816246,0.00085228303,0.5055893,0.34614754,0.14591637],"study_design_scores_gemma":[0.00015290167,0.00001579272,0.015307625,4.5235345e-7,0.00015455433,9.788237e-7,0.010676248,0.03201179,0.00053303747,0.033786964,0.90724266,0.00011700543],"about_ca_topic_score_codex":0.000050596802,"about_ca_topic_score_gemma":0.0007369413,"teacher_disagreement_score":0.6231222,"about_ca_system_score_codex":0.000051568233,"about_ca_system_score_gemma":0.000011648993,"threshold_uncertainty_score":0.51918584},"labels":[],"label_agreement":null},{"id":"W2146211415","doi":"10.5430/wjss.v1n1p37","title":"Privacy in the Age of Big Data: Exploring the Role of Modern Identity Management Systems","year":2013,"lang":"en","type":"article","venue":"World Journal of Social Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University","keywords":"Identity management; Big data; Identity (music); Digital identity; Government (linguistics); Internet privacy; Information privacy; Identity theft; Data management; Business; Data security; Data Protection Act 1998; Data science; Computer security; Computer science; Authentication (law); Access control","score_opus":0.36061467841899086,"score_gpt":0.39160121053047325,"score_spread":0.03098653211148239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2146211415","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":[0.971722,0.0008601239,0.0082956925,0.0056144255,0.0006533994,0.0005658801,0.000027048038,0.000009383537,0.012252051],"genre_scores_gemma":[0.9994377,0.000079528036,0.00031848747,0.000029198241,0.00007247214,0.000010157156,2.5669567e-7,0.000001521641,0.000050694613],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99728435,0.000074013085,0.0006273581,0.00016087513,0.0016936245,0.0001598059],"domain_scores_gemma":[0.9981343,0.00024321816,0.000621283,0.0007528783,0.00022741749,0.000020882224],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0064925654,0.00005121824,0.00016434453,0.00027679245,0.00027124467,0.00031974103,0.007334167,0.000013125183,0.000007414513],"category_scores_gemma":[0.00040836752,0.000024735253,0.00004483716,0.0028410056,0.00071993656,0.001534952,0.0010990436,0.00016446669,0.0000064635533],"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":[0.0000051047423,0.00013464001,0.0069366847,0.000009320266,0.000013632156,0.0000037713519,0.0041983183,0.00009755699,0.006396367,0.26344663,0.0031716933,0.7155863],"study_design_scores_gemma":[0.0002578328,0.000034821765,0.44737327,0.0000866544,0.000026156955,0.000009099303,0.05021312,0.0013085518,0.00054697227,0.40752771,0.092484295,0.00013151363],"about_ca_topic_score_codex":0.00017480833,"about_ca_topic_score_gemma":0.000106433654,"teacher_disagreement_score":0.71545476,"about_ca_system_score_codex":0.000030513365,"about_ca_system_score_gemma":0.000046068326,"threshold_uncertainty_score":0.9980366},"labels":[],"label_agreement":null},{"id":"W2189821794","doi":"10.48550/arxiv.1512.02019","title":"Status Report Of The Dphep Collaboration: A Global Effort For Sustainable Data Preservation In High Energy Physics","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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":"Institute of Particle Physics","funders":"","keywords":"Blueprint; National laboratory; Library science; Data sharing; Political science; Medical education; Engineering; Medicine; Computer science; Engineering physics; Alternative medicine","score_opus":0.3405370817150935,"score_gpt":0.3135485827336533,"score_spread":0.02698849898144018,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2189821794","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":[0.47390148,0.00011182076,0.51438797,0.0016728988,0.0004422625,0.0017752112,0.004308202,0.00012012369,0.0032800534],"genre_scores_gemma":[0.99524325,0.00005701698,0.0009113054,0.000027642795,0.000044988712,0.000010192733,0.0009035772,0.0000075015055,0.0027945456],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99782705,0.00007007209,0.0004833582,0.0010266645,0.0003079197,0.0002849382],"domain_scores_gemma":[0.9927341,0.0001820475,0.00087651424,0.0044938517,0.0016527793,0.00006072105],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011872784,0.00016800038,0.00032804837,0.0000912581,0.00013241782,0.00013657215,0.003737603,0.0002725363,0.000008065213],"category_scores_gemma":[0.0017656878,0.00013803437,0.00007415059,0.0027450533,0.00019985564,0.0007907548,0.005827838,0.00016852861,0.000002205938],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000051205356,0.00009731585,0.025504798,0.000025475241,0.000025636971,0.000028058757,0.000023410108,0.051761415,0.0000016111352,0.88218313,0.039496295,0.0008016695],"study_design_scores_gemma":[0.0003728176,0.000021683416,0.004253242,0.000017456447,0.000042214117,0.0000012216941,0.0013599226,0.05340445,0.000045129156,0.87394005,0.06639019,0.00015159165],"about_ca_topic_score_codex":0.003248836,"about_ca_topic_score_gemma":0.0025394415,"teacher_disagreement_score":0.52134174,"about_ca_system_score_codex":0.00036579501,"about_ca_system_score_gemma":0.001267585,"threshold_uncertainty_score":0.7263983},"labels":[],"label_agreement":null},{"id":"W2206422764","doi":"","title":"Big data Analysis: The n ext f rontier","year":2013,"lang":"en","type":"article","venue":"Bank of Canada review","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Exploit; Big data; Complement (music); Inflation (cosmology); Set (abstract data type); Data science; Economics; Computer science; Data mining; Computer security","score_opus":0.35629134290762593,"score_gpt":0.3743734165200423,"score_spread":0.01808207361241637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206422764","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009483947,0.70137143,0.012720023,0.26586697,0.00041510278,0.001686131,0.0011673331,0.000051856685,0.015772767],"genre_scores_gemma":[0.7540415,0.20096652,0.0059616244,0.025045274,0.00023955705,0.0005146944,0.00042983505,0.000029512119,0.01277152],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818623,0.000060330083,0.0005258228,0.0003060409,0.0007792006,0.00014238594],"domain_scores_gemma":[0.99502033,0.0002674632,0.000274576,0.004201445,0.00018957951,0.000046618137],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012584479,0.00007238768,0.00033254878,0.00004844118,0.000090782545,0.000054694377,0.0038050124,0.000023574288,0.0011858508],"category_scores_gemma":[0.0014677878,0.000035120673,0.00006579326,0.0019342175,0.00007915649,0.00012865143,0.00055498467,0.0000726953,0.000056327204],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.7070007e-8,0.000002339831,0.00008703877,0.00000991129,0.000026261217,1.1117131e-7,4.7001902e-7,6.4928287e-7,0.0000014065749,0.00073319115,0.6210644,0.37807414],"study_design_scores_gemma":[0.000013675144,0.0000019823437,0.0059180795,0.000045998353,0.00016502939,7.503371e-7,0.000051132214,0.00021621231,0.000006575397,0.0015115825,0.9920208,0.000048189824],"about_ca_topic_score_codex":0.19149408,"about_ca_topic_score_gemma":0.49258155,"teacher_disagreement_score":0.75309306,"about_ca_system_score_codex":0.0000144304295,"about_ca_system_score_gemma":0.00032118167,"threshold_uncertainty_score":0.9997272},"labels":[],"label_agreement":null},{"id":"W2216178707","doi":"","title":"Big data curation","year":2014,"lang":"en","type":"article","venue":"International Conference on Management of Data","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Data science; Data curation; Variety (cybernetics); Data management; Analytics; Semantics (computer science); Data modeling; Data mining; Database; Artificial intelligence","score_opus":0.7668386003949124,"score_gpt":0.4910349129574692,"score_spread":0.27580368743744316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2216178707","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":[0.0024213877,0.000017066777,0.6792082,0.033963222,0.0010733022,0.0003499206,0.005483822,0.00011970179,0.27736336],"genre_scores_gemma":[0.9827741,0.00017812251,0.011260544,0.00019070243,0.0001007873,0.000008815004,0.004116593,0.0000047733906,0.0013655806],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.997626,0.000037035374,0.00042933313,0.0007013965,0.001106019,0.00010020687],"domain_scores_gemma":[0.99424666,0.00016650026,0.0002664218,0.005107256,0.00018550004,0.0000276828],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0014737687,0.00008721791,0.000116828196,0.00017860909,0.000053152733,0.00022813452,0.01170412,0.00003662635,0.00043028573],"category_scores_gemma":[0.0004970837,0.00006815664,0.000015291835,0.00027240635,0.00009156787,0.001007236,0.0049964115,0.000081911305,0.00048069173],"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":[0.000005251692,0.000039376497,0.00009350134,0.0000018125213,0.000018305309,3.5441036e-7,0.000001746248,0.0000032752162,0.000041298063,0.48448837,0.036176022,0.4791307],"study_design_scores_gemma":[0.00022306877,0.000032188622,0.0027831148,0.000038789567,0.000013861391,6.292803e-7,0.0003140316,0.081826754,0.000070774215,0.12960614,0.7849844,0.00010621746],"about_ca_topic_score_codex":0.000020948824,"about_ca_topic_score_gemma":0.000034718407,"teacher_disagreement_score":0.9803527,"about_ca_system_score_codex":0.000009660845,"about_ca_system_score_gemma":0.000014040683,"threshold_uncertainty_score":0.99364305},"labels":[],"label_agreement":null},{"id":"W2220295922","doi":"","title":"Predicament and Countermeasures in Exploitation and Utilization of College Archives Compiling Achievements","year":2015,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Exploit; Compiler; Computer science; Staffing; Engineering management; Engineering ethics; Political science; Engineering; Computer security; Programming language","score_opus":0.3092714976103863,"score_gpt":0.43816311471459807,"score_spread":0.12889161710421176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2220295922","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":[0.99246126,0.0001589044,0.00036206385,0.0010424387,0.00012849635,0.00018557631,0.000027521603,0.000009024986,0.0056246803],"genre_scores_gemma":[0.998547,0.000024569883,0.0012200018,0.00003519363,0.000012469035,0.000017317509,0.000003087048,0.0000014775834,0.00013886811],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987898,0.000034400593,0.00029201712,0.00020463631,0.00059861474,0.00008055246],"domain_scores_gemma":[0.99931306,0.000103665385,0.00021118353,0.0001241001,0.00020211973,0.000045895402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095482176,0.000043275555,0.00009967742,0.00022489291,0.00010033238,0.000036490106,0.00027801216,0.000025941052,0.000008495541],"category_scores_gemma":[0.00030153678,0.00003678448,0.000007690436,0.0008252328,0.00085706904,0.00030644352,0.00010878485,0.000033129545,6.2625895e-7],"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":[0.000028479482,0.00038940017,0.13981326,0.00002009175,0.000003236596,4.9817974e-8,0.010011197,0.0000061887267,0.017945243,0.74792814,0.0019938862,0.081860855],"study_design_scores_gemma":[0.00016980212,0.000033543212,0.9317297,0.00001913595,0.000002361943,2.174182e-7,0.009941578,0.00016096275,0.0015215405,0.0520275,0.0043511936,0.000042495605],"about_ca_topic_score_codex":0.00003131689,"about_ca_topic_score_gemma":0.0000037601287,"teacher_disagreement_score":0.79191643,"about_ca_system_score_codex":0.000026465128,"about_ca_system_score_gemma":0.00021566286,"threshold_uncertainty_score":0.31579065},"labels":[],"label_agreement":null},{"id":"W2261525379","doi":"10.1016/j.ijinfomgt.2014.10.007","title":"Beyond the hype: Big data concepts, methods, and analytics","year":2014,"lang":"en","type":"article","venue":"International Journal of Information Management","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4125,"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":"Big data; Data science; Computer science; Unstructured data; LEAPS; Leverage (statistics); Analytics; Data analysis; Data mining; Artificial intelligence","score_opus":0.23655520585197082,"score_gpt":0.4581771931797269,"score_spread":0.22162198732775606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2261525379","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":[0.0010293863,0.00007495159,0.9636453,0.0218739,0.00095549587,0.00009710473,0.000055624234,0.000012143613,0.012256131],"genre_scores_gemma":[0.6700888,0.0012722268,0.3189251,0.008342655,0.0006534676,0.000008513316,0.0001255369,0.00000766288,0.0005760093],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979556,0.000072352144,0.0007981947,0.000092872506,0.0010030429,0.00007789022],"domain_scores_gemma":[0.9974319,0.0005097968,0.00080174836,0.0006530798,0.0005662616,0.00003724702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004771884,0.000066176275,0.00011036589,0.00032722644,0.00008932712,0.0005748239,0.0030687507,0.000029112858,0.00004319624],"category_scores_gemma":[0.0013899339,0.000037480535,0.000036767073,0.00027682868,0.00010918147,0.0012482179,0.0010820336,0.00012559783,0.00005731056],"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":[0.0000059042186,0.0000070030105,0.00013714013,0.000001142985,0.000054079166,4.210728e-7,0.000054833617,0.00013538913,0.0000037743005,0.102921054,0.057105772,0.8395735],"study_design_scores_gemma":[0.00024448227,0.000016674723,0.003764349,0.000006485138,0.000020184103,0.000025551708,0.001422873,0.012106438,0.0000347203,0.07782294,0.9044902,0.000045113007],"about_ca_topic_score_codex":0.0000040749865,"about_ca_topic_score_gemma":0.000003145575,"teacher_disagreement_score":0.8473844,"about_ca_system_score_codex":0.000023503811,"about_ca_system_score_gemma":0.000015401623,"threshold_uncertainty_score":0.57025534},"labels":[],"label_agreement":null},{"id":"W2281400598","doi":"10.4033/iee.2015.8.15.e","title":"The problem with data","year":2015,"lang":"en","type":"article","venue":"Ideas in Ecology and Evolution","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","score_opus":0.23942108589981206,"score_gpt":0.38072477722674514,"score_spread":0.14130369132693307,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2281400598","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":[0.9484131,0.0012130737,0.009087208,0.034604196,0.0001769501,0.00042586782,0.000050342052,0.000086568565,0.0059427316],"genre_scores_gemma":[0.9974728,0.000041945186,0.0021594453,0.000052662763,0.000014214433,0.000026817335,0.000008827656,0.0000015120145,0.00022172407],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9992632,0.00005319109,0.00016038127,0.00024373076,0.0001499898,0.00012945749],"domain_scores_gemma":[0.9988124,0.0003458627,0.00006424897,0.0006815244,0.00006754529,0.000028462271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018927311,0.000039386425,0.00006548816,0.00004831683,0.00017735608,0.000049493356,0.00071956543,0.00006888691,0.0000028482405],"category_scores_gemma":[0.0008366106,0.000020252712,0.0000035873918,0.00032812372,0.0002922885,0.00020936651,0.0004062024,0.00010066917,0.00006106935],"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":[0.000042118987,0.000034568297,0.6179775,6.110583e-7,0.000004850131,0.0000019021155,0.000047612262,0.00007145693,0.000005552541,0.24382536,0.07855757,0.05943089],"study_design_scores_gemma":[0.00017437636,0.00004786161,0.39199188,0.0000015106482,0.0000023041273,0.000014499962,0.0007452833,0.0019987223,0.0000012014551,0.4957812,0.10920583,0.00003529723],"about_ca_topic_score_codex":0.00007941903,"about_ca_topic_score_gemma":0.0071790577,"teacher_disagreement_score":0.25195587,"about_ca_system_score_codex":0.000027624003,"about_ca_system_score_gemma":0.000066790795,"threshold_uncertainty_score":0.40060827},"labels":[],"label_agreement":null},{"id":"W2339387061","doi":"10.15168/11572_142585","title":"Big Data: Privacy and Intellectual Property in a Comparative Perspective","year":2016,"lang":"en","type":"article","venue":"Institutional Research Information System (Università degli Studi di Trento)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"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":"","keywords":"Intellectual property; Perspective (graphical); Big data; Internet privacy; Information privacy; Property (philosophy); Computer science; Business; Epistemology; Data mining; Artificial intelligence","score_opus":0.6992794951661098,"score_gpt":0.4643512250992411,"score_spread":0.23492827006686867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2339387061","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":[0.64092684,0.00061255175,0.14491707,0.023072852,0.00069697143,0.0038590268,0.0032558306,0.00045331576,0.18220556],"genre_scores_gemma":[0.9989281,0.00009173517,0.00021975278,0.00001655466,0.000045294913,0.000047528374,0.000046475445,0.0000026561947,0.0006018798],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963268,0.00026343876,0.00054934045,0.0005250423,0.0019441936,0.00039115615],"domain_scores_gemma":[0.9956881,0.0014240661,0.00018064046,0.0009856422,0.0015776353,0.0001439251],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029269329,0.00015583081,0.0002917943,0.0015395109,0.0008768116,0.00032047258,0.0018631265,0.00010787098,0.000047603244],"category_scores_gemma":[0.0042965733,0.000085464104,0.000037492817,0.0026306952,0.0010754958,0.0045126285,0.0024891545,0.00028523893,0.00093306403],"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":[0.00032271823,0.0001700749,0.007426798,0.000035502948,0.000103356884,0.000020228674,0.0148445,0.000037945727,0.00008652936,0.68160933,0.048192773,0.24715027],"study_design_scores_gemma":[0.0027114754,0.00018931263,0.045429774,0.00030641444,0.000011058572,0.00006103671,0.27359807,0.0053680437,0.0000642742,0.0020207036,0.6698831,0.00035678325],"about_ca_topic_score_codex":0.0006072095,"about_ca_topic_score_gemma":0.0004221818,"teacher_disagreement_score":0.6795886,"about_ca_system_score_codex":0.0010408796,"about_ca_system_score_gemma":0.0005501481,"threshold_uncertainty_score":0.99984485},"labels":[],"label_agreement":null},{"id":"W2340450237","doi":"10.5040/9781501306549.0006","title":"Big Data as System of Knowledge: Investigating Canadian Governance","year":2016,"lang":"en","type":"book-chapter","venue":"Bloomsbury Academic eBooks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"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":"","keywords":"Corporate governance; Big data; Data science; Knowledge management; Business; Computer science; Political science; Data mining; Finance","score_opus":0.3485527211434682,"score_gpt":0.36656413680526895,"score_spread":0.018011415661800756,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2340450237","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002825735,0.005889216,0.00014919386,0.0012118303,0.00068159244,0.00059370336,0.006792407,0.00020295428,0.98419654],"genre_scores_gemma":[0.05069325,0.00088031427,0.0005874792,0.000375768,0.0011419597,0.000055438075,0.0001281518,0.00010772193,0.9460299],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99511045,0.000051637347,0.0016749526,0.0014670488,0.001149886,0.0005459981],"domain_scores_gemma":[0.9917207,0.0009533109,0.0016272954,0.004927428,0.00032825654,0.0004430256],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0021960775,0.00047576026,0.0008291174,0.00040715534,0.00027693153,0.000066432935,0.00895338,0.0016634731,0.00010652355],"category_scores_gemma":[0.002116263,0.00035468503,0.00013685481,0.00012522002,0.000967185,0.00016710676,0.0024777288,0.001453066,0.0017806115],"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":[0.0000015296752,0.0000013532148,0.000046635803,0.000034027824,0.00002844414,0.0000055644305,0.000023594335,7.371827e-8,0.00021503135,0.60184145,0.07446891,0.32333338],"study_design_scores_gemma":[0.00013998275,0.000017065438,0.00003049405,0.0011437341,0.0000555685,0.00004059061,0.00005650435,0.000029549525,0.00038778532,0.11908738,0.87864614,0.00036517845],"about_ca_topic_score_codex":0.0029741216,"about_ca_topic_score_gemma":0.007998808,"teacher_disagreement_score":0.8041772,"about_ca_system_score_codex":0.00025356282,"about_ca_system_score_gemma":0.001741719,"threshold_uncertainty_score":0.9998905},"labels":[],"label_agreement":null},{"id":"W2347110650","doi":"","title":"Big data en gerelateerde begrippen gedefinieerd","year":2015,"lang":"nl","type":"article","venue":"TU/e Research Portal (Eindhoven University of Technology)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Gnowit (Canada)","funders":"","keywords":"Political science; Art; Humanities","score_opus":0.5272846497970922,"score_gpt":0.422525839706591,"score_spread":0.1047588100905012,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2347110650","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":[0.6589292,0.008500817,0.004261426,0.15720487,0.0013182278,0.0037814719,0.010968163,0.0019051316,0.15313068],"genre_scores_gemma":[0.9782678,0.0024793705,0.0047532604,0.000025318643,0.00011299763,0.0000033039978,0.00035895538,0.00004177784,0.013957222],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919798,0.00038068628,0.0008716616,0.002037737,0.0032675157,0.0014626194],"domain_scores_gemma":[0.98851985,0.00084534363,0.0006293945,0.007846272,0.0016153045,0.00054385077],"candidate_categories":["metaepi_narrow","sts","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science","research_integrity","insufficient_payload"],"category_scores_codex":[0.009426666,0.00042117937,0.0009237102,0.0030514915,0.00082043814,0.00017248878,0.017801017,0.0018434448,0.0009767398],"category_scores_gemma":[0.0070312126,0.0004295854,0.00018873718,0.006976291,0.0041482686,0.0008741549,0.019736934,0.0029834933,0.005659536],"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":[0.00018508422,0.00078804296,0.009208865,0.000042567714,0.00031017174,0.0007917216,0.00038991577,0.000014660382,0.0008619849,0.051551905,0.63773924,0.29811582],"study_design_scores_gemma":[0.0013524586,0.0006562486,0.0020104505,0.00014313428,0.00008929668,0.00007927938,0.043099135,0.000559112,0.00083633815,0.05120869,0.8994479,0.00051794323],"about_ca_topic_score_codex":0.0031020415,"about_ca_topic_score_gemma":0.0018401354,"teacher_disagreement_score":0.3193386,"about_ca_system_score_codex":0.0002899689,"about_ca_system_score_gemma":0.001834153,"threshold_uncertainty_score":0.9999365},"labels":[],"label_agreement":null},{"id":"W2358695901","doi":"","title":"Research on Hibernated Data Management with Data Blackbox","year":2009,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data management; Database","score_opus":0.5800919552134488,"score_gpt":0.5077003854134302,"score_spread":0.0723915698000186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2358695901","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":[0.0028846527,0.00014299323,0.9341326,0.0352243,0.000016155534,0.0025032526,0.0017713021,0.00054384035,0.022780918],"genre_scores_gemma":[0.23184358,0.000235229,0.7562771,0.002635869,0.000337501,0.0005092537,0.005243397,0.000039811388,0.0028782783],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99608606,0.00007420433,0.00045982416,0.0018220405,0.0011304654,0.00042738448],"domain_scores_gemma":[0.98753786,0.0003922529,0.00013043637,0.011553316,0.0002766784,0.00010943446],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020363145,0.00017389741,0.00019288139,0.00046029643,0.00055158394,0.0005803073,0.014387258,0.00009068764,0.00005998774],"category_scores_gemma":[0.0000074099394,0.00012384441,0.000020166053,0.0028995178,0.00022667302,0.00042246984,0.0038204272,0.00039799814,0.0024801744],"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":[0.0000075404196,0.00022448211,0.00002020985,0.000001415922,0.000014603,0.0000028479437,0.000009601627,0.0000306848,0.00013190163,0.05243107,0.34233668,0.60478896],"study_design_scores_gemma":[0.00023752754,0.000056506557,0.0027705,0.00001261535,0.000011028315,0.000009990841,0.00019419883,0.0024735064,0.00019659405,0.023240743,0.9706376,0.00015917189],"about_ca_topic_score_codex":0.000016384687,"about_ca_topic_score_gemma":0.000023211458,"teacher_disagreement_score":0.62830096,"about_ca_system_score_codex":0.000042786985,"about_ca_system_score_gemma":0.000042529155,"threshold_uncertainty_score":0.9982965},"labels":[],"label_agreement":null},{"id":"W2369109021","doi":"","title":"The Exploration of the Consumer Situation: a New Level of Advertising in the Age of Big Data","year":2014,"lang":"en","type":"article","venue":"Journal of Northwest University","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"","keywords":"Advertising; Point (geometry); Space (punctuation); Business; Big data; Marketing; Computer science; Mathematics; Data mining","score_opus":0.5319355688591457,"score_gpt":0.3614875757777705,"score_spread":0.1704479930813752,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2369109021","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":[0.92170155,0.00010205605,0.06721043,0.010113631,0.00016020074,0.00015440363,0.00016541086,0.0000028511995,0.00038944586],"genre_scores_gemma":[0.9991024,0.00013139426,0.00066112465,0.000021405289,0.000020292151,3.531942e-8,0.0000039941315,0.0000011420761,0.000058210615],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.998745,0.0001588274,0.00040425357,0.000086308835,0.0005473183,0.00005827755],"domain_scores_gemma":[0.99698573,0.00090880063,0.0008969773,0.00091744936,0.00027605586,0.000015003841],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015472616,0.00004311873,0.00014020047,0.00009402469,0.00013705951,0.000019823057,0.0023935968,0.000036872712,0.000004082694],"category_scores_gemma":[0.0010428365,0.000020431962,0.000059400707,0.00075295946,0.000260017,0.00044856995,0.0003308796,0.0001359982,9.159597e-7],"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":[0.00020808657,0.0003777718,0.21510066,0.000013815178,0.00008863363,0.000009961265,0.004523152,0.0008432266,0.0042939503,0.03048644,0.024560845,0.71949345],"study_design_scores_gemma":[0.0007803113,0.00010702586,0.7871027,0.00007258428,0.00007379121,0.000017328062,0.015039059,0.00043672294,0.0008775479,0.015654886,0.17976294,0.00007512974],"about_ca_topic_score_codex":0.0005839979,"about_ca_topic_score_gemma":0.009411136,"teacher_disagreement_score":0.71941835,"about_ca_system_score_codex":0.000014846446,"about_ca_system_score_gemma":0.00013880974,"threshold_uncertainty_score":0.5251635},"labels":[],"label_agreement":null},{"id":"W2374386622","doi":"","title":"Design and Implementation of Security Mechanism of CashCard","year":2004,"lang":"en","type":"article","venue":"Microcomputer applications","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Smart card; Computer security; Mechanism (biology); Realization (probability); Contactless smart card; Identification (biology); Security service; Process (computing); MULTOS; Computer security model; Information security; Card security code; Credit card; World Wide Web; Operating system","score_opus":0.09699630332220563,"score_gpt":0.3716422638321056,"score_spread":0.2746459605099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2374386622","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":[0.071650214,0.00006339749,0.92652583,0.0008565716,0.000004627772,0.0007305068,0.000088954584,0.00003580309,0.00004408373],"genre_scores_gemma":[0.6796053,0.000028944693,0.32014367,0.00003868538,0.000009357004,0.00015687873,0.000010370945,0.0000039541746,0.0000028646307],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885476,0.000023457607,0.00047969155,0.0003044489,0.00022921726,0.000108421526],"domain_scores_gemma":[0.99885,0.00015060417,0.0002634803,0.00050362205,0.00019653657,0.000035744586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044891593,0.00008121834,0.00017384198,0.00014911928,0.00008742664,0.000032059823,0.00053838623,0.000059635437,0.00001906884],"category_scores_gemma":[0.0000025534791,0.00006994318,0.000041234893,0.000563338,0.000116807685,0.00010411096,0.0002364,0.000058684378,0.000017210737],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000033186127,0.00012780125,0.00026772328,0.000015814152,0.0000228203,1.9915626e-7,0.0009490583,0.00016138509,0.08832041,0.54413104,0.0009531089,0.36504734],"study_design_scores_gemma":[0.00040834126,0.00005305589,0.0014542635,0.0000057249567,0.000016271546,0.0000109006405,0.00091124536,0.00017898998,0.30939654,0.66616833,0.021289892,0.00010646766],"about_ca_topic_score_codex":0.0000980114,"about_ca_topic_score_gemma":0.000020314264,"teacher_disagreement_score":0.6079551,"about_ca_system_score_codex":0.00001665323,"about_ca_system_score_gemma":0.000047347174,"threshold_uncertainty_score":0.28522},"labels":[],"label_agreement":null},{"id":"W2461694268","doi":"10.3968/7672","title":"On the Analysis of Library Information Ethics and the Standard Construction in the Era of Big Data","year":2015,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Information ethics; Big data; Personally identifiable information; The Internet; Internet privacy; Information security; Freedom of information; Computer science; Sociology; Public relations; Engineering ethics; Political science; World Wide Web; Computer security; Law; Engineering; Data mining","score_opus":0.2588652072134615,"score_gpt":0.4199736750678363,"score_spread":0.16110846785437477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461694268","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":[0.93325096,0.021272676,0.00021759133,0.04051251,0.00011726732,0.00037601893,0.0016833069,0.000011960917,0.0025576795],"genre_scores_gemma":[0.99746305,0.00152329,0.0002674704,0.0006641673,0.000012731505,0.000008267024,0.00005428632,7.738584e-7,0.0000059576732],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9990798,0.00021695094,0.00026081724,0.00009834843,0.00029725145,0.000046833033],"domain_scores_gemma":[0.9964059,0.0027335826,0.00013540185,0.0006485166,0.00007084245,0.0000057832276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031918858,0.000047775684,0.00016812593,0.00013369053,0.000073136835,0.00009864421,0.00049156725,0.000053292355,0.000002045973],"category_scores_gemma":[0.0037318387,0.000016680146,0.00001606738,0.0016213463,0.0006626285,0.00029938255,0.0003513335,0.0003594661,1.7087082e-7],"study_design_candidate":"qualitative","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":[0.00018247392,0.00001738508,0.0043675853,0.000023845854,0.00016147213,0.0000015461711,0.3094774,0.00001927144,0.0000038514017,0.48803583,0.020705055,0.17700431],"study_design_scores_gemma":[0.0010876247,0.000084149724,0.013047937,0.00016585994,0.00014945646,0.000006113393,0.76171774,0.00082539563,0.000069301146,0.17921205,0.04352349,0.0001108656],"about_ca_topic_score_codex":0.000025196687,"about_ca_topic_score_gemma":0.00015348919,"teacher_disagreement_score":0.45224038,"about_ca_system_score_codex":0.000002485075,"about_ca_system_score_gemma":0.000016622453,"threshold_uncertainty_score":0.44676292},"labels":[],"label_agreement":null},{"id":"W2476192065","doi":"10.1108/lhtn-05-2016-0025","title":"Libraries, data and the fourth industrial revolution (Data Deluge Column)","year":2016,"lang":"en","type":"article","venue":"Library Hi Tech News","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Industrial Revolution; Big data; Originality; Information revolution; Humanity; Government (linguistics); Guardian; Value (mathematics); Media studies; Sociology; Political science; Public relations; Computer science; Law; Creativity","score_opus":0.4012844435733259,"score_gpt":0.35252483549302904,"score_spread":0.048759608080296835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2476192065","genre_codex":"commentary","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":[0.035473008,0.007794262,0.109676406,0.79464287,0.0012377414,0.00352159,0.0284394,0.0026873255,0.016527427],"genre_scores_gemma":[0.7956992,0.015054228,0.13201915,0.009825279,0.0036207805,0.00037256183,0.006052465,0.00019098519,0.03716537],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99740785,0.00017594917,0.0005836236,0.000998088,0.0005492018,0.00028526422],"domain_scores_gemma":[0.9901059,0.001776655,0.0002853837,0.00771267,0.000021293568,0.000098075936],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011055437,0.00015975987,0.00027061263,0.00012296041,0.0003550969,0.00071687164,0.009063158,0.00023807149,0.00037403213],"category_scores_gemma":[0.003121498,0.0000748319,0.000030612642,0.0010844838,0.00083709595,0.006465628,0.010855339,0.00025183486,0.00020585947],"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":[0.00004123306,0.000011609874,0.002844023,4.0099573e-7,0.000005937482,9.911174e-7,0.000005239631,3.59261e-8,0.000026560621,0.050229847,0.6242539,0.3225802],"study_design_scores_gemma":[0.00092433504,0.000019760519,0.000708656,0.00001330292,0.000012076863,0.000008783712,0.00014155869,0.0008196203,0.00009430127,0.12769547,0.8694432,0.00011894095],"about_ca_topic_score_codex":0.000074106385,"about_ca_topic_score_gemma":0.000053496373,"teacher_disagreement_score":0.7848176,"about_ca_system_score_codex":0.000006643917,"about_ca_system_score_gemma":0.00017786298,"threshold_uncertainty_score":0.9971447},"labels":[],"label_agreement":null},{"id":"W2492606138","doi":"10.1057/9780230523784_2","title":"Introduction to Applied Probability for Energy Risk Management","year":2005,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Lottery; Actuarial science; Aside; Quarter (Canadian coin); Stock (firearms); Work (physics); Business; Economics; Engineering; Microeconomics; Geography","score_opus":0.08122904166277486,"score_gpt":0.29971952719890643,"score_spread":0.21849048553613157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492606138","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016224962,0.00013441966,0.07823793,0.001633833,0.0003357194,0.002332391,0.0011556348,0.0002999179,0.9158539],"genre_scores_gemma":[0.8081036,0.00032199043,0.09679756,0.0006812143,0.003541684,0.0027169094,0.00046029314,0.00015913398,0.08721761],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958139,0.000021118625,0.0010046876,0.0017872315,0.0009190915,0.00045398346],"domain_scores_gemma":[0.99558145,0.00026638125,0.0005895429,0.0031099378,0.00027735182,0.00017534327],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011696313,0.00049778906,0.0006114452,0.00051463395,0.00032227737,0.00019899484,0.0016754633,0.0004226285,0.0005060617],"category_scores_gemma":[0.00018161819,0.0004056138,0.0002911324,0.00009690987,0.00020909174,0.0000010848001,0.00081344735,0.00025589587,0.000644442],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028892517,5.797038e-7,0.0000024296664,0.000006893255,0.000038944272,4.0157136e-7,0.000012012845,0.000011473691,0.000011199035,0.5748908,0.005271929,0.41972446],"study_design_scores_gemma":[0.000120926336,0.000036372963,0.0000241577,0.0000060301363,0.000046136578,0.0000014738324,0.000024885876,0.000015991442,0.000116915726,0.5425855,0.4567697,0.0002519094],"about_ca_topic_score_codex":0.00001719884,"about_ca_topic_score_gemma":0.00027016943,"teacher_disagreement_score":0.82863635,"about_ca_system_score_codex":0.00016134288,"about_ca_system_score_gemma":0.000031591622,"threshold_uncertainty_score":0.99983954},"labels":[],"label_agreement":null},{"id":"W2497415448","doi":"10.1090/conm/622","title":"Perspectives on Big Data Analysis","year":2014,"lang":"en","type":"book","venue":"Contemporary mathematics - American Mathematical Society","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Mathematics; Big data; Computer science; Data mining","score_opus":0.38667462333794594,"score_gpt":0.400313487758653,"score_spread":0.013638864420707053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2497415448","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006874415,0.0004208169,0.43109226,0.003006148,0.000095598894,0.0009394891,0.0021439523,0.00051699404,0.56171596],"genre_scores_gemma":[0.020792196,0.00040679908,0.19267903,0.0016505888,0.0012105785,0.00027795896,0.0023645589,0.00034728934,0.780271],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99079186,0.0001833696,0.0024858587,0.0026443203,0.0032449174,0.0006496958],"domain_scores_gemma":[0.9757504,0.00811501,0.0028665676,0.01241912,0.0004750764,0.00037381527],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00491413,0.0009851087,0.0033219,0.0005170956,0.00041428086,0.00069129677,0.008750131,0.00061188417,0.0006791845],"category_scores_gemma":[0.004846799,0.0006988258,0.001694944,0.002649647,0.0029031711,0.0002459661,0.0029615378,0.0012894121,0.0030074883],"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":[0.00000556969,0.00049346645,0.000007377789,0.00011015284,0.0015922608,0.000004128854,0.001514144,0.0000068913314,0.0000028240438,0.259502,0.7246007,0.012160542],"study_design_scores_gemma":[0.00018807474,0.00014801562,0.000008552425,0.00014280382,0.00081709464,0.000004890852,0.011641002,0.0229116,0.0000031290358,0.5581414,0.40517202,0.0008214174],"about_ca_topic_score_codex":0.000013075266,"about_ca_topic_score_gemma":0.0000062320064,"teacher_disagreement_score":0.31942865,"about_ca_system_score_codex":0.00026455487,"about_ca_system_score_gemma":0.000589484,"threshold_uncertainty_score":0.99981034},"labels":[],"label_agreement":null},{"id":"W2500329317","doi":"10.1007/978-3-642-53974-9","title":"Specifying Big Data Benchmarks","year":2013,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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":"University of Toronto","funders":"","keywords":"Big data; Computer science; Data science; Data mining","score_opus":0.2982924050768856,"score_gpt":0.37123925728618384,"score_spread":0.07294685220929825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2500329317","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":[0.00008709445,0.0005418055,0.98372895,0.002854422,0.0021402647,0.00044247924,0.00017102816,0.000108095126,0.009925847],"genre_scores_gemma":[0.07925711,0.0005026052,0.89699924,0.0050519397,0.0066531934,0.00008956078,0.0011632266,0.000105679595,0.010177431],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9934953,0.000046325633,0.0008525438,0.0026637034,0.002268456,0.0006737152],"domain_scores_gemma":[0.989029,0.0021922998,0.00046499856,0.00783459,0.000333923,0.00014520026],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0031038083,0.00039277688,0.0005530333,0.001086699,0.0003847372,0.0016702223,0.019209225,0.0004687006,0.00035082607],"category_scores_gemma":[0.002327959,0.0002833227,0.00007523939,0.0026692483,0.001567051,0.0007833193,0.010023615,0.0010924544,0.0006431459],"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":[6.6296866e-7,0.000014669683,0.000056901506,0.0000038875337,0.0000024513397,0.000006849042,0.00003940011,0.00060945115,0.000025013092,0.00065769115,0.047091596,0.9514914],"study_design_scores_gemma":[0.00010622701,0.000038530834,0.00038864615,0.000116937765,0.00000626084,0.000025805448,0.0000015801094,0.094033375,0.000177496,0.47941768,0.42517245,0.0005150259],"about_ca_topic_score_codex":0.00005505683,"about_ca_topic_score_gemma":0.0002396814,"teacher_disagreement_score":0.9509764,"about_ca_system_score_codex":0.00022066459,"about_ca_system_score_gemma":0.0009847508,"threshold_uncertainty_score":0.9999619},"labels":[],"label_agreement":null},{"id":"W2508439080","doi":"","title":"RTEMP: Exploring an end-to-end, agnostic platform for multidisciplinary real-time analytics in the space physics community and beyond","year":2014,"lang":"en","type":"article","venue":"2014 AGU Fall Meeting","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Analytics; Multidisciplinary approach; Data science; Computer science; Space (punctuation); Physics; Sociology; Operating system; Social science","score_opus":0.2438440652087375,"score_gpt":0.3729799717944513,"score_spread":0.1291359065857138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2508439080","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":[0.9882592,0.000018614199,0.006879138,0.0021432885,0.00006473692,0.00046798927,0.00007472486,0.00008863053,0.002003691],"genre_scores_gemma":[0.98170555,0.00004833428,0.017734319,0.00014652108,0.00010932799,0.00015292336,0.000043517466,0.000017042077,0.00004246448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811673,0.00020590404,0.0004556285,0.00040061175,0.0004582616,0.00036283693],"domain_scores_gemma":[0.9912192,0.006954961,0.00021624965,0.0013973156,0.000117082185,0.0000951905],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005633584,0.00017928891,0.00029059823,0.00014153367,0.00081145065,0.00026952956,0.0014755239,0.00009157683,0.0000029065936],"category_scores_gemma":[0.0031759557,0.00012355234,0.00005619411,0.0005554476,0.00014825081,0.00046429812,0.0007168865,0.00034431694,0.00006281095],"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":[0.00014493146,0.0010997343,0.12346264,0.00011861603,0.00006090537,0.0000070310753,0.035815254,0.008266728,0.01965045,0.09106086,0.033137187,0.68717563],"study_design_scores_gemma":[0.0021099716,0.0013256754,0.15009227,0.0003042428,0.00013831368,0.000020814843,0.114659615,0.3903726,0.0032861312,0.30473408,0.031382058,0.0015742222],"about_ca_topic_score_codex":0.0019185742,"about_ca_topic_score_gemma":0.0050113047,"teacher_disagreement_score":0.6856014,"about_ca_system_score_codex":0.000028885523,"about_ca_system_score_gemma":0.000018546187,"threshold_uncertainty_score":0.62411046},"labels":[],"label_agreement":null},{"id":"W2509022704","doi":"10.1109/tsg.2016.2593358","title":"Guest Editorial Big Data Analytics for Grid Modernization","year":2016,"lang":"en","type":"editorial","venue":"IEEE Transactions on Smart Grid","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Big data; Smart grid; Software deployment; Variety (cybernetics); Data science; Computer science; Analytics; Volume (thermodynamics); Computer security; Grid; Engineering; Data mining","score_opus":0.26379187914905644,"score_gpt":0.3909505788722479,"score_spread":0.12715869972319144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509022704","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[8.533757e-7,0.000016610657,0.4408128,0.0006577604,0.50031966,0.0004305296,0.057516415,0.00018302276,0.0000623728],"genre_scores_gemma":[0.0001683761,0.00048259372,0.001035415,0.000037200854,0.9908517,0.00032902355,0.004337664,0.000091421934,0.0026666198],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928836,0.000102523954,0.0013142556,0.0020033151,0.0031122032,0.0005840912],"domain_scores_gemma":[0.9864027,0.0055178176,0.00068723835,0.0056345435,0.0015648598,0.0001928672],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002049688,0.000558257,0.0007776926,0.00072727527,0.0007735672,0.00060558,0.005268008,0.0018676147,0.00007575301],"category_scores_gemma":[0.0023019111,0.00041326354,0.0003113955,0.0010666815,0.0002869896,0.00064498594,0.00005482624,0.0010798094,0.00078329566],"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":[0.00009407924,0.00015073687,5.8701335e-7,0.000012937066,0.0000747934,6.473542e-7,0.000007853296,0.00020817535,0.00003707877,0.000015202765,0.9672086,0.032189287],"study_design_scores_gemma":[0.0007749079,0.0001515227,6.488983e-7,0.000057157,0.00020491045,9.48596e-7,0.000027192582,0.001356322,0.00047626757,0.001570913,0.99487895,0.0005002401],"about_ca_topic_score_codex":0.00009793951,"about_ca_topic_score_gemma":0.0006287084,"teacher_disagreement_score":0.49053204,"about_ca_system_score_codex":0.0001932147,"about_ca_system_score_gemma":0.00067401497,"threshold_uncertainty_score":0.9999947},"labels":[],"label_agreement":null},{"id":"W2509480191","doi":"","title":"Postglacial Rebound Model ICE-6G_C (VM5a) Constrained by Geodetic and Geologic Observations","year":2014,"lang":"en","type":"article","venue":"2014 AGU Fall Meeting","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Geology; Geodetic datum; Cryosphere; Geodesy; Climatology; Physical geography; Geography; Sea ice","score_opus":0.1536119042783524,"score_gpt":0.33080647046147,"score_spread":0.1771945661831176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509480191","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":[0.92247033,0.00023130672,0.056675978,0.009014831,0.00010984486,0.0003043025,0.00014822846,0.0002811587,0.01076404],"genre_scores_gemma":[0.97800034,0.00005809197,0.02008181,0.0008857458,0.00006313266,0.00004307881,0.000050282826,0.000013595101,0.0008038916],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976533,0.00010612427,0.0006065291,0.00069270644,0.00053666,0.00040468058],"domain_scores_gemma":[0.99733543,0.0011536125,0.00031486794,0.0008498822,0.00022665129,0.00011955746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019991575,0.00019705911,0.00029973127,0.00012175278,0.00059577037,0.00034904276,0.0009343836,0.00021530307,0.000020607204],"category_scores_gemma":[0.004193857,0.0001569762,0.000062660954,0.0003635523,0.00046250894,0.00026632793,0.00044704427,0.00023701179,0.00018167464],"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":[0.000039401148,0.00024771751,0.22589976,0.00002982425,0.00005262829,0.0000035361368,0.00061008177,0.0025654433,0.04325164,0.23864342,0.35228586,0.13637069],"study_design_scores_gemma":[0.0006990454,0.00011200155,0.012654848,0.00003404707,0.000041438834,0.000017480983,0.00089962274,0.6461588,0.00036610398,0.23366845,0.104768276,0.0005798836],"about_ca_topic_score_codex":0.0004355166,"about_ca_topic_score_gemma":0.0005908353,"teacher_disagreement_score":0.6435934,"about_ca_system_score_codex":0.00002065268,"about_ca_system_score_gemma":0.00004385139,"threshold_uncertainty_score":0.64013034},"labels":[],"label_agreement":null},{"id":"W2509992382","doi":"","title":"Exploiting Big Earth Data: Computation, Testing, and CyberGIS I Posters","year":2015,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"","keywords":"Big data; Computer science; Earth (classical element); Data mining; Mathematics","score_opus":0.7147836349230444,"score_gpt":0.4329859695462856,"score_spread":0.2817976653767588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509992382","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":[0.7634499,0.00020899484,0.1890874,0.0126908,0.00027461947,0.0003522706,0.0002590196,0.0007231095,0.032953873],"genre_scores_gemma":[0.90098953,0.0000055931027,0.09796429,0.00037582775,0.000051045437,0.0000057222896,0.000039926075,0.0000055839537,0.00056245324],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871117,0.000024953977,0.000283855,0.00042707846,0.00041698996,0.000135976],"domain_scores_gemma":[0.9979378,0.0007727645,0.000111008514,0.0008270825,0.00025314445,0.000098186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001073873,0.00006968843,0.000105580184,0.00009732795,0.00012701338,0.00033039073,0.0008149127,0.00003970181,0.000018119417],"category_scores_gemma":[0.0053431652,0.000048616803,0.000007877422,0.0006721495,0.00011942213,0.00036786302,0.0010123665,0.00006720372,0.00022699981],"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":[0.0000017089577,0.00001840402,0.014849091,8.2922344e-7,0.0000037698971,0.0000017964331,0.00009433051,0.000044170883,0.00018305462,0.0032952076,0.10443024,0.8770774],"study_design_scores_gemma":[0.0012862787,0.00022365559,0.04630326,0.000032063774,0.000025055644,0.00012667179,0.02293498,0.10552107,0.000986019,0.19001329,0.63181925,0.00072841125],"about_ca_topic_score_codex":0.00021179627,"about_ca_topic_score_gemma":0.00011969706,"teacher_disagreement_score":0.876349,"about_ca_system_score_codex":0.000004817761,"about_ca_system_score_gemma":0.000041113864,"threshold_uncertainty_score":0.63966537},"labels":[],"label_agreement":null},{"id":"W2512799421","doi":"","title":"Exploiting Big Earth Data: Computation, Testing, and CyberGIS III","year":2015,"lang":"en","type":"article","venue":"2015 AGU Fall Meeting","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Esri (Canada)","funders":"","keywords":"Computer science; Big data; Earth (classical element); Data mining; Mathematics","score_opus":0.47480885034592535,"score_gpt":0.4043836811288045,"score_spread":0.07042516921712083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2512799421","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":[0.96049994,0.00073676737,0.019412827,0.0029328612,0.00031274842,0.00028503008,0.000113913695,0.000394234,0.015311648],"genre_scores_gemma":[0.9219775,0.0000173178,0.077206634,0.00017572753,0.00021880097,0.000014993307,0.000044475084,0.000015520458,0.00032902454],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976111,0.000077704775,0.0005717297,0.00070499873,0.0007353559,0.0002991245],"domain_scores_gemma":[0.99650705,0.0013847683,0.00036061593,0.0010704747,0.00050313276,0.00017398057],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0034413724,0.00014501449,0.00022940595,0.00014980063,0.00030756055,0.00045446894,0.0012186321,0.00008917522,0.0000021014307],"category_scores_gemma":[0.014301071,0.00011582915,0.000018191438,0.0008516607,0.00015706109,0.00037894037,0.0015768156,0.00017569553,0.00017163403],"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":[0.000008379564,0.00006123091,0.10979891,0.000007256471,0.000017878023,0.00000958994,0.0006984681,0.0005872371,0.0011272399,0.0017627443,0.16922855,0.7166925],"study_design_scores_gemma":[0.0024434244,0.00021350452,0.02889162,0.00024803303,0.00006471962,0.00013240273,0.024985852,0.19820787,0.00071294524,0.0787725,0.66403556,0.0012915705],"about_ca_topic_score_codex":0.0018781151,"about_ca_topic_score_gemma":0.0012019165,"teacher_disagreement_score":0.71540093,"about_ca_system_score_codex":0.000014574279,"about_ca_system_score_gemma":0.00008087565,"threshold_uncertainty_score":0.99400187},"labels":[],"label_agreement":null},{"id":"W2515320058","doi":"10.15353/joci.v12i2.3229","title":"To the Cloud: Big Data in a Turbulent World by Vincent Mosco","year":2016,"lang":"en","type":"article","venue":"The Journal of Community Informatics","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cloud computing; Reading (process); Upload; World Wide Web; Media studies; Computer science; Visual arts; History; Art; Sociology; Law; Political science","score_opus":0.3204031877869045,"score_gpt":0.3920554610042206,"score_spread":0.0716522732173161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2515320058","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":[0.7857896,0.00014729079,0.052097507,0.1604322,0.00024941313,0.00025731695,0.00025365973,0.000016152748,0.0007568381],"genre_scores_gemma":[0.9963233,0.00035708965,0.0005144673,0.0026274433,0.000048441423,0.0000020656066,0.0000039069746,0.0000033105437,0.00011995793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99752533,0.0003765392,0.0010928654,0.000017013264,0.0008138672,0.00017438336],"domain_scores_gemma":[0.9924279,0.0031117604,0.00069261785,0.003514105,0.00019222173,0.000061393366],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.011127073,0.00008583931,0.00018112703,0.00017071648,0.00034631914,0.00014494536,0.010682941,0.000034139284,0.000026221449],"category_scores_gemma":[0.0021956875,0.00002950817,0.000032573178,0.0009158688,0.00017286393,0.00047478147,0.0025180292,0.00066718226,0.00014631492],"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":[0.000030848074,0.00009220399,0.00025057374,0.0000021047263,0.000012944828,1.1997814e-7,0.0072863647,0.000084296065,0.00007070517,0.0012236971,0.57664496,0.4143012],"study_design_scores_gemma":[0.00022743577,0.00006497843,0.0011238236,0.00005217009,0.000009642471,0.00002841791,0.034122694,0.00019653622,0.00020302691,0.008578414,0.9553327,0.000060172915],"about_ca_topic_score_codex":0.000110929446,"about_ca_topic_score_gemma":0.0007433386,"teacher_disagreement_score":0.41424102,"about_ca_system_score_codex":0.000081615784,"about_ca_system_score_gemma":0.00006256607,"threshold_uncertainty_score":0.99466974},"labels":[],"label_agreement":null},{"id":"W2518845274","doi":"10.1145/2938503.2939572","title":"Panel","year":2016,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; McGill University; University of Ottawa; Concordia University; Université du Québec à Montréal","funders":"University of Waterloo","keywords":"Computer science; Data science; Engineering ethics; Internet privacy; Knowledge management; Engineering","score_opus":0.5695457893644045,"score_gpt":0.4220832082759214,"score_spread":0.1474625810884831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2518845274","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":[0.11893031,0.00003147759,0.5081708,0.14778873,0.00014695342,0.00012634025,0.00006317894,0.00055584003,0.22418638],"genre_scores_gemma":[0.97559726,0.00001032336,0.002745971,0.00023197063,0.00001197893,0.000006613051,1.8463065e-7,0.0000011134202,0.021394607],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99946064,0.0000051577476,0.00010927509,0.00014638982,0.0002084911,0.00007005989],"domain_scores_gemma":[0.9990416,0.00030081812,0.000023063725,0.0005746244,0.00003947706,0.00002037532],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00026381202,0.000022729357,0.00003710629,0.00003557766,0.00003578784,0.000033156888,0.00057860475,0.000024135,0.0022549077],"category_scores_gemma":[0.0007261268,0.0000083381965,0.00001717079,0.00020907854,0.000054110824,0.00009520889,0.00013036958,0.0000121450075,0.007118708],"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":[2.2598063e-7,0.0000034265486,0.0009951027,1.5205835e-8,3.159264e-7,1.01916065e-7,9.698988e-7,1.0497147e-8,0.002676618,0.18044381,0.16219601,0.65368336],"study_design_scores_gemma":[0.000035921454,0.0000039589045,0.0066570537,4.818037e-7,2.3774267e-7,9.0502095e-7,0.000053591582,0.000005297418,0.0035102626,0.23597011,0.7537388,0.000023334816],"about_ca_topic_score_codex":0.0000043312893,"about_ca_topic_score_gemma":0.000007834269,"teacher_disagreement_score":0.8566669,"about_ca_system_score_codex":0.0000034723219,"about_ca_system_score_gemma":0.000005180057,"threshold_uncertainty_score":0.99865717},"labels":[],"label_agreement":null},{"id":"W2531566274","doi":"","title":"Internet-of-things, cyber-physical systems demarcation and contribution to the big data realm","year":2021,"lang":"en","type":"article","venue":"The Journal of Internet Banking and Commerce","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Realm; Cyber-physical system; Internet of Things; Big data; Computer science; The Internet; Data science; World Wide Web; Internet privacy; Political science; Data mining","score_opus":0.21611164448455553,"score_gpt":0.3662666324624272,"score_spread":0.15015498797787166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2531566274","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":[0.8357624,0.001872987,0.1440595,0.017678203,0.00027681954,0.00011116748,0.000023528228,0.000008961084,0.00020647144],"genre_scores_gemma":[0.9988864,0.00028150948,0.00018939594,0.00034404232,0.00010846508,0.0000017079146,0.000007736813,0.000003709648,0.00017700117],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986397,0.00024858268,0.00047709336,0.00015322861,0.00038154353,0.00009985764],"domain_scores_gemma":[0.99709487,0.0012860841,0.00044777928,0.00075759966,0.0003756792,0.000038017854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002945519,0.0000754506,0.00021470849,0.000060409435,0.00008947054,0.00021911493,0.0014045731,0.00003989824,0.0000049448795],"category_scores_gemma":[0.0013861901,0.000036462192,0.00003022313,0.0002868074,0.00012027332,0.00018814205,0.0010149321,0.00025661156,0.000005127852],"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":[0.00011686353,0.00010385234,0.0031099636,0.000014155277,0.0001220119,0.00000457372,0.0036582984,0.000038691014,0.0030827983,0.05843325,0.06580918,0.86550635],"study_design_scores_gemma":[0.0014783929,0.0008567179,0.05170611,0.0015771099,0.00045695764,0.002607011,0.018637443,0.12789014,0.011471077,0.058870796,0.72391665,0.00053156697],"about_ca_topic_score_codex":0.00024329948,"about_ca_topic_score_gemma":0.000046842477,"teacher_disagreement_score":0.8649748,"about_ca_system_score_codex":0.000015319914,"about_ca_system_score_gemma":0.00002790916,"threshold_uncertainty_score":0.26100695},"labels":[],"label_agreement":null},{"id":"W2537383304","doi":"10.1177/2053951716674238","title":"Critical data studies: An introduction","year":2016,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":432,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"Arts and Humanities Research Council; University College London","keywords":"Big data; Multitude; Data science; Theme (computing); Sociology; Epistemology; Computer science; Data mining; World Wide Web","score_opus":0.7517157753114562,"score_gpt":0.5101888192272449,"score_spread":0.24152695608421126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2537383304","genre_codex":"commentary","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":[0.025921755,0.0026950683,0.32987678,0.5957236,0.0040468876,0.00060413324,0.039801035,0.0010985314,0.0002321703],"genre_scores_gemma":[0.86880994,0.0068836557,0.105454974,0.0026982871,0.008736468,0.00007671584,0.0059568537,0.000055314336,0.001327816],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99679893,0.00008504961,0.0004535983,0.0015822285,0.0007760777,0.0003041359],"domain_scores_gemma":[0.9850859,0.001321568,0.00011324344,0.013045994,0.00033036195,0.00010291154],"candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.003708911,0.00013401954,0.00021984552,0.000031256684,0.0003650005,0.00024188346,0.0077478797,0.00014337391,0.00014705531],"category_scores_gemma":[0.016626716,0.00007338097,0.00004282488,0.0006242695,0.00080803386,0.0025793205,0.007139632,0.00015472723,0.00050381],"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":[0.0000017527555,0.00004503547,0.0000701897,0.0000016071516,0.000014501012,2.7680153e-7,0.00004882887,4.965606e-8,0.0008052422,0.0056434576,0.67260015,0.3207689],"study_design_scores_gemma":[0.00013851676,0.000025648213,0.00049305643,0.0000057515795,0.000020571555,0.0000060220405,0.004950306,0.0005544246,0.00014179395,0.020851031,0.97267467,0.00013822413],"about_ca_topic_score_codex":0.000022435543,"about_ca_topic_score_gemma":0.00007436008,"teacher_disagreement_score":0.8428882,"about_ca_system_score_codex":0.00004093213,"about_ca_system_score_gemma":0.0000697156,"threshold_uncertainty_score":0.9976207},"labels":[],"label_agreement":null},{"id":"W2569162955","doi":"10.1609/aaai.v30i1.9910","title":"Big-Data Mechanisms and Energy-Policy Design","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Leverage (statistics); Mechanism design; Incentive; Big data; Stakeholder; Computer science; Task (project management); Mechanism (biology); Risk analysis (engineering); Business; Economics; Microeconomics; Management","score_opus":0.565963653801508,"score_gpt":0.40025083783055404,"score_spread":0.165712815970954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2569162955","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":[0.011903266,0.000049324444,0.901636,0.077273786,0.00038393168,0.00038044667,0.00022469835,0.00016854338,0.007979988],"genre_scores_gemma":[0.9937305,0.00023428244,0.004815435,0.0002451944,0.00007906739,0.000027031461,5.3861754e-7,0.000009252024,0.00085873285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9977029,0.000020610518,0.00058451085,0.00070474553,0.000712069,0.00027519313],"domain_scores_gemma":[0.9973636,0.0005670997,0.00041265544,0.0010142346,0.00055802916,0.00008436417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014362583,0.00016837432,0.00022906323,0.00021811912,0.00022014052,0.0002592933,0.004356899,0.00011607664,0.00008538786],"category_scores_gemma":[0.005412601,0.0000827887,0.000045480992,0.00098267,0.0006297573,0.0003603778,0.0016218589,0.00011167283,0.000121080484],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000131874895,0.000019818497,0.000011096018,9.1701054e-7,0.0000026840685,4.0714465e-8,0.000022068007,3.3428836e-7,0.054943707,0.5141483,0.001018665,0.4298192],"study_design_scores_gemma":[0.000012576229,0.000059720325,0.0000393976,0.000042902197,0.000004967503,0.0000022700444,0.00033386284,0.001625747,0.3092905,0.685647,0.002848723,0.00009231815],"about_ca_topic_score_codex":0.000070422626,"about_ca_topic_score_gemma":0.000022121967,"teacher_disagreement_score":0.9818272,"about_ca_system_score_codex":0.000022032373,"about_ca_system_score_gemma":0.00010938482,"threshold_uncertainty_score":0.8096275},"labels":[],"label_agreement":null},{"id":"W2581315808","doi":"10.5539/mas.v11n4p1","title":"The Study of Semantic Analysis on Intelligence Research under the Environment of Big Data","year":2017,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data science; Semantic technology; Intelligence analysis; Semantic analysis (machine learning); Semantic computing; Visualization; Meaning (existential); Business intelligence; Big data; Information retrieval; Strengths and weaknesses; Semantic Web; Knowledge management; Artificial intelligence; Data mining; Psychology","score_opus":0.6982545098271963,"score_gpt":0.49961235825021594,"score_spread":0.19864215157698034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2581315808","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":[0.7387347,0.000054059525,0.2525,0.0037242936,0.00007061196,0.0008903126,0.000052625674,0.000014801677,0.003958553],"genre_scores_gemma":[0.9996105,0.00005045308,0.00017596428,0.000014787421,0.000009278637,0.00004040189,9.660768e-7,0.000003011229,0.000094653384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9949879,0.000077403645,0.00047869323,0.0008523431,0.0032957715,0.00030786506],"domain_scores_gemma":[0.98590946,0.0015541455,0.0004244077,0.011948652,0.000118502445,0.000044859076],"candidate_categories":["sts","open_science"],"consensus_categories":["sts"],"category_scores_codex":[0.014782783,0.000087738954,0.00019938112,0.00028500092,0.002983713,0.0005327549,0.020262945,0.000033292938,0.0000110121655],"category_scores_gemma":[0.0010931607,0.000039872466,0.000035031335,0.0019029501,0.005346589,0.00014769204,0.005881051,0.00024276288,0.000055627257],"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":[0.000024402496,0.0005984422,0.0029721023,0.0000013813049,0.000073316754,4.2768332e-7,0.0011233747,0.004894952,0.02691225,0.061636735,0.00035995521,0.90140265],"study_design_scores_gemma":[0.00019952681,0.0002474683,0.16466497,0.000008066184,0.00012142428,4.474215e-7,0.04916111,0.3945293,0.015494978,0.37271518,0.0026194225,0.00023810678],"about_ca_topic_score_codex":0.000222653,"about_ca_topic_score_gemma":0.00047497623,"teacher_disagreement_score":0.90116453,"about_ca_system_score_codex":0.000026712341,"about_ca_system_score_gemma":0.00008178812,"threshold_uncertainty_score":0.99831426},"labels":[],"label_agreement":null},{"id":"W2592740096","doi":"10.22230/cjc.2017v42n1a3152","title":"Big Data, Little Data, No Data: Scholarship in the Networked World","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Communication","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scholarship; Big data; Data science; Computer science; Political science; Data mining","score_opus":0.7184773296688539,"score_gpt":0.4597071714925218,"score_spread":0.2587701581763321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592740096","genre_codex":"commentary","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":[0.12244391,0.037299637,0.010175902,0.7345137,0.0048396545,0.0019930054,0.0130213,0.00007573123,0.07563717],"genre_scores_gemma":[0.99394745,0.00054558256,0.0037404734,0.00051552255,0.00026191294,0.0000025091415,0.0007495376,0.000007206711,0.00022979813],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99794376,0.00035879546,0.00068641006,0.00029653666,0.0004822947,0.00023220602],"domain_scores_gemma":[0.96762896,0.0009884719,0.0009264095,0.029967269,0.00032278636,0.00016610126],"candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0128171425,0.00008984377,0.00019156579,0.00031488552,0.0010795194,0.0019059164,0.06293576,0.00007477979,0.000060851457],"category_scores_gemma":[0.011637077,0.000060316484,0.000021931357,0.00052165985,0.000422429,0.0030114385,0.002862837,0.0007969225,0.00014488416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000065340114,0.00002374371,0.034011193,0.0000010488325,0.000012907375,0.000008467233,0.00007944024,0.000013976781,0.000005160226,0.004408267,0.525566,0.4358633],"study_design_scores_gemma":[0.00013989037,0.000007460903,0.117562875,0.00004263814,0.000011591871,0.000016498281,0.00028480726,0.001477628,0.0000011365611,0.012044294,0.868345,0.00006613744],"about_ca_topic_score_codex":0.008265081,"about_ca_topic_score_gemma":0.5553377,"teacher_disagreement_score":0.87150353,"about_ca_system_score_codex":0.000048726455,"about_ca_system_score_gemma":0.0007917179,"threshold_uncertainty_score":0.9991302},"labels":[],"label_agreement":null},{"id":"W2592881435","doi":"10.24242/jclis.v1i1.22","title":"A Case for Critical Data Studies in Library and Information Studies","year":2017,"lang":"en","type":"article","venue":"Journal of Critical Library and Information Studies","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Argument (complex analysis); Critical theory; Sociology; Politics; Epistemology; Big data; Public relations; Work (physics); Engineering ethics; Social science; Political science; Data science; Computer science; Law; Engineering; Medicine","score_opus":0.5011702460060182,"score_gpt":0.5034852273212985,"score_spread":0.0023149813152802956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2592881435","genre_codex":"commentary","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":[0.23214334,0.07163027,0.005828396,0.67662746,0.0027664327,0.0014122826,0.0032383318,0.00022752154,0.0061259726],"genre_scores_gemma":[0.93805546,0.040797595,0.017943103,0.002914849,0.000188821,0.000036438323,0.000022327536,0.000006503322,0.00003491108],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99764276,0.00006402963,0.001526537,0.00015940805,0.00038216874,0.00022508946],"domain_scores_gemma":[0.9922564,0.006067195,0.000533388,0.00066537014,0.00036597584,0.000111683476],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0011541388,0.00016828101,0.0005864238,0.00043428337,0.0009295569,0.0011549954,0.00082078937,0.00010339179,0.000008256235],"category_scores_gemma":[0.03285304,0.000108183274,0.00005251934,0.00021475911,0.0017727049,0.16373453,0.002266505,0.0002697333,0.0000055595438],"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":[0.00017054209,0.000053214222,0.001525793,0.0005753097,0.00014801226,0.00006540173,0.0030257974,0.000001864601,0.0000018896725,0.86122584,0.062794596,0.070411734],"study_design_scores_gemma":[0.0014477437,0.0005223265,0.0044421037,0.000433435,0.0001336397,0.0017182521,0.17425855,0.0013298234,0.00016616742,0.33042145,0.48476106,0.00036543686],"about_ca_topic_score_codex":1.9923579e-7,"about_ca_topic_score_gemma":2.863744e-7,"teacher_disagreement_score":0.7059121,"about_ca_system_score_codex":0.000005774345,"about_ca_system_score_gemma":0.000047552236,"threshold_uncertainty_score":0.9998819},"labels":[],"label_agreement":null},{"id":"W2606761684","doi":"10.1002/nem.1974","title":"Big data analytics for network and service management","year":2017,"lang":"en","type":"article","venue":"International Journal of Network Management","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Big data; Data science; Analytics; Service (business); Data analysis; Data mining","score_opus":0.45428205358572255,"score_gpt":0.43808036888178165,"score_spread":0.0162016847039409,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2606761684","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":[0.0044099884,0.0007839036,0.84392256,0.10843819,0.0085461205,0.00096551067,0.00026177763,0.000051722745,0.032620214],"genre_scores_gemma":[0.7218554,0.010047957,0.25163335,0.0051950994,0.007941352,0.00004697457,0.00012038981,0.000041331743,0.0031181797],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768066,0.000022022028,0.0007172176,0.00035212017,0.000996548,0.00023145173],"domain_scores_gemma":[0.9963348,0.00023304837,0.0011425416,0.0016891919,0.000528512,0.00007188612],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0026490884,0.00012074387,0.00021562955,0.00015597799,0.00037620397,0.0010566218,0.0071322387,0.000045148023,0.000021026155],"category_scores_gemma":[0.00017601973,0.00009268962,0.000068994355,0.0001889862,0.0000807926,0.0004600022,0.0039143595,0.000115202805,0.000017273871],"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":[0.00005017982,0.000032934233,0.0014801277,0.000006304218,0.00040328124,0.00003354801,0.0000057290094,0.0036559973,3.7355014e-7,0.040090207,0.29184872,0.6623926],"study_design_scores_gemma":[0.00056727126,0.000025948235,0.021459894,0.00006668943,0.0000940416,0.000016909911,0.00015848331,0.011619869,7.293855e-7,0.1185877,0.84730726,0.00009520551],"about_ca_topic_score_codex":0.000006592812,"about_ca_topic_score_gemma":0.00007544146,"teacher_disagreement_score":0.7174454,"about_ca_system_score_codex":0.000035076875,"about_ca_system_score_gemma":0.000011678058,"threshold_uncertainty_score":0.9999804},"labels":[],"label_agreement":null},{"id":"W2626239355","doi":"10.3968/9588","title":"Textual and Quantitative Research on China’s Action Plan for Promoting the Development of Big Data From the Perspective of Policy Tools","year":2017,"lang":"en","type":"article","venue":"Canadian social science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Action plan; China; Perspective (graphical); Government (linguistics); Action (physics); Development plan; Plan (archaeology); Value (mathematics); Computer science; Data science; Political science; Management; Economics; Engineering","score_opus":0.8006922304219257,"score_gpt":0.5643946563422805,"score_spread":0.23629757407964525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626239355","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":[0.8995244,0.00003537915,0.0008252345,0.06441459,0.000104094295,0.0009678803,0.0037650538,0.000008460024,0.03035489],"genre_scores_gemma":[0.9991604,0.0000032228768,0.0006716785,0.00003632702,0.00007908755,0.000017339982,0.000006586728,0.0000017541427,0.000023617007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9986202,0.000049503717,0.00016614851,0.0003378239,0.00060238165,0.00022392914],"domain_scores_gemma":[0.9973584,0.0011500225,0.00020270096,0.0008514964,0.00037424042,0.0000631741],"candidate_categories":["metaresearch","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.004789092,0.000043770357,0.00008426859,0.00012809719,0.004072054,0.0003938782,0.0037289741,0.0000368164,0.00000332617],"category_scores_gemma":[0.01867131,0.000023782117,0.000012103459,0.00062128564,0.0027968015,0.00029070853,0.00053380674,0.00012503624,0.0000030918989],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000077194645,0.0000092973605,0.0009191584,8.6981146e-7,0.000005281086,7.303726e-8,0.012396327,1.11521246e-7,0.0014830505,0.5792004,0.00233372,0.403644],"study_design_scores_gemma":[0.00012595736,0.00006591693,0.5330107,0.000021902506,0.0000036254098,2.6192555e-7,0.36021706,0.00032543042,0.0023337211,0.07768453,0.026121411,0.00008946862],"about_ca_topic_score_codex":0.060971256,"about_ca_topic_score_gemma":0.23370515,"teacher_disagreement_score":0.53209156,"about_ca_system_score_codex":0.00017155279,"about_ca_system_score_gemma":0.0019553425,"threshold_uncertainty_score":0.99991703},"labels":[],"label_agreement":null},{"id":"W2725980232","doi":"10.4324/9781315270449","title":"The Routledge Handbook of Developments in Digital Journalism Studies","year":2018,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":89,"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":"","keywords":"Journalism; Newspaper; Media studies; Digital media; Audience measurement; Sociology; Political science; Law","score_opus":0.3668295760981434,"score_gpt":0.429821876957204,"score_spread":0.0629923008590606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2725980232","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00034662176,0.011472931,0.0014292987,0.0018869505,0.00054453354,0.0005418268,0.00025179164,0.000072311625,0.98345375],"genre_scores_gemma":[0.0017019862,0.0029079414,0.0009553281,0.00005951872,0.0000718023,0.000026971644,0.000013652494,0.000011094663,0.9942517],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976871,0.000013752361,0.00093590183,0.00033742114,0.0008315916,0.00019422286],"domain_scores_gemma":[0.99658376,0.0014436408,0.00050278206,0.00088968565,0.00054984336,0.000030307214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012303175,0.00016455447,0.00038203425,0.0002191283,0.00020130636,0.00029404648,0.0021341702,0.00018559303,0.000067471214],"category_scores_gemma":[0.0023354164,0.00007822131,0.00008537013,0.00028130502,0.00073301553,0.00018709744,0.0010943746,0.00023364439,0.00056513137],"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":[0.0000031627185,0.000010316659,0.0001369373,0.0000021316496,0.00003849368,0.0000011296837,0.00008996477,7.6859656e-8,0.0000015793543,0.030782403,0.8567033,0.112230495],"study_design_scores_gemma":[0.00006773355,0.000012839899,0.00010779781,0.000090379144,0.0000031555242,0.0000021873554,0.00039853688,0.000001745355,0.000057156467,0.29326627,0.70591545,0.000076759046],"about_ca_topic_score_codex":0.0000020391685,"about_ca_topic_score_gemma":0.00017605422,"teacher_disagreement_score":0.26248387,"about_ca_system_score_codex":0.000102065234,"about_ca_system_score_gemma":0.00028236944,"threshold_uncertainty_score":0.7263809},"labels":[],"label_agreement":null},{"id":"W2737798405","doi":"10.23974/ijol.2017.vol2.1.33","title":"Book Review of the Data Librarian's Handbook","year":2017,"lang":"en","type":"article","venue":"International Journal of Librarianship","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Publishing; Library science; Facet (psychology); Computer science; Art; Psychology; Psychoanalysis; Literature","score_opus":0.43389396930065643,"score_gpt":0.44659151163798116,"score_spread":0.01269754233732473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2737798405","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004965212,0.25391188,0.011309822,0.70152766,0.00449967,0.0003963124,0.001130828,0.000032929765,0.02669436],"genre_scores_gemma":[0.38531184,0.3087267,0.038289607,0.20346498,0.0074477806,0.000034865414,0.0001993393,0.00014329332,0.05638159],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99707216,0.00009432905,0.0009934751,0.00021189736,0.0015258604,0.00010226031],"domain_scores_gemma":[0.9933371,0.0005383822,0.0024744377,0.0030847955,0.0005056966,0.000059603026],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0017418546,0.00009088332,0.0002609347,0.00012005896,0.00018185159,0.00071171776,0.022134162,0.00006861228,0.001627728],"category_scores_gemma":[0.009302197,0.000049613227,0.00017309231,0.00013263542,0.00032039348,0.0037076632,0.0028224892,0.0002822463,0.000040722953],"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":[0.00001436391,0.000031944262,0.0026380648,0.000014812457,0.000046810077,0.000007476586,0.000009714164,5.827303e-7,0.00007077732,0.009670446,0.95277315,0.034721833],"study_design_scores_gemma":[0.00021740647,0.00001542293,0.014313731,0.0016155577,0.000019533161,0.00006679518,0.00002249752,0.00004018,0.0012020841,0.024764212,0.95766735,0.00005523389],"about_ca_topic_score_codex":0.0000057469997,"about_ca_topic_score_gemma":0.0000016772168,"teacher_disagreement_score":0.49806267,"about_ca_system_score_codex":0.000012125789,"about_ca_system_score_gemma":0.00029808175,"threshold_uncertainty_score":0.9992849},"labels":[],"label_agreement":null},{"id":"W2738756939","doi":"10.1007/978-981-10-5427-3","title":"Advances in Computing and Data Sciences","year":2017,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Information retrieval; Data science","score_opus":0.3816037324148056,"score_gpt":0.48544327055234704,"score_spread":0.10383953813754143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738756939","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008385393,0.011828028,0.102709435,0.010458433,0.00061304134,0.0013728886,0.00046234397,0.0001712999,0.871546],"genre_scores_gemma":[0.39109966,0.14621194,0.45486352,0.0025925764,0.00021634749,0.00009156424,0.00091635727,0.000030113546,0.003977915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972658,0.00005446207,0.00096377666,0.0006199885,0.000830554,0.00026542434],"domain_scores_gemma":[0.9919939,0.001177608,0.00071809726,0.005798197,0.00024605662,0.000066113826],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["sts","scholarly_communication","open_science"],"category_scores_codex":[0.007514168,0.00017262608,0.00031804928,0.0015093352,0.0014395156,0.0022704247,0.014925385,0.00013079194,0.0000040277137],"category_scores_gemma":[0.0014108978,0.0001431058,0.000015424015,0.0010929186,0.005691566,0.016135205,0.015353404,0.00047265063,0.000034337714],"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":[6.268758e-7,0.000008843449,0.0009268496,0.000007882856,4.568463e-7,1.2085847e-7,0.00025881952,0.000060793933,2.4363533e-7,0.10082075,0.0019801047,0.8959345],"study_design_scores_gemma":[0.00014568018,0.000019252213,0.0062961658,0.0001668004,0.0000018121699,0.000011554049,0.00017091067,0.29748282,6.0136034e-7,0.046613324,0.64890426,0.00018682187],"about_ca_topic_score_codex":0.000026298829,"about_ca_topic_score_gemma":0.00016838618,"teacher_disagreement_score":0.89574766,"about_ca_system_score_codex":0.000074049676,"about_ca_system_score_gemma":0.0005566854,"threshold_uncertainty_score":0.99986047},"labels":[],"label_agreement":null},{"id":"W2791337913","doi":"","title":"The Data Librarian's Handbook by Robin Rice and John Southall (review)","year":2017,"lang":"en","type":"article","venue":"Canadian journal of information science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Sociology; History; Data science","score_opus":0.18935163474659197,"score_gpt":0.3617327287424731,"score_spread":0.1723810939958811,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791337913","genre_codex":"commentary","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":[0.03198599,0.12009966,0.12805021,0.57948184,0.005247959,0.0023794821,0.0051290253,0.000096291355,0.12752955],"genre_scores_gemma":[0.9535687,0.02675376,0.010133868,0.008266175,0.00013864925,0.00001128101,0.000035109704,0.000009357148,0.001083114],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983218,0.000018359284,0.0006017023,0.00012512768,0.0007037377,0.00022927848],"domain_scores_gemma":[0.99599034,0.00020785788,0.0010792009,0.0017911713,0.0005446883,0.00038676878],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.005906568,0.000064893364,0.00011998677,0.0002181727,0.0025872614,0.0034498833,0.008396667,0.000033829885,0.00003165754],"category_scores_gemma":[0.0122148935,0.00003645762,0.000021269097,0.0004240219,0.0013895633,0.011765609,0.0004443924,0.00016873758,0.0000847556],"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":[0.0000010388463,0.000001067319,0.00041325775,0.0000038378257,0.000002214302,9.3438933e-7,0.00010662241,0.0000013001966,0.000045848858,0.0053579095,0.7020526,0.29201335],"study_design_scores_gemma":[0.00008042666,0.000013130239,0.004727478,0.00006726583,0.000004207627,0.00005814643,0.000432294,0.00048632713,0.00012309698,0.0028316574,0.9911154,0.000060567512],"about_ca_topic_score_codex":0.0005402066,"about_ca_topic_score_gemma":0.0010140162,"teacher_disagreement_score":0.9215827,"about_ca_system_score_codex":0.00003247477,"about_ca_system_score_gemma":0.0014538601,"threshold_uncertainty_score":0.9987112},"labels":[],"label_agreement":null},{"id":"W2801061359","doi":"","title":"Dealing with real-life laboratories in energy research : the power of the experimenter","year":2018,"lang":"en","type":"article","venue":"ORBi (University of Liège)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Power (physics); Computer science","score_opus":0.19090141907614092,"score_gpt":0.36956174115216056,"score_spread":0.17866032207601965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801061359","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":[0.98486227,0.000042954034,0.00086006004,0.009169567,0.00002725478,0.0000691285,0.00002250976,0.000010548686,0.004935728],"genre_scores_gemma":[0.998959,0.00004379102,0.0004963209,0.00003698561,0.000007986611,3.9347853e-7,3.839222e-7,0.000002290719,0.00045286206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99897206,0.00008916865,0.00010517694,0.00017271965,0.0005399795,0.000120879864],"domain_scores_gemma":[0.9983772,0.00024665505,0.00010757511,0.0008219003,0.0004238004,0.000022859553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000816646,0.000042202555,0.000097230244,0.00010182645,0.0002900892,0.000020679023,0.0013503407,0.000049027527,0.00019333206],"category_scores_gemma":[0.00006537646,0.00002331478,0.000023019216,0.0013422356,0.0012062798,0.0001300312,0.00055172644,0.00009722611,0.000011363191],"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":[0.00017163076,0.0001312136,0.10042165,0.000003287667,0.000031180658,0.0000041259727,0.009581014,0.0000154877,0.00809153,0.8500424,0.02758415,0.0039223456],"study_design_scores_gemma":[0.0009961675,0.0005252361,0.30018088,0.00011177662,0.00001577133,0.000003041107,0.32602206,0.00040755433,0.03179527,0.028086543,0.31158018,0.00027551994],"about_ca_topic_score_codex":0.003591547,"about_ca_topic_score_gemma":0.0030422406,"teacher_disagreement_score":0.82195586,"about_ca_system_score_codex":0.00001634588,"about_ca_system_score_gemma":0.00008174624,"threshold_uncertainty_score":0.54293686},"labels":[],"label_agreement":null},{"id":"W2911770460","doi":"","title":"Proceedings of the 11th International Symposium on Algorithms and Data Structures","year":2009,"lang":"en","type":"article","venue":"Workshop on Algorithms and Data Structures","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Carleton University","funders":"","keywords":"Computer science; Algorithm","score_opus":0.1330494260001287,"score_gpt":0.3836235653197722,"score_spread":0.2505741393196435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2911770460","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":[0.7652788,0.0037964087,0.0069977664,0.14926888,0.004578253,0.0034891309,0.055233743,0.0007095957,0.010647425],"genre_scores_gemma":[0.9668615,0.0013820786,0.028506007,0.0018009243,0.0005155282,0.000009102575,0.00065628317,0.000023901808,0.00024468638],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966877,0.00002202984,0.0005371905,0.0013543441,0.0011213341,0.0002773626],"domain_scores_gemma":[0.99626344,0.0003421199,0.00036854614,0.0027685072,0.00015169478,0.00010569917],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00069879455,0.00028580974,0.00033053453,0.0001555637,0.00036098238,0.00067312334,0.005981727,0.00020371823,0.0000664805],"category_scores_gemma":[0.00096268055,0.00016090948,0.000037548623,0.00056756055,0.00042588715,0.0006715755,0.002906178,0.00044514766,0.0000030434344],"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":[0.00004514742,0.00004077661,0.00044045883,0.00000383031,0.000031212872,0.0000012174336,0.000067579764,0.000019932068,0.00032379854,0.044738866,0.0669462,0.88734096],"study_design_scores_gemma":[0.0013058104,0.0003211774,0.2656965,0.00014890305,0.00009538426,0.00011990092,0.0024758666,0.02237925,0.0017874208,0.25399277,0.45086923,0.00080780743],"about_ca_topic_score_codex":0.000029327204,"about_ca_topic_score_gemma":0.000020195648,"teacher_disagreement_score":0.8865332,"about_ca_system_score_codex":0.00001613803,"about_ca_system_score_gemma":0.000029082423,"threshold_uncertainty_score":0.9993964},"labels":[],"label_agreement":null},{"id":"W2920833540","doi":"10.1017/s1551929519000026","title":"Management, Analysis, and Simulation of Micrographs with Cloud Computing","year":2019,"lang":"en","type":"article","venue":"Microscopy Today","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Automotive Fuel Cell Cooperation (Canada)","funders":"","keywords":"Cloud computing; Micrograph; Computer science; Materials science; Computer graphics (images); Operating system; Composite material","score_opus":0.04500624072573308,"score_gpt":0.35876348383713663,"score_spread":0.31375724311140357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920833540","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":[0.911364,0.000112356065,0.08740448,0.00012627582,0.000030980533,0.00019313567,0.00003248873,0.00003605365,0.00070022524],"genre_scores_gemma":[0.9780585,0.000020807282,0.021578407,0.000045162735,0.000005481293,0.0000017901426,0.000015859468,0.0000043808955,0.00026959906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989443,0.000022694285,0.000292249,0.00036091922,0.0002453965,0.00013443256],"domain_scores_gemma":[0.9988305,0.00020624259,0.00020805953,0.00064810755,0.000082446146,0.000024676032],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044901014,0.00008365964,0.00021541341,0.00034302057,0.000074209835,0.00009802247,0.00039446278,0.00004791792,0.000067475325],"category_scores_gemma":[0.000018804401,0.000058233265,0.000051297884,0.0019516684,0.000117788375,0.00008917051,0.00020310069,0.0000594388,0.000039647082],"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":[0.000046553436,0.00010816638,0.86188585,0.000027556289,0.00037552195,0.0000017250493,0.00021709445,0.010797291,0.037258834,0.00400776,0.0012610728,0.084012575],"study_design_scores_gemma":[0.0020210617,0.00045478647,0.68624127,0.00011330506,0.0007804696,0.0000056417043,0.004121982,0.07645918,0.085278414,0.0098259235,0.1338471,0.0008508835],"about_ca_topic_score_codex":0.000026557474,"about_ca_topic_score_gemma":0.00001820888,"teacher_disagreement_score":0.17564459,"about_ca_system_score_codex":0.0000058605947,"about_ca_system_score_gemma":0.000004523352,"threshold_uncertainty_score":0.23746836},"labels":[],"label_agreement":null},{"id":"W2945518138","doi":"10.1002/9781119629610","title":"Digital identities in tension : between autonomy and control","year":2019,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Autonomy; Tension (geology); Control (management); Computer science; Political science; Materials science; Artificial intelligence; Composite material; Law","score_opus":0.06370739542023025,"score_gpt":0.29080931814703315,"score_spread":0.2271019227268029,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945518138","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":[0.56220806,0.0016030805,0.33429888,0.038782805,0.00026902865,0.0014694943,0.0013799438,0.0004441137,0.05954461],"genre_scores_gemma":[0.98476994,0.00021493476,0.004893777,0.00006893933,0.000016704656,0.00007147888,0.0003370679,0.00002312102,0.009604052],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995624,0.0012919332,0.0009093728,0.0011181734,0.0007230946,0.0003333911],"domain_scores_gemma":[0.99004644,0.004747392,0.0006362545,0.0031241558,0.0013251659,0.00012060192],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0066135842,0.0002946102,0.0005841447,0.0004754521,0.0002173278,0.0017890681,0.0023449126,0.00040916153,0.000071505485],"category_scores_gemma":[0.0053095897,0.00026499294,0.00014693178,0.00056312035,0.00042729426,0.000440333,0.0033825934,0.0007244578,0.00017898783],"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":[0.000011633136,0.000323357,0.29001993,0.00008169652,0.000074295924,0.0000061009514,0.002761126,0.00008532218,0.0004973463,0.07206032,0.0058034207,0.62827545],"study_design_scores_gemma":[0.002449951,0.0000016998625,0.4012315,0.0020874282,0.00009607456,0.000019778308,0.0017300106,0.033097763,0.00499212,0.3499708,0.2026946,0.0016282734],"about_ca_topic_score_codex":0.0003365132,"about_ca_topic_score_gemma":0.00038229467,"teacher_disagreement_score":0.6266472,"about_ca_system_score_codex":0.00010356372,"about_ca_system_score_gemma":0.00027635362,"threshold_uncertainty_score":0.9999802},"labels":[],"label_agreement":null},{"id":"W2947081365","doi":"10.5539/jsd.v12n3p146","title":"Harnessing Big Data for Sustainable Development in Nigeria","year":2019,"lang":"en","type":"article","venue":"Journal of Sustainable Development","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Variety (cybernetics); Sustainable development; Diversification (marketing strategy); Sustainable growth rate; Inclusive growth; Corporate governance; Government (linguistics); Business; Poverty; Economic growth; Economics; Marketing; Computer science; Political science; Management","score_opus":0.15868452995225626,"score_gpt":0.35556488311741336,"score_spread":0.1968803531651571,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947081365","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":[0.9603742,0.0006002168,0.03370682,0.0024267868,0.00039129748,0.0012736784,0.0000075894536,0.00003533311,0.0011840839],"genre_scores_gemma":[0.92051256,0.000033376506,0.056488555,0.00017171892,0.00009968151,0.00007203724,0.000040619245,0.000027068778,0.022554358],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9955753,0.000055336866,0.001812732,0.00056386186,0.001118741,0.000874044],"domain_scores_gemma":[0.9951798,0.0005221633,0.0009755321,0.0012291039,0.0019569069,0.00013651125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008604231,0.00022254727,0.00055539445,0.0011509449,0.00035637023,0.0006077051,0.00326245,0.00015037363,0.00008610025],"category_scores_gemma":[0.0031089447,0.00016815036,0.000062060826,0.001675954,0.00005878195,0.0014300627,0.0017306014,0.0002978937,0.000062693056],"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":[0.00056355464,0.0010424231,0.05389043,0.00064574246,0.00021889947,0.0010834057,0.0067189354,0.00065551803,0.00094557845,0.035754185,0.15386227,0.7446191],"study_design_scores_gemma":[0.0008899016,0.00004594038,0.0153265735,0.00005535908,0.00000463569,0.0000260402,0.08732996,0.00008585583,0.001539276,0.009344059,0.88511336,0.00023901367],"about_ca_topic_score_codex":0.000012631484,"about_ca_topic_score_gemma":0.000030253424,"teacher_disagreement_score":0.74438006,"about_ca_system_score_codex":0.00077173044,"about_ca_system_score_gemma":0.0033098005,"threshold_uncertainty_score":0.6856973},"labels":[],"label_agreement":null},{"id":"W2947182476","doi":"10.1109/icccbda.2019.8725660","title":"Design and Implementation of Meteorological Big Data Platform Based on Hadoop and Elasticsearch","year":2019,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l'Économie, de la Science et de l'Innovation - Québec","keywords":"Computer science; Big data; Operating system; Database","score_opus":0.5454127380640832,"score_gpt":0.4547144353797887,"score_spread":0.09069830268429452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2947182476","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":[0.576365,0.000023690714,0.4200416,0.0021559522,0.00003948461,0.0005006886,0.00018146154,0.000037934886,0.0006542268],"genre_scores_gemma":[0.96998775,0.000023026685,0.029762417,0.00013446917,0.0000053084873,0.000007114946,0.000030909516,0.0000021959806,0.00004678465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988927,0.00002741311,0.00023053371,0.0003620973,0.00037768824,0.00010955697],"domain_scores_gemma":[0.9973973,0.0016119546,0.00007275031,0.00082886085,0.000054752643,0.000034394037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014341195,0.00005720098,0.000119623895,0.000116130745,0.000050788527,0.000071725204,0.0005725779,0.000054781904,0.00032615528],"category_scores_gemma":[0.0003293768,0.00003388309,0.0000074703653,0.0002551125,0.00010561274,0.0001354727,0.0004689517,0.000066275854,0.000040691903],"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":[0.000053070828,0.000047999856,0.018080536,0.0000050101594,0.0000073397014,4.248099e-7,0.000019521274,0.00006512088,0.004775249,0.026533365,0.0072973766,0.943115],"study_design_scores_gemma":[0.0031728612,0.002742455,0.26174098,0.000017748236,0.000042300322,0.000008478985,0.005852986,0.55971587,0.033491977,0.091339454,0.041382466,0.0004924093],"about_ca_topic_score_codex":0.00003515001,"about_ca_topic_score_gemma":0.000021502596,"teacher_disagreement_score":0.9426226,"about_ca_system_score_codex":0.0000041325547,"about_ca_system_score_gemma":0.000027021073,"threshold_uncertainty_score":0.35711715},"labels":[],"label_agreement":null},{"id":"W2969189173","doi":"10.3998/ticker.16481003.0003.201","title":"Harnessing the Data Deluge: Introduction","year":2019,"lang":"en","type":"article","venue":"Ticker The Academic Business Librarianship Review","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Data science; Computer science","score_opus":0.38061994551728817,"score_gpt":0.4016453283991342,"score_spread":0.021025382881846022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969189173","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002556264,0.13402167,0.0074287793,0.85167444,0.0010273019,0.0015534775,0.00008834062,0.000251095,0.0013986278],"genre_scores_gemma":[0.3998081,0.45051143,0.0054728948,0.110363916,0.008897666,0.00075719325,0.0016003344,0.00026425876,0.022324208],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964214,0.00039780937,0.0009525025,0.0009000465,0.0009698422,0.00035837913],"domain_scores_gemma":[0.9904852,0.0013829613,0.0005816218,0.0072854566,0.00021201618,0.00005277694],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0065896316,0.00022779826,0.00043194368,0.00007792807,0.0004314066,0.00046525188,0.011398621,0.00020142102,0.0012458864],"category_scores_gemma":[0.0062357243,0.000098107994,0.00007118975,0.004015235,0.00038899362,0.0023748863,0.0028061753,0.0010784181,0.0043517635],"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":[0.0000043121754,0.0000097177535,0.0010371297,0.0001328189,0.000012853648,3.3143002e-7,0.000026541584,0.0000059352788,0.00008488295,0.04567785,0.5994753,0.3535323],"study_design_scores_gemma":[0.00007501259,0.0000025521847,0.007888892,0.00039172758,0.000075161675,0.000043003092,0.00014850943,0.0005274691,0.000024580608,0.029009447,0.9616623,0.00015135187],"about_ca_topic_score_codex":0.000013312001,"about_ca_topic_score_gemma":0.0000010840391,"teacher_disagreement_score":0.74131054,"about_ca_system_score_codex":0.000016906517,"about_ca_system_score_gemma":0.00015562499,"threshold_uncertainty_score":0.9996671},"labels":[],"label_agreement":null},{"id":"W2983654909","doi":"10.23962/10539/27534","title":"A Proposed \"Agricultural Data Commons\" in Support of Food Security","year":2019,"lang":"en","type":"article","venue":"The African Journal of Information and Communication (AJIC)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canada First Research Excellence Fund; Social Sciences and Humanities Research Council of Canada; International Development Research Centre","keywords":"Food security; Agriculture; Commons; Business; Computer science; Computer security; Internet privacy; Political science; Biology; Ecology; Law","score_opus":0.1300621430092644,"score_gpt":0.33018160991400264,"score_spread":0.20011946690473822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983654909","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":[0.9650639,0.00026254164,0.0006026742,0.02399093,0.000046110235,0.0003940319,0.00018516091,0.0000156401,0.00943898],"genre_scores_gemma":[0.9983466,0.00022416007,0.0011718135,0.00018370776,0.0000042975694,0.0000024198669,0.000046150686,0.0000015021587,0.00001932135],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815524,0.0001586651,0.0010505295,0.00006285122,0.00048263924,0.00009008479],"domain_scores_gemma":[0.99615866,0.0004667427,0.0012903583,0.0016351568,0.00041210392,0.000036961625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030166036,0.000069633716,0.0002104847,0.00018903805,0.00009415222,0.00012629284,0.0032574197,0.000047099216,0.00006111377],"category_scores_gemma":[0.00054560404,0.000036916023,0.000036897192,0.0007159678,0.00017313079,0.0016582991,0.0007976703,0.000287173,0.000030015022],"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":[0.000429019,0.00056057575,0.02287114,0.000066961955,0.00015202576,4.6091264e-7,0.033463534,0.0002458138,0.00094704307,0.55066514,0.12532866,0.2652696],"study_design_scores_gemma":[0.0029497887,0.0010794826,0.13120712,0.00011137787,0.000052721192,0.00022932701,0.13294894,0.004122893,0.0013605687,0.14746007,0.5780757,0.000401992],"about_ca_topic_score_codex":0.000022489423,"about_ca_topic_score_gemma":0.00007708868,"teacher_disagreement_score":0.45274705,"about_ca_system_score_codex":0.0000187562,"about_ca_system_score_gemma":0.000089379086,"threshold_uncertainty_score":0.605315},"labels":[],"label_agreement":null},{"id":"W3000750835","doi":"10.1109/tps.2019.2961571","title":"Special Issue on Machine Learning, Data Science, and Artificial Intelligence in Plasma Research","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Plasma Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":23,"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":"","keywords":"Big data; Computer science; Data science; Artificial intelligence; Data mining","score_opus":0.4464670136898698,"score_gpt":0.44894955899565075,"score_spread":0.0024825453057809588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3000750835","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":[0.7219392,0.000032432905,0.13076235,0.08804361,0.0040645506,0.0025594519,0.0015651778,0.0006874181,0.05034578],"genre_scores_gemma":[0.9966882,0.000099013334,0.002396989,0.00020697652,0.00035107162,0.000026316535,0.0000026052978,0.000009720225,0.00021909384],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99237937,0.00012232192,0.0006095537,0.0020175679,0.004127684,0.0007435136],"domain_scores_gemma":[0.9961319,0.0013391032,0.00011321815,0.0015569855,0.0004898102,0.00036899454],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.008941715,0.00019162748,0.00024316942,0.0016900839,0.0021056267,0.0010554966,0.0062286183,0.00010392632,0.00044386537],"category_scores_gemma":[0.0044149286,0.00015514475,0.000026851738,0.0147736445,0.0058559147,0.0016895958,0.00016934187,0.0013268733,0.0015182631],"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":[0.000115362105,0.0002060398,0.000044882338,0.0000027935855,0.0000017371874,0.00001063599,0.0005562293,0.006011517,0.0056872633,0.008309979,0.0034664609,0.9755871],"study_design_scores_gemma":[0.00017028463,0.00063728535,0.00025009675,0.000025717105,0.000004471173,0.000015333238,0.0030924622,0.69380605,0.09579085,0.0036338412,0.20224293,0.0003306524],"about_ca_topic_score_codex":0.00010100915,"about_ca_topic_score_gemma":0.0005806327,"teacher_disagreement_score":0.97525644,"about_ca_system_score_codex":0.00014105931,"about_ca_system_score_gemma":0.0006407188,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W3036150657","doi":"10.1177/2053951720935143","title":"Personalization as a promise: Can Big Data change the practice of insurance?","year":2020,"lang":"en","type":"article","venue":"Big Data & Society","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Big data; Data science; Pooling; Personalization; Telematics; Computer science; Analytics; Data mining; Artificial intelligence; World Wide Web","score_opus":0.6585193461766956,"score_gpt":0.4307756542434794,"score_spread":0.2277436919332162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036150657","genre_codex":"commentary","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":[0.03406731,0.007471021,0.045999285,0.8060657,0.0010547407,0.0034238966,0.099564604,0.00054453744,0.0018089279],"genre_scores_gemma":[0.9710442,0.003902538,0.0070332936,0.0113216555,0.0009766662,0.00009324613,0.0055080284,0.00002314883,0.00009722438],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973727,0.00010792034,0.00042731993,0.00087347755,0.0010145049,0.00020407683],"domain_scores_gemma":[0.9935889,0.00070657564,0.0004696566,0.00489326,0.00026267656,0.000078902325],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0018487653,0.00013245767,0.0002038236,0.000017125054,0.0003016113,0.00021716458,0.007332259,0.000115963325,0.000040776544],"category_scores_gemma":[0.007829034,0.000082814804,0.00005655404,0.0016098198,0.00031993538,0.00090845214,0.0045319647,0.00023704165,0.00009031744],"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":[0.000015528492,0.000084976666,0.00081881246,0.000021280337,0.00004748676,0.0000010551502,0.0036277326,7.040265e-7,0.0005016452,0.0013054475,0.6086323,0.38494298],"study_design_scores_gemma":[0.00020857136,0.000029622042,0.0021763025,0.000011023911,0.00003602146,0.0000049663026,0.011693812,0.0046820957,0.00010819692,0.00050951587,0.98042524,0.000114605464],"about_ca_topic_score_codex":0.00086676766,"about_ca_topic_score_gemma":0.00017348975,"teacher_disagreement_score":0.9369769,"about_ca_system_score_codex":0.000017011009,"about_ca_system_score_gemma":0.0001870829,"threshold_uncertainty_score":0.99803853},"labels":[],"label_agreement":null},{"id":"W3044486411","doi":"10.1111/insr.12395","title":"Interview with Professor Adrian FM Smith","year":2020,"lang":"en","type":"article","venue":"International Statistical Review","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Treasury; Government (linguistics); Majesty; Conversation; Management; State (computer science); Political science; Library science; Law; Media studies; Sociology; Mathematics; Philosophy","score_opus":0.4273704481634134,"score_gpt":0.4698770728995282,"score_spread":0.04250662473611477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044486411","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":[0.000045164463,0.007826817,0.6001854,0.38090217,0.00012122272,0.00054789695,0.0008949484,0.00011943855,0.009356942],"genre_scores_gemma":[0.41928238,0.0772697,0.25593936,0.23957804,0.00087549613,0.0009872577,0.0009289529,0.00012297885,0.005015833],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997687,0.00009628584,0.0006050544,0.00046786483,0.0009841416,0.00015968233],"domain_scores_gemma":[0.99826,0.00065540074,0.0001993679,0.00039908136,0.00032583563,0.00016031743],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00064169115,0.00012876271,0.00031698882,0.000034124478,0.000058567126,0.00013267015,0.0014829435,0.00003628953,0.004598693],"category_scores_gemma":[0.0056044036,0.000075407675,0.00005678791,0.00048355723,0.00014065174,0.00016136936,0.00031602223,0.00020390915,0.0025004698],"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":[0.000007635483,0.000030119545,0.000109481116,0.000095966985,0.000019392732,0.000012818616,0.000008072639,3.3851924e-7,0.0000041947487,0.21689288,0.2693394,0.5134797],"study_design_scores_gemma":[0.000117753974,0.0000719109,0.0010855924,0.0004961958,0.000020517793,0.000011233941,0.00003268742,0.00045498693,0.000011649042,0.013315106,0.98427373,0.00010860924],"about_ca_topic_score_codex":0.0000038901953,"about_ca_topic_score_gemma":0.0000068935697,"teacher_disagreement_score":0.71493435,"about_ca_system_score_codex":0.00002591818,"about_ca_system_score_gemma":0.000052301628,"threshold_uncertainty_score":0.9982762},"labels":[],"label_agreement":null},{"id":"W3080961046","doi":"10.1109/dsc50466.2020.00005","title":"Message from the General ChairsDSC 2020","year":2020,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cyberspace; Pleasure; China; Computer science; World Wide Web; Telecommunications; The Internet; Library science; Political science; Psychology","score_opus":0.2914835952647328,"score_gpt":0.3795147392486793,"score_spread":0.08803114398394651,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080961046","genre_codex":"commentary","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":[0.12731358,0.00032398602,0.043859668,0.7932133,0.00018976536,0.00024907265,0.0005885328,0.00042065897,0.033841413],"genre_scores_gemma":[0.97619414,0.000053967065,0.0052166954,0.015634269,0.0002773838,0.000020558522,0.00002081325,0.000005086522,0.0025770706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989417,0.000026327125,0.00020334091,0.00031906232,0.00040024976,0.00010931507],"domain_scores_gemma":[0.99874014,0.00040541586,0.000053115942,0.0007071852,0.000037188925,0.00005697246],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00022794484,0.00006053825,0.00009278675,0.0000070645133,0.00013880483,0.00018010431,0.0016738641,0.000046384645,0.0037486455],"category_scores_gemma":[0.0007393356,0.000028262315,0.000048836147,0.00048765968,0.00008264911,0.00007363657,0.0004880711,0.00011111658,0.0020658434],"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":[0.0000014668597,0.000004513727,0.00089679,5.747989e-8,0.0000028897637,8.5829066e-7,0.000056435383,0.000004833396,0.00086952833,0.023607036,0.9293282,0.045227405],"study_design_scores_gemma":[0.00006622709,0.0000094916795,0.006068197,3.9644945e-7,0.0000027221613,3.461306e-7,0.0008301975,0.003116803,0.0011317405,0.031981453,0.9567352,0.00005720432],"about_ca_topic_score_codex":0.00013279676,"about_ca_topic_score_gemma":0.00007370119,"teacher_disagreement_score":0.8488806,"about_ca_system_score_codex":0.0000032213109,"about_ca_system_score_gemma":0.000012879858,"threshold_uncertainty_score":0.99871117},"labels":[],"label_agreement":null},{"id":"W3081485903","doi":"10.1089/big.2020.29039.cfp","title":"<i>Call for Special Issue Papers:</i> Programming Models and Algorithms for Big Data","year":2020,"lang":"en","type":"article","venue":"Big Data","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"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; Library science; Algorithm; Data mining","score_opus":0.692660615863904,"score_gpt":0.4300657800872848,"score_spread":0.26259483577661924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3081485903","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":[0.0001615588,0.0005806062,0.85521984,0.058356322,0.0010511837,0.0024426891,0.081066266,0.00027159989,0.0008499497],"genre_scores_gemma":[0.024789164,0.0014813979,0.86850053,0.0078642825,0.047108293,0.00091296545,0.0475388,0.00013839891,0.0016661781],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99728394,0.00001837327,0.00046459775,0.0014427002,0.00045118167,0.0003391904],"domain_scores_gemma":[0.9949991,0.0006565019,0.00016708985,0.003914109,0.00010933129,0.00015387224],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011344259,0.00016431998,0.00028864242,0.00005655472,0.00027974276,0.0005274423,0.0060077216,0.00012891335,0.000015565292],"category_scores_gemma":[0.002971579,0.00012555307,0.000035390094,0.0004835332,0.00016511866,0.0006629131,0.0050063753,0.00011044861,0.000041739306],"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":[0.0000143549805,0.00001922947,0.000006327788,0.000007872048,0.000006937886,4.1451153e-7,0.000023118722,0.0000015381543,0.00006533935,0.0006233268,0.4063394,0.59289217],"study_design_scores_gemma":[0.00043822153,0.00007158811,0.000011912204,0.0000061538067,0.000027630767,0.0000022668498,0.0003567349,0.055297773,0.00007227677,0.0054580634,0.93809205,0.00016535172],"about_ca_topic_score_codex":0.000029299172,"about_ca_topic_score_gemma":0.00014804582,"teacher_disagreement_score":0.59272677,"about_ca_system_score_codex":0.000006694931,"about_ca_system_score_gemma":0.00007031256,"threshold_uncertainty_score":0.9993703},"labels":[],"label_agreement":null},{"id":"W3094472893","doi":"10.1016/s0262-4079(20)31883-2","title":"Big data's first election victory","year":2020,"lang":"en","type":"article","venue":"The New Scientist","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"World Federation of Science Journalists","funders":"","keywords":"Victory; Big data; Social media; Political science; Computer science; Data science; Law; Politics; Data mining","score_opus":0.40323472136983307,"score_gpt":0.3840087457571395,"score_spread":0.01922597561269357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094472893","genre_codex":"commentary","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":[0.027952716,0.0006734558,0.27064538,0.6772417,0.0034689817,0.00072270713,0.0005897439,0.0008209971,0.01788433],"genre_scores_gemma":[0.9896919,0.000046229427,0.001446998,0.0028784093,0.0007952754,0.000008103479,0.00005466891,0.000008871578,0.0050695064],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99834114,0.000027015418,0.00022995166,0.0005353453,0.0006879785,0.00017853656],"domain_scores_gemma":[0.9976633,0.00022668205,0.00010879082,0.0018372274,0.000057425666,0.00010652778],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008925474,0.00007098486,0.000092049675,0.000054218253,0.0005931281,0.00048057036,0.004212679,0.00003803339,0.0002616807],"category_scores_gemma":[0.0014013825,0.00004054926,0.000030273259,0.0020354418,0.0002408457,0.00025203772,0.001213211,0.00013403999,0.0024384952],"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":[0.0000023405896,0.0000067321553,0.00012230292,4.1924517e-7,0.000001858639,3.9598154e-7,0.00005661148,0.0000072048,0.0007643618,0.0027504766,0.8527277,0.14355959],"study_design_scores_gemma":[0.000076220545,0.000013942726,0.002313197,0.0000013588195,0.0000047835674,0.0000033283352,0.0001398431,0.0020795753,0.0006088419,0.007070813,0.9876307,0.000057341396],"about_ca_topic_score_codex":0.00011157983,"about_ca_topic_score_gemma":0.0006027574,"teacher_disagreement_score":0.96173924,"about_ca_system_score_codex":0.000013243599,"about_ca_system_score_gemma":0.000072334566,"threshold_uncertainty_score":0.9983382},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W3113601839","doi":"","title":"A History lesson on the future of cities","year":2020,"lang":"en","type":"article","venue":"Journal of Professional Communication","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Niagara Health System","funders":"","keywords":"Hacker; Smart city; Big data; Key (lock); Stakeholder; Public relations; Utopia; Townsend; Data collection; Sociology; Engineering ethics; Political science; Internet of Things; Engineering; Internet privacy; Social science; Computer science; Computer security; Law","score_opus":0.41932294231976236,"score_gpt":0.4171300552817399,"score_spread":0.0021928870380224508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113601839","genre_codex":"commentary","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":[0.38758916,0.008134543,0.0009451812,0.5991438,0.000512724,0.00022338625,0.000030276058,0.000022238106,0.0033986692],"genre_scores_gemma":[0.9959005,0.00048484124,0.0015338317,0.0017216372,0.000108458284,0.000005457422,0.0000028382678,0.0000039768765,0.00023845915],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812317,0.0003155644,0.0006196747,0.000079640966,0.00080018654,0.00006177308],"domain_scores_gemma":[0.996274,0.001320157,0.0011380989,0.0007286685,0.000500618,0.000038447535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017149949,0.00006087105,0.00017105466,0.00008184285,0.00014374472,0.000016609916,0.0022774416,0.00007295181,0.00025680102],"category_scores_gemma":[0.0011490954,0.000030209143,0.00009760027,0.00027834057,0.0001768916,0.00018082482,0.0003116931,0.00052656943,0.000023346462],"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":[0.000121347264,0.00012445773,0.0004820018,0.000005772694,0.000016577073,4.6352577e-7,0.0021149607,0.0000150891165,0.0034122074,0.30269125,0.63903373,0.051982116],"study_design_scores_gemma":[0.00019299432,0.00014836594,0.008381282,0.00008490784,0.000010147119,0.0000050781623,0.015329194,0.00024808562,0.0011434965,0.0595625,0.9148327,0.00006123492],"about_ca_topic_score_codex":0.000001863058,"about_ca_topic_score_gemma":0.00000274322,"teacher_disagreement_score":0.60831136,"about_ca_system_score_codex":0.000051972962,"about_ca_system_score_gemma":0.00014656974,"threshold_uncertainty_score":0.42320907},"labels":[],"label_agreement":null},{"id":"W3127641471","doi":"10.21810/jicw.v3i3.2530","title":"Data Analytics and Public Safety","year":2021,"lang":"en","type":"article","venue":"The Journal of Intelligence Conflict and Warfare","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Analytics; Data science; Key (lock); Data analysis; Public security; Big data; Computer security; Business intelligence; Computer science; Business; Knowledge management; Public relations; Political science; Data mining","score_opus":0.49428065406193394,"score_gpt":0.4249144124178849,"score_spread":0.06936624164404903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127641471","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":[0.3341077,0.058404747,0.4185055,0.18452038,0.00054252706,0.00029309903,0.0010142054,0.000054585755,0.0025572937],"genre_scores_gemma":[0.9731147,0.024772627,0.0013063044,0.000462117,0.000061510524,2.9261602e-7,0.000009216816,0.0000042568913,0.00026895065],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985948,0.00008224196,0.00057381985,0.0001722207,0.0004399505,0.00013696594],"domain_scores_gemma":[0.9968842,0.0010232227,0.00032043114,0.0010466069,0.00063083327,0.00009466455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022916102,0.00008022041,0.00019962448,0.000087319306,0.00024656137,0.00027664116,0.0016550523,0.000057139332,0.00014707277],"category_scores_gemma":[0.0033055171,0.0000419686,0.000029232358,0.0005663314,0.00031198908,0.000364675,0.00096479006,0.0002578144,0.000011916758],"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":[0.000030634685,0.000047810063,0.004681579,0.0000056239783,0.000068001806,0.000020828826,0.00054870336,0.000024928671,0.00055068725,0.029470187,0.020681286,0.9438697],"study_design_scores_gemma":[0.0000757009,0.00005655549,0.0035441164,0.000024642803,0.000048308604,0.0006517804,0.018507965,0.0030926045,0.0015913482,0.015020548,0.95728004,0.00010637612],"about_ca_topic_score_codex":0.000009107556,"about_ca_topic_score_gemma":0.000053100794,"teacher_disagreement_score":0.9437634,"about_ca_system_score_codex":0.000007296155,"about_ca_system_score_gemma":0.00009158583,"threshold_uncertainty_score":0.39572513},"labels":[],"label_agreement":null},{"id":"W3136339334","doi":"10.1145/3259177","title":"Session details: Big data","year":2012,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Session (web analytics); Computer science; Big data; World Wide Web; Data mining","score_opus":0.6753629625174868,"score_gpt":0.46186421164325314,"score_spread":0.2134987508742337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136339334","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":[0.18866916,0.0014888508,0.6054054,0.029697994,0.002177612,0.0004932884,0.0005803341,0.0011206823,0.1703667],"genre_scores_gemma":[0.98667574,0.00003120485,0.010277787,0.00031272002,0.00015722249,0.0000062557906,0.000041939988,0.0000032202047,0.0024938865],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.998895,0.000020353655,0.00021120168,0.00026415737,0.00041632322,0.0001929949],"domain_scores_gemma":[0.99677074,0.00028282357,0.000060958617,0.002771835,0.000042275035,0.000071342016],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013059875,0.000051812836,0.000078110796,0.000069846785,0.00011598357,0.0001059537,0.0023109685,0.000058752117,0.0006892067],"category_scores_gemma":[0.0012304059,0.000028789233,0.00001579399,0.00054778764,0.000057496618,0.0006242325,0.0016271477,0.00006921556,0.0034962138],"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":[4.276144e-7,0.000025700447,0.008446067,1.6642117e-7,9.649692e-7,5.8240044e-8,0.000005980727,8.041684e-8,0.00034104922,0.012058421,0.30416924,0.67495185],"study_design_scores_gemma":[0.000035936293,0.0000031485763,0.011311668,0.0000010214438,0.0000022691893,0.0000026217174,0.0005116113,0.00025860715,0.0009989801,0.008876852,0.97794175,0.000055551234],"about_ca_topic_score_codex":0.000022881606,"about_ca_topic_score_gemma":0.000028100769,"teacher_disagreement_score":0.7980066,"about_ca_system_score_codex":0.000005221702,"about_ca_system_score_gemma":0.000013120901,"threshold_uncertainty_score":0.9972797},"labels":[],"label_agreement":null},{"id":"W3149180268","doi":"10.2139/ssrn.3791018","title":"Understanding Big Data: Data Calculus in the Digital Era","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Calculus (dental); Computer science; Data science; Data mining; Medicine","score_opus":0.5917623436835,"score_gpt":0.4080369243857217,"score_spread":0.1837254192977783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3149180268","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":[0.023881469,0.005626773,0.8973148,0.065498516,0.00053770904,0.00021730945,0.000942293,0.00006744958,0.0059137153],"genre_scores_gemma":[0.9969136,0.0020411636,0.00011208097,0.00020409492,0.00021390773,0.0000017796646,0.00021770889,0.000006990199,0.00028864932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9969551,0.00009944556,0.0004302541,0.00052680133,0.0008336812,0.0011547423],"domain_scores_gemma":[0.9959971,0.0005606255,0.00015675159,0.0031899952,0.000057484813,0.00003807371],"candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.006119426,0.00010009143,0.00014909547,0.00012113397,0.0003497348,0.0012137387,0.0065387883,0.00006885911,0.000021846112],"category_scores_gemma":[0.0023468353,0.000059466453,0.000036180285,0.0013409758,0.00010775646,0.000951061,0.0016973667,0.0018122528,0.00007614268],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006040979,0.000083734165,0.0011827237,5.706145e-7,0.000032204734,0.000030257279,0.000053560925,0.000009190903,0.000042308882,0.56476027,0.02303213,0.410767],"study_design_scores_gemma":[0.0002520461,0.000026811385,0.00041067865,0.000006730945,0.000010889573,0.0009093589,0.025709394,0.0011411855,0.000007798287,0.80956376,0.16185193,0.00010939913],"about_ca_topic_score_codex":0.000025988373,"about_ca_topic_score_gemma":0.00453285,"teacher_disagreement_score":0.9730322,"about_ca_system_score_codex":0.00033577665,"about_ca_system_score_gemma":0.0018951112,"threshold_uncertainty_score":0.9998231},"labels":[],"label_agreement":null},{"id":"W3158455121","doi":"10.1016/j.jsams.2021.04.003","title":"Data analytics in military human performance: Getting in the game","year":2021,"lang":"en","type":"article","venue":"Journal of science and medicine in sport","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Defence Research and Development Canada; North Atlantic Treaty Organization","keywords":"Analytics; Operationalization; Data science; Relevance (law); Data analysis; Digital transformation; Big data; Business analytics; Computer science; Business; Political science; Marketing; World Wide Web","score_opus":0.31980265141786174,"score_gpt":0.45434160816329383,"score_spread":0.1345389567454321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158455121","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":[0.9868482,0.0007373788,0.000021331716,0.011686373,0.00006990295,0.000042776133,0.00000239871,0.0000013475228,0.0005903297],"genre_scores_gemma":[0.9980709,0.000954751,0.00038377283,0.0005000109,0.00006333248,6.619428e-7,0.0000020056805,0.0000010430404,0.000023549517],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99750745,0.000015296993,0.00076752773,0.00023401836,0.0013037481,0.00017197299],"domain_scores_gemma":[0.9987027,0.00017078573,0.0001902659,0.00065348356,0.00023899648,0.000043791184],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016534245,0.000051702602,0.0002137391,0.0005646438,0.000090139496,0.000029746518,0.0019624843,0.000030233206,0.000019433328],"category_scores_gemma":[0.0026926072,0.000026583883,0.000010063806,0.0034553218,0.0009972315,0.0007083834,0.00031328958,0.00035275816,9.06231e-7],"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":[0.0000057145403,0.00008582436,0.9224657,0.0000059827544,0.0000010843764,0.0002822671,0.0016048969,0.0000721063,0.0014311934,0.0009859463,0.005581222,0.067478105],"study_design_scores_gemma":[0.0002958599,0.00005912411,0.94792557,0.00013178129,0.0000037880848,0.00020791605,0.030778423,0.002555154,0.00005508447,0.003852367,0.0140921455,0.000042778876],"about_ca_topic_score_codex":0.00008801801,"about_ca_topic_score_gemma":0.0004784595,"teacher_disagreement_score":0.06743533,"about_ca_system_score_codex":0.000032785734,"about_ca_system_score_gemma":0.0002878439,"threshold_uncertainty_score":0.5730472},"labels":[],"label_agreement":null},{"id":"W3166656511","doi":"10.5430/jms.v12n1p36","title":"Study on Generation and Development of Social Prediction System","year":2021,"lang":"en","type":"article","venue":"Journal of Management and Strategy","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Social system; Political system; Politics; Soul; Relation (database); Predictive modelling; Computer science; Political science; Artificial intelligence; Law; Epistemology; Data mining; Machine learning","score_opus":0.32523890941703476,"score_gpt":0.3796087575758754,"score_spread":0.05436984815884066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3166656511","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":[0.9934888,0.00009993032,0.0043972973,0.00020596413,0.000061353865,0.00008527059,0.0000038441867,0.000004955956,0.0016526],"genre_scores_gemma":[0.99868625,0.000033134536,0.001092498,0.000006039469,0.000036834335,0.0000024871608,0.0000012698584,0.000001271845,0.00014021911],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99902517,0.000035118825,0.00041746142,0.00010337442,0.00037519285,0.00004370435],"domain_scores_gemma":[0.99951476,0.000022543467,0.00023560534,0.0000850935,0.00012525952,0.000016715607],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073446333,0.000040903546,0.000113730544,0.00010320963,0.00011811108,0.000094017065,0.00009839839,0.000023350796,0.000006432142],"category_scores_gemma":[0.000015450063,0.00002841547,0.000014190898,0.00014581686,0.00001730025,0.00009372234,0.00006474129,0.000048255846,0.000001231582],"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":[0.000039567265,0.0004547306,0.009576496,0.000040369694,0.00020847846,0.000055968387,0.0013956643,0.00008720443,0.0013226038,0.055894632,0.008279348,0.9226449],"study_design_scores_gemma":[0.001407462,0.000554574,0.8191908,0.00004416561,0.000082018174,0.000036477726,0.1574187,0.00053992105,0.0020542173,0.0015959273,0.016955888,0.00011986216],"about_ca_topic_score_codex":2.9866604e-7,"about_ca_topic_score_gemma":0.000005249308,"teacher_disagreement_score":0.92252505,"about_ca_system_score_codex":0.00001290306,"about_ca_system_score_gemma":0.000018264484,"threshold_uncertainty_score":0.115874924},"labels":[],"label_agreement":null},{"id":"W3186134273","doi":"","title":"A path to Big Data readiness","year":2021,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Environment and Climate Change Canada","funders":"","keywords":"Big data; Section (typography); Variety (cybernetics); Data science; Context (archaeology); Path (computing); Space (punctuation); Computer science; Checklist; Work (physics); Government (linguistics); Knowledge management; Engineering; Data mining; Psychology; Geography; Artificial intelligence","score_opus":0.28479799167223824,"score_gpt":0.39628025606606204,"score_spread":0.1114822643938238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186134273","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":[0.18500271,0.0060604746,0.70180696,0.100570686,0.0012079998,0.000284865,0.00038595565,0.00020336859,0.0044769878],"genre_scores_gemma":[0.98775655,0.002795976,0.0022169957,0.0007086654,0.0005103073,0.000008855907,0.00005224798,0.000015242228,0.0059351707],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99700415,0.00006622542,0.0003993708,0.0005180509,0.00069028616,0.0013219251],"domain_scores_gemma":[0.99715936,0.00018177762,0.00013659947,0.0021190476,0.00029585772,0.00010738381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038976918,0.00009967558,0.00017499161,0.00014159895,0.00027576642,0.00034873246,0.003116181,0.0000698842,0.00007476119],"category_scores_gemma":[0.0027986723,0.00007166976,0.00005078487,0.001482831,0.000038998103,0.0002616166,0.0010646727,0.0009952151,0.00053629495],"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":[0.000006400121,0.00004801388,0.0005313762,5.990858e-7,0.000023387542,0.00001069835,0.000019211779,0.000002990915,0.0009910188,0.16430432,0.032612123,0.80144984],"study_design_scores_gemma":[0.00013621911,0.0000455397,0.0005778683,0.0000071228014,0.000009321246,0.0005884972,0.002724681,0.00007768249,0.00023940435,0.5749719,0.42051128,0.000110507885],"about_ca_topic_score_codex":0.000028824852,"about_ca_topic_score_gemma":0.0016900472,"teacher_disagreement_score":0.8027538,"about_ca_system_score_codex":0.00017529665,"about_ca_system_score_gemma":0.0021496187,"threshold_uncertainty_score":0.6893165},"labels":[],"label_agreement":null},{"id":"W3199027794","doi":"","title":"The Study on Monitoring and Evaluation System of Teaching Quality of China Higher Education Institutions in the Era of Big Data","year":2016,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"China; Christian ministry; Construct (python library); Big data; Quality (philosophy); Monitoring and evaluation; Higher education; Data collection; Political science; Computer science; Business; Engineering management; Data science; Data mining; Engineering; Sociology; Social science","score_opus":0.5055560520441864,"score_gpt":0.5342532820220081,"score_spread":0.028697229977821648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199027794","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":[0.98823315,0.00012231193,0.00005151011,0.0036434708,0.0008800959,0.0005080472,0.000039419938,0.000007169036,0.0065148035],"genre_scores_gemma":[0.99957204,0.000010256595,0.00013387228,0.0000070702868,0.00010418154,0.000064444415,0.0000023989774,0.0000019178613,0.00010379489],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9970949,0.00037662513,0.00068834896,0.00031750335,0.0014165716,0.00010601494],"domain_scores_gemma":[0.99687517,0.0007366592,0.0007928456,0.0010736901,0.0005012802,0.00002034701],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010190934,0.00006694934,0.0001556539,0.00015144126,0.00048666238,0.00005120338,0.0018706593,0.000040948984,0.000006288306],"category_scores_gemma":[0.0011913924,0.00003339847,0.000022217771,0.0012703916,0.00096892676,0.0004006912,0.00023956403,0.00010634277,0.000001246557],"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":[0.000007800621,0.00062457996,0.045365155,0.00001029419,0.000003880276,3.3129255e-9,0.002080252,0.0000017844147,0.0073199826,0.7402737,0.00032735316,0.2039852],"study_design_scores_gemma":[0.00011196417,0.00003374078,0.9770725,0.000062518324,0.000010511479,9.993809e-8,0.014412527,0.000003403779,0.00055782415,0.0057796407,0.0019165017,0.000038774513],"about_ca_topic_score_codex":0.00073400955,"about_ca_topic_score_gemma":0.000014432733,"teacher_disagreement_score":0.9317073,"about_ca_system_score_codex":0.00009674411,"about_ca_system_score_gemma":0.00088878605,"threshold_uncertainty_score":0.37430626},"labels":[],"label_agreement":null},{"id":"W3210359963","doi":"10.1142/s2424922x21420043","title":"Research on Intelligent Management System of Meteorological Archives Based on Big Data Framework","year":2021,"lang":"en","type":"article","venue":"Advances in Data Science and Adaptive Analysis","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vanier College","funders":"","keywords":"Big data; Computer science; Geospatial analysis; Data management; Data science; Analytics; Visualization; Data analysis; Data processing; Data mining; Business intelligence; Data visualization; Database; Remote sensing","score_opus":0.5419266624503839,"score_gpt":0.5022757446171617,"score_spread":0.039650917833222166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210359963","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":[0.012411026,0.0026798204,0.9629402,0.0037419235,0.000201915,0.0004762494,0.0030680008,0.000054342243,0.014426517],"genre_scores_gemma":[0.95671624,0.002162469,0.040764287,0.00013000591,0.000019870371,0.000019314968,0.00015064508,0.000002850918,0.000034301844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99443424,0.00029832523,0.00054588146,0.0019401973,0.0024111914,0.00037015765],"domain_scores_gemma":[0.98870814,0.0040817424,0.00018650084,0.0066392925,0.00028895427,0.00009535183],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008175008,0.0001286718,0.00038896245,0.001722673,0.00034619882,0.00020436717,0.007487353,0.00005448854,0.000027899647],"category_scores_gemma":[0.004445101,0.00008512623,0.000042195265,0.01548912,0.0020028092,0.0008308454,0.0056770635,0.00034191823,0.000020220938],"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":[0.0000631635,0.00024410198,0.0020787404,0.000011047243,0.000055585602,0.00003336467,0.000026467096,0.0052202987,0.000066759654,0.22530395,0.00028313365,0.76661336],"study_design_scores_gemma":[0.00027236168,0.00037639856,0.01907811,0.00033997346,0.0002282688,0.0000021021492,0.041750867,0.76805615,0.0024532967,0.065719046,0.10131479,0.0004086426],"about_ca_topic_score_codex":0.000023671353,"about_ca_topic_score_gemma":0.00021932903,"teacher_disagreement_score":0.94430524,"about_ca_system_score_codex":0.00004151517,"about_ca_system_score_gemma":0.00011426753,"threshold_uncertainty_score":0.9978826},"labels":[],"label_agreement":null},{"id":"W4200197283","doi":"10.1038/s41561-021-00881-3","title":"Publisher Correction: Machine learning in Earth and environmental science requires education and research policy reforms","year":2021,"lang":"en","type":"article","venue":"Nature Geoscience","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Environment and Climate Change Canada; University of British Columbia","funders":"","keywords":"Earth system science; Earth (classical element); Political science; Computer science; Earth science; Engineering ethics; Geology; Engineering; Oceanography; Physics","score_opus":0.089396662525709,"score_gpt":0.4143253945636533,"score_spread":0.3249287320379443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200197283","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":[0.9745738,0.002535915,0.00010135035,0.01501795,0.0006897768,0.00015093063,0.000009709578,0.000043305943,0.0068772603],"genre_scores_gemma":[0.989021,0.00046922584,0.0014470735,0.00028460583,0.000047063626,0.000015810403,0.000008787757,0.0000032641028,0.008703184],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9971764,0.000079637306,0.00021819501,0.000822217,0.0013459781,0.0003575436],"domain_scores_gemma":[0.9987872,0.00029032855,0.00007099714,0.0005338186,0.00019792134,0.0001196873],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004033232,0.00008072753,0.00010258927,0.0007925213,0.0008653535,0.0009587757,0.00076938653,0.00014780738,0.00002781527],"category_scores_gemma":[0.011159427,0.000058400918,0.000012053501,0.0056149815,0.001713745,0.001481376,0.001050995,0.00097449264,0.000011344502],"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":[0.0000061930755,0.00013149744,0.11509701,0.0000030542271,7.2507123e-7,0.0000043730233,0.00046825927,0.000006958678,0.013581845,0.031726833,0.0044518844,0.83452135],"study_design_scores_gemma":[0.00016180487,0.00007149679,0.66503143,0.000028410717,0.0000011312304,0.0001856326,0.007946751,0.0033140746,0.0018024195,0.047735747,0.27353227,0.00018886405],"about_ca_topic_score_codex":0.000363568,"about_ca_topic_score_gemma":0.0004269591,"teacher_disagreement_score":0.8343325,"about_ca_system_score_codex":0.00010721445,"about_ca_system_score_gemma":0.00071471673,"threshold_uncertainty_score":0.99717},"labels":[],"label_agreement":null},{"id":"W4206331798","doi":"10.53106/256299802019120101002","title":"Big Data: Ideology vs. Enlightenment","year":2019,"lang":"en","type":"article","venue":"International Journal of Computer Auditing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Ideology; Big data; Politics; Epistemology; Philosophy; Political science; Computer science; Law","score_opus":0.24788207223685746,"score_gpt":0.3951213362030417,"score_spread":0.14723926396618423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206331798","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":[0.3774764,0.0001254811,0.5810943,0.031006178,0.007985234,0.00011021399,0.00010353913,0.00003849168,0.002060145],"genre_scores_gemma":[0.9678116,0.00003673555,0.029051844,0.0010865133,0.0018531996,7.757074e-7,0.000016452961,0.000005446704,0.00013742187],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751675,0.000048291746,0.00082788244,0.00026308815,0.0012093558,0.00013460495],"domain_scores_gemma":[0.99684215,0.0007483431,0.0009895517,0.00064530806,0.000726853,0.000047769452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015285038,0.00008369163,0.00021547811,0.00030645565,0.00004080203,0.0002480451,0.004450898,0.000052612453,0.00021369955],"category_scores_gemma":[0.00047437559,0.00005950107,0.000080411526,0.00018672021,0.00005326038,0.00049779605,0.0014700288,0.00022121008,0.00042079002],"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":[0.000020421317,0.000055989745,0.011561806,9.513026e-7,0.000090933994,0.00005251013,0.000043091124,0.00038185745,0.00047854954,0.007530312,0.07968594,0.90009767],"study_design_scores_gemma":[0.00069915724,0.00014112038,0.021471672,0.00006072137,0.000010865138,0.0007830483,0.00022280177,0.017966116,0.00074432895,0.028893992,0.92885476,0.0001514307],"about_ca_topic_score_codex":0.000005747948,"about_ca_topic_score_gemma":0.0000033876006,"teacher_disagreement_score":0.8999462,"about_ca_system_score_codex":0.00004617482,"about_ca_system_score_gemma":0.00006535059,"threshold_uncertainty_score":0.82709503},"labels":[],"label_agreement":null},{"id":"W4206677790","doi":"10.1007/978-3-030-79891-8","title":"Advances in Data Science","year":2021,"lang":"en","type":"book","venue":"Association for Women in Mathematics series","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science","score_opus":0.1797360089877833,"score_gpt":0.40390702686504715,"score_spread":0.22417101787726385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206677790","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00029429098,0.00096325355,0.00033074635,0.0028451006,0.00046883518,0.0011417017,0.0027274545,0.00011298335,0.9911156],"genre_scores_gemma":[0.0005690582,0.0016996361,0.005870183,0.000023168634,0.000057092493,0.00036650477,0.00041176338,0.000023739753,0.99097884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960771,0.00002725248,0.0010638298,0.00081857044,0.0014719884,0.00054121105],"domain_scores_gemma":[0.99420196,0.0021977685,0.0010966021,0.0019901707,0.000461485,0.00005200903],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009077201,0.00019559993,0.0006237873,0.0005870927,0.00017337225,0.00051433034,0.0034929013,0.000293508,0.00008525231],"category_scores_gemma":[0.020726288,0.0001744466,0.000046691566,0.0014515161,0.0002272502,0.0020340227,0.001276396,0.00028205995,0.0000717126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007825109,0.00020430436,0.00091875973,0.00021060421,0.000017853612,0.0000031123398,0.0025654617,0.00002947016,0.000032663414,0.92006105,0.06622767,0.009721201],"study_design_scores_gemma":[0.00008664438,0.000009429319,0.000047072223,0.000055198616,0.0000025466034,5.850155e-7,0.0025807964,0.0002009925,0.000014833836,0.5791589,0.41772795,0.000115073344],"about_ca_topic_score_codex":0.0000016150634,"about_ca_topic_score_gemma":0.000597625,"teacher_disagreement_score":0.35150027,"about_ca_system_score_codex":0.0017746491,"about_ca_system_score_gemma":0.0009563862,"threshold_uncertainty_score":0.98752254},"labels":[],"label_agreement":null},{"id":"W4211174732","doi":"10.1007/978-3-319-32010-6_505","title":"Big Data and Theory","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Memorial University of Newfoundland","funders":"","keywords":"Computer science; History","score_opus":0.5387377163173658,"score_gpt":0.39539874161286653,"score_spread":0.14333897470449924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211174732","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000030137198,0.0008936792,0.0037738697,0.0029222027,0.00016507124,0.00013221201,0.0025820793,0.00011653988,0.98941135],"genre_scores_gemma":[0.0005866764,0.0011683137,0.001027982,0.00047540202,0.000081501385,0.000009442833,0.0003839064,0.000014699049,0.99625206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826324,0.000012707896,0.00029181907,0.0007575119,0.0005800049,0.00009471906],"domain_scores_gemma":[0.995014,0.0007785241,0.00014726279,0.003987674,0.00003476715,0.00003774272],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001419623,0.0001237788,0.00019232008,0.0001616927,0.00018365371,0.00014668702,0.0034166402,0.00014046098,0.014653066],"category_scores_gemma":[0.00043650175,0.00008223687,0.000028289802,0.0000671799,0.00022679818,0.00010776114,0.0068851463,0.00028582397,0.00056563417],"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":[6.590993e-7,0.0000011968172,0.0000013052738,2.6598252e-7,0.0000035871844,8.5695456e-7,0.0000014722185,1.3425388e-8,6.137508e-7,0.49214283,0.13712375,0.37072346],"study_design_scores_gemma":[0.000015522231,0.0000053454105,0.0000051554744,0.0000010078141,0.000005623881,0.0000038705125,0.000055067103,0.000010572946,6.4362035e-7,0.46328998,0.53654695,0.00006028481],"about_ca_topic_score_codex":0.000008542946,"about_ca_topic_score_gemma":0.000037480862,"teacher_disagreement_score":0.39942318,"about_ca_system_score_codex":0.000008617951,"about_ca_system_score_gemma":0.000036851823,"threshold_uncertainty_score":0.98624766},"labels":[],"label_agreement":null},{"id":"W4226151601","doi":"10.1080/2325548x.2022.2036546","title":"Data Lives: How Data Are Made and Shape Our World","year":2022,"lang":"en","type":"article","venue":"The AAG Review of Books","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Internet privacy","score_opus":0.5255716264645494,"score_gpt":0.43481926929440246,"score_spread":0.0907523571701469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226151601","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004432257,0.60500515,0.0004328717,0.35992756,0.00021925448,0.0019047488,0.021447742,0.00017035112,0.0064600534],"genre_scores_gemma":[0.5062031,0.4173853,0.010246165,0.031152135,0.00034393277,0.00042654193,0.002654146,0.00007450222,0.031514175],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981973,0.00014821572,0.00036111762,0.00053055765,0.000629916,0.00013286165],"domain_scores_gemma":[0.9915564,0.0003525215,0.00044301443,0.00756795,0.00004663461,0.000033459022],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0035846839,0.000092550436,0.00030267736,0.000061235536,0.0002837468,0.00009108946,0.009246561,0.000012388246,0.0002308772],"category_scores_gemma":[0.0014066816,0.00005251806,0.00003053757,0.0005100808,0.0001234271,0.00023845497,0.013156171,0.00023222879,0.000039079394],"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":[0.0000014960929,0.000014602705,0.00019135598,0.00009780333,0.000009158074,0.0000012254367,0.00001007349,1.0185557e-7,0.00002826834,0.0021310926,0.7208172,0.2766976],"study_design_scores_gemma":[0.000042997104,0.0000116568535,0.0010082248,0.00031681138,0.000036041318,0.000013739447,0.0012669644,0.00047387983,0.000008489778,0.00342803,0.9933229,0.00007027798],"about_ca_topic_score_codex":0.000014318313,"about_ca_topic_score_gemma":0.000049977785,"teacher_disagreement_score":0.50177085,"about_ca_system_score_codex":0.0000068327977,"about_ca_system_score_gemma":0.00003490171,"threshold_uncertainty_score":0.9961139},"labels":[],"label_agreement":null},{"id":"W4234131857","doi":"10.1007/978-1-4939-7131-2_100062","title":"Big Data","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science","score_opus":0.7146096992358584,"score_gpt":0.4311886544452919,"score_spread":0.28342104479056646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234131857","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000016481816,0.00014174731,0.009763086,0.002743566,0.00036171018,0.00012526517,0.0016788737,0.00019025136,0.9849939],"genre_scores_gemma":[0.0001359984,0.00018286938,0.0036923732,0.00038828523,0.00049251725,0.000003180667,0.0004090026,0.000015953638,0.9946798],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772316,0.0000037345494,0.00043038983,0.0009279493,0.0007790202,0.0001357461],"domain_scores_gemma":[0.99132967,0.00028444367,0.0002189253,0.007940647,0.00017487876,0.00005145898],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00075662974,0.00015898328,0.00023630876,0.00018194373,0.000104235995,0.00022446977,0.006932908,0.00034845035,0.018168217],"category_scores_gemma":[0.0005524127,0.00009981154,0.00005075485,0.00008546567,0.00033618978,0.000121347824,0.004131954,0.0001979194,0.037079595],"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":[2.939832e-7,0.0000014253208,6.3125265e-7,2.028268e-7,0.0000035844891,4.897467e-7,7.833979e-7,3.2224265e-9,0.0000010231539,0.19933926,0.5398554,0.2607969],"study_design_scores_gemma":[0.000014853684,0.0000071506984,0.000003374588,0.0000038467006,0.0000052760383,0.0000020018497,0.000012264146,0.000019134452,0.0000058816777,0.3952972,0.6045448,0.00008421858],"about_ca_topic_score_codex":0.000011095998,"about_ca_topic_score_gemma":0.00018748175,"teacher_disagreement_score":0.26071268,"about_ca_system_score_codex":0.000010062407,"about_ca_system_score_gemma":0.0000575223,"threshold_uncertainty_score":0.9984401},"labels":[],"label_agreement":null},{"id":"W4235267710","doi":"10.17975/sfj-2019-001","title":"2019 National High School Big Data Challenge: Big Data de Terre","year":2019,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Political science; Computer science; Data mining","score_opus":0.5394255743286756,"score_gpt":0.4134806470450783,"score_spread":0.12594492728359724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235267710","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":[0.5441433,0.0141762905,0.09832662,0.21095929,0.027446257,0.0031000029,0.030863712,0.0011185023,0.06986601],"genre_scores_gemma":[0.98549134,0.00080111274,0.0033453477,0.00057671155,0.002394525,0.000007981056,0.00057565334,0.00003120149,0.006776144],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99517685,0.00019118573,0.0008867643,0.0010220839,0.0021885086,0.0005346324],"domain_scores_gemma":[0.99275297,0.00070164126,0.0005707771,0.005248374,0.0004177009,0.00030855957],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065617575,0.00022852192,0.00034299417,0.00040065832,0.00041111436,0.0010268934,0.012263595,0.00024280752,0.00078147545],"category_scores_gemma":[0.0016969419,0.0001663078,0.000073637246,0.00082503946,0.00013869618,0.0012949253,0.0038288948,0.0009668125,0.005081515],"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":[0.000020282201,0.000100451085,0.005174752,0.000005307425,0.000049215956,0.000017415066,0.0000316755,0.00002728397,0.00041708013,0.0029164215,0.6675399,0.32370022],"study_design_scores_gemma":[0.00076366065,0.00007469145,0.011454748,0.0000614194,0.000026302307,0.00031590377,0.0018187582,0.0024498727,0.00007830602,0.045462437,0.9371389,0.00035495646],"about_ca_topic_score_codex":0.00006184378,"about_ca_topic_score_gemma":0.0001401655,"teacher_disagreement_score":0.44134802,"about_ca_system_score_codex":0.00012484471,"about_ca_system_score_gemma":0.0008271021,"threshold_uncertainty_score":0.99569315},"labels":[],"label_agreement":null},{"id":"W4236178279","doi":"10.1007/978-3-030-36365-9","title":"Advances in Data Science, Cyber Security and IT Applications","year":2019,"lang":"en","type":"book","venue":"Communications in computer and information science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Network security; Computer security; Information security; Data science","score_opus":0.19542752318846085,"score_gpt":0.42541409552921283,"score_spread":0.22998657234075198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4236178279","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00032190248,0.0047807684,0.07316661,0.010419447,0.0003936331,0.0030604142,0.00101433,0.00016810531,0.9066748],"genre_scores_gemma":[0.41464573,0.27461183,0.2829666,0.009116889,0.00033695923,0.0016297991,0.0038597486,0.00007948075,0.012752926],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962732,0.000046339308,0.0012144392,0.0008489949,0.0012620329,0.00035500136],"domain_scores_gemma":[0.989792,0.0009877029,0.0005624833,0.007908114,0.00063165784,0.00011806276],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.006600542,0.00022094123,0.00036263457,0.0025646025,0.00078495307,0.001429977,0.013407706,0.0001678309,0.00001295609],"category_scores_gemma":[0.0006671801,0.00019201945,0.000021112777,0.004344832,0.0054597375,0.021801531,0.013517541,0.00065175287,0.00016697338],"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":[0.0000018119407,0.000038686365,0.0006269292,0.000022766106,0.0000010704127,7.98532e-8,0.0007697287,0.000056843488,0.0000019001536,0.3232496,0.00581613,0.66941446],"study_design_scores_gemma":[0.00016481332,0.000011378012,0.0015220405,0.00007256742,0.0000028271497,0.000008542197,0.00032649736,0.08967214,0.00000160076,0.044825483,0.86317825,0.00021385218],"about_ca_topic_score_codex":0.00001657294,"about_ca_topic_score_gemma":0.00018897478,"teacher_disagreement_score":0.89392185,"about_ca_system_score_codex":0.00019676719,"about_ca_system_score_gemma":0.0011985797,"threshold_uncertainty_score":0.9996066},"labels":[],"label_agreement":null},{"id":"W4238254745","doi":"10.1007/978-3-319-95810-1","title":"Applications of Data Management and Analysis","year":2018,"lang":"en","type":"book","venue":"Lecture notes in social networks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Social network analysis; Computer science; Data science; Segmentation; Network analysis; Data mining; Operations research; Artificial intelligence; World Wide Web; Engineering; Social media","score_opus":0.13290521553753176,"score_gpt":0.38706398945844395,"score_spread":0.2541587739209122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238254745","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":[0.0000050977155,0.0017396499,0.96479166,0.0006002409,0.000044179844,0.0004963722,0.00073685934,0.000043982727,0.031541985],"genre_scores_gemma":[0.3891789,0.015638381,0.32941067,0.0038485287,0.012987127,0.00171462,0.038381387,0.00039687305,0.20844351],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99762833,0.00005148166,0.00064562744,0.00090307713,0.0005543357,0.00021713805],"domain_scores_gemma":[0.9962455,0.00095566106,0.00050772756,0.0021337084,0.00012492081,0.00003247117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009931155,0.00020206653,0.000596697,0.0005125502,0.00019813735,0.00010210824,0.0026884524,0.00066581956,0.00013735337],"category_scores_gemma":[0.00013781028,0.00016738992,0.00011119369,0.0024622686,0.0005679411,0.00008343488,0.0019091602,0.00042319347,0.000014535659],"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":[0.000004963373,0.000023825522,0.00047093414,0.0000108144095,0.0002865479,8.8849987e-7,0.00004480782,0.0002293885,1.287766e-7,0.014667164,0.095466025,0.8887945],"study_design_scores_gemma":[0.000075332646,0.000007961263,0.0008224304,0.000012765591,0.0004133945,2.874942e-7,0.00001578354,0.005486814,5.606091e-7,0.37553376,0.61746126,0.00016967417],"about_ca_topic_score_codex":0.000014020868,"about_ca_topic_score_gemma":0.00053950906,"teacher_disagreement_score":0.88862485,"about_ca_system_score_codex":0.000045915254,"about_ca_system_score_gemma":0.000038256894,"threshold_uncertainty_score":0.6825963},"labels":[],"label_agreement":null},{"id":"W4238755784","doi":"10.3138/jsp.38.4.183","title":"The Post-petroleum Future of Academic Libraries","year":2007,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vision; Abandonment (legal); Petroleum; Economics; Industrial organization; Business; Political science; Natural resource economics; Sociology; Biology","score_opus":0.11420193585016919,"score_gpt":0.34909092409906506,"score_spread":0.23488898824889587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238755784","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":[0.69329774,0.014477602,0.009073776,0.27585432,0.0016205686,0.000108668595,0.000047859136,0.000048341015,0.0054711383],"genre_scores_gemma":[0.9904116,0.00053604983,0.0066539044,0.0010381563,0.00096953486,8.87124e-7,0.000001949686,0.000010028043,0.00037793754],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99574536,0.00008327365,0.0014547644,0.00017346333,0.0022523014,0.0002908209],"domain_scores_gemma":[0.99232066,0.0022993423,0.001845723,0.0006773789,0.0027042762,0.00015264358],"candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01967688,0.000099196586,0.0002405839,0.0005139983,0.00044584117,0.01860869,0.0055039166,0.0003425611,0.000029434252],"category_scores_gemma":[0.028870067,0.000051633207,0.00016492553,0.0013977381,0.00021731044,0.0637701,0.0005706597,0.0029382634,0.000010115045],"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":[0.00008384001,0.000029187779,0.028108431,0.0000022810898,0.000034039916,0.000008240457,0.00030336968,0.000007403859,0.0051358817,0.20342514,0.1798312,0.583031],"study_design_scores_gemma":[0.00020667718,0.000079231475,0.08139428,0.000022299302,0.00001043989,0.00007270518,0.013143299,0.000009555233,0.0016849246,0.10123516,0.80207163,0.00006982591],"about_ca_topic_score_codex":0.000009174726,"about_ca_topic_score_gemma":0.000014650353,"teacher_disagreement_score":0.62224036,"about_ca_system_score_codex":0.000036765818,"about_ca_system_score_gemma":0.00022009085,"threshold_uncertainty_score":0.9998768},"labels":[],"label_agreement":null},{"id":"W4241866799","doi":"10.1007/978-3-030-24367-8_2","title":"Big Data","year":2019,"lang":"en","type":"book-chapter","venue":"Advanced information and knowledge processing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Big data; Data science; Business intelligence; Computer science; Analytics; Business analytics; Data analysis; Variety (cybernetics); Cultural analytics; Unstructured data; Software analytics; Predictive analytics; Cloud computing; Data visualization; Visualization; Knowledge management; Data mining; World Wide Web; Semantic analytics; Artificial intelligence; Business analysis; The Internet; Business model; Management","score_opus":0.2807200847194476,"score_gpt":0.38604348324466553,"score_spread":0.10532339852521794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241866799","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001094935,0.004760286,0.034675594,0.0005129112,0.00040066903,0.00032363686,0.00041141815,0.00018501566,0.9587195],"genre_scores_gemma":[0.022815516,0.0050261016,0.016576154,0.001173257,0.0004755085,0.000039237497,0.0035636132,0.00007330837,0.9502573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981451,0.0000056782224,0.0008133802,0.00043108064,0.00042859677,0.00017615494],"domain_scores_gemma":[0.9970234,0.00017039946,0.0007083041,0.0015509161,0.00047930315,0.00006765122],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00062963966,0.00023525133,0.00032305493,0.00037687938,0.0002645159,0.00056990737,0.0015027921,0.0002800131,0.00008611267],"category_scores_gemma":[0.00053924095,0.00018106462,0.00003467571,0.00018368944,0.00015839483,0.0031204347,0.001360939,0.00033283074,0.002546769],"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":[0.0000037339767,0.0000031253728,0.000003276244,0.000047657995,0.0000035389994,7.718121e-8,0.00010036325,0.0000018035932,0.0000031599272,0.045162544,0.00957251,0.9450982],"study_design_scores_gemma":[0.0001772669,0.000013132446,0.000014817127,0.00013151852,0.0000115563635,0.0000060669045,0.00024459977,0.0031731538,0.000012628022,0.045644097,0.9503415,0.00022964746],"about_ca_topic_score_codex":7.075775e-7,"about_ca_topic_score_gemma":0.000014678487,"teacher_disagreement_score":0.94486856,"about_ca_system_score_codex":0.000028306953,"about_ca_system_score_gemma":0.00029867276,"threshold_uncertainty_score":0.99822986},"labels":[],"label_agreement":null},{"id":"W4242595350","doi":"10.4095/223363","title":"Radiometric data","year":2007,"lang":"en","type":"report","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Radiometric dating; Computer science; Remote sensing; Environmental science; Geology","score_opus":0.8588006933303317,"score_gpt":0.5665591600270822,"score_spread":0.29224153330324953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242595350","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000039524595,0.0030018045,0.0778396,0.0015658787,0.0011106404,0.00027027223,0.0018973638,0.00036592444,0.913909],"genre_scores_gemma":[0.025840567,0.026335156,0.086546525,0.0010090802,0.0030275658,0.00006769723,0.011156376,0.00013567813,0.84588134],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930478,0.000018136909,0.0009600119,0.001274137,0.0043951855,0.00030474662],"domain_scores_gemma":[0.9865213,0.0014476484,0.00051761564,0.010623269,0.0007946921,0.000095443604],"candidate_categories":["metaresearch","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.010925731,0.00018788081,0.00044385446,0.0022740536,0.00011762565,0.00035667664,0.010835744,0.0005674434,0.0027915991],"category_scores_gemma":[0.02282454,0.00011731686,0.00008426527,0.0073222173,0.00014878664,0.0002409724,0.004114289,0.00046199287,0.0034687235],"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":[1.970944e-7,0.000010215901,0.00018635394,0.0000011527399,0.0000058729584,0.00000293323,2.5664673e-7,4.281471e-8,7.0906464e-7,0.0005736245,0.5643289,0.43488976],"study_design_scores_gemma":[0.000029150942,0.0000071070453,0.0013891883,0.0000045778556,0.000014550767,0.000041572937,0.00005414818,0.000054748256,0.000017976292,0.004416999,0.9938115,0.00015851198],"about_ca_topic_score_codex":0.00046566103,"about_ca_topic_score_gemma":0.0001588794,"teacher_disagreement_score":0.43473125,"about_ca_system_score_codex":0.00009931108,"about_ca_system_score_gemma":0.0006727615,"threshold_uncertainty_score":0.99812},"labels":[],"label_agreement":null},{"id":"W4245289973","doi":"10.3138/jsp.41.1.92","title":"The Current Status of the Publishing Industry in China","year":2009,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Publishing; Prosperity; China; Dominance (genetics); Information industry; Business; Economics; Economic geography; Economy; Economic growth; Political science; Law","score_opus":0.1730678444820716,"score_gpt":0.3784927582432827,"score_spread":0.2054249137612111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245289973","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":[0.7736214,0.004556739,0.00045297394,0.21579233,0.0009830003,0.00016115603,0.000032895627,0.000017075296,0.004382452],"genre_scores_gemma":[0.9983143,0.00037912358,0.00060351554,0.0004397126,0.00018782481,0.0000016458782,8.5501415e-7,0.000005083106,0.00006789219],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9947799,0.0002669345,0.0015296476,0.00022652434,0.0027455173,0.00045148798],"domain_scores_gemma":[0.99431676,0.00093718193,0.0019914128,0.0010386886,0.0015498742,0.00016608044],"candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.015026483,0.00011853454,0.0002621411,0.0004861769,0.0004363192,0.055206638,0.0068664653,0.00040647632,0.000015432533],"category_scores_gemma":[0.09351587,0.000055379594,0.00017270351,0.0032860537,0.00014596623,0.07615182,0.00066619494,0.009738802,0.0000020074242],"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":[0.000010688844,0.00006737413,0.06228465,9.474006e-7,0.00000578681,0.0000014752956,0.00021855763,0.000057671463,0.00019638844,0.017909372,0.074008696,0.8452384],"study_design_scores_gemma":[0.0002519689,0.00003244581,0.57042813,0.0000758657,0.000005213279,0.000014098981,0.0013953698,0.000050858896,0.000113867456,0.12081666,0.30675778,0.000057736266],"about_ca_topic_score_codex":0.00007379554,"about_ca_topic_score_gemma":0.00006916944,"teacher_disagreement_score":0.84518063,"about_ca_system_score_codex":0.00015881468,"about_ca_system_score_gemma":0.00050125184,"threshold_uncertainty_score":0.99850684},"labels":[],"label_agreement":null},{"id":"W4246210298","doi":"10.36227/techrxiv.12094137.v1","title":"Search Is Not Yet a Solved Problem","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Reading (process); Perspective (graphical); Quality (philosophy); Index (typography); Transformation (genetics); Computer science; Mathematics education; World Wide Web; Psychology; Artificial intelligence; Linguistics; Epistemology; Philosophy","score_opus":0.5724159156680648,"score_gpt":0.45599132128277525,"score_spread":0.11642459438528957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246210298","genre_codex":"commentary","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":[0.020774337,0.00015920373,0.18745957,0.66579753,0.0004872489,0.0026086483,0.0031798868,0.0019025116,0.11763104],"genre_scores_gemma":[0.8346108,0.00022659765,0.14436494,0.006772914,0.00014210732,0.00040072232,0.00017016906,0.00003586255,0.013275862],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99637926,0.000044838154,0.000630368,0.0012845873,0.0013647918,0.00029616375],"domain_scores_gemma":[0.9965204,0.000399713,0.00018147296,0.0024780068,0.0002910063,0.00012942596],"candidate_categories":["open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009938488,0.00021018634,0.00038801087,0.0001771125,0.00013749272,0.0007052323,0.004180628,0.000419654,0.0024746524],"category_scores_gemma":[0.0006417352,0.00014332333,0.00018015224,0.0007357979,0.00016707239,0.000083419654,0.008088924,0.00091718516,0.0053595854],"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":[0.000006837985,0.00003807727,0.0002465131,0.00001574357,0.000021081698,0.000002795916,0.00018724758,0.000019806357,0.00072130054,0.041716028,0.83572906,0.121295534],"study_design_scores_gemma":[0.00011295504,0.000027333286,0.000699245,0.000020239995,0.000010741611,0.0000017375977,0.0007134914,0.005485935,0.009310045,0.43547484,0.5478437,0.00029976052],"about_ca_topic_score_codex":0.00023097976,"about_ca_topic_score_gemma":0.00003763516,"teacher_disagreement_score":0.8138365,"about_ca_system_score_codex":0.000030319296,"about_ca_system_score_gemma":0.0002212974,"threshold_uncertainty_score":0.9999335},"labels":[],"label_agreement":null},{"id":"W4250020071","doi":"10.1108/9781787432956","title":"Becoming Digital","year":2017,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":168,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","score_opus":0.41728069732990664,"score_gpt":0.42157374350514704,"score_spread":0.0042930461752404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250020071","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00000605629,0.00006625806,0.0028461502,0.0019853876,0.00013771298,0.00010656959,0.00039711292,0.00015050136,0.99430424],"genre_scores_gemma":[0.0008517279,0.000022242424,0.0006541184,0.000089458365,0.00011496287,0.000009107831,0.000086781874,0.000010683717,0.9981609],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99843264,0.0000023955056,0.00032917733,0.00048070407,0.00061208574,0.0001430271],"domain_scores_gemma":[0.9963705,0.0003866661,0.00034513805,0.002746426,0.00010475328,0.00004651153],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00031261932,0.00013479724,0.00024949524,0.00013466329,0.00025883364,0.0017290718,0.0035611747,0.00029623602,0.0011019696],"category_scores_gemma":[0.001369312,0.000087547305,0.00012252812,0.000040598294,0.00021300392,0.0003443881,0.0010761229,0.00023230287,0.009716382],"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":[1.7324136e-7,0.0000024268525,0.000008409418,3.2325542e-7,0.0000025917384,0.0000010485684,0.0000014596144,2.7763205e-8,2.5923953e-7,0.06586767,0.63102955,0.30308607],"study_design_scores_gemma":[0.000019056697,0.000003663268,0.000020165597,0.000005564879,0.000002039806,0.00000205025,0.000017872946,0.000008761147,0.0000030966312,0.3663118,0.6335288,0.00007712334],"about_ca_topic_score_codex":0.0000032180342,"about_ca_topic_score_gemma":0.000018252857,"teacher_disagreement_score":0.30300894,"about_ca_system_score_codex":0.00003212266,"about_ca_system_score_gemma":0.0001405781,"threshold_uncertainty_score":0.9998112},"labels":[],"label_agreement":null},{"id":"W4253593273","doi":"10.17975/sfj-2018-006","title":"Abstracts from the High School Big Data Challenge 2017-2018: Think Global, Act Local with Big Data","year":2018,"lang":"en","type":"article","venue":"STEM Fellowship Journal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Data mining","score_opus":0.5067818066705747,"score_gpt":0.3921677662893942,"score_spread":0.1146140403811805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253593273","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":[0.47044477,0.011938046,0.23484719,0.19332798,0.015446662,0.0022003457,0.043068603,0.00095423,0.027772177],"genre_scores_gemma":[0.990823,0.00075163937,0.0027502512,0.00074935745,0.0042646835,0.0000051874586,0.00030264162,0.000025039673,0.000328257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9946333,0.00023721857,0.0010208818,0.0012943064,0.002152663,0.000661638],"domain_scores_gemma":[0.98680586,0.0009927358,0.00091839494,0.010453126,0.00041506859,0.00041483738],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004765468,0.0003499122,0.000424144,0.000102811406,0.001277676,0.0018634156,0.018517144,0.00028639004,0.00033713307],"category_scores_gemma":[0.0011947629,0.00017720555,0.00006718993,0.00097608264,0.0010989988,0.0014406254,0.004305548,0.0011093381,0.0029794034],"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":[0.0000756481,0.0000976184,0.0020214894,0.0000014601108,0.00009891358,0.000044932567,0.000072504175,0.000006512674,0.000026544472,0.00046704756,0.548086,0.44900134],"study_design_scores_gemma":[0.00091613334,0.00027316203,0.043013733,0.0001325149,0.00011494626,0.00035896388,0.0067419545,0.0006866157,0.00009442777,0.033761147,0.9134427,0.00046375708],"about_ca_topic_score_codex":0.0006594356,"about_ca_topic_score_gemma":0.0073511037,"teacher_disagreement_score":0.5203782,"about_ca_system_score_codex":0.0001022656,"about_ca_system_score_gemma":0.0006251694,"threshold_uncertainty_score":0.99917275},"labels":[],"label_agreement":null},{"id":"W4288696362","doi":"10.1145/3552490.3552499","title":"Reminiscences on Influential Papers","year":2022,"lang":"en","type":"article","venue":"ACM SIGMOD Record","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Column (typography); Computer science; Value (mathematics); Citation; Key (lock); Reading (process); Library science; World Wide Web; Operations research; History; Telecommunications; Law; Computer security; Political science; Mathematics","score_opus":0.22026839757357825,"score_gpt":0.3827781944790289,"score_spread":0.16250979690545064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288696362","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":[0.93411416,0.00006708889,0.0001836838,0.021537522,0.0012334053,0.0003321043,0.00017886402,0.0003241413,0.042029005],"genre_scores_gemma":[0.99430376,0.000026733993,0.0017140809,0.0010570543,0.00006572925,0.00013623937,0.000012899053,0.000007853504,0.002675664],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979301,0.00007752057,0.00034074622,0.000518248,0.00091741205,0.00021593609],"domain_scores_gemma":[0.9971546,0.0008424714,0.00016659834,0.0017461838,0.000039192477,0.00005096927],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00080584746,0.00009833144,0.00014673338,0.00016152946,0.0005940971,0.00010990865,0.0030362746,0.000048641443,0.0035551793],"category_scores_gemma":[0.0021846136,0.00007420227,0.00008354829,0.0008881112,0.00010461822,0.00009871886,0.0014343912,0.000284494,0.00043932415],"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":[0.00002489847,0.000058705155,0.003114775,3.8697618e-7,0.000005856742,0.0000038777384,0.00005621438,0.000044796157,0.0011059722,0.008006719,0.13876474,0.84881306],"study_design_scores_gemma":[0.00011696088,0.00018170718,0.0030383682,0.0000015366029,0.0000035699322,0.0000043979744,0.0013495557,0.00007547249,0.00047510254,0.045237415,0.9493995,0.00011646649],"about_ca_topic_score_codex":0.00004856706,"about_ca_topic_score_gemma":0.000028472874,"teacher_disagreement_score":0.8486966,"about_ca_system_score_codex":0.000032451884,"about_ca_system_score_gemma":0.000039305585,"threshold_uncertainty_score":0.9973557},"labels":[],"label_agreement":null},{"id":"W4293070708","doi":"10.5121/ijaia.2022.13305","title":"Data Standardization using Deep Learning for Healthcare Insurance Claims","year":2022,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence & Applications","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Standardization; Computer science; Metadata; Receipt; Deep learning; Task (project management); Data mining; Artificial intelligence; Data science; Machine learning; Information retrieval; World Wide Web; Engineering","score_opus":0.4530248982000601,"score_gpt":0.49727896117340903,"score_spread":0.04425406297334894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293070708","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":[0.007179593,0.0003193905,0.9832578,0.0065868082,0.000571328,0.00053388835,0.0014725646,0.000036084108,0.00004254953],"genre_scores_gemma":[0.9614671,0.00013282085,0.03721066,0.00021562132,0.00045442535,0.0002239497,0.0002464233,0.000017010554,0.000032012616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99618345,0.000120355166,0.0014420138,0.00044078098,0.0016105222,0.00020288289],"domain_scores_gemma":[0.9948333,0.0007378826,0.0013305087,0.0007901334,0.0022231021,0.000085095424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027646748,0.00012178483,0.00023137516,0.00046656834,0.0008377697,0.00031531972,0.0045462945,0.000057347865,0.00021138162],"category_scores_gemma":[0.0011962897,0.00011449471,0.00012573933,0.0010165886,0.00013802478,0.00058406376,0.0008372273,0.0004472707,0.000019967345],"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":[0.00009654676,0.00016521913,0.00082636724,0.000002259433,0.000044459823,0.0000017365783,0.00015793313,0.09308926,0.0018822799,0.10027859,0.0007266341,0.8027287],"study_design_scores_gemma":[0.00006890553,0.0001237726,0.00018813791,0.000009327702,0.000019679217,0.00008848519,0.005292367,0.11770597,0.0012821794,0.30478987,0.5702663,0.00016500175],"about_ca_topic_score_codex":0.000027034152,"about_ca_topic_score_gemma":0.00006288179,"teacher_disagreement_score":0.95428747,"about_ca_system_score_codex":0.00024374273,"about_ca_system_score_gemma":0.00024957678,"threshold_uncertainty_score":0.84482217},"labels":[],"label_agreement":null},{"id":"W4293791092","doi":"10.3390/app12168248","title":"Big Data Analysis and Visualization: Challenges and Solutions","year":2022,"lang":"en","type":"article","venue":"Applied Sciences","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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":"University of Manitoba","keywords":"Big data; Computer science; Visualization; Data science; Core (optical fiber); Data mining; Telecommunications","score_opus":0.6092219036420985,"score_gpt":0.42565579693940025,"score_spread":0.18356610670269824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293791092","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":[0.31622007,0.09438035,0.2875185,0.2174772,0.0010738311,0.0022615548,0.0031690258,0.0013474331,0.07655205],"genre_scores_gemma":[0.9954421,0.0022471885,0.0019742853,0.00014726033,0.00002531994,0.00005972054,0.000027630245,0.0000023486841,0.00007418242],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99787694,0.000049161386,0.0002398879,0.0008546884,0.0007856081,0.00019371539],"domain_scores_gemma":[0.99834436,0.0004717351,0.00012360363,0.0009801276,0.000026600133,0.000053567655],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0030430711,0.00007669809,0.00016121533,0.00046187654,0.001798238,0.00024408383,0.0017891803,0.000026558106,0.00008614869],"category_scores_gemma":[0.000196326,0.000058273552,0.000016471638,0.0034198866,0.0007646058,0.00019796798,0.003541066,0.00008097163,0.000009324652],"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":[0.0000011491913,0.000025992444,0.00059542595,9.2353963e-7,0.000019735748,2.612732e-7,0.00027354324,0.00005289173,0.0001661815,0.48309764,0.002575342,0.5131909],"study_design_scores_gemma":[0.00020068232,0.00008269944,0.027796188,0.0000015138812,0.00015454437,0.000014786849,0.040794943,0.024864174,0.00008580273,0.3798711,0.52577966,0.00035388395],"about_ca_topic_score_codex":0.000022064318,"about_ca_topic_score_gemma":0.00023026793,"teacher_disagreement_score":0.679222,"about_ca_system_score_codex":0.00000738773,"about_ca_system_score_gemma":0.000039033774,"threshold_uncertainty_score":0.9995013},"labels":[],"label_agreement":null},{"id":"W4294760824","doi":"10.4095/330541","title":"Open disaster risk reduction data platform","year":2022,"lang":"en","type":"report","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Natural Resources Canada","funders":"","keywords":"Reduction (mathematics); Disaster risk reduction; Computer science; Geography; Environmental planning; Mathematics","score_opus":0.7792185618769631,"score_gpt":0.5264706855282165,"score_spread":0.2527478763487466,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294760824","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000628089,0.00045306285,0.0044919355,0.0035344143,0.002876915,0.0014843246,0.02144573,0.0003356536,0.9647499],"genre_scores_gemma":[0.016926493,0.0150952125,0.025833808,0.00024286454,0.0014111791,0.0010123029,0.03330846,0.00013209168,0.90603757],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942191,0.00005059117,0.0009657031,0.0016943093,0.0028161292,0.00025411698],"domain_scores_gemma":[0.98793674,0.00034182984,0.0010282219,0.010339837,0.00028263315,0.00007076961],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0074535706,0.00021929084,0.00046345728,0.00026598558,0.00059875374,0.001392348,0.020413673,0.00028696947,0.024767367],"category_scores_gemma":[0.0043115043,0.00014488756,0.00008169397,0.0010822157,0.00014057691,0.0012602815,0.035992596,0.0008330619,0.0010211729],"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":[0.000002527437,0.000024368339,0.00006728634,0.0000011639793,0.000014657042,9.2580234e-7,0.000008374643,0.0000015474543,0.0000010438027,0.00076621736,0.6575178,0.34159407],"study_design_scores_gemma":[0.00006572566,0.000021783859,0.0002767376,0.000005079542,0.000037606023,0.00006598118,0.002413389,0.00011123412,0.0000064255573,0.026383448,0.9704062,0.00020641783],"about_ca_topic_score_codex":0.004203831,"about_ca_topic_score_gemma":0.00079322176,"teacher_disagreement_score":0.34138766,"about_ca_system_score_codex":0.00017768226,"about_ca_system_score_gemma":0.00075976696,"threshold_uncertainty_score":0.99975663},"labels":[],"label_agreement":null},{"id":"W4300669487","doi":"10.17615/5mx2-pb29","title":"Mapping Health Data: Improved Privacy Protection With Donut Method Geomasking","year":2020,"lang":"en","type":"article","venue":"UNC Libraries","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; School of Medicine, University of North Carolina at Chapel Hill; National Institutes of Health; University of Toronto","keywords":"Privacy protection; Internet privacy; Computer science; Data Protection Act 1998; Computer security; Business","score_opus":0.46158372907178014,"score_gpt":0.3930748585083757,"score_spread":0.06850887056340443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300669487","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":[0.0013787269,0.00021730151,0.89300764,0.103811584,0.000052122152,0.00058089243,0.00013280522,0.000505541,0.00031340477],"genre_scores_gemma":[0.07631715,0.00001127806,0.91972834,0.003289344,0.00020690319,0.000090717935,0.00013520934,0.000023235098,0.00019781165],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978808,0.0000977563,0.0004597093,0.0008069838,0.00047493711,0.00027978347],"domain_scores_gemma":[0.9976078,0.00029318308,0.00035042866,0.001561557,0.00006498932,0.00012201924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008773475,0.00014567724,0.00027537026,0.000115866496,0.00044939978,0.0008491962,0.0020769876,0.000077911514,0.000059892565],"category_scores_gemma":[0.001549586,0.000095344796,0.000028513594,0.0015845858,0.00013619782,0.0020299032,0.001530405,0.0002691615,0.00005620981],"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":[0.00009193086,0.000048463386,0.0007880387,0.000050622806,0.000043051128,0.0000031967845,0.0025467337,0.000038129183,0.0023257798,0.17045473,0.05413411,0.7694752],"study_design_scores_gemma":[0.00033848692,0.0001847358,0.0011968997,0.000026730206,0.0000052441983,0.000009566607,0.00444295,0.023349041,0.0029526579,0.12386121,0.8433939,0.00023853987],"about_ca_topic_score_codex":0.00012268932,"about_ca_topic_score_gemma":0.000020667636,"teacher_disagreement_score":0.78925985,"about_ca_system_score_codex":0.00001553671,"about_ca_system_score_gemma":0.0002363173,"threshold_uncertainty_score":0.81888187},"labels":[],"label_agreement":null},{"id":"W4309978161","doi":"10.18438/b85g85","title":"Call for Proposals – 3rd Qualitative and Quantitative Methods in Libraries International Conference","year":2010,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Library science; World Wide Web; Data science","score_opus":0.28576652700539773,"score_gpt":0.51212428366607,"score_spread":0.22635775666067226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309978161","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":[0.011673564,0.00031534035,0.5606243,0.41958433,0.0003357893,0.0010762019,0.00031766723,0.0001574422,0.005915357],"genre_scores_gemma":[0.07948457,0.00049953937,0.90945697,0.010089989,0.000021776314,0.00020468823,0.00007022833,0.000005249179,0.0001669975],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983321,0.00034454107,0.0006324524,0.00025156117,0.0003069259,0.00013244558],"domain_scores_gemma":[0.98065364,0.018235339,0.0004937952,0.0003147157,0.00023158386,0.00007094638],"candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0034037745,0.00011253935,0.00016456239,0.00032461286,0.00015663187,0.0013175168,0.0005423696,0.00011548866,0.00017750161],"category_scores_gemma":[0.03297051,0.00008588069,0.000024002937,0.0005304412,0.00031776296,0.16213964,0.00025259913,0.00029670735,0.000018930055],"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":[0.00018757711,0.000019203586,0.000204406,0.000012757669,0.000005130981,2.4110966e-7,0.0014545037,0.0000031964978,0.0005222309,0.92284644,0.0026024964,0.07214181],"study_design_scores_gemma":[0.00042469212,0.0001679821,0.0027236927,0.00007035733,0.000009939042,0.000008733889,0.028389625,0.03284585,0.0049636997,0.11849691,0.81169385,0.00020467212],"about_ca_topic_score_codex":0.000009389469,"about_ca_topic_score_gemma":9.885232e-7,"teacher_disagreement_score":0.8090913,"about_ca_system_score_codex":0.000003374926,"about_ca_system_score_gemma":0.00019018819,"threshold_uncertainty_score":0.9997192},"labels":[],"label_agreement":null},{"id":"W4312442817","doi":"10.1007/978-3-031-06947-5","title":"30th Biennial Symposium on Communications 2021","year":2022,"lang":"en","type":"book","venue":"Signals and communication technology","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan; University of Manitoba; Université du Québec à Montréal","funders":"","keywords":"Political science; History","score_opus":0.1491956718034218,"score_gpt":0.3650486482847204,"score_spread":0.2158529764812986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312442817","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00026826453,0.01830457,0.00072165905,0.18212624,0.00020923169,0.0014913086,0.0014629056,0.000908831,0.79450697],"genre_scores_gemma":[0.074509054,0.08886499,0.009300767,0.002729962,0.00015017751,0.0029441803,0.0029442974,0.00020066324,0.8183559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963279,0.00032154386,0.00113643,0.0009761995,0.0008684084,0.000369515],"domain_scores_gemma":[0.9835974,0.0019459486,0.001031052,0.012972181,0.00036368752,0.00008976288],"candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.0017110661,0.00041094187,0.00071710127,0.001503093,0.0016205723,0.00026785154,0.011172876,0.0009327786,0.0023928646],"category_scores_gemma":[0.0006253364,0.0003704076,0.00016673142,0.0014055026,0.001842027,0.00014496496,0.008592007,0.0021832422,0.0006536445],"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":[0.00000884402,0.00011657259,0.00002119701,0.000003662892,0.000038771846,0.0000011723805,0.00004996795,0.000005737497,0.00017374913,0.63317245,0.21442875,0.15197913],"study_design_scores_gemma":[0.00013330096,0.00012759976,0.0000096572985,0.000030150059,0.000025444877,0.000011735327,0.00040448736,0.000112568516,0.00006967256,0.3643778,0.63446045,0.00023712372],"about_ca_topic_score_codex":0.000020728441,"about_ca_topic_score_gemma":0.00006757847,"teacher_disagreement_score":0.42003173,"about_ca_system_score_codex":0.00019454358,"about_ca_system_score_gemma":0.00029635456,"threshold_uncertainty_score":0.9998748},"labels":[],"label_agreement":null},{"id":"W4319165547","doi":"10.48550/arxiv.2302.00695","title":"Versatile Energy-Based Probabilistic Models for High Energy Physics","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institut de Valorisation des Données","keywords":"Computer science; Spurious relationship; Probabilistic logic; Generative model; Event (particle physics); Particle physics; Artificial intelligence; Generative grammar; Physics; Machine learning","score_opus":0.42430525959342325,"score_gpt":0.26969133847192295,"score_spread":0.1546139211215003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319165547","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":[0.0051606866,0.0000157855,0.99110264,0.00052480504,0.0003633811,0.0003085155,0.0014734581,0.000526058,0.0005246816],"genre_scores_gemma":[0.9930457,0.000064053034,0.0023216857,0.00012939567,0.00009784175,0.000038600454,0.00048478757,0.000037997397,0.003779926],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9972724,0.00006943611,0.00037361393,0.0016248222,0.00026752581,0.00039222214],"domain_scores_gemma":[0.9953275,0.0011515921,0.0004424258,0.0024934832,0.0004660076,0.000119034106],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040037074,0.00032562314,0.00045340162,0.00029804843,0.0002749985,0.0001793797,0.0028068337,0.00045325782,0.000038002665],"category_scores_gemma":[0.0003454076,0.00031939114,0.0003112248,0.0012773959,0.00027902258,0.0002156474,0.0016359969,0.00025434137,0.00007539279],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018842284,0.000049165013,0.000017219501,0.000010830803,0.00002081993,0.000005571602,0.000005456569,0.39846212,0.000003992241,0.59057665,0.008359557,0.0024697857],"study_design_scores_gemma":[0.00020095592,0.000022961316,0.000014632688,0.000016059874,0.000042696127,7.832626e-8,0.00005862197,0.43837455,0.00012579792,0.55709803,0.003845171,0.00020045991],"about_ca_topic_score_codex":0.0008000934,"about_ca_topic_score_gemma":0.00036080592,"teacher_disagreement_score":0.9887809,"about_ca_system_score_codex":0.00018018541,"about_ca_system_score_gemma":0.00030403424,"threshold_uncertainty_score":0.9999258},"labels":[],"label_agreement":null},{"id":"W4320931091","doi":"10.5281/zenodo.7015039","title":"Deliverable 1.8 Data Management Plan V2","year":2021,"lang":"en","type":"report","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"Horizon 2020 Framework Programme","keywords":"Deliverable; Plan (archaeology); Computer science; Operations management; Engineering; Geology; Systems engineering","score_opus":0.5504077258314425,"score_gpt":0.394461531706845,"score_spread":0.15594619412459748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320931091","genre_codex":"other","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00018057573,0.0010019313,0.0129708545,0.0025675518,0.00046980678,0.000852434,0.010925229,0.0014761287,0.9695555],"genre_scores_gemma":[0.078770615,0.05820016,0.022741865,0.0014293883,0.0030068073,0.0000014843455,0.5207435,0.013227199,0.30187902],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9941431,0.00029585086,0.0007456879,0.0016285966,0.002702429,0.00048433032],"domain_scores_gemma":[0.9914498,0.00010120452,0.00042668363,0.005718183,0.0021258441,0.00017828865],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0044578607,0.00025519286,0.0003790962,0.0005353438,0.0026306456,0.0034486754,0.0111090075,0.0002438781,0.032585528],"category_scores_gemma":[0.0045186975,0.0002336785,0.000086821405,0.0016778501,0.00022734627,0.00041748435,0.020875657,0.0006466897,0.022160713],"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":[0.0000041665226,0.000056044206,7.9445994e-7,0.000029346449,0.000048529047,0.000034696513,0.000022812032,0.000005439936,0.000021461708,0.0018406669,0.65056473,0.34737128],"study_design_scores_gemma":[0.00015672433,0.00003830926,0.00014720245,0.000060806866,0.000040260296,0.0001825558,0.00071645447,0.00019714098,0.000025040083,0.001079103,0.99710375,0.00025263973],"about_ca_topic_score_codex":0.000062415806,"about_ca_topic_score_gemma":0.0000029509845,"teacher_disagreement_score":0.66767645,"about_ca_system_score_codex":0.00026538732,"about_ca_system_score_gemma":0.000028740138,"threshold_uncertainty_score":0.9986678},"labels":[],"label_agreement":null},{"id":"W4366150443","doi":"10.2139/ssrn.4411115","title":"Measuring Discrete Risks on Infinite Domains: Theoretical Foundations, Conditional Five Number Summaries, and Data Analyses","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Econometrics; Statistics; Mathematics; Statistical physics; Physics","score_opus":0.3801287071028057,"score_gpt":0.4715815128302072,"score_spread":0.0914528057274015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366150443","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":[0.7622972,0.0016062928,0.1659528,0.05652851,0.00046033558,0.0007702399,0.0044384548,0.00065790454,0.0072882664],"genre_scores_gemma":[0.9948701,0.003545543,0.00038908643,0.00013610897,0.00014153395,0.000013945613,0.0005898216,0.000013027295,0.00030081373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966792,0.00016663414,0.00050657894,0.00053620717,0.0010131848,0.0010982117],"domain_scores_gemma":[0.9969968,0.0014963319,0.00023641495,0.0010088489,0.00016233444,0.00009925994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005189038,0.00015810979,0.00022206223,0.00027969168,0.00086600956,0.00058550393,0.0015511026,0.000103714556,0.00023326396],"category_scores_gemma":[0.003726458,0.00011081948,0.000067054614,0.0010895755,0.0005831432,0.0005715023,0.00068746076,0.0012725305,0.0005447691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028774803,0.000018327897,0.0024559253,6.7913174e-7,0.00008562809,0.0000031420154,0.000021906262,0.000059345617,0.00003990263,0.970494,0.0052735046,0.021518921],"study_design_scores_gemma":[0.00029982405,0.00005433209,0.0068715503,0.000010427004,0.000036329016,0.00011147742,0.0024578993,0.0021407001,0.000024822159,0.9656022,0.022249456,0.00014095592],"about_ca_topic_score_codex":0.000050067614,"about_ca_topic_score_gemma":0.00038434588,"teacher_disagreement_score":0.23257291,"about_ca_system_score_codex":0.00015621253,"about_ca_system_score_gemma":0.0006460273,"threshold_uncertainty_score":0.70020866},"labels":[],"label_agreement":null},{"id":"W4366809734","doi":"10.5220/0006108300001482","title":"A Surveillance Application of Satellite AIS","year":2017,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CAE (Canada); Defence Research and Development Canada","funders":"","keywords":"Remote sensing; Satellite; Computer science; Environmental science; Geology; Aerospace engineering; Engineering","score_opus":0.2541899468411294,"score_gpt":0.4263073034113857,"score_spread":0.17211735657025629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366809734","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":[0.28997293,0.00048585577,0.37792107,0.03898832,0.00021409735,0.0007984475,0.00025456175,0.00036199504,0.29100272],"genre_scores_gemma":[0.99561256,0.000096267955,0.0033896258,0.00003752538,0.000012221481,0.000018201465,0.0000035219691,0.0000021684514,0.00082792825],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.999114,0.00000967371,0.0002551353,0.00023389753,0.00030407842,0.00008324443],"domain_scores_gemma":[0.9969866,0.00017213293,0.00030562223,0.0023608916,0.00015198375,0.000022770784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007115689,0.00004359145,0.0001133073,0.000045066306,0.00018361559,0.00012770081,0.0017220416,0.00004774871,0.0000819713],"category_scores_gemma":[0.0010157388,0.000028973733,0.00003566104,0.00013905851,0.00019097679,0.00015716843,0.00027695074,0.000037402282,0.00036772573],"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":[0.0000018618257,0.000014876505,0.0670943,7.5664525e-7,0.000001757515,6.2435454e-8,0.000006999465,8.3257277e-7,0.0022383449,0.09902663,0.003010433,0.82860315],"study_design_scores_gemma":[0.000064396525,0.000008452364,0.48596877,9.467227e-7,7.782166e-7,6.488167e-7,0.00007148132,0.0005800015,0.0040730564,0.06841221,0.440766,0.00005325735],"about_ca_topic_score_codex":0.00017304004,"about_ca_topic_score_gemma":0.0002582114,"teacher_disagreement_score":0.82854986,"about_ca_system_score_codex":0.0000039272977,"about_ca_system_score_gemma":0.0000091848515,"threshold_uncertainty_score":0.4726493},"labels":[],"label_agreement":null},{"id":"W4378420534","doi":"10.1007/978-3-031-33743-7","title":"Proceedings of the 2023 International Conference on Advances in Computing Research (ACR’23)","year":2023,"lang":"en","type":"book","venue":"Lecture notes in networks and systems","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Lomonosov Moscow State University; Consejo Superior de Investigaciones Científicas; Politechnika Koszalińska; Universität Potsdam; Klaipedos Universitetas; Cardiff Metropolitan University; Central Queensland University; University of South Australia; Conservatoire National des Arts et Métiers; Trent University; Australian Catholic University; York University; King's College London; Nottingham Trent University; University of West Florida; Syddansk Universitet; University of Patras; Rutgers Cancer Institute of New Jersey; Università degli Studi Mediterranea di Reggio Calabria; University of Nicosia; Arab Academy for Science, Technology and Maritime Transport; German University in Cairo; Princeton University","keywords":"Political science; Engineering ethics; Library science; Computer science; Engineering","score_opus":0.2557063377403421,"score_gpt":0.42384406917994427,"score_spread":0.16813773143960214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378420534","genre_codex":"other","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":[0.024109177,0.052579146,0.038995977,0.025571583,0.017862309,0.011848492,0.0011877988,0.00056008925,0.8272854],"genre_scores_gemma":[0.97720695,0.002549921,0.000057983492,0.000044010976,0.00049812894,0.00006469862,0.000027725655,0.000022952805,0.019527659],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972202,0.000065166554,0.0007306894,0.00060323346,0.0010897691,0.0002908942],"domain_scores_gemma":[0.9961987,0.002605342,0.0004023067,0.00038396424,0.00038264197,0.000027010798],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031726398,0.00017342143,0.0004282917,0.0004458212,0.00012468686,0.00028611824,0.001677092,0.00045958092,0.00000876713],"category_scores_gemma":[0.0014555264,0.000103606806,0.000053352753,0.0012086703,0.0003272701,0.00008400405,0.0007186469,0.0012524262,0.000011779871],"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":[0.00007351968,0.00007820323,0.014212052,0.0002566699,0.000042656957,0.00001061094,0.0007052609,0.10056836,0.000060223494,0.46847185,0.095180236,0.32034034],"study_design_scores_gemma":[0.00044278882,0.00012874317,0.0031560815,0.0062409537,0.000007191905,0.0000135203845,0.0010966954,0.4259676,0.000016229522,0.35308403,0.20937145,0.00047471758],"about_ca_topic_score_codex":0.000054764398,"about_ca_topic_score_gemma":0.00059576926,"teacher_disagreement_score":0.95309776,"about_ca_system_score_codex":0.000096974945,"about_ca_system_score_gemma":0.00007395538,"threshold_uncertainty_score":0.5441238},"labels":[],"label_agreement":null},{"id":"W4382878092","doi":"10.23977/acss.2023.070503","title":"Opportunities and Challenges of Technological Innovation in China: Based on the Analysis of China's Big Data Development","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Monopolization; China; Big data; Strengths and weaknesses; State (computer science); Politics; Human capital; Intervention (counseling); Business; Political science; Economic growth; Economics; Market economy; Computer science","score_opus":0.4951525341569511,"score_gpt":0.38684790370311656,"score_spread":0.10830463045383454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382878092","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":[0.92453724,0.006475039,0.06138795,0.0066442303,0.000107534,0.00041148154,0.0001563136,0.000060877326,0.00021933118],"genre_scores_gemma":[0.99521506,0.0039300844,0.0007642883,0.000017095765,0.0000072859457,0.000032549953,0.000027778973,0.0000021945675,0.000003684415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99838686,0.00009822415,0.00071611034,0.00034670674,0.00034731536,0.000104797786],"domain_scores_gemma":[0.9980265,0.00092382194,0.00030259482,0.0006803339,0.000056252302,0.00001047868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032755437,0.00008571729,0.00034782593,0.0010816369,0.000049745016,0.000039576724,0.000728022,0.000065419124,0.0000017359679],"category_scores_gemma":[0.00024107119,0.000048647005,0.000013078028,0.003140383,0.00019435563,0.0001320499,0.00044404934,0.00008031111,4.2456708e-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":[0.0000054281363,0.000046009398,0.00654223,0.00003710959,0.000022591485,0.000002207846,0.00015822292,0.007324404,0.00003791514,0.0564435,0.00006108897,0.92931926],"study_design_scores_gemma":[0.00024506834,0.0000990033,0.28134426,0.0002491483,0.000015536147,0.0000012073137,0.0033988582,0.68116313,0.00017267965,0.009895301,0.023241278,0.0001744988],"about_ca_topic_score_codex":0.00002119471,"about_ca_topic_score_gemma":0.00008185407,"teacher_disagreement_score":0.9291448,"about_ca_system_score_codex":0.000006090831,"about_ca_system_score_gemma":0.000019595438,"threshold_uncertainty_score":0.19837673},"labels":[],"label_agreement":null},{"id":"W4385407315","doi":"","title":"The problem with data","year":2016,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Data science","score_opus":0.732120171553172,"score_gpt":0.6369879614823646,"score_spread":0.09513221007080741,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385407315","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":[0.6352053,0.05296132,0.09870356,0.11817396,0.0015442267,0.0060062273,0.004832122,0.0007281985,0.08184504],"genre_scores_gemma":[0.9759246,0.01682731,0.0035786398,0.0003320687,0.00013705656,0.00011499997,0.00001627698,0.000039616505,0.0030294098],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963053,0.00016523081,0.00091692386,0.0007269667,0.001509148,0.00037641422],"domain_scores_gemma":[0.9921948,0.0023245562,0.0010633683,0.0037740534,0.00048893364,0.00015434345],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004806501,0.00020296048,0.00041779736,0.00033259144,0.00068557635,0.0034616652,0.024269942,0.00008519225,0.0036102766],"category_scores_gemma":[0.0017046176,0.000080990394,0.000064111686,0.001821594,0.0005660297,0.0040250877,0.0066524427,0.00024338743,0.00016284733],"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":[0.000048802398,0.000057511206,0.07044889,0.000002136081,0.00004385911,0.0000038882417,0.000009679032,0.000002624265,0.0073252483,0.0026455428,0.4487271,0.4706847],"study_design_scores_gemma":[0.00025430907,0.000007883086,0.12724912,0.00011208509,0.000020977484,0.000013409739,0.00013114068,0.000024573486,0.00382425,0.11721288,0.7509489,0.00020044243],"about_ca_topic_score_codex":0.0002045003,"about_ca_topic_score_gemma":0.0002729075,"teacher_disagreement_score":0.47048426,"about_ca_system_score_codex":0.00003390898,"about_ca_system_score_gemma":0.00016290315,"threshold_uncertainty_score":0.99757284},"labels":[],"label_agreement":null},{"id":"W4387295506","doi":"10.5281/zenodo.8403803","title":"Small Data projects/Big Data research: contemporary problems and historical solutions","year":2023,"lang":"en","type":"paratext","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Big data; Computer science; Data science; Data mining","score_opus":0.9396265901188896,"score_gpt":0.4017279743574359,"score_spread":0.5378986157614537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387295506","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015351224,0.012992467,0.03295927,0.04302689,0.002993467,0.0065692905,0.13334891,0.0042809006,0.7636753],"genre_scores_gemma":[0.025041617,0.017936999,0.0026676944,0.00038301435,0.0031782342,0.000004419441,0.4543032,0.007654376,0.48883045],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9918796,0.0013088578,0.0010120372,0.0028334192,0.0020470829,0.0009189941],"domain_scores_gemma":[0.9870999,0.0007049687,0.00045494642,0.009610931,0.0017847366,0.00034453018],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.012249771,0.00034262802,0.0005320268,0.0013642621,0.0059965164,0.0038818503,0.020693332,0.00045186732,0.0040628803],"category_scores_gemma":[0.0163831,0.00030541365,0.00005228371,0.0039673485,0.0009953314,0.00074574165,0.06323745,0.0017797141,0.10125659],"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":[0.000015365364,0.000110306144,4.796279e-7,0.000059832397,0.00003772977,0.000008536882,0.00016857323,0.0000026364685,0.00008051703,0.00087809964,0.8413318,0.15730613],"study_design_scores_gemma":[0.00026742715,0.00013832048,0.000025482792,0.00008593349,0.00001592774,0.000054823107,0.00084412727,0.0012288892,0.0000047908984,0.0011769232,0.9958339,0.0003235083],"about_ca_topic_score_codex":0.00069433975,"about_ca_topic_score_gemma":0.000035670328,"teacher_disagreement_score":0.3209543,"about_ca_system_score_codex":0.00041103672,"about_ca_system_score_gemma":0.00008981234,"threshold_uncertainty_score":0.9999398},"labels":[{"model":"gemma","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["sts"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"agree"},{"id":"W4387656228","doi":"10.23977/jeis.2023.080405","title":"Development of Electric Power Information Communication in the Era of Big Data","year":2023,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Electric power; Information security; Context (archaeology); Data science; Power (physics); Computer science; Telecommunications; Computer security; Data mining; Geography","score_opus":0.180039499419098,"score_gpt":0.3769273172819031,"score_spread":0.1968878178628051,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387656228","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":[0.9860957,0.00024219524,0.009569561,0.002560308,0.000052497908,0.00016166185,0.000016864618,0.0000071165086,0.0012940688],"genre_scores_gemma":[0.99626416,0.0011503911,0.0024611396,0.000105292056,0.0000027579106,0.00000197714,0.000012783885,6.2586486e-7,8.930129e-7],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.997379,0.000027909062,0.0012359194,0.00005571634,0.0011539756,0.00014746703],"domain_scores_gemma":[0.9970794,0.0002680831,0.0012534679,0.00066167244,0.0007149255,0.00002247661],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010846789,0.00004804349,0.00012717514,0.0008331165,0.00016539067,0.00017197315,0.0025500928,0.000034012613,0.0000030386232],"category_scores_gemma":[0.0019816395,0.00002844852,0.000017247901,0.004752644,0.00015315544,0.0072587635,0.0003444091,0.00022864185,0.000008396986],"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":[0.000018415732,0.000031584004,0.000489644,0.000008404786,0.0000045452657,4.689858e-8,0.0053490503,0.00019059597,0.0026075672,0.07438398,0.0026654934,0.9142507],"study_design_scores_gemma":[0.00090931484,0.0003597057,0.17239349,0.000089632325,0.000012358916,0.00005429752,0.021456258,0.043306783,0.0120618865,0.02804593,0.7210836,0.00022674851],"about_ca_topic_score_codex":0.0000035897406,"about_ca_topic_score_gemma":0.000006629295,"teacher_disagreement_score":0.91402394,"about_ca_system_score_codex":0.000034258064,"about_ca_system_score_gemma":0.00066606374,"threshold_uncertainty_score":0.52624285},"labels":[],"label_agreement":null},{"id":"W4388105430","doi":"10.18280/ts.400525","title":"Secure Image Retrieval and Sharing Technologies for Digital Inclusive Finance: Methods and Applications","year":2023,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Image (mathematics); Information retrieval; Computer vision","score_opus":0.1128725283278505,"score_gpt":0.42201654756679235,"score_spread":0.30914401923894186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388105430","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":[0.15089215,0.000689066,0.828532,0.013855363,0.000050788018,0.0022783948,0.0016536695,0.0013691525,0.00067944167],"genre_scores_gemma":[0.9177065,0.00040551322,0.080388345,0.000083470724,0.000073727715,0.0008591584,0.000119810305,0.00002061038,0.00034285177],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984714,0.000011947698,0.0003647902,0.00061069126,0.0002905357,0.00025068503],"domain_scores_gemma":[0.9984268,0.00082207326,0.00013918983,0.00044740108,0.00013100107,0.000033563516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001092064,0.00013509332,0.00019815416,0.00023998882,0.0004395405,0.00045283957,0.0006883355,0.00011780413,0.000016380092],"category_scores_gemma":[0.0006303882,0.00010613758,0.000045113353,0.001077762,0.00033870645,0.00038611528,0.0010675198,0.00012472297,0.00002317135],"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":[0.000034272005,0.000039474984,0.00052429613,0.000021727305,0.000020968688,0.0000015928251,0.0001873729,0.000010235091,0.011696668,0.085660994,0.0076571917,0.8941452],"study_design_scores_gemma":[0.000540781,0.000119129014,0.002800031,0.000015209682,0.000021470212,0.000010015826,0.00519588,0.00893312,0.009519561,0.62098134,0.35159644,0.00026700756],"about_ca_topic_score_codex":0.0000014371393,"about_ca_topic_score_gemma":0.0000018275166,"teacher_disagreement_score":0.8938782,"about_ca_system_score_codex":0.000019580017,"about_ca_system_score_gemma":0.000019399688,"threshold_uncertainty_score":0.43667424},"labels":[],"label_agreement":null},{"id":"W4388543182","doi":"10.1007/978-3-031-46402-7","title":"Data Enclaves","year":2023,"lang":"es","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Economic and Social Research Council; Social Sciences and Humanities Research Council of Canada; Copenhagen Business School","keywords":"Big data; Business; Internet privacy; Computer science; Data science; Data mining","score_opus":0.6079265092522445,"score_gpt":0.4614987018091529,"score_spread":0.14642780744309153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388543182","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000027912532,0.00059810025,0.012635287,0.021903677,0.001283685,0.00080107554,0.04037806,0.001900467,0.9204717],"genre_scores_gemma":[0.00022328342,0.0050049922,0.0044630505,0.00033870322,0.00032745657,0.000034849836,0.0047657164,0.000047917125,0.984794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950804,0.000041131912,0.000953875,0.0020157637,0.0014524807,0.0004563465],"domain_scores_gemma":[0.98526603,0.0023341428,0.00041413042,0.011681644,0.0001808656,0.00012316582],"candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0017885164,0.0003727005,0.00055894046,0.00046814952,0.00039255142,0.0009367715,0.016455473,0.0007457342,0.0033745428],"category_scores_gemma":[0.0029257005,0.00026018065,0.00011631891,0.0011783942,0.0006823234,0.0004972272,0.013476205,0.00060145074,0.079365835],"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":[7.9514604e-7,0.0000137945135,0.000019570676,0.000006217241,0.000019676136,0.000004986859,0.000003106241,2.8953122e-7,0.0000114521345,0.16063708,0.668854,0.17042907],"study_design_scores_gemma":[0.000050309092,0.000018594743,0.00020474778,0.00004829295,0.000030661104,0.0000035735916,0.00030810796,0.0005734836,0.000019695392,0.1528555,0.845599,0.0002880292],"about_ca_topic_score_codex":0.00006716653,"about_ca_topic_score_gemma":0.0002293522,"teacher_disagreement_score":0.17674504,"about_ca_system_score_codex":0.00004320086,"about_ca_system_score_gemma":0.0004908399,"threshold_uncertainty_score":0.99998504},"labels":[],"label_agreement":null},{"id":"W4388998246","doi":"10.23977/jaip.2023.060707","title":"Artificial intelligence for satellite communications and geophysics: current and future trends","year":2023,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Communications satellite; Process (computing); Boom; Field (mathematics); Telecommunications; Computer science; Data science; Artificial intelligence; Engineering; Satellite","score_opus":0.42613064045003063,"score_gpt":0.4966793961804116,"score_spread":0.070548755730381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388998246","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":[0.040413734,0.02568078,0.5376237,0.38872895,0.0041551925,0.0012015845,0.00044180336,0.00031391496,0.001440364],"genre_scores_gemma":[0.80230236,0.1184936,0.07582576,0.00056264777,0.002496658,0.00008841866,0.000037477443,0.000051823215,0.00014123034],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99692214,0.00017528389,0.0015232606,0.0003870554,0.0006873332,0.0003049541],"domain_scores_gemma":[0.99124515,0.005399262,0.0011795993,0.0009210657,0.0010948284,0.00016007078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004352304,0.00018483549,0.0003516348,0.0006030231,0.0005245466,0.00064300734,0.0013596796,0.00012672514,0.000030493478],"category_scores_gemma":[0.004569473,0.0001442775,0.00013170215,0.0021052628,0.0005099311,0.0012760747,0.00048473148,0.0005740578,0.00011467283],"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":[0.000081171434,0.00011441743,0.000023565453,0.000004928822,0.000018709383,0.0000022012484,0.00060289714,0.000009308791,0.0004420716,0.17405494,0.00061716564,0.8240286],"study_design_scores_gemma":[0.000012259391,0.00021496785,0.00021319735,0.000018953224,0.00006566126,0.000052995034,0.015563808,0.0050677997,0.0016072536,0.42473558,0.55229384,0.00015370644],"about_ca_topic_score_codex":0.0000131602865,"about_ca_topic_score_gemma":0.000045260243,"teacher_disagreement_score":0.82387495,"about_ca_system_score_codex":0.00002956194,"about_ca_system_score_gemma":0.000085021085,"threshold_uncertainty_score":0.6200534},"labels":[],"label_agreement":null},{"id":"W4390539753","doi":"10.4324/9781003388418","title":"Global Digital Data Governance","year":2024,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre for Global Cooperation Research; Universität Duisburg-Essen; Wissenschaftszentrum Berlin für Sozialforschung; York University; Alexander von Humboldt-Stiftung","keywords":"Data governance; Corporate governance; Business; Computer science; Data quality; Finance","score_opus":0.3330702791145367,"score_gpt":0.41508136882333235,"score_spread":0.08201108970879567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390539753","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.515729e-7,0.0014832707,0.0036304053,0.004580925,0.00035169063,0.00012874698,0.050935555,0.0003563857,0.93853205],"genre_scores_gemma":[0.00033324945,0.00018955054,0.0007959107,0.00018246198,0.00018341585,0.0000062568256,0.0015153321,0.000012038611,0.99678177],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969727,0.0000032978069,0.00045473682,0.0012050167,0.0011811303,0.0001831358],"domain_scores_gemma":[0.9940277,0.0002390008,0.00017090979,0.005430679,0.000076252094,0.000055498393],"candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003272436,0.0001926079,0.00025902755,0.000035021007,0.00005434226,0.0015571485,0.008204417,0.0003024213,0.0010308945],"category_scores_gemma":[0.0009151281,0.00012335017,0.00007948844,0.00044701147,0.00019514436,0.00055082224,0.006772027,0.00023036983,0.024870703],"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":[2.7433865e-7,0.000003031684,0.0000048329944,0.0000012502704,0.0000056517633,0.000003690255,2.219899e-7,8.394885e-8,1.4466485e-8,0.27960727,0.530547,0.18982665],"study_design_scores_gemma":[0.000011813972,0.000003890019,0.000022419697,0.000012830585,0.0000065956706,0.0000068060203,0.000007874771,0.000107383144,1.1019327e-7,0.40209988,0.5976261,0.00009432421],"about_ca_topic_score_codex":0.000010814269,"about_ca_topic_score_gemma":0.00012209047,"teacher_disagreement_score":0.18973233,"about_ca_system_score_codex":0.000117621006,"about_ca_system_score_gemma":0.0003519504,"threshold_uncertainty_score":0.9998823},"labels":[],"label_agreement":null},{"id":"W4390982406","doi":"10.23977/acss.2023.071115","title":"Design and Research of Data-driven Scientific Research Management Platform","year":2023,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Yunnan Provincial Department of Education","keywords":"Research data; Data management; Data science; Computer science; Management science; Knowledge management; Engineering management; Systems engineering; Engineering; Database; Data curation","score_opus":0.7113757234689406,"score_gpt":0.5370656310658665,"score_spread":0.17431009240307416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390982406","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":[0.22777897,0.01713971,0.74813795,0.0013652764,0.00094542664,0.0031252594,0.00022818375,0.00017840322,0.0011008454],"genre_scores_gemma":[0.97789896,0.0029813542,0.018619336,0.000004981117,0.000050600407,0.00010098806,0.000022954726,0.0000073800475,0.000313431],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963341,0.00034921747,0.0005472962,0.0008492498,0.0015300113,0.00039016092],"domain_scores_gemma":[0.99481475,0.003343877,0.00009337706,0.0013664556,0.000321062,0.000060461123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02103187,0.00008099603,0.00024431117,0.0011381212,0.00040038384,0.00064992224,0.0018692443,0.000060863495,0.0000042585893],"category_scores_gemma":[0.00014402767,0.000058154168,0.000011160374,0.0035827118,0.00072287134,0.0008276733,0.002903766,0.00021056797,0.000049667116],"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":[0.000018745108,0.000055396136,0.0012388703,0.00014381621,0.000014657899,0.000026873258,0.00045425651,0.011349512,0.0003618063,0.04479994,0.034826744,0.9067094],"study_design_scores_gemma":[0.0002637318,0.00013279867,0.0010207125,0.00022212001,0.0000019239444,0.0000066682987,0.0025877203,0.74974924,0.00010630932,0.08245152,0.16333458,0.00012264377],"about_ca_topic_score_codex":0.000028180102,"about_ca_topic_score_gemma":0.000019332314,"teacher_disagreement_score":0.9065867,"about_ca_system_score_codex":0.000015455536,"about_ca_system_score_gemma":0.000024793386,"threshold_uncertainty_score":0.7289268},"labels":[],"label_agreement":null},{"id":"W4392600544","doi":"10.5194/egusphere-egu24-6798","title":"Novel environmental big data grid integration and interoperability model","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"College of Family Physicians of Canada; General Electric (Canada)","funders":"","keywords":"Interoperability; Computer science; Big data; Grid; Data science; Data integration; Database; Data mining; World Wide Web; Geography","score_opus":0.5400495817871738,"score_gpt":0.4070020343157101,"score_spread":0.1330475474714637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392600544","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":[0.17019169,0.00064137904,0.7901342,0.0123029975,0.0012719276,0.0007311437,0.021261662,0.000375406,0.0030895856],"genre_scores_gemma":[0.9695495,0.00028376924,0.0273204,0.0001615765,0.00012442707,0.000056757417,0.0013225985,0.000013176726,0.0011678037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971285,0.000021396745,0.0005744107,0.0016032939,0.00053148565,0.00014093099],"domain_scores_gemma":[0.99543333,0.00014852086,0.0001182843,0.0042139925,0.000026217202,0.00005963776],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0011884535,0.00021555697,0.00025923678,0.00015608864,0.000083440544,0.0007013838,0.0029208423,0.00028533489,0.000099759876],"category_scores_gemma":[0.00045319344,0.00013512616,0.000052221196,0.00014961557,0.00031084192,0.00015993897,0.026641445,0.0007601077,0.00024532177],"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":[0.0000054709785,0.00012289347,0.000120448574,0.000013518656,0.000021040329,4.8418707e-7,0.000114049726,0.00017012862,0.005373897,0.00710798,0.061621066,0.925329],"study_design_scores_gemma":[0.00006791382,0.000012964935,0.0005354849,0.00003057514,0.000028923296,0.0000068585327,0.00093666883,0.73716044,0.0005743263,0.24085571,0.019541597,0.000248537],"about_ca_topic_score_codex":0.00015239348,"about_ca_topic_score_gemma":0.0003263108,"teacher_disagreement_score":0.9250805,"about_ca_system_score_codex":0.000058179823,"about_ca_system_score_gemma":0.000061048406,"threshold_uncertainty_score":0.9812309},"labels":[],"label_agreement":null},{"id":"W4392733155","doi":"10.1017/9781108874144.012","title":"Overview of analytic methods for multivariate GFs","year":2024,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Multivariate statistics; Computer science; Mathematics; Statistics","score_opus":0.37811485258637656,"score_gpt":0.4235050655656161,"score_spread":0.045390212979239564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392733155","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000005709552,0.0012793873,0.07948483,0.00011800527,0.00020938582,0.0006655446,0.0030276556,0.00013994549,0.9150695],"genre_scores_gemma":[0.00015090953,0.00025461306,0.016894402,0.000028137834,0.000038515973,0.0000033376682,0.000050927993,0.000028668648,0.9825505],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981212,0.00003827999,0.000469437,0.00079641474,0.00036638806,0.0002082774],"domain_scores_gemma":[0.9964525,0.0010562319,0.000470708,0.0015283864,0.0004029715,0.000089196474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008682565,0.00027702964,0.00065571093,0.00044142842,0.00012446257,0.000083900406,0.0018363048,0.0004211128,0.0000133981],"category_scores_gemma":[0.00023316838,0.000246224,0.0004954292,0.000055758817,0.0003334903,0.000080849786,0.001170817,0.0003225068,0.000035318735],"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":[0.000018451296,0.0000055746123,1.8071277e-7,0.00007967525,0.00011778656,0.000006143256,0.000009795481,0.0000012671322,0.00009858444,0.90617085,0.047262736,0.046228938],"study_design_scores_gemma":[0.00019780868,0.00003517077,0.0000050920416,0.00013656163,0.00034417165,0.0000027770695,0.000051664498,0.0012036827,0.0005057827,0.009295267,0.98798054,0.00024148045],"about_ca_topic_score_codex":0.00009019074,"about_ca_topic_score_gemma":0.0000025796046,"teacher_disagreement_score":0.9407178,"about_ca_system_score_codex":0.000084503954,"about_ca_system_score_gemma":0.000093079616,"threshold_uncertainty_score":0.999999},"labels":[],"label_agreement":null},{"id":"W4392749861","doi":"10.23977/acss.2024.080113","title":"Research on Information Management and Decision Support System Based on Big Data","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Data science; Computer science; Decision support system; Knowledge management; Data mining","score_opus":0.3332079687068855,"score_gpt":0.44813486115973833,"score_spread":0.11492689245285281,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392749861","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":[0.005066681,0.0029596444,0.9861672,0.00042568299,0.0013378593,0.0006957525,0.00022363712,0.0001287849,0.0029947846],"genre_scores_gemma":[0.9938119,0.0006106129,0.0052105393,0.00008878209,0.00012122472,0.00007222102,0.000048086105,0.0000057900565,0.000030847626],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99740285,0.00011440376,0.0005877123,0.0006074127,0.0010741415,0.0002135066],"domain_scores_gemma":[0.99660736,0.0019947747,0.00007564114,0.0011788874,0.000085755186,0.000057599722],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0046233316,0.00011818601,0.00020952869,0.0008287248,0.00016068008,0.0011492328,0.00093554106,0.00007296299,0.000003445372],"category_scores_gemma":[0.00004889396,0.00007770919,0.000015953869,0.0009949397,0.00008169097,0.00086953345,0.00064224645,0.00018881712,0.00013000806],"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":[0.000015467807,0.000014471086,0.00009773144,0.00013649007,0.000003401748,0.000015156722,0.000023429635,0.005380294,8.42134e-7,0.03145508,0.011066768,0.95179087],"study_design_scores_gemma":[0.00015479558,0.00014537683,0.00030293607,0.00066219864,0.0000018711795,0.000007506457,0.0005649373,0.64689845,0.000003818112,0.003343493,0.34783387,0.000080769554],"about_ca_topic_score_codex":0.000015863381,"about_ca_topic_score_gemma":0.000008968638,"teacher_disagreement_score":0.9887452,"about_ca_system_score_codex":0.000040695508,"about_ca_system_score_gemma":0.000019219646,"threshold_uncertainty_score":0.99988765},"labels":[],"label_agreement":null},{"id":"W4393178192","doi":"10.1051/0004-6361/202348239","title":"Galaxy merger challenge: A comparison study between machine learning-based detection methods","year":2024,"lang":"en","type":"preprint","venue":"Astronomy and Astrophysics","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Agencia Estatal de Investigación; Ministerio de Ciencia e Innovación; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Science and Technology Facilities Council; European Commission; Rijksuniversiteit Groningen; Comunidad de Madrid","keywords":"Galaxy; Computer science; Artificial intelligence; Astrophysics; Physics","score_opus":0.17749497253984287,"score_gpt":0.42132149206836367,"score_spread":0.2438265195285208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393178192","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":[0.16726217,0.0005090558,0.8297631,0.0009223086,0.0002864285,0.0006576372,0.00023357564,0.00027866964,0.00008702768],"genre_scores_gemma":[0.8908188,0.000008874489,0.10846629,0.0000047323956,0.00026569693,0.00020111477,0.00012789998,0.000032899054,0.000073729636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99660367,0.00039900033,0.0008036332,0.0012826554,0.00056651834,0.00034455015],"domain_scores_gemma":[0.99750453,0.0005228099,0.0005116266,0.001198744,0.00014054429,0.00012176457],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012711115,0.00043915078,0.0008021814,0.00028217625,0.0003458997,0.00056928926,0.000988638,0.00025485668,0.000043083775],"category_scores_gemma":[0.00013573068,0.0003555199,0.00022612527,0.00051715184,0.00016517272,0.00008985098,0.0026230726,0.0021904074,0.00012880182],"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":[0.0000105822855,0.00015662097,0.0042052004,0.000014150846,0.000110721936,8.0998e-7,0.00012376255,0.0029297287,0.00009058184,0.00014133296,0.00010049247,0.99211603],"study_design_scores_gemma":[0.0015758694,0.0028148799,0.041788336,0.00019201527,0.0013695732,0.00000159392,0.009727584,0.10518394,0.0058645885,0.07395529,0.7553632,0.002163121],"about_ca_topic_score_codex":0.0001671202,"about_ca_topic_score_gemma":0.000045590725,"teacher_disagreement_score":0.9899529,"about_ca_system_score_codex":0.00004994296,"about_ca_system_score_gemma":0.00008470885,"threshold_uncertainty_score":0.9998897},"labels":[],"label_agreement":null},{"id":"W4393435570","doi":"10.54097/2z61sv46","title":"Preface: 5th International Conference on Computer Science and Intelligent Communication (CSIC 2023)","year":2024,"lang":"en","type":"article","venue":"Highlights in Science Engineering and Technology","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Library science; Computer science; Engineering","score_opus":0.10577708866243837,"score_gpt":0.3596516828673061,"score_spread":0.2538745942048677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393435570","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":[0.8752982,0.0015618087,0.029674122,0.08743815,0.0016510976,0.0005140786,0.00004584045,0.0011011873,0.0027154912],"genre_scores_gemma":[0.99060935,0.000761308,0.008470565,0.00002960302,0.00001912426,0.00003251184,0.0000011854489,0.0000046848804,0.000071652204],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978994,0.000008042417,0.00029822692,0.00076891074,0.0007359727,0.0002894183],"domain_scores_gemma":[0.9986658,0.00018688742,0.000045259356,0.0007743093,0.00026034887,0.000067362314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019043261,0.00012623357,0.00014350285,0.0022461473,0.0002564474,0.000693118,0.002034362,0.000104202525,0.000012171172],"category_scores_gemma":[0.00066373264,0.000092224196,0.0000104922665,0.004624747,0.0023318934,0.0005268737,0.0010718178,0.00031024695,0.000113335176],"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":[9.062853e-7,0.000014946589,0.000082609055,0.000002621156,0.0000016584221,0.0000029716941,0.00008486464,0.00013259679,0.009145067,0.90625006,0.00043283266,0.08384887],"study_design_scores_gemma":[0.0001424823,0.00012303889,0.0022999325,0.00021993057,0.000003776534,0.00006564995,0.00043093023,0.7461716,0.020065984,0.07042624,0.15972474,0.00032569785],"about_ca_topic_score_codex":0.000011292174,"about_ca_topic_score_gemma":0.000010767307,"teacher_disagreement_score":0.83582383,"about_ca_system_score_codex":0.00011043552,"about_ca_system_score_gemma":0.00012429299,"threshold_uncertainty_score":0.8591958},"labels":[],"label_agreement":null},{"id":"W4393450344","doi":"10.5281/zenodo.7488070","title":"Human pseudoDB: simulated database of human genetic variants","year":2022,"lang":"pt","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Database; Computer science; Information retrieval","score_opus":0.20754057116717498,"score_gpt":0.3577449677550974,"score_spread":0.15020439658792242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393450344","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006014055,0.00020411894,0.0011876917,0.00051509636,0.000194105,0.0014088217,0.9861815,0.0007002487,0.0035943897],"genre_scores_gemma":[0.0587811,0.00034259976,0.00023916502,0.00012716127,0.000083110564,2.5256026e-7,0.9377172,0.0014741261,0.0012352619],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923659,0.0011801538,0.0016222281,0.001816969,0.002193074,0.0008216716],"domain_scores_gemma":[0.9918992,0.00015896483,0.0012413879,0.005111838,0.0012465074,0.00034213133],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0029207722,0.0005111953,0.0007108485,0.0013052615,0.009131167,0.0016517898,0.0116458405,0.00035820692,0.46486837],"category_scores_gemma":[0.0028630453,0.0005341807,0.00019572712,0.0034861604,0.0009380337,0.00040042496,0.017309215,0.0014115081,0.011713809],"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":[0.000027547825,0.00068650505,0.0000014009397,0.0001215955,0.00009925669,0.000049605667,0.00015967943,0.00018653,0.005183671,0.0021811964,0.97273195,0.01857104],"study_design_scores_gemma":[0.0007400755,0.00071248156,0.00024644096,0.00007550509,0.00010413764,0.00008725745,0.00089392345,0.00054434745,0.00014023628,0.0006844293,0.99525267,0.0005184963],"about_ca_topic_score_codex":0.00028093194,"about_ca_topic_score_gemma":0.0000026339028,"teacher_disagreement_score":0.45315456,"about_ca_system_score_codex":0.00024997612,"about_ca_system_score_gemma":0.000020629826,"threshold_uncertainty_score":0.999711},"labels":[],"label_agreement":null},{"id":"W4393550518","doi":"10.5281/zenodo.4733386","title":"DJIN model of aging synthetic dataset","year":2021,"lang":"en","type":"dataset","venue":"Figshare","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.44214195677123425,"score_gpt":0.417017978966971,"score_spread":0.02512397780426323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393550518","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[3.3184332e-7,0.00057390466,0.000013145831,0.00027614643,0.000033078766,0.000148786,0.99887395,0.000032038457,0.00004862194],"genre_scores_gemma":[0.000013884866,0.00006293796,0.00034386013,0.00016732032,0.000036618596,0.00014671728,0.99913996,0.000010226031,0.00007849933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739575,0.00004427114,0.0006216719,0.00075773225,0.00094353384,0.0002370649],"domain_scores_gemma":[0.99433386,0.0007241939,0.00053588947,0.004094175,0.00024367799,0.000068176116],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024024352,0.00021727316,0.00044220802,0.00024007843,0.00009900191,0.00020682097,0.003763102,0.0003417889,0.17378451],"category_scores_gemma":[0.009602582,0.00017402472,0.00012055335,0.0007102421,0.000029982151,0.0001473216,0.002348853,0.00040318992,0.0066574845],"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":[3.9933906e-7,0.000029765471,6.0990956e-8,0.00006479853,0.000007854091,0.000005918473,0.0000012421087,0.000093356044,0.000005233383,0.0000069425764,0.99653,0.0032544616],"study_design_scores_gemma":[0.000037750848,0.0000053346266,0.0000013154972,0.0006705312,0.000015389283,0.000004247992,0.000033567045,0.0011314631,0.00018829171,0.0005107259,0.9972185,0.00018287887],"about_ca_topic_score_codex":0.000024152107,"about_ca_topic_score_gemma":0.00006592221,"teacher_disagreement_score":0.16712701,"about_ca_system_score_codex":0.000022096561,"about_ca_system_score_gemma":0.00021391848,"threshold_uncertainty_score":0.99873996},"labels":[],"label_agreement":null},{"id":"W4393733384","doi":"10.5281/zenodo.7488069","title":"Human pseudoDB: simulated database of human genetic variants","year":2022,"lang":"pt","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Database; Computer science","score_opus":0.20754057116717498,"score_gpt":0.3577449677550974,"score_spread":0.15020439658792242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393733384","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006014055,0.00020411894,0.0011876917,0.00051509636,0.000194105,0.0014088217,0.9861815,0.0007002487,0.0035943897],"genre_scores_gemma":[0.0587811,0.00034259976,0.00023916502,0.00012716127,0.000083110564,2.5256026e-7,0.9377172,0.0014741261,0.0012352619],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9923659,0.0011801538,0.0016222281,0.001816969,0.002193074,0.0008216716],"domain_scores_gemma":[0.9918992,0.00015896483,0.0012413879,0.005111838,0.0012465074,0.00034213133],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0029207722,0.0005111953,0.0007108485,0.0013052615,0.009131167,0.0016517898,0.0116458405,0.00035820692,0.46486837],"category_scores_gemma":[0.0028630453,0.0005341807,0.00019572712,0.0034861604,0.0009380337,0.00040042496,0.017309215,0.0014115081,0.011713809],"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":[0.000027547825,0.00068650505,0.0000014009397,0.0001215955,0.00009925669,0.000049605667,0.00015967943,0.00018653,0.005183671,0.0021811964,0.97273195,0.01857104],"study_design_scores_gemma":[0.0007400755,0.00071248156,0.00024644096,0.00007550509,0.00010413764,0.00008725745,0.00089392345,0.00054434745,0.00014023628,0.0006844293,0.99525267,0.0005184963],"about_ca_topic_score_codex":0.00028093194,"about_ca_topic_score_gemma":0.0000026339028,"teacher_disagreement_score":0.45315456,"about_ca_system_score_codex":0.00024997612,"about_ca_system_score_gemma":0.000020629826,"threshold_uncertainty_score":0.999711},"labels":[],"label_agreement":null},{"id":"W4394055437","doi":"10.5281/zenodo.4733385","title":"DJIN model of aging synthetic dataset","year":2021,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science","score_opus":0.27945551284278286,"score_gpt":0.356692318225389,"score_spread":0.07723680538260613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394055437","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00003695052,0.00017681895,0.003936495,0.000941985,0.00006391069,0.00026529585,0.992824,0.00020459305,0.0015499556],"genre_scores_gemma":[0.00076397986,0.0005490483,0.0005826737,0.0001163261,0.000052168067,7.97285e-8,0.99732023,0.00042256122,0.00019292664],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964001,0.0003240156,0.00072288356,0.00093815866,0.0012506252,0.00036422373],"domain_scores_gemma":[0.99490714,0.00015759918,0.00047876028,0.003439148,0.0008779411,0.00013942795],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0019477389,0.00022149223,0.00038924528,0.0005527137,0.0013532424,0.0012239094,0.006143977,0.00021309276,0.014943294],"category_scores_gemma":[0.005274996,0.00020263037,0.0000959603,0.0013688334,0.000395131,0.00024978418,0.0070137847,0.0005627512,0.009553414],"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":[0.00000471413,0.00010399227,4.727613e-8,0.00004088143,0.000021378057,0.0000058513933,0.000020655198,0.00012889542,0.00027548513,0.0006265264,0.96436185,0.034409747],"study_design_scores_gemma":[0.00012043139,0.000038649923,0.0000026627856,0.00005189939,0.000029151413,0.00003485353,0.00020047228,0.0009391607,0.00021247118,0.0009373006,0.99723494,0.00019803556],"about_ca_topic_score_codex":0.000037398957,"about_ca_topic_score_gemma":0.0000019056513,"teacher_disagreement_score":0.03421171,"about_ca_system_score_codex":0.000081461476,"about_ca_system_score_gemma":0.00001601535,"threshold_uncertainty_score":0.99994683},"labels":[],"label_agreement":null},{"id":"W4394316133","doi":"10.6084/m9.figshare.4010619","title":"PHEME dataset of rumours and non-rumours","year":2016,"lang":"en","type":"dataset","venue":"Figshare","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Computer science; History","score_opus":0.2710647247861676,"score_gpt":0.40385188843202674,"score_spread":0.13278716364585913,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394316133","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000035950402,0.0002496204,0.0000020523844,0.000628833,0.000052757354,0.00026144713,0.99870473,0.000027346583,0.000069624],"genre_scores_gemma":[0.000028046068,0.00010804941,0.00009051935,0.00014866423,0.00008659031,0.000140843,0.99927366,0.000011086254,0.000112526126],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99751645,0.000029580418,0.00062202854,0.00074826815,0.00079681363,0.00028683664],"domain_scores_gemma":[0.9953512,0.00079194683,0.0007398254,0.0028191677,0.00018461552,0.00011323513],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027752458,0.00025902138,0.0004629635,0.00021245616,0.00011120839,0.00016126674,0.0031910671,0.0004103609,0.13829927],"category_scores_gemma":[0.005398281,0.00016602964,0.00007659456,0.0004451976,0.00007674196,0.00022119125,0.0020178559,0.00027807683,0.007873482],"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":[0.0000024637745,0.00001979547,0.0000034015814,0.000040096453,0.000008966076,0.000004282517,0.0000011179706,5.7614187e-8,0.000006017573,0.000004295291,0.9911937,0.008715787],"study_design_scores_gemma":[0.00012431522,0.000028358858,0.00020589492,0.00055610185,0.000013613007,0.000007032964,0.0000317016,0.000002913633,0.000104542734,0.00069180655,0.9980183,0.00021540662],"about_ca_topic_score_codex":0.000031076255,"about_ca_topic_score_gemma":0.00007730872,"teacher_disagreement_score":0.13042578,"about_ca_system_score_codex":0.000015471564,"about_ca_system_score_gemma":0.00009568939,"threshold_uncertainty_score":0.992899},"labels":[],"label_agreement":null},{"id":"W4394712518","doi":"10.1109/icdt61202.2024.10489227","title":"Comparing the Supersonic Cloud Computing Model to Enhance the Networking and Security in Traditional Data Centers","year":2024,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Cloud computing; Computer science; Cloud computing security; Computer security; Operating system","score_opus":0.44394505898415615,"score_gpt":0.4134127683132938,"score_spread":0.030532290670862328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394712518","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":[0.7813615,0.000929998,0.1654904,0.048913777,0.0003382612,0.00033354876,0.00013127463,0.00014060318,0.002360606],"genre_scores_gemma":[0.99814254,0.000046310597,0.0011148703,0.0005358675,0.00010468783,0.0000067268347,0.000016244481,0.0000034394006,0.00002929412],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99879366,0.000039172937,0.00023985871,0.00043836725,0.0003123681,0.00017655769],"domain_scores_gemma":[0.99803954,0.001070686,0.000023284252,0.0008249003,0.0000147225355,0.000026838545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018285703,0.00006912631,0.00009230546,0.00004950311,0.00026995083,0.0005265465,0.0017580142,0.000027885444,0.000012007292],"category_scores_gemma":[0.00011226425,0.000034048375,0.000017888811,0.0006559913,0.0001232388,0.00019101215,0.0011499763,0.00024769575,0.000021820813],"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":[0.000010843283,0.00006094823,0.0059062364,0.000010613022,0.000027159056,0.0000039377082,0.0037656901,0.02324969,0.00018797664,0.46996725,0.32103336,0.1757763],"study_design_scores_gemma":[0.000020069881,0.000002935498,0.0011152057,0.00002415588,0.0000022831102,0.000004252329,0.001554289,0.94418323,0.000014160977,0.034221563,0.018808214,0.000049612067],"about_ca_topic_score_codex":0.00009395134,"about_ca_topic_score_gemma":0.0007107286,"teacher_disagreement_score":0.92093354,"about_ca_system_score_codex":0.0000188244,"about_ca_system_score_gemma":0.000022870552,"threshold_uncertainty_score":0.50775003},"labels":[],"label_agreement":null},{"id":"W4394912101","doi":"10.1136/bmjsem-2024-001994","title":"Big data. Big potential. Big problems?","year":2024,"lang":"en","type":"editorial","venue":"BMJ Open Sport & Exercise Medicine","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; University of Calgary","funders":"","keywords":"Big data; Data science; Computer science; Data mining","score_opus":0.33112917276274684,"score_gpt":0.4532192369718727,"score_spread":0.12209006420912588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394912101","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042489584,0.0054498296,0.0013976124,0.015879285,0.95283735,0.008317275,0.0061123366,0.0005325458,0.0094312765],"genre_scores_gemma":[0.00068603805,0.009013876,0.0010405463,0.00026261626,0.889914,0.0025250635,0.02097786,0.00020951442,0.0753705],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9840676,0.00006595703,0.0034864503,0.004160124,0.007230942,0.0009889352],"domain_scores_gemma":[0.98166156,0.00079380616,0.0018535084,0.013977467,0.0012192851,0.00049435126],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["open_science","research_integrity","insufficient_payload"],"category_scores_codex":[0.013566626,0.0010318375,0.004008446,0.0013272132,0.00047051263,0.0015856712,0.025311405,0.0017562414,0.0010284868],"category_scores_gemma":[0.0065236627,0.0006561456,0.00023119061,0.0041611423,0.0010397615,0.0005383112,0.016958902,0.002322189,0.004412544],"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":[0.00005942845,0.000071612194,0.000017158636,0.00009869617,0.000038192302,0.00019848859,0.000036147314,0.0000017266694,0.000011112307,0.00010584963,0.6245082,0.37485337],"study_design_scores_gemma":[0.0009551936,0.00014159807,0.00007609975,0.0026450183,0.0005598862,0.000029239189,0.0007620963,0.0000910874,0.00001074715,0.011981876,0.9819289,0.00081824657],"about_ca_topic_score_codex":0.0038886408,"about_ca_topic_score_gemma":0.0013807002,"teacher_disagreement_score":0.37403512,"about_ca_system_score_codex":0.00013282284,"about_ca_system_score_gemma":0.0020603372,"threshold_uncertainty_score":0.9999795},"labels":[],"label_agreement":null},{"id":"W4399471733","doi":"10.23977/jeis.2024.090209","title":"Privacy Protection in Information and Communication Technology Applications Based on Big Data","year":2024,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Computer science; Internet privacy; Computer security; Data science; Data mining","score_opus":0.14111671371730938,"score_gpt":0.37104989226007556,"score_spread":0.22993317854276618,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399471733","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":[0.10663743,0.0025544316,0.8340516,0.052812006,0.00022941812,0.0012126509,0.00008978238,0.00012311325,0.0022895806],"genre_scores_gemma":[0.9951816,0.0015273571,0.0030205634,0.00021107327,0.00001372462,0.000027893228,0.000013304729,0.0000016958452,0.0000027444257],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818915,0.00002140648,0.0008046779,0.000141699,0.00068164745,0.0001613953],"domain_scores_gemma":[0.99808496,0.00017432585,0.00044313588,0.0007914288,0.00045825925,0.000047869922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045454605,0.00007582557,0.0001200557,0.0023300769,0.00025542077,0.00095082086,0.0013627736,0.00008005952,0.000003064383],"category_scores_gemma":[0.0015153346,0.000054800952,0.000014340868,0.0038774314,0.00031279746,0.010769899,0.00033421122,0.00040158373,0.000017229013],"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":[0.000007824641,0.000011718452,0.000118560754,0.000008107626,0.0000011414988,5.9092084e-8,0.000090834845,0.0001458083,0.00021102127,0.08523545,0.00027188493,0.9138976],"study_design_scores_gemma":[0.00021703051,0.00016144419,0.002322005,0.000053185817,0.000004723481,0.000043313587,0.00049106684,0.23114683,0.00041346982,0.036080312,0.7289811,0.00008553648],"about_ca_topic_score_codex":0.000005551421,"about_ca_topic_score_gemma":0.000006641258,"teacher_disagreement_score":0.91381204,"about_ca_system_score_codex":0.00010053846,"about_ca_system_score_gemma":0.00049669965,"threshold_uncertainty_score":0.91687876},"labels":[],"label_agreement":null},{"id":"W4400485157","doi":"10.61091/jcmcc120-22","title":"Construction of Financial Bill Recognition Model Based on Deep Learning","year":2024,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Science Planning Project of Shandong Province","keywords":"Artificial intelligence; Deep learning; Computer science; Finance; Business","score_opus":0.07861500679816442,"score_gpt":0.3208441827489801,"score_spread":0.24222917595081567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400485157","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":[0.66649795,0.00025330158,0.31939974,0.00074090564,0.01144019,0.00029982722,0.0000192084,0.00010762374,0.0012412745],"genre_scores_gemma":[0.97844625,0.000032820328,0.021040909,0.000014163086,0.0004419512,0.0000017702911,0.0000023656994,0.000015995502,0.0000037547154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9970569,0.0001116249,0.0013262057,0.00025789678,0.00105941,0.00018795115],"domain_scores_gemma":[0.9959563,0.0019812412,0.0009766814,0.00026538147,0.0007331056,0.00008728686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035043668,0.00018084324,0.00053843536,0.00048964215,0.0002161395,0.00031254298,0.00047183057,0.00019746735,0.000012147465],"category_scores_gemma":[0.0036949515,0.00012496175,0.00019461173,0.0007772947,0.00014959423,0.00022582021,0.00014152663,0.0006067083,0.0000067302362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006129748,0.0002659503,0.00005922597,0.00008509091,0.000022546417,0.0000074150007,0.00027006646,0.002598325,0.00048467182,0.7893064,0.00038259453,0.20645641],"study_design_scores_gemma":[0.00061891315,0.00038486082,0.000019726656,0.00024388212,0.000032083764,0.000019332518,0.00016999696,0.3620885,0.0007319964,0.6349564,0.00063445873,0.000099819394],"about_ca_topic_score_codex":0.0000031792567,"about_ca_topic_score_gemma":1.7676018e-7,"teacher_disagreement_score":0.3594902,"about_ca_system_score_codex":0.000052133713,"about_ca_system_score_gemma":0.00017611045,"threshold_uncertainty_score":0.5095792},"labels":[],"label_agreement":null},{"id":"W4401467332","doi":"10.62051/3a6dex21","title":"Research on User Profile and User Behavior of Integrating Big Data Platforms","year":2024,"lang":"en","type":"article","venue":"Transactions on Economics Business and Management Research","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Behavioral analysis; Electric power; Process (computing); Human–computer interaction; Power (physics); Portrait; Behavioral pattern; Database; Data mining; Software engineering; Operating system","score_opus":0.6172003303845578,"score_gpt":0.4800867582924546,"score_spread":0.13711357209210318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401467332","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":[0.9065794,0.00038981324,0.06926794,0.009501623,0.0004376275,0.002451401,0.0013728035,0.00014656065,0.009852851],"genre_scores_gemma":[0.9873269,0.005854806,0.0018723889,0.000020936915,0.000037393605,0.0003547263,0.0000480541,0.000020051037,0.004464725],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99786687,0.000044970195,0.00039536014,0.00083069626,0.0005277232,0.00033439294],"domain_scores_gemma":[0.9973865,0.0008245724,0.000037361162,0.0014302606,0.00025338575,0.000067912646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044808798,0.00011661124,0.00018065053,0.0015052995,0.00048422735,0.00075017865,0.0010965411,0.000094130424,0.00013396911],"category_scores_gemma":[0.00007227261,0.00008380294,0.000023880466,0.00191061,0.00047428635,0.0005221151,0.00032258098,0.00053045276,0.000099655816],"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":[0.000035106295,0.00015223167,0.00009438692,0.00008420648,0.000031249874,0.0000046298715,0.00003652498,0.00006032741,0.000051256287,0.13937774,0.005337181,0.85473514],"study_design_scores_gemma":[0.0009124306,0.00044662776,0.028741358,0.0005050126,0.000069675116,0.000014984548,0.017287457,0.026814245,0.0018619273,0.039012212,0.8837893,0.0005447961],"about_ca_topic_score_codex":0.00027843233,"about_ca_topic_score_gemma":0.0005139799,"teacher_disagreement_score":0.8784521,"about_ca_system_score_codex":0.00005155917,"about_ca_system_score_gemma":0.000056907673,"threshold_uncertainty_score":0.72339904},"labels":[],"label_agreement":null},{"id":"W4402095270","doi":"10.23977/jeis.2024.090306","title":"Research on the path of building smart society from the perspective of big data","year":2024,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perspective (graphical); Big data; Path (computing); Data science; Sociology; Computer science; Architectural engineering; Engineering ethics; Engineering; Artificial intelligence; Data mining","score_opus":0.3590658384373373,"score_gpt":0.46441015289265336,"score_spread":0.10534431445531606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402095270","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":[0.87334216,0.0053625097,0.041504443,0.07428753,0.00038906332,0.00032155498,0.00036055507,0.00001330864,0.0044188905],"genre_scores_gemma":[0.99730504,0.001933691,0.0005836395,0.00013566088,0.000034320805,8.994071e-7,9.2455525e-7,9.661377e-7,0.0000048441616],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99761355,0.00004170173,0.0004930985,0.00011583374,0.0015891305,0.00014665729],"domain_scores_gemma":[0.9957925,0.0020103299,0.00034819345,0.0006563284,0.0011672796,0.000025339186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014741807,0.00004150622,0.00009491617,0.0001893215,0.00033774337,0.0004341395,0.0024859312,0.000029146639,0.000009431314],"category_scores_gemma":[0.0028344288,0.00001740611,0.000043995515,0.002465576,0.0007807389,0.002202149,0.0005033307,0.00042829599,0.0000030637125],"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":[0.0000077715185,0.000011247791,0.00005696317,0.0000019415857,0.000010704031,5.5286264e-8,0.0013488458,0.000035919795,0.0036339057,0.90225786,0.019926423,0.072708346],"study_design_scores_gemma":[0.00017386008,0.00048646762,0.004896071,0.00014630394,0.000017711924,0.000018785207,0.062061075,0.08523611,0.012139143,0.37763664,0.45708978,0.00009806548],"about_ca_topic_score_codex":0.000040323495,"about_ca_topic_score_gemma":0.0000054851275,"teacher_disagreement_score":0.52462125,"about_ca_system_score_codex":0.000060699767,"about_ca_system_score_gemma":0.0006832099,"threshold_uncertainty_score":0.5109246},"labels":[],"label_agreement":null},{"id":"W4402592572","doi":"10.1109/tsc.2024.3463431","title":"Towards Auditable and Privacy-Preserving Online Medical Diagnosis Service Over Cloud","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Services Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"China Postdoctoral Science Foundation; National Natural Science Foundation of China","keywords":"Computer science; Cloud computing; Computer security; Internet privacy; Information privacy","score_opus":0.10680652969072472,"score_gpt":0.3745486295845845,"score_spread":0.2677420998938598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402592572","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":[0.5437464,0.00071084104,0.4300408,0.020843852,0.0011902008,0.00032403404,0.0002463422,0.0012145962,0.0016829259],"genre_scores_gemma":[0.99175835,0.00026908153,0.005762913,0.0016024418,0.00020595234,0.000027877692,0.000008907038,0.00004411053,0.00032037124],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970361,0.00007422826,0.0005776981,0.0008319486,0.0011126722,0.00036737203],"domain_scores_gemma":[0.9973696,0.0012513063,0.000103302984,0.00095742574,0.00011980948,0.00019857106],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008922684,0.0002343776,0.00029109817,0.00035892223,0.0004159231,0.0006272734,0.0016863793,0.00022809848,0.0016592535],"category_scores_gemma":[0.00006548713,0.00018642671,0.00009405204,0.0019882084,0.00007270189,0.000404987,0.00011365869,0.0005240398,0.0003578537],"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":[0.000012384394,0.0002964605,0.00050664553,0.0002294445,0.000102916056,0.000029131732,0.00087704306,0.0028739884,0.00021368057,0.0014907337,0.0063104746,0.9870571],"study_design_scores_gemma":[0.000348211,0.000062053114,0.002647153,0.00068372936,0.000058526763,0.000046690715,0.0016737835,0.82179224,0.0012493957,0.0061353254,0.16489148,0.00041138902],"about_ca_topic_score_codex":0.0007632285,"about_ca_topic_score_gemma":0.0018192147,"teacher_disagreement_score":0.9866457,"about_ca_system_score_codex":0.000039032904,"about_ca_system_score_gemma":0.00007247888,"threshold_uncertainty_score":0.9992534},"labels":[],"label_agreement":null},{"id":"W4402594205","doi":"10.1109/sds60720.2024.00011","title":"Mining and Forecasting Energy Consumption Based on Weather Data","year":2024,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; University of Manitoba","funders":"University of Manitoba","keywords":"Energy consumption; Weather forecasting; Computer science; Consumption (sociology); Meteorology; Engineering; Geography","score_opus":0.5665341613022853,"score_gpt":0.4204674190196236,"score_spread":0.1460667422826617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402594205","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":[0.12817715,0.0011530635,0.7843492,0.018693605,0.00037950778,0.00019646305,0.00051986787,0.0010591081,0.06547205],"genre_scores_gemma":[0.98237157,0.000026425316,0.015969452,0.00034436476,0.000025857687,0.000008319699,0.000041658448,0.000005097933,0.0012072282],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906117,0.000014738795,0.0001700968,0.00041858273,0.00024741204,0.00008802394],"domain_scores_gemma":[0.9980091,0.0010925485,0.00002700143,0.00082857703,0.000018333894,0.000024426548],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006626345,0.00005316957,0.00006517511,0.00012125307,0.00009307312,0.00032239713,0.0005098206,0.00004361099,0.0004455382],"category_scores_gemma":[0.0005134279,0.000033402004,0.000011343019,0.0002618543,0.00005990773,0.0001804067,0.00029718608,0.000038497394,0.000068880334],"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":[0.0000016078378,0.0000055330343,0.00061223516,0.0000017538642,0.0000019016809,0.0000015784523,0.000005796634,0.000008682065,0.00016110668,0.031062081,0.045580525,0.9225572],"study_design_scores_gemma":[0.00004617593,0.000013864308,0.000450435,0.000020970601,0.0000031892398,0.000003278646,0.00014129771,0.6474233,0.00023929958,0.0043846983,0.3472137,0.000059812486],"about_ca_topic_score_codex":0.000022088236,"about_ca_topic_score_gemma":0.000069650065,"teacher_disagreement_score":0.9224974,"about_ca_system_score_codex":0.000005237933,"about_ca_system_score_gemma":0.000013538058,"threshold_uncertainty_score":0.48783308},"labels":[],"label_agreement":null},{"id":"W4403116494","doi":"10.57745/p0khag","title":"Insurance dataset","year":2024,"lang":"en","type":"other","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Business","score_opus":0.07562978095177517,"score_gpt":0.3188520873582011,"score_spread":0.24322230640642592,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403116494","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007090924,0.00459494,0.035182662,0.02080876,0.00030026824,0.00039910176,0.012973812,0.0009499625,0.9247196],"genre_scores_gemma":[0.00619358,0.0011627389,0.023262702,0.0002100131,0.000047742906,0.000097680895,0.0034941665,0.0002601781,0.9652712],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99558026,0.0014009883,0.0005898806,0.0011964553,0.00090842677,0.00032401845],"domain_scores_gemma":[0.9920002,0.0013188373,0.0005022719,0.0054647583,0.0005770678,0.00013684155],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0056237406,0.00031151678,0.0003912206,0.0004910994,0.00016408345,0.0008134002,0.00381255,0.00038846853,0.0030887735],"category_scores_gemma":[0.0038409394,0.00026031735,0.00014274771,0.0013900249,0.00042894256,0.00013024942,0.0014770397,0.00050602085,0.008803916],"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":[6.9349625e-7,0.00007552432,0.0000736359,0.00001788698,0.0000199859,0.0000031729141,0.000115848816,1.6207248e-7,0.00006062406,0.09056272,0.84137076,0.067699],"study_design_scores_gemma":[0.00010853398,1.04049384e-7,0.00014719863,0.00050306256,0.000015058558,0.000007262372,0.00006428418,0.00018604157,0.00080534886,0.019110333,0.9787855,0.0002672316],"about_ca_topic_score_codex":0.0009662035,"about_ca_topic_score_gemma":0.0034543455,"teacher_disagreement_score":0.1374148,"about_ca_system_score_codex":0.000036398877,"about_ca_system_score_gemma":0.00010529821,"threshold_uncertainty_score":0.9999849},"labels":[],"label_agreement":null},{"id":"W4403487475","doi":"10.3233/faia240772","title":"A Federated Large Language Model for Long-Term Time Series Forecasting","year":2024,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Term (time); Series (stratigraphy); Computer science; Time series; Econometrics; Mathematics; Machine learning; Geology; Physics","score_opus":0.203687782524059,"score_gpt":0.3686355930938267,"score_spread":0.1649478105697677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403487475","genre_codex":"methods","genre_gemma":"other","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":[0.00006678706,0.0017683369,0.97623426,0.0012217386,0.00012557366,0.0014771117,0.0018488644,0.00017135336,0.017086],"genre_scores_gemma":[0.04499273,0.0014093388,0.04921169,0.00033415025,0.0007043095,0.003805355,0.0017389857,0.0002014412,0.897602],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975457,0.000006912849,0.00087433413,0.0009199945,0.0003121008,0.00034093665],"domain_scores_gemma":[0.9987063,0.0001941861,0.00024342607,0.00060183014,0.0001724888,0.000081809274],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006035397,0.0002995876,0.00044022046,0.00044211332,0.00038996933,0.00051866646,0.00067094195,0.00038681252,0.00009216339],"category_scores_gemma":[0.0001372923,0.0002658763,0.00013582318,0.00032063713,0.00028584714,0.00019597774,0.00030014323,0.0003719762,0.00032299713],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017774422,0.00003549422,0.000024639268,0.000031566535,0.000025645431,0.000003243398,0.00018812327,0.0001055655,0.000043518306,0.5441998,0.01118661,0.444138],"study_design_scores_gemma":[0.000015524483,0.000018944967,0.0000016817474,0.0000634376,0.00003362114,0.0000042939855,0.00045126537,0.2391506,0.00022397174,0.72348726,0.03629388,0.00025552197],"about_ca_topic_score_codex":0.0000034507716,"about_ca_topic_score_gemma":0.00019606782,"teacher_disagreement_score":0.9270226,"about_ca_system_score_codex":0.000058860915,"about_ca_system_score_gemma":0.0000739214,"threshold_uncertainty_score":0.9999793},"labels":[],"label_agreement":null},{"id":"W4403514561","doi":"10.5267/j.ac.2024.7.001","title":"An application of TOPSIS and BWM for portfolio allocation","year":2024,"lang":"en","type":"article","venue":"Accounting","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Portfolio; TOPSIS; Computer science; Portfolio allocation; Business; Operations research; Engineering; Finance","score_opus":0.12198145361857976,"score_gpt":0.4074572582407403,"score_spread":0.28547580462216054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403514561","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":[0.5878861,0.00042446543,0.40880224,0.0016753832,0.00007213874,0.00033455747,0.000055376626,0.00015953065,0.0005901799],"genre_scores_gemma":[0.9919109,0.000022449074,0.00780156,0.000050650913,0.000052109488,0.00008316451,0.000026265383,0.000005344407,0.00004760898],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991919,0.0000051257175,0.00025870017,0.00027734882,0.0001862703,0.00008068378],"domain_scores_gemma":[0.9990767,0.0002859179,0.000091947666,0.0003959065,0.00013435945,0.000015145719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008841316,0.000045876634,0.00007963273,0.00012315318,0.00007735537,0.00018487404,0.00030856015,0.000053231666,0.000012275399],"category_scores_gemma":[0.0003206526,0.0000361287,0.000022987544,0.00047174917,0.00004344836,0.00042584972,0.00005637197,0.000037129215,0.000013572175],"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":[0.0000017572596,0.000010823348,0.0028626497,0.000012964064,0.0000036299389,4.646081e-8,0.000050586495,0.000008398148,0.016510766,0.096125074,0.0022525277,0.8821608],"study_design_scores_gemma":[0.00014740991,0.0000646372,0.036389608,0.00003320954,0.000041603835,0.000007415912,0.0022570535,0.2200553,0.01710412,0.26264232,0.46101782,0.00023949696],"about_ca_topic_score_codex":0.000054904183,"about_ca_topic_score_gemma":0.00001990558,"teacher_disagreement_score":0.8819213,"about_ca_system_score_codex":0.0000069425246,"about_ca_system_score_gemma":0.00001603857,"threshold_uncertainty_score":0.17827447},"labels":[],"label_agreement":null},{"id":"W4404988426","doi":"10.14778/3749646.3749657","title":"TabulaX: Leveraging Large Language Models for Multi-Class Table Transformations","year":2025,"lang":"en","type":"preprint","venue":"Proceedings of the VLDB Endowment","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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 Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Table (database); Class (philosophy); Computer science; Programming language; Natural language processing; Theoretical computer science; Artificial intelligence; Database","score_opus":0.20772441500396746,"score_gpt":0.38232798555009745,"score_spread":0.17460357054613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404988426","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":[0.0804909,0.0037007448,0.7906835,0.03810385,0.0021142354,0.01572897,0.024625953,0.0010228312,0.043529022],"genre_scores_gemma":[0.94836456,0.00029950135,0.0420296,0.00038330173,0.00006541371,0.0022644235,0.00008020388,0.00002424962,0.006488776],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972925,0.000007665031,0.00087402586,0.0006501473,0.00077464787,0.00040102378],"domain_scores_gemma":[0.997761,0.00017859811,0.0006476376,0.00072055997,0.00064054225,0.000051674466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014522112,0.00027074906,0.00046269485,0.00028344453,0.0003878936,0.00029443775,0.003320588,0.0002453949,0.000026220983],"category_scores_gemma":[0.0006134996,0.00017857902,0.00032747473,0.0006769834,0.0000908163,0.00031613387,0.0021580865,0.00044311065,0.0000065193312],"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":[0.000070237445,0.0011960123,0.00048756783,0.0014459601,0.00038693528,2.2990461e-7,0.011041853,0.01306438,0.012276915,0.69742894,0.20822413,0.05437686],"study_design_scores_gemma":[0.0015865577,0.0000331223,0.000109914516,0.0005973117,0.00020420711,0.00000269647,0.012634895,0.4488056,0.08868796,0.31053224,0.13624528,0.00056020985],"about_ca_topic_score_codex":0.000098009274,"about_ca_topic_score_gemma":0.00003123651,"teacher_disagreement_score":0.8678736,"about_ca_system_score_codex":0.00011964114,"about_ca_system_score_gemma":0.00012937322,"threshold_uncertainty_score":0.7282241},"labels":[],"label_agreement":null},{"id":"W4405025969","doi":"10.21810/jicw.v7i2.6735","title":"In-between Spaces: Unconventional Yet Essential Considerations for Defence and Security","year":2024,"lang":"en","type":"article","venue":"The Journal of Intelligence Conflict and Warfare","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada","funders":"","keywords":"Liminality; Context (archaeology); Generative grammar; Computer science; Order (exchange); Epistemology; Computer security; Point (geometry); Cognitive science; Environmental ethics; Sociology; Psychology; Geography; Business; Mathematics; Artificial intelligence; Philosophy; Archaeology","score_opus":0.2289600932555739,"score_gpt":0.417539378934562,"score_spread":0.1885792856789881,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405025969","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":[0.81723905,0.012866297,0.1179343,0.05031078,0.00056143623,0.00048712577,0.00034178555,0.000030798146,0.00022841296],"genre_scores_gemma":[0.9976799,0.0013952411,0.00062490895,0.00012341946,0.000085643784,0.00000510571,0.0000014700756,0.0000036072176,0.000080698315],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99889606,0.000050454266,0.00050858344,0.00014702827,0.00028094434,0.0001168986],"domain_scores_gemma":[0.9960197,0.003351199,0.00015162982,0.00017676466,0.00024910795,0.0000515895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001789897,0.0000817682,0.00017328592,0.00016412108,0.00016966856,0.00031782695,0.00032491478,0.000062628256,0.00010732665],"category_scores_gemma":[0.0011981584,0.00004669703,0.000054780343,0.0002888176,0.0003129892,0.00031761217,0.000106013904,0.0002241292,0.000007909516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000102921476,0.000083243816,0.0080568325,0.00010398092,0.00016724475,0.000033774384,0.013075556,0.00018204756,0.0015557992,0.8168486,0.057819113,0.101970896],"study_design_scores_gemma":[0.000105221334,0.00012431614,0.001391465,0.000120911296,0.000053976066,0.00021814564,0.0068129906,0.0023139582,0.0040316135,0.89142567,0.09328186,0.00011990353],"about_ca_topic_score_codex":0.000023153405,"about_ca_topic_score_gemma":0.000054750755,"teacher_disagreement_score":0.18044084,"about_ca_system_score_codex":0.00001082094,"about_ca_system_score_gemma":0.000078728546,"threshold_uncertainty_score":0.30648127},"labels":[],"label_agreement":null},{"id":"W4405113927","doi":"10.1016/j.procs.2024.11.094","title":"Application of Generative Artificial Intelligence in Minimizing Cyber Attacks on Vehicular Networks","year":2024,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Generative grammar; Artificial intelligence; Computer security; Machine learning","score_opus":0.1429528841429706,"score_gpt":0.38131346463838195,"score_spread":0.23836058049541134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405113927","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":[0.042491812,0.00015814831,0.9545465,0.0019734171,0.00030872025,0.0002680182,0.000005863173,0.00008504634,0.00016243916],"genre_scores_gemma":[0.95462406,0.000020581452,0.0450001,0.00015154446,0.0001272308,0.00006302704,0.000002466383,0.0000049215764,0.00000605541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974927,0.000023920564,0.00054158334,0.00086419005,0.0008080304,0.00026958963],"domain_scores_gemma":[0.99849284,0.000472242,0.000113511276,0.00063529704,0.0002272721,0.000058823603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018347722,0.000117721516,0.00016950109,0.000493853,0.00013382803,0.00037934186,0.0016123154,0.00007360684,0.000007291605],"category_scores_gemma":[0.00030668487,0.00008774924,0.0000441135,0.0045223595,0.0005435682,0.0004201102,0.0004434449,0.00021760707,0.00009683336],"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":[0.0000029199691,0.000041839594,0.00026124786,0.000004162463,0.0000014104826,0.0000018797296,0.0002561525,0.03196745,0.0013401475,0.13553172,0.0003362576,0.8302548],"study_design_scores_gemma":[0.000011711398,0.000042012172,0.0010162389,0.000032071483,0.0000015631698,0.0000029524392,0.00007063385,0.9389263,0.009538343,0.0489906,0.0012698721,0.00009772068],"about_ca_topic_score_codex":0.000010841545,"about_ca_topic_score_gemma":0.000016238258,"teacher_disagreement_score":0.91213226,"about_ca_system_score_codex":0.000053448843,"about_ca_system_score_gemma":0.0001301351,"threshold_uncertainty_score":0.3658002},"labels":[],"label_agreement":null},{"id":"W4405363817","doi":"10.1016/j.enbuild.2024.115177","title":"Explaining deep learning-based anomaly detection in energy consumption data by focusing on contextually relevant data","year":2024,"lang":"en","type":"article","venue":"Energy and Buildings","topic":"Big Data Technologies and Applications","field":"Decision Sciences","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":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada","keywords":"Anomaly detection; Anomaly (physics); Consumption (sociology); Energy consumption; Deep learning; Energy (signal processing); Computer science; Artificial intelligence; Data science; Machine learning; Engineering; Physics; Sociology; Statistics; Mathematics; Social science; Electrical engineering","score_opus":0.16740959644073536,"score_gpt":0.3594454531349252,"score_spread":0.19203585669418985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405363817","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":[0.28355274,0.006733546,0.705047,0.0030420762,0.00034214067,0.00009366301,0.00033667154,0.00048294428,0.0003692117],"genre_scores_gemma":[0.9969937,0.00084911275,0.0011603087,0.00026147006,0.00005727506,0.000015330972,0.0004973434,0.000016090362,0.00014935054],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976974,0.000096352785,0.00042565062,0.001130409,0.00040539211,0.0002448019],"domain_scores_gemma":[0.9973396,0.0011310258,0.00012740723,0.0013063942,0.000037364247,0.00005821449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001433981,0.00016305795,0.00019628314,0.00034684167,0.00027618342,0.0005271299,0.0013186478,0.00016628062,0.00005360673],"category_scores_gemma":[0.0010800564,0.00013254558,0.000021366279,0.0006288717,0.00014357928,0.0007855203,0.00080715114,0.00023989726,0.000013398424],"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":[0.000035139972,0.000030738593,0.00031623212,0.0000050321496,0.000010053187,0.000011437727,0.000027397246,0.00047778388,0.009089825,0.015642865,0.0054435837,0.9689099],"study_design_scores_gemma":[0.00020677954,0.000074759846,0.0001893387,0.00008395495,0.000010328717,0.00001001957,0.00019673584,0.3314343,0.006706523,0.0016052413,0.65930593,0.00017605264],"about_ca_topic_score_codex":0.0005390728,"about_ca_topic_score_gemma":0.0017585075,"teacher_disagreement_score":0.96873385,"about_ca_system_score_codex":0.000036267655,"about_ca_system_score_gemma":0.000031963846,"threshold_uncertainty_score":0.54050523},"labels":[],"label_agreement":null},{"id":"W4406215577","doi":"10.1007/978-3-031-78586-3_14","title":"Post-pandemic Science &amp; Technology Education: Ongoing Challenges to Societies","year":2024,"lang":"en","type":"book-chapter","venue":"Contemporary trends and issues in science education","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Pandemic; Political science; Coronavirus disease 2019 (COVID-19); Engineering ethics; Engineering; Medicine","score_opus":0.22849853467110673,"score_gpt":0.43663186259473946,"score_spread":0.20813332792363273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406215577","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006511643,0.08444463,0.000022585697,0.16887814,0.0027090425,0.0005007647,0.00010435538,0.00032309166,0.73650575],"genre_scores_gemma":[0.27927938,0.0050995806,0.0030131578,0.0007129313,0.00034648052,0.00017745624,0.00004948259,0.000035941463,0.7112856],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99501514,0.000014114663,0.0008814724,0.0021310456,0.0014952755,0.0004629321],"domain_scores_gemma":[0.9961397,0.00017615223,0.00036280227,0.0019314347,0.0011396087,0.00025032318],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0033267718,0.00040074627,0.0005073572,0.006653281,0.00064497645,0.0010641608,0.0033101642,0.00037740843,0.00015478268],"category_scores_gemma":[0.0013123606,0.00033255373,0.00007923016,0.0036414627,0.0042910217,0.0014066658,0.001400097,0.0006028521,0.00054016424],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002409847,0.00004385024,0.00018998912,0.000014149629,0.0000024345413,3.717694e-7,0.0010895123,2.8890813e-7,0.00037254283,0.37360615,0.031173969,0.5935043],"study_design_scores_gemma":[0.000032391166,0.00006636819,0.00092229457,0.00030515427,0.000006130274,0.000019117382,0.0060436437,0.00000826932,0.00005864275,0.24754104,0.74468625,0.00031067315],"about_ca_topic_score_codex":0.00006863823,"about_ca_topic_score_gemma":0.00017925684,"teacher_disagreement_score":0.7135123,"about_ca_system_score_codex":0.00036539207,"about_ca_system_score_gemma":0.0073568732,"threshold_uncertainty_score":0.9999728},"labels":[],"label_agreement":null},{"id":"W4406218525","doi":"10.18280/ts.410603","title":"Real-Time Monitoring and Image Recognition System for Abnormal Activities in Financial Markets Based on Deep Learning","year":2024,"lang":"en","type":"article","venue":"Traitement du signal","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Artificial intelligence; Computer science; Image (mathematics); Business; Computer vision; Finance","score_opus":0.07261815566400061,"score_gpt":0.31790110216115885,"score_spread":0.24528294649715826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406218525","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":[0.9810651,0.000049498933,0.016220305,0.00037910067,0.00013513377,0.0004673171,0.00014472853,0.00025453608,0.0012842794],"genre_scores_gemma":[0.9962306,0.000019567022,0.003261011,0.000007422491,0.00012517086,0.00024752656,0.000030509123,0.000010285254,0.000067903806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868536,0.000064179934,0.00031882993,0.0003746103,0.00035131248,0.0002057208],"domain_scores_gemma":[0.9986652,0.0010539745,0.00006822601,0.00013734982,0.000040513434,0.000034713117],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013497203,0.00011383418,0.00015256825,0.00028588195,0.0001696849,0.00032763576,0.0001912029,0.00007518367,0.000089991794],"category_scores_gemma":[0.00019013562,0.00009474224,0.000049843395,0.00031689796,0.000049674516,0.00031676877,0.00004767225,0.00014618033,0.000040290965],"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":[0.00022747659,0.0000706967,0.0010622088,0.0001207818,0.000008706695,0.000020160116,0.00020750472,0.00026192886,0.035991095,0.0008566818,0.001104625,0.9600681],"study_design_scores_gemma":[0.0032244415,0.0012791296,0.10148342,0.00183404,0.000091365284,0.000026089207,0.008326841,0.74940366,0.103073746,0.007657708,0.022418704,0.0011808843],"about_ca_topic_score_codex":0.000014262795,"about_ca_topic_score_gemma":0.000004674703,"teacher_disagreement_score":0.9588873,"about_ca_system_score_codex":0.000074658106,"about_ca_system_score_gemma":0.00003115717,"threshold_uncertainty_score":0.38634762},"labels":[],"label_agreement":null},{"id":"W4407597021","doi":"10.23987/sts.152099","title":"Calvert Jane (2024) A Place of Science and Technology Studies: Observation, Intervention and Collaboration","year":2025,"lang":"en","type":"article","venue":"Science & Technology Studies","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Intervention (counseling); Psychology; Sociology","score_opus":0.1558318137862283,"score_gpt":0.45256897464784035,"score_spread":0.29673716086161206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407597021","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":[0.9091969,0.015152093,0.0011973567,0.07277455,0.00053879997,0.0005639769,0.000023658926,0.00029149896,0.00026116613],"genre_scores_gemma":[0.9879353,0.0026710534,0.008276619,0.00013007343,0.000004911204,0.00016994869,5.161351e-7,0.0000038524627,0.0008077371],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9966958,0.000024841258,0.00077186676,0.0011606568,0.0009272111,0.00041962112],"domain_scores_gemma":[0.9925305,0.0004305697,0.00041864882,0.0011017676,0.005478789,0.00003967703],"candidate_categories":["metaresearch","bibliometrics","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.004903954,0.00019339794,0.00050290383,0.004999793,0.0016102471,0.00014203382,0.0018775064,0.00019129261,0.0000027021608],"category_scores_gemma":[0.037185326,0.00014581988,0.00002143274,0.0370948,0.038666144,0.0009157409,0.0032418238,0.00023891049,0.0000054523443],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014934219,0.00009942571,0.052803334,0.00005777757,0.000078157966,0.0000018921546,0.0009388359,0.000004422587,0.03383664,0.6660385,0.011138917,0.23498714],"study_design_scores_gemma":[0.00061138486,0.00036467353,0.008191551,0.00025901472,0.0000605572,0.000017562177,0.2346327,0.0005486491,0.05835573,0.6589993,0.037657835,0.00030102194],"about_ca_topic_score_codex":0.000015079807,"about_ca_topic_score_gemma":0.0002492755,"teacher_disagreement_score":0.23468612,"about_ca_system_score_codex":0.00022788325,"about_ca_system_score_gemma":0.00045674795,"threshold_uncertainty_score":0.9996895},"labels":[],"label_agreement":null},{"id":"W4408581329","doi":"10.1515/9783111488738","title":"Data, Governance and Narrative","year":2025,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Narrative; Corporate governance; Political science; Business; Literature; Art; Finance","score_opus":0.2804800969015785,"score_gpt":0.4116678361941457,"score_spread":0.13118773929256722,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408581329","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000029309037,0.001253687,0.0029291157,0.008234324,0.000102956656,0.0001817667,0.005395644,0.00008834777,0.9818112],"genre_scores_gemma":[0.000061118015,0.0007936034,0.0028092829,0.00040490174,0.0000381269,0.000010555812,0.00031546748,0.0000040502528,0.9955629],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99828297,0.000011094377,0.00031313527,0.00080256775,0.00048777304,0.00010243923],"domain_scores_gemma":[0.99611574,0.0006882814,0.00020878269,0.0028564911,0.00010199284,0.000028714881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046032266,0.00013088828,0.0002501963,0.000059681777,0.00014877373,0.00020102787,0.0030074983,0.00023040576,0.0007297367],"category_scores_gemma":[0.0010969001,0.00008627338,0.000022805862,0.00019228512,0.00022343453,0.0002042579,0.0028107546,0.00024233728,0.00026412765],"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":[4.443012e-7,0.0000019942615,0.000002009614,0.000001220132,0.000004299698,4.302986e-7,0.0000069315442,2.9043022e-8,3.112851e-7,0.2565066,0.6413683,0.102107435],"study_design_scores_gemma":[0.000028014327,0.0000046066493,0.00005457327,0.0000157326,0.0000050618087,8.8623705e-7,0.00013492191,0.00006731847,0.0000023678333,0.23962373,0.75998795,0.00007485511],"about_ca_topic_score_codex":0.000015317177,"about_ca_topic_score_gemma":0.00028858945,"teacher_disagreement_score":0.11861962,"about_ca_system_score_codex":0.000027063274,"about_ca_system_score_gemma":0.00025980786,"threshold_uncertainty_score":0.7990105},"labels":[],"label_agreement":null},{"id":"W4408739103","doi":"10.23977/jaip.2025.080111","title":"The Practice and Application of Machine Learning in Data Analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Data science; Machine learning; Artificial intelligence","score_opus":0.22253898466643873,"score_gpt":0.4846734670592484,"score_spread":0.2621344823928097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408739103","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":[0.003572954,0.0021978107,0.91899216,0.07396812,0.000096159776,0.0001416733,0.000014174824,0.00000863917,0.0010082852],"genre_scores_gemma":[0.9743489,0.0028822676,0.02245688,0.00020489458,0.000028073358,0.0000036589988,0.0000035784337,0.0000028772572,0.000068844296],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973516,0.00036270477,0.0013060268,0.00025575387,0.00060726755,0.000116673255],"domain_scores_gemma":[0.98069185,0.015504455,0.0018532815,0.0009472626,0.0009717471,0.00003138864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.013151901,0.00007099716,0.00023807804,0.00048136653,0.000214277,0.00026291312,0.0016451791,0.00006395016,0.000008123819],"category_scores_gemma":[0.0856035,0.000044723303,0.000050870487,0.0036243529,0.00020939899,0.0013646205,0.0004897413,0.00052976795,0.000009234403],"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":[0.00019757957,0.00014955767,0.0014181383,0.0000018712984,0.00013222772,0.0000028577615,0.0001563092,0.0025194925,0.0005324294,0.07059322,0.00032119264,0.9239751],"study_design_scores_gemma":[0.00004003791,0.00008487726,0.0011615409,0.000015490035,0.00058689073,0.00003610939,0.027651642,0.27227044,0.0023006923,0.086424366,0.60933465,0.000093284194],"about_ca_topic_score_codex":0.00031404398,"about_ca_topic_score_gemma":0.00071518985,"teacher_disagreement_score":0.97077596,"about_ca_system_score_codex":0.000023233744,"about_ca_system_score_gemma":0.000105134146,"threshold_uncertainty_score":0.9220989},"labels":[],"label_agreement":null},{"id":"W4408926663","doi":"10.61091/jcmcc125-17","title":"Machine learning and combinatorial analysis-based recognition of sports activity: An investigation using SVM and KNN classifiers","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Support vector machine; Artificial intelligence; Pattern recognition (psychology); Machine learning; Computer science","score_opus":0.09824008008944138,"score_gpt":0.35106266691198096,"score_spread":0.25282258682253955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408926663","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":[0.983793,0.0002150521,0.012764302,0.00022581554,0.0026098,0.00024448073,0.000011267965,0.000033353528,0.000102931524],"genre_scores_gemma":[0.99362457,0.0000657248,0.0060666422,0.000015554433,0.00020149717,0.0000016152621,0.0000068981885,0.000014672711,0.0000028243114],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9965942,0.0002834798,0.0014486555,0.00041038962,0.0010183472,0.00024491665],"domain_scores_gemma":[0.99473166,0.0016563865,0.0021814588,0.00034586532,0.0009007604,0.00018387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043612393,0.00027340365,0.001046302,0.0010071521,0.0004785176,0.00040957096,0.00040020506,0.00028171984,0.0000056338317],"category_scores_gemma":[0.001954294,0.00023646622,0.00015456647,0.0017609634,0.00034353626,0.0003875319,0.00031459655,0.00058889424,1.7957241e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051550765,0.0009941851,0.046786904,0.00031810108,0.00064408255,0.000015717409,0.0009730599,0.00034418658,0.007835835,0.85016453,0.00008973939,0.09131817],"study_design_scores_gemma":[0.0030256743,0.00046096637,0.0020950579,0.00025833512,0.00062343077,0.000013379979,0.00077177095,0.1456159,0.0022036189,0.8445164,0.00016505727,0.00025037353],"about_ca_topic_score_codex":0.000041820284,"about_ca_topic_score_gemma":0.0000019396227,"teacher_disagreement_score":0.14527173,"about_ca_system_score_codex":0.00006299009,"about_ca_system_score_gemma":0.00019995753,"threshold_uncertainty_score":0.96428126},"labels":[],"label_agreement":null},{"id":"W4409337065","doi":"10.9734/jerr/2025/v27i41471","title":"Data-driven Insights Machine Learning Approaches for Netflix Content Analysis and Visualization","year":2025,"lang":"en","type":"article","venue":"Journal of Engineering Research and Reports","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":3,"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":"","keywords":"Computer science; Visualization; Content (measure theory); Data science; Information retrieval; Machine learning; Artificial intelligence; Mathematics","score_opus":0.5210663781089064,"score_gpt":0.4604436965248431,"score_spread":0.06062268158406331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409337065","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":[0.39012575,0.005306226,0.60296655,0.0011382134,0.00009039971,0.0002417538,0.00002270219,0.00002390655,0.00008450177],"genre_scores_gemma":[0.9953995,0.0005369141,0.0037135163,0.000004334655,0.000030198995,0.000006249237,0.000028823075,0.000003629465,0.0002768532],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99858874,0.000026557303,0.00054149947,0.00023867477,0.00046963512,0.00013492232],"domain_scores_gemma":[0.99819785,0.0006911566,0.0002213516,0.00037639355,0.00044070053,0.00007253759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030643807,0.00005981548,0.00023215367,0.0010142497,0.00016518816,0.00023121008,0.0002948591,0.000056816054,0.000002490905],"category_scores_gemma":[0.004669978,0.000038227583,0.0000398756,0.0012947448,0.00007019643,0.00023230976,0.0003332302,0.00023596396,1.109913e-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":[0.00023211684,0.00064444024,0.409878,0.00036162988,0.0037761983,0.000413144,0.00086365856,0.12136118,0.018786777,0.057562303,0.020029036,0.36609152],"study_design_scores_gemma":[0.00035667035,0.0002694874,0.060048115,0.00007693752,0.00015908918,0.00013905844,0.001065674,0.79334486,0.0008330217,0.009327455,0.13423803,0.0001416208],"about_ca_topic_score_codex":0.00001520544,"about_ca_topic_score_gemma":0.000023597056,"teacher_disagreement_score":0.67198366,"about_ca_system_score_codex":0.000015454774,"about_ca_system_score_gemma":0.0000422923,"threshold_uncertainty_score":0.55907375},"labels":[],"label_agreement":null},{"id":"W4409603809","doi":"10.61091/jcmcc127b-184","title":"Research on Real-Time Processing and Risk Management Methods of Enterprise Financial Big Data Based on Distributed Computing Framework","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Finance; Computer science; Data science; Business; Data mining","score_opus":0.15561907467103014,"score_gpt":0.4459331289446279,"score_spread":0.29031405427359774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409603809","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":[0.39907256,0.00028567904,0.59049207,0.0007203494,0.006267572,0.00077264686,0.00010368537,0.00006961808,0.002215811],"genre_scores_gemma":[0.90332663,0.00013453937,0.09609796,0.000019746123,0.0003915799,0.0000021091073,0.0000064292403,0.000015904394,0.0000051184447],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9951395,0.0006405396,0.001726007,0.0005613849,0.0015602633,0.00037232027],"domain_scores_gemma":[0.98605675,0.00996131,0.0016823586,0.001222273,0.00095148815,0.00012585183],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016580034,0.00025865945,0.0008938391,0.00080622593,0.00071644224,0.00050964445,0.0020139925,0.00025599016,0.0000030241808],"category_scores_gemma":[0.00907462,0.00020104056,0.0001029558,0.0019067845,0.00030355147,0.00013604286,0.0018140293,0.0010589364,0.0000018093398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026039899,0.0009149113,0.00039070376,0.00018471133,0.00006921624,0.0000097665215,0.00017776946,0.00022454075,0.00006854463,0.6625433,0.002144232,0.33301193],"study_design_scores_gemma":[0.0019488396,0.0005976276,0.00082484656,0.0016774525,0.000098756675,0.0000038189887,0.0006938262,0.1120223,0.00033744748,0.87919384,0.0024163423,0.00018489892],"about_ca_topic_score_codex":0.000011718224,"about_ca_topic_score_gemma":2.2389544e-7,"teacher_disagreement_score":0.50425404,"about_ca_system_score_codex":0.000079906014,"about_ca_system_score_gemma":0.00020108047,"threshold_uncertainty_score":0.99927235},"labels":[],"label_agreement":null},{"id":"W4409785123","doi":"10.61091/jcmcc127b-466","title":"A Study of Human-Computer Interaction in Evaluating Students’ Emotional Behavior and Educational Management under Big Data","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Psychology; Big data; Applied psychology; Data science; Human–computer interaction; Data mining","score_opus":0.26248944465343654,"score_gpt":0.4691247796666692,"score_spread":0.20663533501323267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409785123","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":[0.9911381,0.000061710234,0.0028417497,0.00028950817,0.005056016,0.00046849565,0.0000041717153,0.000007908793,0.00013235143],"genre_scores_gemma":[0.9960167,0.0000117369,0.003611747,0.000011666239,0.00032163956,0.000006697728,0.0000036604342,0.000007281646,0.000008898904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9964804,0.00015162013,0.0016411592,0.00035230498,0.0012234054,0.00015108423],"domain_scores_gemma":[0.99640685,0.001262924,0.0011265188,0.00066283677,0.0004901452,0.00005070758],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004272465,0.00016050799,0.00051727623,0.00061270176,0.00022481642,0.0003345395,0.0015486719,0.00008410753,0.000005251744],"category_scores_gemma":[0.0006127509,0.00013434917,0.00004680303,0.0007060433,0.000078932906,0.00025140375,0.0024454265,0.00033193876,6.427157e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000069553316,0.008430995,0.048094377,0.000113616385,0.0002257761,0.00000957143,0.0011801238,0.000102076745,0.00021476214,0.8710122,0.00091880525,0.06962812],"study_design_scores_gemma":[0.005537362,0.00081318244,0.117785044,0.00044806759,0.00016127784,0.000024241757,0.008328057,0.0038742418,0.000027298342,0.86276317,0.000067735076,0.00017034468],"about_ca_topic_score_codex":0.000017870385,"about_ca_topic_score_gemma":0.0000051792586,"teacher_disagreement_score":0.06969067,"about_ca_system_score_codex":0.00006740053,"about_ca_system_score_gemma":0.00007893408,"threshold_uncertainty_score":0.5478601},"labels":[],"label_agreement":null},{"id":"W4409787914","doi":"10.61091/jcmcc127a-472","title":"Research on intelligent financial statement analysis and anomaly identification technology based on machine learning","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Identification (biology); Financial statement; Financial statement analysis; Statement (logic); Anomaly (physics); Computer science; Artificial intelligence; Accounting; Business; Financial analysis; Epistemology; Philosophy; Physics","score_opus":0.1043036350811106,"score_gpt":0.4084930354796187,"score_spread":0.30418940039850806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409787914","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":[0.92050153,0.0002250759,0.07245905,0.0030357677,0.002736222,0.0003809015,0.00000951338,0.00005270164,0.0005992455],"genre_scores_gemma":[0.99772054,0.000057613113,0.0020259682,0.000032015985,0.00011961717,0.000006080739,0.000002737765,0.000009026805,0.000026409876],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99614197,0.00024473923,0.0015560776,0.00041430382,0.0013504643,0.00029245354],"domain_scores_gemma":[0.9942824,0.0028911636,0.0010384537,0.0005525063,0.0011439577,0.00009150143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00906813,0.00019638112,0.0006562291,0.0027396083,0.0006795697,0.0005261774,0.0008627456,0.0002158517,0.000009508437],"category_scores_gemma":[0.0057746847,0.00015256417,0.00014086544,0.0037987602,0.00022081318,0.00010031283,0.000440607,0.0009843097,0.000005933603],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000113158174,0.0005761102,0.002210662,0.000027882163,0.00010220368,0.00000607851,0.00010459115,0.0007843875,0.00019077805,0.96148926,0.00045892465,0.033935957],"study_design_scores_gemma":[0.0014349462,0.001073642,0.0017951163,0.00017710659,0.00014195703,0.0000032148762,0.00087415666,0.0769381,0.0024003955,0.9085038,0.0064870343,0.0001705486],"about_ca_topic_score_codex":0.000013830322,"about_ca_topic_score_gemma":0.000002309276,"teacher_disagreement_score":0.07721901,"about_ca_system_score_codex":0.0001226918,"about_ca_system_score_gemma":0.00015244912,"threshold_uncertainty_score":0.6913254},"labels":[],"label_agreement":null},{"id":"W4409794953","doi":"10.61091/jcmcc127b-460","title":"Artificial Intelligence-based Financial Big Data Information Security and Local Risk Prevention and Control","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Control (management); Big data; Computer science; Risk prevention; Security controls; Business; Finance; Computer security; Artificial intelligence; Risk analysis (engineering); Data mining","score_opus":0.09069703440964802,"score_gpt":0.34080531989619994,"score_spread":0.25010828548655195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409794953","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":[0.32993364,0.00029167495,0.66283005,0.0012509295,0.0051475787,0.0003539695,0.00005186326,0.000029716724,0.00011057233],"genre_scores_gemma":[0.99689436,0.000070173664,0.0026264885,0.000042203388,0.0003531835,0.000002048361,0.000005743582,0.0000050387903,7.373586e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9971496,0.00014926052,0.0015627735,0.00026326257,0.00067519123,0.00019990951],"domain_scores_gemma":[0.99553216,0.0018865502,0.0013669374,0.0005283079,0.00058310555,0.000102952254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050685,0.00018738581,0.0005600028,0.00035267478,0.00044463525,0.0006637657,0.0007939875,0.00020984634,0.0000023037342],"category_scores_gemma":[0.0059088077,0.00014991486,0.00006539822,0.000581025,0.00027296122,0.0005430959,0.0006399817,0.00048598912,0.0000016107808],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009651514,0.00018068317,0.00028712576,0.000045207962,0.000026696287,0.0000011566217,0.00017806827,0.000025464311,0.000014136501,0.6680298,0.00040508414,0.33071008],"study_design_scores_gemma":[0.001024816,0.0002758813,0.00031711353,0.000125916,0.00009103867,0.000009821921,0.000752188,0.07784655,0.00020226144,0.91688544,0.0023396371,0.00012936145],"about_ca_topic_score_codex":0.000018675639,"about_ca_topic_score_gemma":0.0000042118663,"teacher_disagreement_score":0.6669607,"about_ca_system_score_codex":0.000034026416,"about_ca_system_score_gemma":0.00024718663,"threshold_uncertainty_score":0.7073822},"labels":[],"label_agreement":null},{"id":"W4410411773","doi":"10.1016/j.ijrobp.2024.12.047","title":"Which Way to (INDI)GO?","year":2025,"lang":"en","type":"editorial","venue":"International Journal of Radiation Oncology*Biology*Physics","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Psychology; Computer science","score_opus":0.06531720183050992,"score_gpt":0.41138397248857694,"score_spread":0.346066770658067,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410411773","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018250543,0.00047410413,0.05520137,0.02389808,0.90973884,0.00048653086,0.0032344586,0.00013450351,0.0050070845],"genre_scores_gemma":[0.032742053,0.0023638082,0.012409561,0.0017872361,0.9452571,0.000113627924,0.0014526712,0.00008260619,0.0037913257],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939135,0.00041554702,0.0023820675,0.0008443644,0.0019985335,0.00044600086],"domain_scores_gemma":[0.98177,0.0067369025,0.0034359621,0.00095218024,0.006887219,0.0002177284],"candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0034872068,0.00045098423,0.0011576057,0.0009876844,0.00020976007,0.00035393043,0.006369657,0.0018280107,0.00020096697],"category_scores_gemma":[0.024125416,0.00036662052,0.00046318426,0.0014382099,0.00022892396,0.00048240638,0.00094089785,0.0020920627,0.0006894725],"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":[0.00008185925,0.00015678347,0.001141909,0.000002474245,0.0002478159,0.000006165543,0.00008981425,0.0001995215,0.00010936957,0.011448989,0.73502827,0.25148705],"study_design_scores_gemma":[0.001123845,0.00041093392,0.00049855415,0.00006142811,0.00007854352,0.00001088622,0.0000903257,0.00019648515,0.0002560135,0.08259897,0.9143883,0.0002857085],"about_ca_topic_score_codex":0.00004606359,"about_ca_topic_score_gemma":0.00010315972,"teacher_disagreement_score":0.25120133,"about_ca_system_score_codex":0.0012332957,"about_ca_system_score_gemma":0.0021599545,"threshold_uncertainty_score":0.9998786},"labels":[],"label_agreement":null},{"id":"W4411097270","doi":"10.1007/978-981-96-2647-2","title":"Data Science and Applications","year":2025,"lang":"en","type":"book","venue":"Lecture notes in networks and systems","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Leibniz-Rechenzentrum; Leibniz-Gemeinschaft; SRM Institute of Science and Technology; Malaviya National Institute of Technology, Jaipur; Indian Institute of Technology Gandhinagar; BMS College of Engineering; Indian Institute of Technology Ropar; Jaypee University of Information Technology; Bayerische Akademie der Wissenschaften; Chandigarh University; National Institute of Technology, Silchar; Taibah University; Anna University; Indian Institute of Technology Roorkee; Université Sidi Mohamed Ben Abdellah; University of Hong Kong; Government of Canada; Gandhi Institute of Technology and Management; Foreign Affairs and International Trade Canada; Charotar University of Science and Technology; Maulana Azad National Institute of Technology; National Institute of Technology Warangal; Imperial College London; Florida International University","keywords":"Computer science","score_opus":0.15253152451517685,"score_gpt":0.3678227501243882,"score_spread":0.21529122560921135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411097270","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":[0.000014579446,0.05839735,0.858326,0.0018264031,0.0006453349,0.0021151328,0.0013259327,0.00014463479,0.07720464],"genre_scores_gemma":[0.6880552,0.05027013,0.00797458,0.0042021065,0.007862845,0.0030259122,0.0042957743,0.00023229819,0.23408116],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687177,0.000040876217,0.00063200947,0.0013851611,0.0007613251,0.000308852],"domain_scores_gemma":[0.99446505,0.0019685826,0.00028328365,0.0029353623,0.00026543107,0.00008230743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030517848,0.00023660577,0.0004924683,0.00045813722,0.0003893884,0.0008959725,0.0028995876,0.00050415006,0.000005790988],"category_scores_gemma":[0.0013632148,0.00016966759,0.000019929137,0.0013873123,0.00087413733,0.00022636131,0.0021602404,0.0005975455,0.0000064856786],"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":[0.000003830944,0.000016337495,0.00039850434,0.0000680398,0.000015593792,0.0000027912322,0.00001961357,0.0030821105,0.0000048058205,0.10335505,0.09128085,0.80175245],"study_design_scores_gemma":[0.00006864252,0.000008619781,0.00009448038,0.00014658368,0.000014880487,0.000011871186,0.000015901214,0.07820896,4.2792314e-7,0.04183349,0.87941635,0.0001798203],"about_ca_topic_score_codex":0.00005159403,"about_ca_topic_score_gemma":0.00030224086,"teacher_disagreement_score":0.8503514,"about_ca_system_score_codex":0.0000788226,"about_ca_system_score_gemma":0.00040650222,"threshold_uncertainty_score":0.86398834},"labels":[],"label_agreement":null},{"id":"W4412361741","doi":"10.33564/ijeast.2025.v10i01.005","title":"CRIME DATA ANALYSIS","year":2025,"lang":"en","type":"article","venue":"International Journal of Engineering Applied Sciences and Technology","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science","score_opus":0.12520565214855978,"score_gpt":0.39664871302534854,"score_spread":0.27144306087678877,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412361741","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":[0.10789943,0.0014433798,0.8518744,0.030760335,0.0010219429,0.000118764976,0.0000835732,0.00015989183,0.0066383],"genre_scores_gemma":[0.97661924,0.00008039448,0.023144515,0.000073581046,0.000029724315,0.000002210777,0.0000024518433,0.0000016547879,0.000046215828],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99854344,0.0000046244927,0.0004885899,0.00030291203,0.00053622364,0.00012423107],"domain_scores_gemma":[0.99864554,0.00029028492,0.00023047616,0.0005128585,0.00029414447,0.000026686801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014259028,0.00007548811,0.00021707629,0.0026720115,0.00007814354,0.00020651316,0.004261908,0.00008817549,0.000021112399],"category_scores_gemma":[0.0011206977,0.000053849843,0.000038521594,0.0036330235,0.0002859923,0.00019594867,0.0009623164,0.00018695238,0.00000451262],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005162,0.000030659092,0.004435002,9.819893e-7,0.00031251475,0.0000056267904,0.000008067314,0.0013829414,0.004730756,0.89105153,0.003004385,0.09503239],"study_design_scores_gemma":[0.00096385315,0.00013411281,0.033663847,0.000057199948,0.00043473305,0.00016384479,0.001669522,0.14209703,0.009525233,0.43222696,0.3785951,0.0004685479],"about_ca_topic_score_codex":0.0000039191686,"about_ca_topic_score_gemma":0.0000028212748,"teacher_disagreement_score":0.8687198,"about_ca_system_score_codex":0.00001736155,"about_ca_system_score_gemma":0.000061307284,"threshold_uncertainty_score":0.7919756},"labels":[],"label_agreement":null},{"id":"W4412819361","doi":"10.1017/s1743921323001394","title":"How do we design data sets for Machine Learning astronomy?","year":2023,"lang":"en","type":"article","venue":"Proceedings of the International Astronomical Union","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Theoretical Astrophysics","funders":"","keywords":"Computer science; Astronomy; Artificial intelligence; Physics","score_opus":0.26442971159024675,"score_gpt":0.3662506250858025,"score_spread":0.10182091349555572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412819361","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":[0.54857653,0.00008631722,0.2094746,0.23787104,0.00078752986,0.001219961,0.0012488945,0.00033327157,0.00040188385],"genre_scores_gemma":[0.9546752,0.000018221619,0.043729756,0.000013904375,0.00009668399,0.000054098135,0.00009605917,0.000011867559,0.0013042282],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99857455,0.000010145714,0.00032237274,0.00044785757,0.00046408665,0.00018097796],"domain_scores_gemma":[0.9985933,0.00050378207,0.0002681744,0.00033472516,0.00026220392,0.000037851125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016810783,0.00010405478,0.00014522694,0.00016706414,0.00014028739,0.00036593011,0.0043280628,0.000057645688,0.000024329836],"category_scores_gemma":[0.0022952943,0.00006893679,0.00008173352,0.000368695,0.00011136647,0.00053997774,0.0020340146,0.00017682675,0.000030969964],"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":[0.00014151298,0.00011161189,0.046649083,0.000009380571,0.000112172,4.832464e-8,0.000059714705,0.0022310114,0.026436538,0.07044915,0.17700683,0.676793],"study_design_scores_gemma":[0.00044535924,0.00007005111,0.00851312,0.00003742756,0.000015784628,0.000001780033,0.00092528504,0.15235369,0.012029852,0.045099095,0.7803637,0.00014486155],"about_ca_topic_score_codex":0.000005418665,"about_ca_topic_score_gemma":0.0000015011258,"teacher_disagreement_score":0.6766481,"about_ca_system_score_codex":0.00004577107,"about_ca_system_score_gemma":0.000026382,"threshold_uncertainty_score":0.80426896},"labels":[],"label_agreement":null},{"id":"W4413684012","doi":"10.2196/70066","title":"Integration of Data and Information Systems Into the Health Data Strategy","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Czech; Computer science; Data science; World Wide Web","score_opus":0.2641624079056417,"score_gpt":0.4708056528706074,"score_spread":0.20664324496496567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413684012","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":[0.033370983,0.0013039373,0.89489144,0.054627802,0.0005239894,0.0021374172,0.002128614,0.00021393613,0.010801877],"genre_scores_gemma":[0.98397696,0.001464187,0.008455643,0.0030913472,0.00004117326,0.0000616746,0.0028108505,0.0000033716906,0.000094788935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719363,0.000056147146,0.0014210719,0.00011968251,0.0010819585,0.00012750507],"domain_scores_gemma":[0.99569595,0.000629988,0.0005390335,0.0028981606,0.00016430479,0.000072547235],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004519491,0.00007991883,0.00020739235,0.00016899873,0.00017333697,0.0003078131,0.0042348756,0.00012621324,0.00001561071],"category_scores_gemma":[0.0024168966,0.000041746203,0.000010581638,0.0008694121,0.00031668306,0.0034989265,0.0026024247,0.0002612235,0.000030400055],"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":[0.0000027924657,0.000011609234,0.000039769693,0.00005225995,0.00000642736,2.4500483e-8,0.0009829474,0.0000028474783,8.210528e-7,0.08390244,0.12210161,0.79289645],"study_design_scores_gemma":[0.00015114868,0.00003166755,0.0005509912,0.000092620554,0.0000046897626,0.0000031575419,0.032181308,0.38150403,0.0000042657744,0.0038908639,0.58153856,0.00004668764],"about_ca_topic_score_codex":0.00020179487,"about_ca_topic_score_gemma":0.00011790651,"teacher_disagreement_score":0.950606,"about_ca_system_score_codex":0.00001760934,"about_ca_system_score_gemma":0.00038904315,"threshold_uncertainty_score":0.7869523},"labels":[],"label_agreement":null},{"id":"W4414511365","doi":"10.23977/jeis.2025.100208","title":"Evaluation and Dynamic Optimization of Big Data Technology in Engineering Project Resource Allocation","year":2025,"lang":"en","type":"article","venue":"Journal of Electronics and Information Science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Big data; Resource (disambiguation); Field (mathematics); Resource allocation; Resource management (computing); Project management","score_opus":0.09487698848080062,"score_gpt":0.38093440424269626,"score_spread":0.28605741576189564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414511365","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":[0.35916334,0.002552648,0.627594,0.009170649,0.00014566086,0.00054763234,0.000018486442,0.000020415058,0.0007871965],"genre_scores_gemma":[0.99291426,0.0010727749,0.005965483,0.000031358566,0.0000031618545,0.0000035477733,0.0000057027673,9.163936e-7,0.000002781776],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99837565,0.000018653762,0.000673819,0.000121550635,0.0006968136,0.00011351505],"domain_scores_gemma":[0.9980947,0.000109112654,0.00051409955,0.0003668497,0.00089999026,0.000015282598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007741465,0.000049188737,0.00012019198,0.0020268487,0.00007732497,0.00013879835,0.00077089365,0.000055855427,8.85687e-7],"category_scores_gemma":[0.0051295236,0.000037913323,0.000008136018,0.00361177,0.00015664505,0.0029932158,0.0002600777,0.00014162027,1.9664064e-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":[0.000013116064,0.000021673628,0.00058157503,0.000013700601,0.0000055483206,5.230231e-8,0.00015538013,0.041892182,0.0031659303,0.0524684,0.0001784315,0.90150404],"study_design_scores_gemma":[0.00026528566,0.00006619807,0.0022895942,0.000037562066,0.0000104919,0.00001155317,0.0006847514,0.98021466,0.0006692865,0.006636514,0.009072016,0.000042072013],"about_ca_topic_score_codex":0.0000033481438,"about_ca_topic_score_gemma":0.000007275676,"teacher_disagreement_score":0.9383225,"about_ca_system_score_codex":0.00009057639,"about_ca_system_score_gemma":0.0006501583,"threshold_uncertainty_score":0.61408895},"labels":[],"label_agreement":null},{"id":"W4414639538","doi":"10.1007/978-3-662-72116-2_2","title":"Data Assetization Journey: Concepts, Principles, and Illustrations","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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 TÉLUQ","funders":"","keywords":"Asset (computer security); Obligation; Line (geometry); Transformation (genetics); Corporate governance; Data governance; Data verification; Word (group theory)","score_opus":0.26451014898457226,"score_gpt":0.39850359266860413,"score_spread":0.13399344368403188,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414639538","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":[0.000025727244,0.00054733764,0.9859219,0.005719249,0.00042416385,0.00034171707,0.00071893545,0.00008449078,0.006216432],"genre_scores_gemma":[0.14466336,0.001628492,0.83589303,0.0039342525,0.00088643125,0.000038743237,0.0012102594,0.000055423643,0.011689993],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99639976,0.00002614992,0.0006684534,0.0015600884,0.0010601986,0.00028536],"domain_scores_gemma":[0.9949415,0.0012368725,0.00035734405,0.0030345526,0.00034320622,0.00008656655],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019161697,0.00025773575,0.00034403577,0.00068602647,0.00042522218,0.0009966427,0.004861844,0.00032719385,0.00006868715],"category_scores_gemma":[0.0020302504,0.00020203044,0.00003347422,0.0009651428,0.0013956224,0.00059475447,0.003720586,0.00059737125,0.000028498176],"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":[0.0000012066121,0.0000108719705,0.00014760465,0.000005617512,0.000004540378,0.0000038769376,0.000045340308,0.0018640878,0.000022351762,0.120275885,0.00257352,0.8750451],"study_design_scores_gemma":[0.00013528776,0.00003632325,0.00068871083,0.00016236323,0.000014549558,0.000022804845,0.000002625406,0.25014305,0.00008703514,0.38370568,0.36463955,0.0003619969],"about_ca_topic_score_codex":0.000011702536,"about_ca_topic_score_gemma":0.00043646098,"teacher_disagreement_score":0.8746831,"about_ca_system_score_codex":0.00008111773,"about_ca_system_score_gemma":0.0005959074,"threshold_uncertainty_score":0.9610649},"labels":[],"label_agreement":null},{"id":"W5421139","doi":"10.1044/jshr.1301.41","title":"The Unfinished Revolution: Making Computers Human-Centric","year":2001,"lang":"en","type":"book","venue":"HarperCollins Publishers eBooks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":10,"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":"","keywords":"Quarter (Canadian coin); Focus (optics); Information revolution; Work (physics); Key (lock); Computer science; Information technology; Data science; Political science; Engineering; History; Computer security; Law","score_opus":0.19964764802077406,"score_gpt":0.3605601265355474,"score_spread":0.16091247851477336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W5421139","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000053779033,0.0006788037,0.0043053557,0.0042110835,0.0017601233,0.0013177159,0.0001981932,0.00068673503,0.9867882],"genre_scores_gemma":[0.0016003767,0.000078185236,0.0015337062,0.0009626626,0.00090082403,0.00024660034,0.0002125681,0.00009805988,0.994367],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9928308,0.00019316071,0.0017905253,0.001662903,0.0025228874,0.0009997217],"domain_scores_gemma":[0.991586,0.0017142828,0.0011937969,0.004385381,0.00090010493,0.00022039395],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0030447892,0.000669312,0.00082565163,0.000779757,0.0027220312,0.0077769575,0.007843838,0.0010879668,0.00047776956],"category_scores_gemma":[0.001249924,0.000455843,0.0005631214,0.0008962118,0.0011541956,0.00076933025,0.0015987167,0.0015691217,0.00080010784],"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":[0.000006844868,0.000020186773,0.000020586245,0.000005207316,0.000049559872,0.000018465907,0.000051697,0.000007796195,0.0000029308442,0.07777276,0.84381014,0.07823384],"study_design_scores_gemma":[0.0003005371,0.000042972857,0.000071096445,0.000079520665,0.000047822832,0.000030650477,0.00037200324,0.00020690325,0.0000022271265,0.10027621,0.89808697,0.0004830916],"about_ca_topic_score_codex":0.00002755155,"about_ca_topic_score_gemma":0.00025057784,"teacher_disagreement_score":0.07775074,"about_ca_system_score_codex":0.0007084675,"about_ca_system_score_gemma":0.000865324,"threshold_uncertainty_score":0.9999779},"labels":[],"label_agreement":null},{"id":"W616817087","doi":"10.1007/978-3-642-40104-6","title":"Algorithms and data structures : 13th international symposium, WADS 2013, London, ON, Canada, August 12-14, 2013 : proceedings","year":2013,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Graphics; Computer science; Data structure; Data mining; Algorithm; Theoretical computer science; Computer graphics (images); Programming language","score_opus":0.11244938248607304,"score_gpt":0.3299356116610665,"score_spread":0.21748622917499344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W616817087","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010417706,0.0013827434,0.001151055,0.12275542,0.0030603702,0.0026433798,0.020629462,0.0005439274,0.84679186],"genre_scores_gemma":[0.0009486562,0.0020400456,0.004825218,0.00137443,0.00057229993,0.00008156874,0.002157097,0.000057817513,0.9879429],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9944896,0.000012016016,0.00091803813,0.0018839464,0.00225298,0.0004433803],"domain_scores_gemma":[0.9954911,0.0004149705,0.00063100125,0.0024141022,0.00080181065,0.0002470128],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005981777,0.000529555,0.00056674314,0.00029706548,0.00028804582,0.0011770612,0.0077153947,0.000570969,0.0039002898],"category_scores_gemma":[0.00044101148,0.00036165546,0.0000569871,0.00021637046,0.0003822086,0.0006324854,0.0037218914,0.00075811805,0.00033302093],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041166045,0.000012874953,0.000080946505,0.000006782728,0.00004960542,0.0000026828814,0.000008259921,0.000002652438,0.000008763266,0.020075785,0.9387315,0.04101606],"study_design_scores_gemma":[0.0001854479,0.00003575222,0.0006483175,0.00003276888,0.000027207798,0.000028017694,0.00011429538,0.0013762199,0.000021640188,0.029501602,0.9675934,0.00043537407],"about_ca_topic_score_codex":0.20507623,"about_ca_topic_score_gemma":0.30776465,"teacher_disagreement_score":0.141151,"about_ca_system_score_codex":0.0002428296,"about_ca_system_score_gemma":0.00084656395,"threshold_uncertainty_score":0.99988353},"labels":[],"label_agreement":null},{"id":"W621215835","doi":"10.1007/978-3-319-09274-4","title":"Artificial General Intelligence: 7th International Conference, AGI 2014, Quebec City, QC, Canada, August 1-4, 2014, Proceedings","year":2014,"lang":"en","type":"book","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Artificial general intelligence; Human intelligence; Field (mathematics); Library science; Engineering ethics; Artificial intelligence; Sociology; Political science; Computer science; Engineering; Mathematics","score_opus":0.17731448731032354,"score_gpt":0.35452701379680784,"score_spread":0.1772125264864843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W621215835","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00035763753,0.00007057203,0.01957165,0.011590322,0.001937761,0.0006331398,0.0014269722,0.00030432883,0.96410763],"genre_scores_gemma":[0.0068879067,0.00018189514,0.0019255066,0.0010245127,0.0012264175,0.000097467324,0.00077873084,0.000042608088,0.98783493],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99337155,0.000024553068,0.0015876716,0.001567198,0.002847155,0.00060186523],"domain_scores_gemma":[0.9954386,0.0003279125,0.0009704867,0.001221859,0.0017665038,0.00027469173],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0012652515,0.0005893996,0.00076928176,0.0005776139,0.00032993287,0.0012737764,0.0058161346,0.00081931363,0.02311798],"category_scores_gemma":[0.00063007476,0.0004551679,0.00021154496,0.00033588475,0.0006067001,0.0003838988,0.0015495725,0.0009787752,0.0024131532],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052985692,0.000018009781,0.000080644764,0.0000034052616,0.000025536192,0.0000019809495,0.000008444923,0.0000039651018,0.000015841162,0.32592937,0.6297151,0.044192445],"study_design_scores_gemma":[0.000036920723,0.000023902985,0.0001426468,0.000025430472,0.000022003895,0.000010019721,0.00020142997,0.0014110261,0.00030411384,0.17334972,0.8239897,0.00048307673],"about_ca_topic_score_codex":0.37615985,"about_ca_topic_score_gemma":0.9193654,"teacher_disagreement_score":0.5432055,"about_ca_system_score_codex":0.0006506532,"about_ca_system_score_gemma":0.003756183,"threshold_uncertainty_score":0.99979},"labels":[],"label_agreement":null},{"id":"W644851440","doi":"","title":"Theoretical high energy physics , MRST 2000, Rochester, New York 8-9 May 2000","year":2000,"lang":"en","type":"book","venue":"American Institute of Physics eBooks","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Physics; Quantum chromodynamics; Range (aeronautics); Particle physics; Boson; High energy; Engineering physics; Nuclear physics; Engineering","score_opus":0.08244976803001097,"score_gpt":0.3053065286154697,"score_spread":0.22285676058545872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W644851440","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0001827281,0.00027045124,0.070713855,0.00053693046,0.0005447589,0.00044237913,0.0013849576,0.00033115223,0.9255928],"genre_scores_gemma":[0.13105096,0.0003014556,0.011974009,0.0014389082,0.0028393136,0.00012312447,0.00082855875,0.00020920583,0.85123444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99482363,0.00006803796,0.001272739,0.0014190543,0.0017395408,0.0006769962],"domain_scores_gemma":[0.9941187,0.00044294342,0.001407394,0.0034647165,0.0002480374,0.00031821692],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00025729337,0.0007950511,0.0015500452,0.00020809243,0.00026519492,0.0002380645,0.0037651688,0.00040634957,0.0003893542],"category_scores_gemma":[0.00007790023,0.0006761151,0.00054657215,0.00062934065,0.007012003,0.0002264089,0.0006640461,0.0007593868,0.0005516515],"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":[0.000017143055,0.00004510793,0.0000011402473,0.0000040503037,0.000052351083,0.000003609097,0.00006160581,0.000033836597,0.000021042419,0.5044865,0.093881786,0.4013918],"study_design_scores_gemma":[0.0001619407,0.0000989467,0.000003940879,0.000060035854,0.000070803166,0.0000032430512,0.000033727138,0.00002809086,0.0007965896,0.4954517,0.50288785,0.0004031362],"about_ca_topic_score_codex":0.0014000823,"about_ca_topic_score_gemma":0.000061055405,"teacher_disagreement_score":0.40900606,"about_ca_system_score_codex":0.0002621296,"about_ca_system_score_gemma":0.0032116326,"threshold_uncertainty_score":0.999569},"labels":[],"label_agreement":null},{"id":"W6912602371","doi":"10.5281/zenodo.4150596","title":"REGARDER''-Falling (2020)]EN STREAMING FILM FR COMPLET jgx","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Falling (accident); Heading (navigation); Imago","score_opus":0.2364160396682274,"score_gpt":0.3293120416767511,"score_spread":0.09289600200852369,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6912602371","genre_codex":"other","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":[0.14665067,0.00081330125,0.25798348,0.17906168,0.0004251432,0.0029297569,0.004484438,0.011309446,0.39634207],"genre_scores_gemma":[0.9944249,0.00010114945,0.0026966585,0.00073896605,0.00018648343,7.596943e-8,0.00083034293,0.0005345397,0.00048692428],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974403,0.00025239468,0.00044373225,0.00070611795,0.000801908,0.0003555456],"domain_scores_gemma":[0.99804115,0.00016256477,0.0001742616,0.00086409174,0.00053738273,0.00022052461],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010446858,0.00014347356,0.0001999994,0.00014415964,0.0020229646,0.0015113483,0.0031853882,0.00008917433,0.014667877],"category_scores_gemma":[0.005046243,0.0001307349,0.00006761256,0.0014013893,0.00018894451,0.0003224357,0.0028451742,0.00037687566,0.02070967],"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":[0.000020933308,0.00005034765,0.000009486016,0.000013925396,0.000018411807,0.000011407334,0.00087841076,0.0001968305,0.0034779003,0.0121967755,0.7489621,0.23416346],"study_design_scores_gemma":[0.00022436008,0.00009931304,0.00043901618,0.000011201976,0.0000064757796,0.000026422775,0.0020221227,0.005050416,0.0003330827,0.0016493597,0.98998606,0.00015214985],"about_ca_topic_score_codex":0.000013959059,"about_ca_topic_score_gemma":8.063463e-7,"teacher_disagreement_score":0.8477742,"about_ca_system_score_codex":0.000057729627,"about_ca_system_score_gemma":0.0000043558985,"threshold_uncertainty_score":0.9995252},"labels":[],"label_agreement":null},{"id":"W6925621578","doi":"10.17910/b7.1387","title":"EmoGoals","year":2021,"lang":"en","type":"dataset","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Zoom; Face (sociological concept); Relation (database); Object (grammar); Perspective (graphical)","score_opus":0.3676709742955122,"score_gpt":0.44506657424098833,"score_spread":0.07739559994547612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925621578","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000019445142,0.00020879052,0.0003531879,0.002929249,0.00024334111,0.00008494601,0.9943731,0.00006588591,0.0017395538],"genre_scores_gemma":[0.0000016422238,0.00036505278,0.000944036,0.00076786894,0.00008248697,0.000028506389,0.9930839,0.000003486806,0.0047230073],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99778575,0.000036599715,0.00046620707,0.00064347836,0.00089414953,0.00017382142],"domain_scores_gemma":[0.99555385,0.00053812447,0.00018643173,0.0034799282,0.0001875753,0.000054095202],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006471221,0.00013939943,0.00030338822,0.00018098656,0.000100680925,0.00044419602,0.0027864033,0.0003533591,0.015593199],"category_scores_gemma":[0.0028020998,0.000088982924,0.00011109706,0.00092187047,0.000088845845,0.000073682844,0.0011814076,0.00028827373,0.011405335],"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":[1.9002128e-7,0.000018648803,9.0257157e-7,0.0000012364303,0.0000044334984,0.000005885122,1.8605273e-7,1.3933818e-7,0.0000019676465,0.00040535672,0.9815075,0.018053558],"study_design_scores_gemma":[0.00002373608,0.0000048973156,0.0000150580745,0.0000044383128,0.0000071187865,0.000006624424,0.000089117835,0.0000018972091,0.00003547254,0.007994871,0.9916974,0.000119371165],"about_ca_topic_score_codex":0.000094636816,"about_ca_topic_score_gemma":0.00031317386,"teacher_disagreement_score":0.017934188,"about_ca_system_score_codex":0.000012722507,"about_ca_system_score_gemma":0.000087372,"threshold_uncertainty_score":0.9893644},"labels":[],"label_agreement":null},{"id":"W6949089475","doi":"10.5281/zenodo.1184303","title":"Big Data Schooling","year":2018,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Big data; Data collection; Work (physics); Period (music)","score_opus":0.4989616570749087,"score_gpt":0.3822047769631415,"score_spread":0.11675688011176721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6949089475","genre_codex":"other","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":[0.048251078,0.00033137525,0.31785786,0.021027826,0.001024834,0.0012077801,0.0046098563,0.0055430587,0.60014635],"genre_scores_gemma":[0.9931278,0.00007402267,0.0023643374,0.0003120457,0.0006655433,2.4692461e-8,0.0017828994,0.0005572547,0.0011160304],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99781495,0.00015473746,0.000328138,0.0007072672,0.00069128966,0.00030362897],"domain_scores_gemma":[0.9959689,0.00007110172,0.0001309083,0.002828125,0.0008739803,0.00012699545],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0022544104,0.00009406103,0.00011559087,0.00027602338,0.0029788904,0.0018485377,0.0067501566,0.00006718837,0.009828992],"category_scores_gemma":[0.0068114237,0.00008029453,0.000025427924,0.001510175,0.0004118464,0.00046571184,0.0074775135,0.00021604016,0.057731703],"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":[0.0000057044826,0.000022995766,0.0000031863963,0.0000011338526,0.0000048154916,9.002869e-7,0.000053464057,8.729749e-7,0.0010032125,0.0051906314,0.4944087,0.49930438],"study_design_scores_gemma":[0.00013148611,0.00006787776,0.00042573333,0.000006098484,0.0000040314967,0.000032666267,0.00043204008,0.0009055425,0.00041105584,0.00488365,0.9926002,0.00009959653],"about_ca_topic_score_codex":0.000016261381,"about_ca_topic_score_gemma":0.0000012209308,"teacher_disagreement_score":0.9448768,"about_ca_system_score_codex":0.000039239763,"about_ca_system_score_gemma":0.0000042222664,"threshold_uncertainty_score":0.99918765},"labels":[],"label_agreement":null},{"id":"W6950135270","doi":"10.5281/zenodo.6917218","title":"Small Data projects/Big Data research: contemporary problems and historical solutions","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Presentation (obstetrics); Minor (academic); Data collection; Small data","score_opus":0.9315210701659241,"score_gpt":0.37772499857736314,"score_spread":0.553796071588561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6950135270","genre_codex":"other","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":[0.019617783,0.016646469,0.12549362,0.22274837,0.002253041,0.013401427,0.10656242,0.01037509,0.48290178],"genre_scores_gemma":[0.9655342,0.00044274222,0.0017891782,0.00027249978,0.0002892812,0.0000016594637,0.025398556,0.0009474531,0.0053244163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99496216,0.0011264974,0.00050942186,0.0014073383,0.0014860289,0.00050858705],"domain_scores_gemma":[0.99343514,0.00030776174,0.00018451393,0.0052088345,0.0006729106,0.00019084926],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.011140573,0.00013051045,0.0001951931,0.0005784121,0.008656606,0.0014262209,0.0121274125,0.00006479698,0.0022073155],"category_scores_gemma":[0.00784076,0.00012175256,0.00002261309,0.0025408086,0.00048373372,0.00060683006,0.057143275,0.00085325714,0.0015222563],"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":[0.000017560938,0.00015997635,0.000009967363,0.000008234934,0.000011735189,0.0000064679666,0.00029293692,0.000005324819,0.00033706118,0.005138807,0.7944408,0.19957112],"study_design_scores_gemma":[0.00025578367,0.00016196074,0.00013274621,0.0000056267177,0.0000054125885,0.000094939576,0.0022296277,0.003012137,0.00000673256,0.002948469,0.99100566,0.0001409297],"about_ca_topic_score_codex":0.00031656038,"about_ca_topic_score_gemma":0.000010922189,"teacher_disagreement_score":0.9459164,"about_ca_system_score_codex":0.00030121848,"about_ca_system_score_gemma":0.000034296027,"threshold_uncertainty_score":0.9996104},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"reproducibility","study_design":"not_applicable","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W6968682310","doi":"10.5281/zenodo.6857202","title":"Small Data projects/Big Data research: contemporary problems and historical solutions","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Presentation (obstetrics); Minor (academic); Data collection; Small data","score_opus":0.9315210701659241,"score_gpt":0.37772499857736314,"score_spread":0.553796071588561,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968682310","genre_codex":"other","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":[0.019617783,0.016646469,0.12549362,0.22274837,0.002253041,0.013401427,0.10656242,0.01037509,0.48290178],"genre_scores_gemma":[0.9655342,0.00044274222,0.0017891782,0.00027249978,0.0002892812,0.0000016594637,0.025398556,0.0009474531,0.0053244163],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99496216,0.0011264974,0.00050942186,0.0014073383,0.0014860289,0.00050858705],"domain_scores_gemma":[0.99343514,0.00030776174,0.00018451393,0.0052088345,0.0006729106,0.00019084926],"candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.011140573,0.00013051045,0.0001951931,0.0005784121,0.008656606,0.0014262209,0.0121274125,0.00006479698,0.0022073155],"category_scores_gemma":[0.00784076,0.00012175256,0.00002261309,0.0025408086,0.00048373372,0.00060683006,0.057143275,0.00085325714,0.0015222563],"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":[0.000017560938,0.00015997635,0.000009967363,0.000008234934,0.000011735189,0.0000064679666,0.00029293692,0.000005324819,0.00033706118,0.005138807,0.7944408,0.19957112],"study_design_scores_gemma":[0.00025578367,0.00016196074,0.00013274621,0.0000056267177,0.0000054125885,0.000094939576,0.0022296277,0.003012137,0.00000673256,0.002948469,0.99100566,0.0001409297],"about_ca_topic_score_codex":0.00031656038,"about_ca_topic_score_gemma":0.000010922189,"teacher_disagreement_score":0.9459164,"about_ca_system_score_codex":0.00030121848,"about_ca_system_score_gemma":0.000034296027,"threshold_uncertainty_score":0.9996104},"labels":[],"label_agreement":null},{"id":"W6969011827","doi":"10.5281/zenodo.8403802","title":"Small Data projects/Big Data research: contemporary problems and historical solutions","year":2023,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Small data; Data collection; Context (archaeology); Work (physics); Key (lock)","score_opus":0.944000042099182,"score_gpt":0.3934813743268047,"score_spread":0.5505186677723772,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6969011827","genre_codex":"other","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":[0.028570583,0.008627415,0.11270099,0.26529777,0.0021960633,0.013008254,0.06786093,0.024221532,0.47751644],"genre_scores_gemma":[0.9380949,0.0019485294,0.002146789,0.00023679913,0.00060892786,0.0000012810349,0.04435712,0.0015888872,0.01101677],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99565995,0.00064996595,0.0005107017,0.0014008029,0.0011908439,0.0005877471],"domain_scores_gemma":[0.9931748,0.00040365726,0.00014839541,0.00517693,0.00087855855,0.00021768441],"candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.010533938,0.00013767842,0.0002024098,0.0007599561,0.004416524,0.0018093752,0.009950855,0.00011727482,0.000608878],"category_scores_gemma":[0.014023017,0.00012004987,0.000022173434,0.003928039,0.0005696988,0.00072995125,0.0326943,0.0005755684,0.009176999],"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":[0.00000927454,0.00006695356,0.00001084852,0.000012240875,0.000010695654,0.0000066965704,0.00022117414,0.0000019140155,0.00040656462,0.0036566358,0.77209395,0.22350307],"study_design_scores_gemma":[0.00022179494,0.00008784524,0.00040228598,0.000016109341,0.000004899193,0.000037525704,0.001276625,0.004482014,0.000012375485,0.003703052,0.9896175,0.00013795968],"about_ca_topic_score_codex":0.00023516508,"about_ca_topic_score_gemma":0.000015766627,"teacher_disagreement_score":0.9095243,"about_ca_system_score_codex":0.00015088716,"about_ca_system_score_gemma":0.000026296259,"threshold_uncertainty_score":0.99922687},"labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"grok","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"opus","categories":["metaresearch"],"domain":"reproducibility","study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W7008270000","doi":"","title":"Big data policing: Schets van de belangrijkste vraagstukken, partijen en nieuwste trends in de praktijk","year":2023,"lang":"nl","type":"book-chapter","venue":"Digital Academic REpository of VU University Amsterdam (Vrije Universiteit Amsterdam)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"L'Alliance Boviteq","funders":"","keywords":"Data collection; Context (archaeology); Work (physics); Qualitative research; Class (philosophy)","score_opus":0.16868662022194747,"score_gpt":0.3164468613362046,"score_spread":0.14776024111425712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7008270000","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45269662,0.00083608204,0.003630442,0.012341476,0.0021943864,0.0026253895,0.017303169,0.0017257697,0.5066467],"genre_scores_gemma":[0.48712766,0.0019869516,0.000584879,0.00024849325,0.0005388993,0.0000019664585,0.0017354307,0.00019600245,0.50757974],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990506,0.00039694703,0.0020610238,0.003188411,0.002042429,0.0018051743],"domain_scores_gemma":[0.9896578,0.0014678756,0.0024983825,0.004960199,0.00055228727,0.0008634065],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":["metaepi_narrow","open_science","research_integrity"],"category_scores_codex":[0.0017893716,0.0013714088,0.001957871,0.0046152505,0.0008681647,0.00045491144,0.011972434,0.0029474266,0.00013056415],"category_scores_gemma":[0.0005459474,0.00157443,0.0007490901,0.0025493489,0.0020783646,0.0037477391,0.010743759,0.003413655,0.0007055163],"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":[0.003577525,0.0017870729,0.14300108,0.0010593239,0.0040183165,0.015039323,0.01881145,0.0020065487,0.008390935,0.10538517,0.15641466,0.54050857],"study_design_scores_gemma":[0.0046081194,0.0007557257,0.017465807,0.0025013352,0.0010756004,0.0006766083,0.029333252,0.0025987192,0.0006476385,0.0045932545,0.9325124,0.0032315636],"about_ca_topic_score_codex":0.0019425043,"about_ca_topic_score_gemma":0.0004942076,"teacher_disagreement_score":0.7760977,"about_ca_system_score_codex":0.0017142587,"about_ca_system_score_gemma":0.0009940421,"threshold_uncertainty_score":0.9999037},"labels":[],"label_agreement":null},{"id":"W7083824749","doi":"10.5281/zenodo.17238041","title":"Table 2 in Bringing Shadowdragons to light: Neurocordulia (Anisoptera: Corduliidae) systematics","year":2025,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"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":"","keywords":"Table (database); Table of contents; Section (typography); Channel (broadcasting); Systematics","score_opus":0.1292442179463484,"score_gpt":0.3320078628657848,"score_spread":0.2027636449194364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083824749","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000104407656,0.000088627065,0.0038167944,0.003975957,0.00032371754,0.0015098953,0.97184855,0.0006492201,0.017682848],"genre_scores_gemma":[0.002455993,0.00018776405,0.00069714757,0.00080211647,0.00013858858,0.0000012011353,0.9930298,0.00053516036,0.0021522539],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.995419,0.00040593694,0.0011140475,0.0012327033,0.0011841801,0.00064413226],"domain_scores_gemma":[0.9954373,0.00022638908,0.00040511118,0.0028492536,0.00085255806,0.0002293745],"candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002064304,0.00034327552,0.0005794332,0.0016685885,0.0018007776,0.0031846114,0.0071491157,0.00026894422,0.0058181947],"category_scores_gemma":[0.008587509,0.00032525227,0.000093722265,0.0047377045,0.00010837426,0.00030241042,0.007449696,0.0008014962,0.010528021],"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":[0.000013204792,0.000108019274,9.79581e-7,0.00014637221,0.000014762841,0.000018986584,0.000059037153,0.00006301494,0.0000845486,0.0010280483,0.9812124,0.017250635],"study_design_scores_gemma":[0.00019804685,0.000099632554,0.000055144825,0.0002847077,0.000019041016,0.000033897613,0.0003601616,0.00028055464,0.00003269818,0.00035927494,0.9979779,0.0002989355],"about_ca_topic_score_codex":0.00013289611,"about_ca_topic_score_gemma":0.000017084121,"teacher_disagreement_score":0.021181243,"about_ca_system_score_codex":0.00019679833,"about_ca_system_score_gemma":0.000019262525,"threshold_uncertainty_score":0.99991995},"labels":[],"label_agreement":null},{"id":"W7099318648","doi":"","title":"Saskatoon By","year":2016,"lang":"en","type":"article","venue":"","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"","score_opus":0.250478889140823,"score_gpt":0.39111953396693544,"score_spread":0.14064064482611244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099318648","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":[0.12922515,0.00013055925,0.43153578,0.20651759,0.00015198089,0.00018975779,0.00027438166,0.00068565377,0.23128913],"genre_scores_gemma":[0.94440794,0.0000139144195,0.0016369829,0.00037536855,0.000008772133,0.000009616417,9.3761736e-7,0.0000018484844,0.053544603],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993491,0.000006898707,0.00012800183,0.00018445274,0.0002461038,0.000085430744],"domain_scores_gemma":[0.99906194,0.00025905384,0.000029851806,0.00058780453,0.000035128276,0.000026234224],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00027472537,0.000030069628,0.000045569457,0.000030064593,0.00004232929,0.000049324193,0.000614423,0.000033181175,0.0021401108],"category_scores_gemma":[0.00035487954,0.00001189919,0.00001838054,0.00022076038,0.00007164065,0.00013987743,0.00012436125,0.000015891412,0.004887263],"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":[2.1154717e-7,0.0000043531445,0.00038807726,1.46335974e-8,2.8293994e-7,3.253959e-8,6.5682536e-7,2.4878892e-9,0.0073297825,0.027200224,0.61785734,0.34721902],"study_design_scores_gemma":[0.00004464211,0.000007681806,0.00070331595,5.566328e-7,2.747674e-7,5.0774116e-7,0.000049592873,0.0000034341367,0.011042125,0.078971066,0.90914786,0.000028921662],"about_ca_topic_score_codex":0.000006924101,"about_ca_topic_score_gemma":0.000017361594,"teacher_disagreement_score":0.8151828,"about_ca_system_score_codex":0.0000053099525,"about_ca_system_score_gemma":0.0000054008665,"threshold_uncertainty_score":0.9987721},"labels":[],"label_agreement":null},{"id":"W7148627237","doi":"10.71465/ajbd780","title":"Big Data for Enhancing Customer Experience in Digital Marketing","year":2023,"lang":"","type":"article","venue":"American Journal Of Big Data","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Digital marketing; Purchasing; Customer advocacy; Customer intelligence; Personalized marketing; Customer experience; Product (mathematics)","score_opus":0.4337847677042681,"score_gpt":0.42811211275846234,"score_spread":0.005672654945805766,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7148627237","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":[0.76729655,0.0020402581,0.1581368,0.01638391,0.0062780767,0.0012595851,0.047670092,0.00018075417,0.00075398054],"genre_scores_gemma":[0.9906608,0.002584328,0.0047300505,0.00018847066,0.0009073682,0.000015063196,0.0007205932,0.000038109483,0.00015524492],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99333054,0.00015171904,0.0026060408,0.0014779884,0.0015041351,0.0009295685],"domain_scores_gemma":[0.9831221,0.005781878,0.002639039,0.007720412,0.00043981578,0.00029674222],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.010258894,0.0003513971,0.0009618491,0.0012061622,0.00035636427,0.0011363185,0.018600864,0.00011283172,0.000043274427],"category_scores_gemma":[0.031794574,0.0002887547,0.00012464466,0.0071016746,0.0013518226,0.0033344831,0.0109398505,0.0006666607,0.00022283095],"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":[0.00013478225,0.000095148614,0.0022838837,0.000011107967,0.000036521862,0.000039916806,0.00027148842,0.000013056965,0.00049792114,0.000023074337,0.05138719,0.9452059],"study_design_scores_gemma":[0.00079784263,0.00034167766,0.00480384,0.00049888244,0.000062512074,0.0001717642,0.06689538,0.008949597,0.00018385042,0.00071217725,0.91596985,0.00061263394],"about_ca_topic_score_codex":0.0001142888,"about_ca_topic_score_gemma":0.00028600844,"teacher_disagreement_score":0.94459325,"about_ca_system_score_codex":0.00008667214,"about_ca_system_score_gemma":0.0007460633,"threshold_uncertainty_score":0.9999565},"labels":[],"label_agreement":null}]}