{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":167,"total_is_capped":false,"direct_labels_cover":4,"predictions_cover":167,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"a02047a22732","filters":{"topic":"Big Data Technologies and Applications"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2365552058519708,"gpt":0.4581771931797269,"spread":0.2216219873277561,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004771884,0.00006617628,0.0001103659,0.0003272264,0.00008932712,0.0005748239,0.003068751,0.00002911286,0.00004319624],"category_scores_gemma":[0.001389934,0.00003748053,0.00003676707,0.0002768287,0.0001091815,0.001248218,0.001082034,0.0001255978,0.00005731056],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002350381,"about_ca_system_score_gemma":0.00001540162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004074986,"about_ca_topic_score_gemma":0.000003145575,"domain_scores_codex":[0.9979556,0.00007235214,0.0007981947,0.00009287251,0.001003043,0.00007789022],"domain_scores_gemma":[0.9974319,0.0005097968,0.0008017484,0.0006530798,0.0005662616,0.00003724702],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005904219,0.000007003011,0.0001371401,0.000001142985,0.00005407917,4.210728e-7,0.00005483362,0.0001353891,0.0000037743,0.1029211,0.05710577,0.8395735],"study_design_scores_gemma":[0.0002444823,0.00001667472,0.003764349,0.000006485138,0.0000201841,0.00002555171,0.001422873,0.01210644,0.0000347203,0.07782294,0.9044902,0.00004511301],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001029386,0.00007495159,0.9636453,0.0218739,0.0009554959,0.00009710473,0.00005562423,0.00001214361,0.01225613],"genre_scores_gemma":[0.6700888,0.001272227,0.3189251,0.008342655,0.0006534676,0.000008513316,0.0001255369,0.00000766288,0.0005760093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8473844,"threshold_uncertainty_score":0.5702553,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7517157753114562,"gpt":0.5101888192272449,"spread":0.2415269560842113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","open_science"],"consensus_categories":[],"category_scores_codex":[0.003708911,0.0001340195,0.0002198455,0.00003125668,0.0003650005,0.0002418835,0.00774788,0.0001433739,0.0001470553],"category_scores_gemma":[0.01662672,0.00007338097,0.00004282488,0.0006242695,0.0008080339,0.00257932,0.007139632,0.0001547272,0.00050381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004093213,"about_ca_system_score_gemma":0.0000697156,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002243554,"about_ca_topic_score_gemma":0.00007436008,"domain_scores_codex":[0.9967989,0.00008504961,0.0004535983,0.001582228,0.0007760777,0.0003041359],"domain_scores_gemma":[0.9850859,0.001321568,0.0001132434,0.01304599,0.0003303619,0.0001029115],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001752755,0.00004503547,0.0000701897,0.000001607152,0.00001450101,2.768015e-7,0.00004882887,4.965606e-8,0.0008052422,0.005643458,0.6726002,0.3207689],"study_design_scores_gemma":[0.0001385168,0.00002564821,0.0004930564,0.000005751579,0.00002057156,0.00000602204,0.004950306,0.0005544246,0.0001417939,0.02085103,0.9726747,0.0001382241],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02592175,0.002695068,0.3298768,0.5957236,0.004046888,0.0006041332,0.03980104,0.001098531,0.0002321703],"genre_scores_gemma":[0.8688099,0.006883656,0.105455,0.002698287,0.008736468,0.00007671584,0.005956854,0.00005531434,0.001327816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8428882,"threshold_uncertainty_score":0.9976207,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.4172806973299066,"gpt":0.421573743505147,"spread":0.0042930461752404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003126193,0.0001347972,0.0002494952,0.0001346633,0.0002588336,0.001729072,0.003561175,0.000296236,0.00110197],"category_scores_gemma":[0.001369312,0.00008754731,0.0001225281,0.00004059829,0.0002130039,0.0003443881,0.001076123,0.0002323029,0.009716382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003212266,"about_ca_system_score_gemma":0.0001405781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003218034,"about_ca_topic_score_gemma":0.00001825286,"domain_scores_codex":[0.9984326,0.000002395506,0.0003291773,0.0004807041,0.0006120857,0.0001430271],"domain_scores_gemma":[0.9963705,0.0003866661,0.000345138,0.002746426,0.0001047533,0.00004651153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[1.732414e-7,0.000002426852,0.000008409418,3.232554e-7,0.000002591738,0.000001048568,0.000001459614,2.776321e-8,2.592395e-7,0.06586767,0.6310295,0.3030861],"study_design_scores_gemma":[0.0000190567,0.000003663268,0.0000201656,0.000005564879,0.000002039806,0.00000205025,0.00001787295,0.000008761147,0.000003096631,0.3663118,0.6335288,0.00007712334],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00000605629,0.00006625806,0.00284615,0.001985388,0.000137713,0.0001065696,0.0003971129,0.0001505014,0.9943042],"genre_scores_gemma":[0.0008517279,0.00002224242,0.0006541184,0.00008945836,0.0001149629,0.000009107831,0.00008678187,0.00001068372,0.9981609],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3030089,"threshold_uncertainty_score":0.9998112,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6585193461766956,"gpt":0.4307756542434794,"spread":0.2277436919332162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001848765,0.0001324577,0.0002038236,0.00001712505,0.0003016113,0.0002171646,0.007332259,0.0001159633,0.00004077654],"category_scores_gemma":[0.007829034,0.0000828148,0.00005655404,0.00160982,0.0003199354,0.0009084521,0.004531965,0.0002370416,0.00009031744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001701101,"about_ca_system_score_gemma":0.0001870829,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008667677,"about_ca_topic_score_gemma":0.0001734898,"domain_scores_codex":[0.9973727,0.0001079203,0.0004273199,0.0008734775,0.001014505,0.0002040768],"domain_scores_gemma":[0.9935889,0.0007065756,0.0004696566,0.00489326,0.0002626766,0.00007890233],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001552849,0.00008497667,0.0008188125,0.00002128034,0.00004748676,0.00000105515,0.003627733,7.040265e-7,0.0005016452,0.001305448,0.6086323,0.384943],"study_design_scores_gemma":[0.0002085714,0.00002962204,0.002176302,0.00001102391,0.00003602146,0.000004966303,0.01169381,0.004682096,0.0001081969,0.0005095159,0.9804252,0.0001146055],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03406731,0.007471021,0.04599928,0.8060657,0.001054741,0.003423897,0.0995646,0.0005445374,0.001808928],"genre_scores_gemma":[0.9710442,0.003902538,0.007033294,0.01132166,0.0009766662,0.00009324613,0.005508028,0.00002314883,0.00009722438],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9369769,"threshold_uncertainty_score":0.9980385,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Journalism; Newspaper; Media studies; Digital media; Audience measurement; Sociology; Political science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.3668295760981434,"gpt":0.429821876957204,"spread":0.0629923008590606,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001230318,0.0001645545,0.0003820343,0.0002191283,0.0002013064,0.0002940465,0.00213417,0.000185593,0.00006747121],"category_scores_gemma":[0.002335416,0.00007822131,0.00008537013,0.000281305,0.0007330155,0.0001870974,0.001094375,0.0002336444,0.0005651314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020652,"about_ca_system_score_gemma":0.0002823694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002039169,"about_ca_topic_score_gemma":0.0001760542,"domain_scores_codex":[0.9976871,0.00001375236,0.0009359018,0.0003374211,0.0008315916,0.0001942229],"domain_scores_gemma":[0.9965838,0.001443641,0.0005027821,0.0008896856,0.0005498434,0.00003030721],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003162718,0.00001031666,0.0001369373,0.00000213165,0.00003849368,0.000001129684,0.00008996477,7.685966e-8,0.000001579354,0.0307824,0.8567033,0.1122305],"study_design_scores_gemma":[0.00006773355,0.0000128399,0.0001077978,0.00009037914,0.000003155524,0.000002187355,0.0003985369,0.000001745355,0.00005715647,0.2932663,0.7059155,0.00007675905],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0003466218,0.01147293,0.001429299,0.00188695,0.0005445335,0.0005418268,0.0002517916,0.00007231162,0.9834538],"genre_scores_gemma":[0.001701986,0.002907941,0.0009553281,0.00005951872,0.0000718023,0.00002697164,0.00001365249,0.00001109466,0.9942517],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.2624839,"threshold_uncertainty_score":0.7263809,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Internet privacy","retraction":null,"screen_n_in":null,"score":{"opus":0.5255716264645494,"gpt":0.4348192692944025,"spread":0.0907523571701469,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003584684,0.00009255044,0.0003026774,0.00006123554,0.0002837468,0.00009108946,0.009246561,0.00001238825,0.0002308772],"category_scores_gemma":[0.001406682,0.00005251806,0.00003053757,0.0005100808,0.0001234271,0.000238455,0.01315617,0.0002322288,0.00003907939],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006832798,"about_ca_system_score_gemma":0.00003490171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001431831,"about_ca_topic_score_gemma":0.00004997779,"domain_scores_codex":[0.9981973,0.0001482157,0.0003611176,0.0005305576,0.000629916,0.0001328616],"domain_scores_gemma":[0.9915564,0.0003525215,0.0004430144,0.00756795,0.00004663461,0.00003345902],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001496093,0.00001460271,0.000191356,0.00009780333,0.000009158074,0.000001225437,0.00001007349,1.018556e-7,0.00002826834,0.002131093,0.7208172,0.2766976],"study_design_scores_gemma":[0.0000429971,0.00001165685,0.001008225,0.0003168114,0.00003604132,0.00001373945,0.001266964,0.0004738798,0.000008489778,0.00342803,0.9933229,0.00007027798],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.004432257,0.6050051,0.0004328717,0.3599276,0.0002192545,0.001904749,0.02144774,0.0001703511,0.006460053],"genre_scores_gemma":[0.5062031,0.4173853,0.01024617,0.03115213,0.0003439328,0.0004265419,0.002654146,0.00007450222,0.03151418],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.5017709,"threshold_uncertainty_score":0.9961139,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2637918791490564,"gpt":0.3909505788722479,"spread":0.1271586997231914,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002049688,0.000558257,0.0007776926,0.0007272753,0.0007735672,0.00060558,0.005268008,0.001867615,0.00007575301],"category_scores_gemma":[0.002301911,0.0004132635,0.0003113955,0.001066681,0.0002869896,0.0006449859,0.00005482624,0.001079809,0.0007832957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001932147,"about_ca_system_score_gemma":0.000674015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009793951,"about_ca_topic_score_gemma":0.0006287084,"domain_scores_codex":[0.9928836,0.000102524,0.001314256,0.002003315,0.003112203,0.0005840912],"domain_scores_gemma":[0.9864027,0.005517818,0.0006872384,0.005634543,0.00156486,0.0001928672],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009407924,0.0001507369,5.870133e-7,0.00001293707,0.0000747934,6.473542e-7,0.000007853296,0.0002081753,0.00003707877,0.00001520277,0.9672086,0.03218929],"study_design_scores_gemma":[0.0007749079,0.0001515227,6.488983e-7,0.000057157,0.0002049105,9.48596e-7,0.00002719258,0.001356322,0.0004762676,0.001570913,0.9948789,0.0005002401],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[8.533757e-7,0.00001661066,0.4408128,0.0006577604,0.5003197,0.0004305296,0.05751641,0.0001830228,0.0000623728],"genre_scores_gemma":[0.0001683761,0.0004825937,0.001035415,0.00003720085,0.9908517,0.0003290235,0.004337664,0.00009142193,0.00266662],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.490532,"threshold_uncertainty_score":0.9999947,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4012844435733259,"gpt":0.352524835493029,"spread":0.04875960808029683,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001105544,0.0001597599,0.0002706126,0.0001229604,0.0003550969,0.0007168716,0.009063158,0.0002380715,0.0003740321],"category_scores_gemma":[0.003121498,0.0000748319,0.00003061264,0.001084484,0.000837096,0.006465628,0.01085534,0.0002518349,0.0002058595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006643917,"about_ca_system_score_gemma":0.000177863,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007410639,"about_ca_topic_score_gemma":0.00005349637,"domain_scores_codex":[0.9974079,0.0001759492,0.0005836236,0.000998088,0.0005492018,0.0002852642],"domain_scores_gemma":[0.9901059,0.001776655,0.0002853837,0.00771267,0.00002129357,0.00009807594],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004123306,0.00001160987,0.002844023,4.009957e-7,0.000005937482,9.911174e-7,0.000005239631,3.59261e-8,0.00002656062,0.05022985,0.6242539,0.3225802],"study_design_scores_gemma":[0.000924335,0.00001976052,0.000708656,0.00001330292,0.00001207686,0.000008783712,0.0001415587,0.0008196203,0.00009430127,0.1276955,0.8694432,0.000118941],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03547301,0.007794262,0.1096764,0.7946429,0.001237741,0.00352159,0.0284394,0.002687325,0.01652743],"genre_scores_gemma":[0.7956992,0.01505423,0.1320191,0.009825279,0.003620781,0.0003725618,0.006052465,0.0001909852,0.03716537],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7848176,"threshold_uncertainty_score":0.9971447,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1674095964407354,"gpt":0.3594454531349252,"spread":0.1920358566941898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001433981,0.0001630579,0.0001962831,0.0003468417,0.0002761834,0.0005271299,0.001318648,0.0001662806,0.00005360673],"category_scores_gemma":[0.001080056,0.0001325456,0.00002136628,0.0006288717,0.0001435793,0.0007855203,0.0008071511,0.0002398973,0.00001339842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003626765,"about_ca_system_score_gemma":0.00003196385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005390728,"about_ca_topic_score_gemma":0.001758507,"domain_scores_codex":[0.9976974,0.00009635279,0.0004256506,0.001130409,0.0004053921,0.0002448019],"domain_scores_gemma":[0.9973396,0.001131026,0.0001274072,0.001306394,0.00003736425,0.00005821449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003513997,0.00003073859,0.0003162321,0.00000503215,0.00001005319,0.00001143773,0.00002739725,0.0004777839,0.009089825,0.01564286,0.005443584,0.9689099],"study_design_scores_gemma":[0.0002067795,0.00007475985,0.0001893387,0.00008395495,0.00001032872,0.00001001957,0.0001967358,0.3314343,0.006706523,0.001605241,0.6593059,0.0001760526],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2835527,0.006733546,0.705047,0.003042076,0.0003421407,0.00009366301,0.0003366715,0.0004829443,0.0003692117],"genre_scores_gemma":[0.9969937,0.0008491128,0.001160309,0.0002614701,0.00005727506,0.00001533097,0.0004973434,0.00001609036,0.0001493505],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9687338,"threshold_uncertainty_score":0.5405052,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.04500624072573308,"gpt":0.3587634838371366,"spread":0.3137572431114036,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004490101,0.00008365964,0.0002154134,0.0003430206,0.00007420983,0.00009802247,0.0003944628,0.00004791792,0.00006747532],"category_scores_gemma":[0.0000188044,0.00005823327,0.00005129788,0.001951668,0.0001177884,0.00008917051,0.0002031007,0.0000594388,0.00003964708],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005860595,"about_ca_system_score_gemma":0.000004523352,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002655747,"about_ca_topic_score_gemma":0.00001820888,"domain_scores_codex":[0.9989443,0.00002269428,0.000292249,0.0003609192,0.0002453965,0.0001344326],"domain_scores_gemma":[0.9988305,0.0002062426,0.0002080595,0.0006481076,0.00008244615,0.00002467603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00004655344,0.0001081664,0.8618858,0.00002755629,0.000375522,0.000001725049,0.0002170944,0.01079729,0.03725883,0.00400776,0.001261073,0.08401258],"study_design_scores_gemma":[0.002021062,0.0004547865,0.6862413,0.0001133051,0.0007804696,0.000005641704,0.004121982,0.07645918,0.08527841,0.009825923,0.1338471,0.0008508835],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.911364,0.0001123561,0.08740448,0.0001262758,0.00003098053,0.0001931357,0.00003248873,0.00003605365,0.0007002252],"genre_scores_gemma":[0.9780585,0.00002080728,0.02157841,0.00004516273,0.000005481293,0.000001790143,0.00001585947,0.000004380895,0.0002695991],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1756446,"threshold_uncertainty_score":0.2374684,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6079265092522445,"gpt":0.4614987018091529,"spread":0.1464278074430915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.001788516,0.0003727005,0.0005589405,0.0004681495,0.0003925514,0.0009367715,0.01645547,0.0007457342,0.003374543],"category_scores_gemma":[0.002925701,0.0002601806,0.0001163189,0.001178394,0.0006823234,0.0004972272,0.01347621,0.0006014507,0.07936583],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004320086,"about_ca_system_score_gemma":0.0004908399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006716653,"about_ca_topic_score_gemma":0.0002293522,"domain_scores_codex":[0.9950804,0.00004113191,0.000953875,0.002015764,0.001452481,0.0004563465],"domain_scores_gemma":[0.985266,0.002334143,0.0004141304,0.01168164,0.0001808656,0.0001231658],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[7.95146e-7,0.00001379451,0.00001957068,0.000006217241,0.00001967614,0.000004986859,0.000003106241,2.895312e-7,0.00001145213,0.1606371,0.668854,0.1704291],"study_design_scores_gemma":[0.00005030909,0.00001859474,0.0002047478,0.00004829295,0.0000306611,0.000003573592,0.000308108,0.0005734836,0.00001969539,0.1528555,0.845599,0.0002880292],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00002791253,0.0005981002,0.01263529,0.02190368,0.001283685,0.0008010755,0.04037806,0.001900467,0.9204717],"genre_scores_gemma":[0.0002232834,0.005004992,0.004463051,0.0003387032,0.0003274566,0.00003484984,0.004765716,0.00004791712,0.984794],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.176745,"threshold_uncertainty_score":0.999985,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Big data; Computer science; Data science; Artificial intelligence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.4464670136898698,"gpt":0.4489495589956508,"spread":0.002482545305780959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["sts"],"category_scores_codex":[0.008941715,0.0001916275,0.0002431694,0.001690084,0.002105627,0.001055497,0.006228618,0.0001039263,0.0004438654],"category_scores_gemma":[0.004414929,0.0001551447,0.00002685174,0.01477364,0.005855915,0.001689596,0.0001693419,0.001326873,0.001518263],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001410593,"about_ca_system_score_gemma":0.0006407188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001010092,"about_ca_topic_score_gemma":0.0005806327,"domain_scores_codex":[0.9923794,0.0001223219,0.0006095537,0.002017568,0.004127684,0.0007435136],"domain_scores_gemma":[0.9961319,0.001339103,0.0001132181,0.001556986,0.0004898102,0.0003689945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001153621,0.0002060398,0.00004488234,0.000002793586,0.000001737187,0.00001063599,0.0005562293,0.006011517,0.005687263,0.008309979,0.003466461,0.9755871],"study_design_scores_gemma":[0.0001702846,0.0006372854,0.0002500968,0.00002571711,0.000004471173,0.00001533324,0.003092462,0.6938061,0.09579085,0.003633841,0.2022429,0.0003306524],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7219392,0.0000324329,0.1307624,0.08804361,0.004064551,0.002559452,0.001565178,0.0006874181,0.05034578],"genre_scores_gemma":[0.9966882,0.00009901333,0.002396989,0.0002069765,0.0003510716,0.00002631653,0.000002605298,0.000009720225,0.0002190938],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9752564,"threshold_uncertainty_score":0.9999815,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Data science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.2982924050768856,"gpt":0.3712392572861838,"spread":0.07294685220929825,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003103808,0.0003927769,0.0005530333,0.001086699,0.0003847372,0.001670222,0.01920922,0.0004687006,0.0003508261],"category_scores_gemma":[0.002327959,0.0002833227,0.00007523939,0.002669248,0.001567051,0.0007833193,0.01002362,0.001092454,0.0006431459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002206646,"about_ca_system_score_gemma":0.0009847508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005505683,"about_ca_topic_score_gemma":0.0002396814,"domain_scores_codex":[0.9934953,0.00004632563,0.0008525438,0.002663703,0.002268456,0.0006737152],"domain_scores_gemma":[0.989029,0.0021923,0.0004649986,0.00783459,0.000333923,0.0001452003],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[6.629687e-7,0.00001466968,0.00005690151,0.000003887534,0.00000245134,0.000006849042,0.00003940011,0.0006094511,0.00002501309,0.0006576912,0.0470916,0.9514914],"study_design_scores_gemma":[0.000106227,0.00003853083,0.0003886461,0.0001169378,0.00000626084,0.00002580545,0.000001580109,0.09403338,0.000177496,0.4794177,0.4251724,0.0005150259],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00008709445,0.0005418055,0.9837289,0.002854422,0.002140265,0.0004424792,0.0001710282,0.0001080951,0.009925847],"genre_scores_gemma":[0.07925711,0.0005026052,0.8969992,0.00505194,0.006653193,0.00008956078,0.001163227,0.0001056796,0.01017743],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9509764,"threshold_uncertainty_score":0.9999619,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.6092219036420985,"gpt":0.4256557969394003,"spread":0.1835661067026982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003043071,0.00007669809,0.0001612153,0.0004618765,0.001798238,0.0002440838,0.00178918,0.00002655811,0.00008614869],"category_scores_gemma":[0.000196326,0.00005827355,0.00001647164,0.003419887,0.0007646058,0.000197968,0.003541066,0.00008097163,0.000009324652],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000738773,"about_ca_system_score_gemma":0.00003903377,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002206432,"about_ca_topic_score_gemma":0.0002302679,"domain_scores_codex":[0.9978769,0.00004916139,0.0002398879,0.0008546884,0.0007856081,0.0001937154],"domain_scores_gemma":[0.9983444,0.0004717351,0.0001236036,0.0009801276,0.00002660013,0.00005356766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001149191,0.00002599244,0.000595426,9.235396e-7,0.00001973575,2.612732e-7,0.0002735432,0.00005289173,0.0001661815,0.4830976,0.002575342,0.5131909],"study_design_scores_gemma":[0.0002006823,0.00008269944,0.02779619,0.000001513881,0.0001545444,0.00001478685,0.04079494,0.02486417,0.00008580273,0.3798711,0.5257797,0.000353884],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3162201,0.09438035,0.2875185,0.2174772,0.001073831,0.002261555,0.003169026,0.001347433,0.07655205],"genre_scores_gemma":[0.9954421,0.002247188,0.001974285,0.0001472603,0.00002531994,0.00005972054,0.00002763025,0.000002348684,0.00007418242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.679222,"threshold_uncertainty_score":0.9995013,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Folksonomy; Bookmarking; World Wide Web; Computer science; The Internet; Information retrieval; Multimedia","retraction":null,"screen_n_in":null,"score":{"opus":0.0279978366962107,"gpt":0.3093080577571535,"spread":0.2813102210609428,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004535011,0.0001054428,0.0001976996,0.000216384,0.001137236,0.0002249516,0.00147587,0.00006645253,0.000008235218],"category_scores_gemma":[0.001801791,0.00005802179,0.00009370518,0.002534573,0.00769943,0.0004380341,0.0007891731,0.0001694208,0.00001005919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004342565,"about_ca_system_score_gemma":0.00007417425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002389975,"about_ca_topic_score_gemma":0.00000503656,"domain_scores_codex":[0.9984854,0.000008417146,0.0004918008,0.0002597866,0.0004695019,0.0002850962],"domain_scores_gemma":[0.9974095,0.0004126489,0.0007345114,0.0007840791,0.0006250414,0.00003424904],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001671294,0.0000124451,0.001125631,0.00000906872,0.00001786479,2.109932e-8,0.0007045872,0.000003607382,0.001903564,0.1674356,0.1988634,0.6299075],"study_design_scores_gemma":[0.0001158365,0.00004739195,0.003295943,0.000002499162,0.000008399303,0.00001551806,0.04767761,0.0001933558,0.003033376,0.00640172,0.9391318,0.00007653701],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3774877,0.0002577449,0.01748326,0.6025895,0.0002748942,0.0007340564,0.00004762219,0.0001600492,0.0009650788],"genre_scores_gemma":[0.9583711,0.0003905132,0.03740639,0.003474253,0.0001522595,0.00007110286,0.000002121815,0.000005540834,0.000126685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7402684,"threshold_uncertainty_score":0.995001,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3330702791145367,"gpt":0.4150813688233324,"spread":0.08201108970879567,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003272436,0.0001926079,0.0002590276,0.00003502101,0.00005434226,0.001557149,0.008204417,0.0003024213,0.001030894],"category_scores_gemma":[0.0009151281,0.0001233502,0.00007948844,0.0004470115,0.0001951444,0.0005508222,0.006772027,0.0002303698,0.0248707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000117621,"about_ca_system_score_gemma":0.0003519504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001081427,"about_ca_topic_score_gemma":0.0001220905,"domain_scores_codex":[0.9969727,0.000003297807,0.0004547368,0.001205017,0.00118113,0.0001831358],"domain_scores_gemma":[0.9940277,0.0002390008,0.0001709098,0.005430679,0.00007625209,0.00005549839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[2.743386e-7,0.000003031684,0.000004832994,0.00000125027,0.000005651763,0.000003690255,2.219899e-7,8.394885e-8,1.446648e-8,0.2796073,0.530547,0.1898267],"study_design_scores_gemma":[0.00001181397,0.000003890019,0.0000224197,0.00001283058,0.000006595671,0.00000680602,0.000007874771,0.0001073831,1.101933e-7,0.4020999,0.5976261,0.00009432421],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[9.515729e-7,0.001483271,0.003630405,0.004580925,0.0003516906,0.000128747,0.05093556,0.0003563857,0.9385321],"genre_scores_gemma":[0.0003332495,0.0001895505,0.0007959107,0.000182462,0.0001834158,0.000006256826,0.001515332,0.00001203861,0.9967818],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1897323,"threshold_uncertainty_score":0.9998823,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Information retrieval; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.3816037324148056,"gpt":0.485443270552347,"spread":0.1038395381375414,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["sts","scholarly_communication","open_science"],"category_scores_codex":[0.007514168,0.0001726261,0.0003180493,0.001509335,0.001439516,0.002270425,0.01492538,0.0001307919,0.000004027714],"category_scores_gemma":[0.001410898,0.0001431058,0.00001542402,0.001092919,0.005691566,0.0161352,0.0153534,0.0004726506,0.00003433771],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007404968,"about_ca_system_score_gemma":0.0005566854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002629883,"about_ca_topic_score_gemma":0.0001683862,"domain_scores_codex":[0.9972658,0.00005446207,0.0009637767,0.0006199885,0.000830554,0.0002654243],"domain_scores_gemma":[0.9919939,0.001177608,0.0007180973,0.005798197,0.0002460566,0.00006611383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[6.268758e-7,0.000008843449,0.0009268496,0.000007882856,4.568463e-7,1.208585e-7,0.0002588195,0.00006079393,2.436353e-7,0.1008207,0.001980105,0.8959345],"study_design_scores_gemma":[0.0001456802,0.00001925221,0.006296166,0.0001668004,0.00000181217,0.00001155405,0.0001709107,0.2974828,6.013603e-7,0.04661332,0.6489043,0.0001868219],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.0008385393,0.01182803,0.1027094,0.01045843,0.0006130413,0.001372889,0.000462344,0.0001712999,0.871546],"genre_scores_gemma":[0.3910997,0.1462119,0.4548635,0.002592576,0.0002163475,0.00009156424,0.0009163573,0.00003011355,0.003977915],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8957477,"threshold_uncertainty_score":0.9998605,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary; Carleton University","funders":"","keywords":"Computer science; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.1330494260001287,"gpt":0.3836235653197722,"spread":0.2505741393196435,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006987946,0.0002858097,0.0003305345,0.0001555637,0.0003609824,0.0006731233,0.005981727,0.0002037182,0.0000664805],"category_scores_gemma":[0.0009626806,0.0001609095,0.00003754862,0.0005675605,0.0004258871,0.0006715755,0.002906178,0.0004451477,0.000003043434],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001613803,"about_ca_system_score_gemma":0.00002908242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000293272,"about_ca_topic_score_gemma":0.00002019565,"domain_scores_codex":[0.9966877,0.00002202984,0.0005371905,0.001354344,0.001121334,0.0002773626],"domain_scores_gemma":[0.9962634,0.0003421199,0.0003685461,0.002768507,0.0001516948,0.0001056992],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004514742,0.00004077661,0.0004404588,0.00000383031,0.00003121287,0.000001217434,0.00006757976,0.00001993207,0.0003237985,0.04473887,0.0669462,0.887341],"study_design_scores_gemma":[0.00130581,0.0003211774,0.2656965,0.0001489031,0.00009538426,0.0001199009,0.002475867,0.02237925,0.001787421,0.2539928,0.4508692,0.0008078074],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7652788,0.003796409,0.006997766,0.1492689,0.004578253,0.003489131,0.05523374,0.0007095957,0.01064743],"genre_scores_gemma":[0.9668615,0.001382079,0.02850601,0.001800924,0.0005155282,0.000009102575,0.0006562832,0.00002390181,0.0002446864],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8865332,"threshold_uncertainty_score":0.9993964,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1774949725398429,"gpt":0.4213214920683637,"spread":0.2438265195285208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001271112,0.0004391508,0.0008021814,0.0002821762,0.0003458997,0.0005692893,0.000988638,0.0002548567,0.00004308378],"category_scores_gemma":[0.0001357307,0.0003555199,0.0002261253,0.0005171518,0.0001651727,0.00008985098,0.002623073,0.002190407,0.0001288018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004994296,"about_ca_system_score_gemma":0.00008470885,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001671202,"about_ca_topic_score_gemma":0.00004559072,"domain_scores_codex":[0.9966037,0.0003990003,0.0008036332,0.001282655,0.0005665183,0.0003445501],"domain_scores_gemma":[0.9975045,0.0005228099,0.0005116266,0.001198744,0.0001405443,0.0001217646],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001058229,0.000156621,0.0042052,0.00001415085,0.0001107219,8.0998e-7,0.0001237626,0.002929729,0.00009058184,0.000141333,0.0001004925,0.992116],"study_design_scores_gemma":[0.001575869,0.00281488,0.04178834,0.0001920153,0.001369573,0.00000159392,0.009727584,0.1051839,0.005864589,0.07395529,0.7553632,0.002163121],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1672622,0.0005090558,0.8297631,0.0009223086,0.0002864285,0.0006576372,0.0002335756,0.0002786696,0.00008702768],"genre_scores_gemma":[0.8908188,0.000008874489,0.1084663,0.000004732396,0.0002656969,0.0002011148,0.0001279,0.00003289905,0.00007372964],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9899529,"threshold_uncertainty_score":0.9998897,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2583378344107343,"gpt":0.4562441576380132,"spread":0.1979063232272789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003100455,0.00007069016,0.0002139717,0.0001051967,0.0004816475,0.00001422141,0.002144065,0.00007881304,0.00001058834],"category_scores_gemma":[0.006362577,0.00003970255,0.00003171177,0.0008059565,0.07953224,0.0003169515,0.0007837602,0.0001442538,0.00003826087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003522091,"about_ca_system_score_gemma":0.0000354483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001106989,"about_ca_topic_score_gemma":0.0000174353,"domain_scores_codex":[0.9984931,0.00008211807,0.0003528012,0.0004558632,0.0003628761,0.0002532368],"domain_scores_gemma":[0.9976472,0.001169563,0.0001997184,0.0007315861,0.0002284782,0.00002341822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001724503,0.0002106189,0.2325285,0.000007534621,0.00003477488,6.994464e-7,0.05709507,0.0001068463,0.009989424,0.3235629,0.2345053,0.141941],"study_design_scores_gemma":[0.0001898781,0.0002617907,0.06062321,0.000007955843,0.00000474494,0.000004995262,0.1439454,0.00189002,0.00064157,0.7553895,0.03689224,0.0001487112],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9813123,0.0005199206,0.001339477,0.01528735,0.0002029487,0.0001023108,0.00003786186,0.00002072277,0.001177071],"genre_scores_gemma":[0.9986636,0.0001595491,0.0005439584,0.0005033627,0.00001851756,0.00001947663,0.000001539564,0.000001501391,0.0000884704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4318266,"threshold_uncertainty_score":0.9229727,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Ottawa","funders":"","keywords":"Multimedia; Computer science; Software; Library science; Telecommunications; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.277358758662118,"gpt":0.3742508454132318,"spread":0.09689208675111383,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003728008,0.00006469087,0.0001059048,0.00006048537,0.00006686968,0.00005455132,0.0006994581,0.00007808476,0.000180166],"category_scores_gemma":[0.0009461734,0.00003202201,0.00002813614,0.0004812104,0.000127612,0.0001085886,0.0002744159,0.0001038449,0.00004316784],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004618435,"about_ca_system_score_gemma":0.00001223928,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002314058,"about_ca_topic_score_gemma":0.0001214206,"domain_scores_codex":[0.9990591,0.000003671777,0.000183186,0.0002534206,0.0003730871,0.0001274941],"domain_scores_gemma":[0.9991459,0.0003003748,0.00009084497,0.0003320482,0.00007945632,0.00005132675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006635165,0.00004848254,0.001934215,0.000001395179,0.000003746089,1.401161e-7,0.0002991327,3.447401e-7,0.0002560229,0.06207542,0.2182169,0.7171576],"study_design_scores_gemma":[0.0002857786,0.00004128827,0.02665894,0.0000319912,0.000006653104,0.000009433116,0.007391368,0.0009494463,0.002287569,0.2701865,0.692022,0.0001289851],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6645984,0.001042953,0.0001514939,0.1947855,0.0001104951,0.0004743941,0.00001455181,0.0001620907,0.1386601],"genre_scores_gemma":[0.9870119,0.00369962,0.002248314,0.0003367806,0.00005185911,0.00001152893,3.50456e-7,0.000004878722,0.006634763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7170286,"threshold_uncertainty_score":0.1972691,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1300621430092644,"gpt":0.3301816099140026,"spread":0.2001194669047382,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003016604,0.00006963372,0.0002104847,0.0001890381,0.00009415222,0.0001262928,0.00325742,0.00004709922,0.00006111377],"category_scores_gemma":[0.000545604,0.00003691602,0.00003689719,0.0007159678,0.0001731308,0.001658299,0.0007976703,0.000287173,0.00003001502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000187562,"about_ca_system_score_gemma":0.00008937909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002248942,"about_ca_topic_score_gemma":0.00007708868,"domain_scores_codex":[0.9981552,0.0001586651,0.00105053,0.00006285122,0.0004826392,0.00009008479],"domain_scores_gemma":[0.9961587,0.0004667427,0.001290358,0.001635157,0.0004121039,0.00003696162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000429019,0.0005605757,0.02287114,0.00006696195,0.0001520258,4.609126e-7,0.03346353,0.0002458138,0.0009470431,0.5506651,0.1253287,0.2652696],"study_design_scores_gemma":[0.002949789,0.001079483,0.1312071,0.0001113779,0.00005272119,0.000229327,0.1329489,0.004122893,0.001360569,0.1474601,0.5780757,0.000401992],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9650639,0.0002625416,0.0006026742,0.02399093,0.00004611024,0.0003940319,0.0001851609,0.0000156401,0.00943898],"genre_scores_gemma":[0.9983466,0.0002241601,0.001171813,0.0001837078,0.000004297569,0.000002419867,0.00004615069,0.000001502159,0.00001932135],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.452747,"threshold_uncertainty_score":0.605315,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3280054473452616,"gpt":0.4708973819526968,"spread":0.1428919346074352,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.004400928,0.0001277734,0.0002743758,0.0002292157,0.0001385784,0.0003032423,0.001780328,0.0001412076,0.002544142],"category_scores_gemma":[0.005386485,0.00007504445,0.0001478228,0.0006491694,0.0001919867,0.000106658,0.0002576734,0.0004494624,0.006458849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001268359,"about_ca_system_score_gemma":0.00008138108,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003235975,"about_ca_topic_score_gemma":0.00008011416,"domain_scores_codex":[0.9969928,0.00005419204,0.001045102,0.0006600961,0.001013754,0.0002340071],"domain_scores_gemma":[0.9935569,0.003586937,0.0002014641,0.002299892,0.000187184,0.000167675],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002223831,0.0002378888,0.009557418,8.360403e-7,0.00000359761,0.000007334787,0.000002573376,0.00007005099,0.0001309467,0.04206476,0.2252739,0.7226285],"study_design_scores_gemma":[0.0002074002,0.0001453433,0.007349082,0.000005409341,0.000003952621,0.000007392684,0.0001734959,0.0308378,0.000778997,0.007681564,0.9526718,0.0001377925],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4671628,0.0000131849,0.459678,0.008044789,0.004960896,0.001002714,0.0001518981,0.0007242969,0.05826144],"genre_scores_gemma":[0.9882426,0.00001209746,0.009152052,0.0006994185,0.00009844331,0.00004256815,0.00001625992,0.0000084635,0.00172807],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7273979,"threshold_uncertainty_score":0.9983677,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1996476480207741,"gpt":0.3605601265355474,"spread":0.1609124785147734,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003044789,0.000669312,0.0008256516,0.000779757,0.002722031,0.007776957,0.007843838,0.001087967,0.0004777696],"category_scores_gemma":[0.001249924,0.000455843,0.0005631214,0.0008962118,0.001154196,0.0007693302,0.001598717,0.001569122,0.0008001078],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007084675,"about_ca_system_score_gemma":0.000865324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002755155,"about_ca_topic_score_gemma":0.0002505778,"domain_scores_codex":[0.9928308,0.0001931607,0.001790525,0.001662903,0.002522887,0.0009997217],"domain_scores_gemma":[0.991586,0.001714283,0.001193797,0.004385381,0.0009001049,0.000220394],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006844868,0.00002018677,0.00002058625,0.000005207316,0.00004955987,0.00001846591,0.000051697,0.000007796195,0.000002930844,0.07777276,0.8438101,0.07823384],"study_design_scores_gemma":[0.0003005371,0.00004297286,0.00007109645,0.00007952067,0.00004782283,0.00003065048,0.0003720032,0.0002069032,0.000002227127,0.1002762,0.898087,0.0004830916],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00005377903,0.0006788037,0.004305356,0.004211084,0.001760123,0.001317716,0.0001981932,0.000686735,0.9867882],"genre_scores_gemma":[0.001600377,0.00007818524,0.001533706,0.0009626626,0.000900824,0.0002466003,0.0002125681,0.00009805988,0.994367],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.07775074,"threshold_uncertainty_score":0.9999779,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brock University","funders":"","keywords":"Mathematics; Big data; Computer science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.3866746233379459,"gpt":0.400313487758653,"spread":0.01363886442070705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00491413,0.0009851087,0.0033219,0.0005170956,0.0004142809,0.0006912968,0.008750131,0.0006118842,0.0006791845],"category_scores_gemma":[0.004846799,0.0006988258,0.001694944,0.002649647,0.002903171,0.0002459661,0.002961538,0.001289412,0.003007488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002645549,"about_ca_system_score_gemma":0.000589484,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001307527,"about_ca_topic_score_gemma":0.000006232006,"domain_scores_codex":[0.9907919,0.0001833696,0.002485859,0.00264432,0.003244917,0.0006496958],"domain_scores_gemma":[0.9757504,0.00811501,0.002866568,0.01241912,0.0004750764,0.0003738153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000556969,0.0004934664,0.000007377789,0.0001101528,0.001592261,0.000004128854,0.001514144,0.000006891331,0.000002824044,0.259502,0.7246007,0.01216054],"study_design_scores_gemma":[0.0001880747,0.0001480156,0.000008552425,0.0001428038,0.0008170946,0.000004890852,0.011641,0.0229116,0.000003129036,0.5581414,0.405172,0.0008214174],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00006874415,0.0004208169,0.4310923,0.003006148,0.00009559889,0.0009394891,0.002143952,0.000516994,0.561716],"genre_scores_gemma":[0.0207922,0.0004067991,0.192679,0.001650589,0.001210578,0.000277959,0.002364559,0.0003472893,0.780271],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3194287,"threshold_uncertainty_score":0.9998103,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.7668386003949124,"gpt":0.4910349129574692,"spread":0.2758036874374432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001473769,0.00008721791,0.0001168282,0.0001786091,0.00005315273,0.0002281345,0.01170412,0.00003662635,0.0004302857],"category_scores_gemma":[0.0004970837,0.00006815664,0.00001529183,0.0002724064,0.00009156787,0.001007236,0.004996412,0.0000819113,0.0004806917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009660845,"about_ca_system_score_gemma":0.00001404068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002094882,"about_ca_topic_score_gemma":0.00003471841,"domain_scores_codex":[0.997626,0.00003703537,0.0004293331,0.0007013965,0.001106019,0.0001002069],"domain_scores_gemma":[0.9942467,0.0001665003,0.0002664218,0.005107256,0.0001855,0.0000276828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005251692,0.0000393765,0.00009350134,0.000001812521,0.00001830531,3.544104e-7,0.000001746248,0.000003275216,0.00004129806,0.4844884,0.03617602,0.4791307],"study_design_scores_gemma":[0.0002230688,0.00003218862,0.002783115,0.00003878957,0.00001386139,6.292803e-7,0.0003140316,0.08182675,0.00007077421,0.1296061,0.7849844,0.0001062175],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002421388,0.00001706678,0.6792082,0.03396322,0.001073302,0.0003499206,0.005483822,0.0001197018,0.2773634],"genre_scores_gemma":[0.9827741,0.0001781225,0.01126054,0.0001907024,0.0001007873,0.000008815004,0.004116593,0.000004773391,0.001365581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803527,"threshold_uncertainty_score":0.993643,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3405370817150935,"gpt":0.3135485827336533,"spread":0.02698849898144018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001187278,0.0001680004,0.0003280484,0.0000912581,0.0001324178,0.0001365722,0.003737603,0.0002725363,0.000008065213],"category_scores_gemma":[0.001765688,0.0001380344,0.00007415059,0.002745053,0.0001998556,0.0007907548,0.005827838,0.0001685286,0.000002205938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000365795,"about_ca_system_score_gemma":0.001267585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003248836,"about_ca_topic_score_gemma":0.002539441,"domain_scores_codex":[0.9978271,0.00007007209,0.0004833582,0.001026665,0.0003079197,0.0002849382],"domain_scores_gemma":[0.9927341,0.0001820475,0.0008765142,0.004493852,0.001652779,0.00006072105],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00005120536,0.00009731585,0.0255048,0.00002547524,0.00002563697,0.00002805876,0.00002341011,0.05176141,0.000001611135,0.8821831,0.0394963,0.0008016695],"study_design_scores_gemma":[0.0003728176,0.00002168342,0.004253242,0.00001745645,0.00004221412,0.000001221694,0.001359923,0.05340445,0.00004512916,0.8739401,0.06639019,0.0001515917],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4739015,0.0001118208,0.514388,0.001672899,0.0004422625,0.001775211,0.004308202,0.0001201237,0.003280053],"genre_scores_gemma":[0.9952433,0.00005701698,0.0009113054,0.00002764279,0.00004498871,0.00001019273,0.0009035772,0.000007501505,0.002794546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5213417,"threshold_uncertainty_score":0.7263983,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5419266624503839,"gpt":0.5022757446171617,"spread":0.03965091783322217,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.008175008,0.0001286718,0.0003889624,0.001722673,0.0003461988,0.0002043672,0.007487353,0.00005448854,0.00002789965],"category_scores_gemma":[0.004445101,0.00008512623,0.00004219526,0.01548912,0.002002809,0.0008308454,0.005677063,0.0003419182,0.00002022094],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004151517,"about_ca_system_score_gemma":0.0001142675,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002367135,"about_ca_topic_score_gemma":0.000219329,"domain_scores_codex":[0.9944342,0.0002983252,0.0005458815,0.001940197,0.002411191,0.0003701576],"domain_scores_gemma":[0.9887081,0.004081742,0.0001865008,0.006639292,0.0002889543,0.00009535183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000631635,0.000244102,0.00207874,0.00001104724,0.0000555856,0.00003336467,0.0000264671,0.005220299,0.00006675965,0.2253039,0.0002831336,0.7666134],"study_design_scores_gemma":[0.0002723617,0.0003763986,0.01907811,0.0003399735,0.0002282688,0.000002102149,0.04175087,0.7680562,0.002453297,0.06571905,0.1013148,0.0004086426],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01241103,0.00267982,0.9629402,0.003741923,0.000201915,0.0004762494,0.003068001,0.00005434224,0.01442652],"genre_scores_gemma":[0.9567162,0.002162469,0.04076429,0.0001300059,0.00001987037,0.00001931497,0.0001506451,0.000002850918,0.00003430184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9443052,"threshold_uncertainty_score":0.9978826,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3562913429076259,"gpt":0.3743734165200423,"spread":0.01808207361241637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001258448,0.00007238768,0.0003325488,0.00004844118,0.00009078255,0.00005469438,0.003805012,0.00002357429,0.001185851],"category_scores_gemma":[0.001467788,0.00003512067,0.00006579326,0.001934218,0.00007915649,0.0001286514,0.0005549847,0.0000726953,0.0000563272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001443043,"about_ca_system_score_gemma":0.0003211817,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1914941,"about_ca_topic_score_gemma":0.4925815,"domain_scores_codex":[0.9981862,0.00006033008,0.0005258228,0.0003060409,0.0007792006,0.0001423859],"domain_scores_gemma":[0.9950203,0.0002674632,0.000274576,0.004201445,0.0001895795,0.00004661814],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[4.707001e-8,0.000002339831,0.00008703877,0.00000991129,0.00002626122,1.111713e-7,4.70019e-7,6.492829e-7,0.000001406575,0.0007331911,0.6210644,0.3780741],"study_design_scores_gemma":[0.00001367514,0.000001982344,0.00591808,0.00004599835,0.0001650294,7.503371e-7,0.00005113221,0.0002162123,0.000006575397,0.001511583,0.9920208,0.00004818982],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0009483947,0.7013714,0.01272002,0.265867,0.0004151028,0.001686131,0.001167333,0.00005185668,0.01577277],"genre_scores_gemma":[0.7540415,0.2009665,0.005961624,0.02504527,0.000239557,0.0005146944,0.0004298351,0.00002951212,0.01277152],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.7530931,"threshold_uncertainty_score":0.9997272,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Term (time); Series (stratigraphy); Computer science; Time series; Econometrics; Mathematics; Machine learning; Geology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.203687782524059,"gpt":0.3686355930938267,"spread":0.1649478105697677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006035397,0.0002995876,0.0004402205,0.0004421133,0.0003899693,0.0005186665,0.000670942,0.0003868125,0.00009216339],"category_scores_gemma":[0.0001372923,0.0002658763,0.0001358232,0.0003206371,0.0002858471,0.0001959777,0.0003001432,0.0003719762,0.0003229971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005886091,"about_ca_system_score_gemma":0.0000739214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003450772,"about_ca_topic_score_gemma":0.0001960678,"domain_scores_codex":[0.9975457,0.000006912849,0.0008743341,0.0009199945,0.0003121008,0.0003409366],"domain_scores_gemma":[0.9987063,0.0001941861,0.0002434261,0.0006018301,0.0001724888,0.00008180927],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001777442,0.00003549422,0.00002463927,0.00003156653,0.00002564543,0.000003243398,0.0001881233,0.0001055655,0.00004351831,0.5441998,0.01118661,0.444138],"study_design_scores_gemma":[0.00001552448,0.00001894497,0.000001681747,0.0000634376,0.00003362114,0.000004293986,0.0004512654,0.2391506,0.0002239717,0.7234873,0.03629388,0.000255522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00006678706,0.001768337,0.9762343,0.001221739,0.0001255737,0.001477112,0.001848864,0.0001713534,0.017086],"genre_scores_gemma":[0.04499273,0.001409339,0.04921169,0.0003341502,0.0007043095,0.003805355,0.001738986,0.0002014412,0.897602],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9270226,"threshold_uncertainty_score":0.9999793,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5011702460060182,"gpt":0.5034852273212985,"spread":0.002314981315280296,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.001154139,0.000168281,0.0005864238,0.0004342834,0.0009295569,0.001154995,0.0008207894,0.0001033918,0.000008256235],"category_scores_gemma":[0.03285304,0.0001081833,0.00005251934,0.0002147591,0.001772705,0.1637345,0.002266505,0.0002697333,0.000005559544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005774345,"about_ca_system_score_gemma":0.00004755224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":1.992358e-7,"about_ca_topic_score_gemma":2.863744e-7,"domain_scores_codex":[0.9976428,0.00006402963,0.001526537,0.0001594081,0.0003821687,0.0002250895],"domain_scores_gemma":[0.9922564,0.006067195,0.000533388,0.0006653701,0.0003659758,0.0001116835],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001705421,0.00005321422,0.001525793,0.0005753097,0.0001480123,0.00006540173,0.003025797,0.000001864601,0.000001889672,0.8612258,0.0627946,0.07041173],"study_design_scores_gemma":[0.001447744,0.0005223265,0.004442104,0.000433435,0.0001336397,0.001718252,0.1742585,0.001329823,0.0001661674,0.3304214,0.4847611,0.0003654369],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.2321433,0.07163027,0.005828396,0.6766275,0.002766433,0.001412283,0.003238332,0.0002275215,0.006125973],"genre_scores_gemma":[0.9380555,0.04079759,0.0179431,0.002914849,0.000188821,0.00003643832,0.00002232754,0.000006503322,0.00003491108],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7059121,"threshold_uncertainty_score":0.9998819,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5454127380640832,"gpt":0.4547144353797887,"spread":0.09069830268429452,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00143412,0.00005720098,0.0001196239,0.0001161307,0.00005078853,0.0000717252,0.0005725779,0.0000547819,0.0003261553],"category_scores_gemma":[0.0003293768,0.00003388309,0.000007470365,0.0002551125,0.0001056127,0.0001354727,0.0004689517,0.00006627585,0.0000406919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004132555,"about_ca_system_score_gemma":0.00002702107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003515001,"about_ca_topic_score_gemma":0.0000215026,"domain_scores_codex":[0.9988927,0.00002741311,0.0002305337,0.0003620973,0.0003776882,0.000109557],"domain_scores_gemma":[0.9973973,0.001611955,0.00007275031,0.0008288609,0.00005475264,0.00003439404],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005307083,0.00004799986,0.01808054,0.000005010159,0.000007339701,4.248099e-7,0.00001952127,0.00006512088,0.004775249,0.02653337,0.007297377,0.943115],"study_design_scores_gemma":[0.003172861,0.002742455,0.261741,0.00001774824,0.00004230032,0.000008478985,0.005852986,0.5597159,0.03349198,0.09133945,0.04138247,0.0004924093],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.576365,0.00002369071,0.4200416,0.002155952,0.00003948461,0.0005006886,0.0001814615,0.00003793489,0.0006542268],"genre_scores_gemma":[0.9699878,0.00002302669,0.02976242,0.0001344692,0.000005308487,0.000007114946,0.00003090952,0.000002195981,0.00004678465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9426226,"threshold_uncertainty_score":0.3571171,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2807200847194476,"gpt":0.3860434832446655,"spread":0.1053233985252179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006296397,0.0002352513,0.0003230549,0.0003768794,0.0002645159,0.0005699074,0.001502792,0.0002800131,0.00008611267],"category_scores_gemma":[0.000539241,0.0001810646,0.00003467571,0.0001836894,0.0001583948,0.003120435,0.001360939,0.0003328307,0.002546769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002830695,"about_ca_system_score_gemma":0.0002986728,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.075775e-7,"about_ca_topic_score_gemma":0.00001467849,"domain_scores_codex":[0.9981451,0.000005678222,0.0008133802,0.0004310806,0.0004285968,0.0001761549],"domain_scores_gemma":[0.9970234,0.0001703995,0.0007083041,0.001550916,0.0004793032,0.00006765122],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003733977,0.000003125373,0.000003276244,0.000047658,0.000003538999,7.718121e-8,0.0001003632,0.000001803593,0.000003159927,0.04516254,0.00957251,0.9450982],"study_design_scores_gemma":[0.0001772669,0.00001313245,0.00001481713,0.0001315185,0.00001155636,0.000006066904,0.0002445998,0.003173154,0.00001262802,0.0456441,0.9503415,0.0002296475],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00001094935,0.004760286,0.03467559,0.0005129112,0.000400669,0.0003236369,0.0004114182,0.0001850157,0.9587195],"genre_scores_gemma":[0.02281552,0.005026102,0.01657615,0.001173257,0.0004755085,0.0000392375,0.003563613,0.00007330837,0.9502573],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9448686,"threshold_uncertainty_score":0.9982299,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vision; Abandonment (legal); Petroleum; Economics; Industrial organization; Business; Political science; Natural resource economics; Sociology; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.1142019358501692,"gpt":0.3490909240990651,"spread":0.2348889882488959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science","research_integrity"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.01967688,0.00009919659,0.0002405839,0.0005139983,0.0004458412,0.01860869,0.005503917,0.0003425611,0.00002943425],"category_scores_gemma":[0.02887007,0.00005163321,0.0001649255,0.001397738,0.0002173104,0.0637701,0.0005706597,0.002938263,0.00001011505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003676582,"about_ca_system_score_gemma":0.0002200908,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009174726,"about_ca_topic_score_gemma":0.00001465035,"domain_scores_codex":[0.9957454,0.00008327365,0.001454764,0.0001734633,0.002252301,0.0002908209],"domain_scores_gemma":[0.9923207,0.002299342,0.001845723,0.0006773789,0.002704276,0.0001526436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008384001,0.00002918778,0.02810843,0.00000228109,0.00003403992,0.000008240457,0.0003033697,0.000007403859,0.005135882,0.2034251,0.1798312,0.583031],"study_design_scores_gemma":[0.0002066772,0.00007923147,0.08139428,0.0000222993,0.00001043989,0.00007270518,0.0131433,0.000009555233,0.001684925,0.1012352,0.8020716,0.00006982591],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6932977,0.0144776,0.009073776,0.2758543,0.001620569,0.0001086686,0.00004785914,0.00004834101,0.005471138],"genre_scores_gemma":[0.9904116,0.0005360498,0.006653904,0.001038156,0.0009695349,8.87124e-7,0.000001949686,0.00001002804,0.0003779375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6222404,"threshold_uncertainty_score":0.9998768,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Calculus (dental); Computer science; Data science; Data mining; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.5917623436835,"gpt":0.4080369243857217,"spread":0.1837254192977783,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.006119426,0.0001000914,0.0001490955,0.000121134,0.0003497348,0.001213739,0.006538788,0.00006885911,0.00002184611],"category_scores_gemma":[0.002346835,0.00005946645,0.00003618028,0.001340976,0.0001077565,0.000951061,0.001697367,0.001812253,0.00007614268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003357767,"about_ca_system_score_gemma":0.001895111,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002598837,"about_ca_topic_score_gemma":0.00453285,"domain_scores_codex":[0.9969551,0.00009944556,0.0004302541,0.0005268013,0.0008336812,0.001154742],"domain_scores_gemma":[0.9959971,0.0005606255,0.0001567516,0.003189995,0.00005748481,0.00003807371],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006040979,0.00008373416,0.001182724,5.706145e-7,0.00003220473,0.00003025728,0.00005356093,0.000009190903,0.00004230888,0.5647603,0.02303213,0.410767],"study_design_scores_gemma":[0.0002520461,0.00002681139,0.0004106787,0.000006730945,0.00001088957,0.0009093589,0.02570939,0.001141186,0.000007798287,0.8095638,0.1618519,0.0001093991],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02388147,0.005626773,0.8973148,0.06549852,0.000537709,0.0002173095,0.000942293,0.00006744958,0.005913715],"genre_scores_gemma":[0.9969136,0.002041164,0.000112081,0.0002040949,0.0002139077,0.000001779665,0.0002177089,0.000006990199,0.0002886493],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9730322,"threshold_uncertainty_score":0.9998231,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Graphics; Computer science; Data structure; Data mining; Algorithm; Theoretical computer science; Computer graphics (images); Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.112449382486073,"gpt":0.3299356116610665,"spread":0.2174862291749934,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005981777,0.000529555,0.0005667431,0.0002970655,0.0002880458,0.001177061,0.007715395,0.000570969,0.00390029],"category_scores_gemma":[0.0004410115,0.0003616555,0.0000569871,0.0002163705,0.0003822086,0.0006324854,0.003721891,0.0007581181,0.0003330209],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002428296,"about_ca_system_score_gemma":0.000846564,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2050762,"about_ca_topic_score_gemma":0.3077646,"domain_scores_codex":[0.9944896,0.00001201602,0.0009180381,0.001883946,0.00225298,0.0004433803],"domain_scores_gemma":[0.9954911,0.0004149705,0.0006310013,0.002414102,0.0008018106,0.0002470128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004116604,0.00001287495,0.00008094651,0.000006782728,0.00004960542,0.000002682881,0.000008259921,0.000002652438,0.000008763266,0.02007578,0.9387315,0.04101606],"study_design_scores_gemma":[0.0001854479,0.00003575222,0.0006483175,0.00003276888,0.0000272078,0.00002801769,0.0001142954,0.00137622,0.00002164019,0.0295016,0.9675934,0.0004353741],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001041771,0.001382743,0.001151055,0.1227554,0.00306037,0.00264338,0.02062946,0.0005439274,0.8467919],"genre_scores_gemma":[0.0009486562,0.002040046,0.004825218,0.00137443,0.0005722999,0.00008156874,0.002157097,0.00005781751,0.9879429],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.141151,"threshold_uncertainty_score":0.9998835,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.5205431722637939,"gpt":0.3891481667219264,"spread":0.1313950055418674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075743,0.00004234007,0.0001230592,0.0001379875,0.0001939758,0.0000300719,0.003743756,0.00004223398,0.00001522713],"category_scores_gemma":[0.0009625726,0.00002942485,0.00001835039,0.00143733,0.002348728,0.0001961027,0.0004779356,0.00005351705,0.000003207951],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001515465,"about_ca_system_score_gemma":0.001638129,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1385355,"about_ca_topic_score_gemma":0.211658,"domain_scores_codex":[0.9988051,0.0000265724,0.000128718,0.0002500026,0.0006386314,0.000150966],"domain_scores_gemma":[0.9981247,0.0001906227,0.0001719871,0.0007892887,0.0006231653,0.0001002148],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001170879,0.00002980611,0.01172376,0.000002188466,0.00002369814,0.000002338997,0.0273073,0.000008415789,0.003710022,0.6203139,0.05002156,0.2868452],"study_design_scores_gemma":[0.0001988233,0.00005243499,0.02102668,0.00001323226,0.00002179904,6.744212e-7,0.6606896,0.00102089,0.002142895,0.2615049,0.05317283,0.0001552299],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8099762,0.0008818389,0.00355136,0.04420741,0.0005492783,0.0004348125,0.01868529,0.00003296621,0.1216809],"genre_scores_gemma":[0.9995307,0.000007740636,0.0002726384,0.00006949761,0.00004357794,7.614342e-7,0.000004975798,0.000001410199,0.00006874704],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6333823,"threshold_uncertainty_score":0.867201,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2588652072134615,"gpt":0.4199736750678363,"spread":0.1611084678543748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003191886,0.00004777568,0.0001681259,0.0001336905,0.00007313683,0.00009864421,0.0004915672,0.00005329236,0.000002045973],"category_scores_gemma":[0.003731839,0.00001668015,0.00001606738,0.001621346,0.0006626285,0.0002993825,0.0003513335,0.0003594661,1.708708e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000002485075,"about_ca_system_score_gemma":0.00001662245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002519669,"about_ca_topic_score_gemma":0.0001534892,"domain_scores_codex":[0.9990798,0.0002169509,0.0002608172,0.00009834843,0.0002972514,0.00004683303],"domain_scores_gemma":[0.9964059,0.002733583,0.0001354018,0.0006485166,0.00007084245,0.000005783228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","study_design_scores_codex":[0.0001824739,0.00001738508,0.004367585,0.00002384585,0.0001614721,0.000001546171,0.3094774,0.00001927144,0.000003851402,0.4880358,0.02070506,0.1770043],"study_design_scores_gemma":[0.001087625,0.00008414972,0.01304794,0.0001658599,0.0001494565,0.000006113393,0.7617177,0.0008253956,0.00006930115,0.179212,0.04352349,0.0001108656],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.933251,0.02127268,0.0002175913,0.04051251,0.0001172673,0.0003760189,0.001683307,0.00001196092,0.00255768],"genre_scores_gemma":[0.997463,0.00152329,0.0002674704,0.0006641673,0.00001273151,0.000008267024,0.00005428632,7.738584e-7,0.000005957673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4522404,"threshold_uncertainty_score":0.4467629,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Business","retraction":null,"screen_n_in":null,"score":{"opus":0.07562978095177517,"gpt":0.3188520873582011,"spread":0.2432223064064259,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.005623741,0.0003115168,0.0003912206,0.0004910994,0.0001640835,0.0008134002,0.00381255,0.0003884685,0.003088773],"category_scores_gemma":[0.003840939,0.0002603173,0.0001427477,0.001390025,0.0004289426,0.0001302494,0.00147704,0.0005060208,0.008803916],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003639888,"about_ca_system_score_gemma":0.0001052982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009662035,"about_ca_topic_score_gemma":0.003454346,"domain_scores_codex":[0.9955803,0.001400988,0.0005898806,0.001196455,0.0009084268,0.0003240184],"domain_scores_gemma":[0.9920002,0.001318837,0.0005022719,0.005464758,0.0005770678,0.0001368416],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[6.934962e-7,0.00007552432,0.0000736359,0.00001788698,0.0000199859,0.000003172914,0.0001158488,1.620725e-7,0.00006062406,0.09056272,0.8413708,0.067699],"study_design_scores_gemma":[0.000108534,1.040494e-7,0.0001471986,0.0005030626,0.00001505856,0.000007262372,0.00006428418,0.0001860416,0.0008053489,0.01911033,0.9787855,0.0002672316],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.00007090924,0.00459494,0.03518266,0.02080876,0.0003002682,0.0003991018,0.01297381,0.0009499625,0.9247196],"genre_scores_gemma":[0.00619358,0.001162739,0.0232627,0.0002100131,0.00004774291,0.0000976809,0.003494167,0.0002601781,0.9652712],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.1374148,"threshold_uncertainty_score":0.9999849,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4615837290717801,"gpt":0.3930748585083757,"spread":0.06850887056340443,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008773475,0.0001456772,0.0002753703,0.0001158665,0.0004493998,0.0008491962,0.002076988,0.00007791151,0.00005989257],"category_scores_gemma":[0.001549586,0.0000953448,0.00002851359,0.001584586,0.0001361978,0.002029903,0.001530405,0.0002691615,0.00005620981],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001553671,"about_ca_system_score_gemma":0.0002363173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001226893,"about_ca_topic_score_gemma":0.00002066764,"domain_scores_codex":[0.9978808,0.0000977563,0.0004597093,0.0008069838,0.0004749371,0.0002797835],"domain_scores_gemma":[0.9976078,0.0002931831,0.0003504287,0.001561557,0.00006498932,0.0001220192],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00009193086,0.00004846339,0.0007880387,0.00005062281,0.00004305113,0.000003196785,0.002546734,0.00003812918,0.00232578,0.1704547,0.05413411,0.7694752],"study_design_scores_gemma":[0.0003384869,0.0001847358,0.0011969,0.00002673021,0.000005244198,0.000009566607,0.00444295,0.02334904,0.002952658,0.1238612,0.8433939,0.0002385399],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001378727,0.0002173015,0.8930076,0.1038116,0.00005212215,0.0005808924,0.0001328052,0.000505541,0.0003134048],"genre_scores_gemma":[0.07631715,0.00001127806,0.9197283,0.003289344,0.0002069032,0.00009071793,0.0001352093,0.0000232351,0.0001978116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7892599,"threshold_uncertainty_score":0.8188819,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Network security; Computer security; Information security; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.1954275231884608,"gpt":0.4254140955292128,"spread":0.229986572340752,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.006600542,0.0002209412,0.0003626346,0.002564603,0.0007849531,0.001429977,0.01340771,0.0001678309,0.00001295609],"category_scores_gemma":[0.0006671801,0.0001920194,0.00002111278,0.004344832,0.005459737,0.02180153,0.01351754,0.0006517529,0.0001669734],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001967672,"about_ca_system_score_gemma":0.00119858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001657294,"about_ca_topic_score_gemma":0.0001889748,"domain_scores_codex":[0.9962732,0.00004633931,0.001214439,0.0008489949,0.001262033,0.0003550014],"domain_scores_gemma":[0.989792,0.0009877029,0.0005624833,0.007908114,0.0006316578,0.0001180628],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001811941,0.00003868636,0.0006269292,0.00002276611,0.000001070413,7.98532e-8,0.0007697287,0.00005684349,0.000001900154,0.3232496,0.00581613,0.6694145],"study_design_scores_gemma":[0.0001648133,0.00001137801,0.00152204,0.00007256742,0.00000282715,0.000008542197,0.0003264974,0.08967214,0.00000160076,0.04482548,0.8631783,0.0002138522],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0003219025,0.004780768,0.07316661,0.01041945,0.0003936331,0.003060414,0.00101433,0.0001681053,0.9066748],"genre_scores_gemma":[0.4146457,0.2746118,0.2829666,0.009116889,0.0003369592,0.001629799,0.003859749,0.00007948075,0.01275293],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8939219,"threshold_uncertainty_score":0.9996066,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Sunnybrook Health Science Centre","funders":"","keywords":"Psychology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06531720183050992,"gpt":0.4113839724885769,"spread":0.346066770658067,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003487207,0.0004509842,0.001157606,0.0009876844,0.0002097601,0.0003539304,0.006369657,0.001828011,0.000200967],"category_scores_gemma":[0.02412542,0.0003666205,0.0004631843,0.00143821,0.000228924,0.0004824064,0.0009408979,0.002092063,0.0006894725],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001233296,"about_ca_system_score_gemma":0.002159955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004606359,"about_ca_topic_score_gemma":0.0001031597,"domain_scores_codex":[0.9939135,0.000415547,0.002382067,0.0008443644,0.001998533,0.0004460009],"domain_scores_gemma":[0.98177,0.006736903,0.003435962,0.0009521802,0.006887219,0.0002177284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008185925,0.0001567835,0.001141909,0.000002474245,0.0002478159,0.000006165543,0.00008981425,0.0001995215,0.0001093696,0.01144899,0.7350283,0.251487],"study_design_scores_gemma":[0.001123845,0.0004109339,0.0004985541,0.00006142811,0.00007854352,0.00001088622,0.0000903257,0.0001964852,0.0002560135,0.08259897,0.9143883,0.0002857085],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"editorial","genre_gemma":"editorial","genre_scores_codex":[0.001825054,0.0004741041,0.05520137,0.02389808,0.9097388,0.0004865309,0.003234459,0.0001345035,0.005007084],"genre_scores_gemma":[0.03274205,0.002363808,0.01240956,0.001787236,0.9452571,0.0001136279,0.001452671,0.00008260619,0.003791326],"genre_candidate":"editorial","genre_consensus":"editorial","teacher_disagreement_score":0.2512013,"threshold_uncertainty_score":0.9998786,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1797360089877833,"gpt":0.4039070268650471,"spread":0.2241710178772638,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009077201,0.0001955999,0.0006237873,0.0005870927,0.0001733722,0.0005143303,0.003492901,0.000293508,0.00008525231],"category_scores_gemma":[0.02072629,0.0001744466,0.00004669157,0.001451516,0.0002272502,0.002034023,0.001276396,0.0002820599,0.0000717126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001774649,"about_ca_system_score_gemma":0.0009563862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001615063,"about_ca_topic_score_gemma":0.000597625,"domain_scores_codex":[0.9960771,0.00002725248,0.00106383,0.0008185704,0.001471988,0.000541211],"domain_scores_gemma":[0.994202,0.002197769,0.001096602,0.001990171,0.000461485,0.00005200903],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007825109,0.0002043044,0.0009187597,0.0002106042,0.00001785361,0.00000311234,0.002565462,0.00002947016,0.00003266341,0.9200611,0.06622767,0.009721201],"study_design_scores_gemma":[0.00008664438,0.000009429319,0.00004707222,0.00005519862,0.000002546603,5.850155e-7,0.002580796,0.0002009925,0.00001483384,0.5791589,0.4177279,0.0001150733],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.000294291,0.0009632536,0.0003307463,0.002845101,0.0004688352,0.001141702,0.002727455,0.0001129833,0.9911156],"genre_scores_gemma":[0.0005690582,0.001699636,0.005870183,0.00002316863,0.00005709249,0.0003665048,0.0004117634,0.00002373975,0.9909788],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3515003,"threshold_uncertainty_score":0.9875225,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Scholarship; Big data; Data science; Computer science; Political science; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.7184773296688539,"gpt":0.4597071714925218,"spread":0.2587701581763321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.01281714,0.00008984377,0.0001915658,0.0003148855,0.001079519,0.001905916,0.06293576,0.00007477979,0.00006085146],"category_scores_gemma":[0.01163708,0.00006031648,0.00002193136,0.0005216599,0.000422429,0.003011439,0.002862837,0.0007969225,0.0001448842],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004872646,"about_ca_system_score_gemma":0.0007917179,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008265081,"about_ca_topic_score_gemma":0.5553377,"domain_scores_codex":[0.9979438,0.0003587955,0.0006864101,0.0002965367,0.0004822947,0.000232206],"domain_scores_gemma":[0.967629,0.0009884719,0.0009264095,0.02996727,0.0003227864,0.0001661013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000006534011,0.00002374371,0.03401119,0.000001048832,0.00001290738,0.000008467233,0.00007944024,0.00001397678,0.000005160226,0.004408267,0.525566,0.4358633],"study_design_scores_gemma":[0.0001398904,0.000007460903,0.1175629,0.00004263814,0.00001159187,0.00001649828,0.0002848073,0.001477628,0.000001136561,0.01204429,0.868345,0.00006613744],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1224439,0.03729964,0.0101759,0.7345137,0.004839655,0.001993005,0.0130213,0.00007573123,0.07563717],"genre_scores_gemma":[0.9939474,0.0005455826,0.003740473,0.0005155226,0.0002619129,0.000002509141,0.0007495376,0.000007206711,0.0002297981],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8715035,"threshold_uncertainty_score":0.9991302,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Saskatchewan; University of Manitoba; Université du Québec à Montréal","funders":"","keywords":"Political science; History","retraction":null,"screen_n_in":null,"score":{"opus":0.1491956718034218,"gpt":0.3650486482847204,"spread":0.2158529764812986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.001711066,0.0004109419,0.0007171013,0.001503093,0.001620572,0.0002678515,0.01117288,0.0009327786,0.002392865],"category_scores_gemma":[0.0006253364,0.0003704076,0.0001667314,0.001405503,0.001842027,0.000144965,0.008592007,0.002183242,0.0006536445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001945436,"about_ca_system_score_gemma":0.0002963546,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002072844,"about_ca_topic_score_gemma":0.00006757847,"domain_scores_codex":[0.9963279,0.0003215439,0.00113643,0.0009761995,0.0008684084,0.000369515],"domain_scores_gemma":[0.9835974,0.001945949,0.001031052,0.01297218,0.0003636875,0.00008976288],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00000884402,0.0001165726,0.00002119701,0.000003662892,0.00003877185,0.000001172381,0.00004996795,0.000005737497,0.0001737491,0.6331725,0.2144288,0.1519791],"study_design_scores_gemma":[0.000133301,0.0001275998,0.000009657299,0.00003015006,0.00002544488,0.00001173533,0.0004044874,0.0001125685,0.00006967256,0.3643778,0.6344604,0.0002371237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002682645,0.01830457,0.000721659,0.1821262,0.0002092317,0.001491309,0.001462906,0.000908831,0.794507],"genre_scores_gemma":[0.07450905,0.08886499,0.009300767,0.002729962,0.0001501775,0.00294418,0.002944297,0.0002006632,0.8183559],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.4200317,"threshold_uncertainty_score":0.9998748,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1329052155375318,"gpt":0.3870639894584439,"spread":0.2541587739209122,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009931155,0.0002020665,0.000596697,0.0005125502,0.0001981373,0.0001021082,0.002688452,0.0006658196,0.0001373534],"category_scores_gemma":[0.0001378103,0.0001673899,0.0001111937,0.002462269,0.0005679411,0.00008343488,0.00190916,0.0004231935,0.00001453566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004591525,"about_ca_system_score_gemma":0.00003825689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001402087,"about_ca_topic_score_gemma":0.0005395091,"domain_scores_codex":[0.9976283,0.00005148166,0.0006456274,0.0009030771,0.0005543357,0.000217138],"domain_scores_gemma":[0.9962455,0.0009556611,0.0005077276,0.002133708,0.0001249208,0.00003247117],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004963373,0.00002382552,0.0004709341,0.00001081441,0.0002865479,8.884999e-7,0.00004480782,0.0002293885,1.287766e-7,0.01466716,0.09546603,0.8887945],"study_design_scores_gemma":[0.00007533265,0.000007961263,0.0008224304,0.00001276559,0.0004133945,2.874942e-7,0.00001578354,0.005486814,5.606091e-7,0.3755338,0.6174613,0.0001696742],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000005097716,0.00173965,0.9647917,0.0006002409,0.00004417984,0.0004963722,0.0007368593,0.00004398273,0.03154198],"genre_scores_gemma":[0.3891789,0.01563838,0.3294107,0.003848529,0.01298713,0.00171462,0.03838139,0.000396873,0.2084435],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8886248,"threshold_uncertainty_score":0.6825963,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.3198026514178617,"gpt":0.4543416081632938,"spread":0.1345389567454321,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01653424,0.0000517026,0.0002137391,0.0005646438,0.0000901395,0.00002974652,0.001962484,0.00003023321,0.00001943333],"category_scores_gemma":[0.002692607,0.00002658388,0.00001006381,0.003455322,0.0009972315,0.0007083834,0.0003132896,0.0003527582,9.06231e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003278573,"about_ca_system_score_gemma":0.0002878439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008801801,"about_ca_topic_score_gemma":0.0004784595,"domain_scores_codex":[0.9975075,0.00001529699,0.0007675277,0.0002340184,0.001303748,0.000171973],"domain_scores_gemma":[0.9987027,0.0001707857,0.0001902659,0.0006534836,0.0002389965,0.00004379118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000571454,0.00008582436,0.9224657,0.000005982754,0.000001084376,0.0002822671,0.001604897,0.0000721063,0.001431193,0.0009859463,0.005581222,0.06747811],"study_design_scores_gemma":[0.0002958599,0.00005912411,0.9479256,0.0001317813,0.000003788085,0.000207916,0.03077842,0.002555154,0.00005508447,0.003852367,0.01409215,0.00004277888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9868482,0.0007373788,0.00002133172,0.01168637,0.00006990295,0.00004277613,0.00000239871,0.000001347523,0.0005903297],"genre_scores_gemma":[0.9980709,0.000954751,0.0003837728,0.0005000109,0.00006333248,6.619428e-7,0.00000200568,0.00000104304,0.00002354952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06743533,"threshold_uncertainty_score":0.5730472,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.565963653801508,"gpt":0.400250837830554,"spread":0.165712815970954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001436258,0.0001683743,0.0002290632,0.0002181191,0.0002201405,0.0002592933,0.004356899,0.0001160766,0.00008538786],"category_scores_gemma":[0.005412601,0.0000827887,0.00004548099,0.00098267,0.0006297573,0.0003603778,0.001621859,0.0001116728,0.0001210805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002203237,"about_ca_system_score_gemma":0.0001093848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007042263,"about_ca_topic_score_gemma":0.00002212197,"domain_scores_codex":[0.9977029,0.00002061052,0.0005845109,0.0007047455,0.000712069,0.0002751931],"domain_scores_gemma":[0.9973636,0.0005670997,0.0004126554,0.001014235,0.0005580292,0.00008436417],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001318749,0.0000198185,0.00001109602,9.170105e-7,0.000002684068,4.071446e-8,0.00002206801,3.342884e-7,0.05494371,0.5141483,0.001018665,0.4298192],"study_design_scores_gemma":[0.00001257623,0.00005972033,0.0000393976,0.0000429022,0.000004967503,0.000002270044,0.0003338628,0.001625747,0.3092905,0.685647,0.002848723,0.00009231815],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01190327,0.00004932444,0.901636,0.07727379,0.0003839317,0.0003804467,0.0002246983,0.0001685434,0.007979988],"genre_scores_gemma":[0.9937305,0.0002342824,0.004815435,0.0002451944,0.00007906739,0.00002703146,5.386175e-7,0.000009252024,0.0008587328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9818272,"threshold_uncertainty_score":0.8096275,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Corporate governance; Big data; Data science; Knowledge management; Business; Computer science; Political science; Data mining; Finance","retraction":null,"screen_n_in":null,"score":{"opus":0.3485527211434682,"gpt":0.3665641368052689,"spread":0.01801141566180076,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002196077,0.0004757603,0.0008291174,0.0004071553,0.0002769315,0.00006643293,0.00895338,0.001663473,0.0001065235],"category_scores_gemma":[0.002116263,0.000354685,0.0001368548,0.00012522,0.000967185,0.0001671068,0.002477729,0.001453066,0.001780611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002535628,"about_ca_system_score_gemma":0.001741719,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002974122,"about_ca_topic_score_gemma":0.007998808,"domain_scores_codex":[0.9951105,0.00005163735,0.001674953,0.001467049,0.001149886,0.0005459981],"domain_scores_gemma":[0.9917207,0.0009533109,0.001627295,0.004927428,0.0003282565,0.0004430256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001529675,0.000001353215,0.0000466358,0.00003402782,0.00002844414,0.00000556443,0.00002359434,7.371827e-8,0.0002150314,0.6018414,0.07446891,0.3233334],"study_design_scores_gemma":[0.0001399827,0.00001706544,0.00003049405,0.001143734,0.0000555685,0.00004059061,0.00005650435,0.00002954952,0.0003877853,0.1190874,0.8786461,0.0003651785],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0002825735,0.005889216,0.0001491939,0.00121183,0.0006815924,0.0005937034,0.006792407,0.0002029543,0.9841965],"genre_scores_gemma":[0.05069325,0.0008803143,0.0005874792,0.000375768,0.00114196,0.00005543807,0.0001281518,0.0001077219,0.9460299],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8041772,"threshold_uncertainty_score":0.9998905,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Visualization; Content (measure theory); Data science; Information retrieval; Machine learning; Artificial intelligence; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.5210663781089064,"gpt":0.4604436965248431,"spread":0.06062268158406331,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003064381,0.00005981548,0.0002321537,0.00101425,0.0001651882,0.0002312101,0.0002948591,0.00005681605,0.000002490905],"category_scores_gemma":[0.004669978,0.00003822758,0.0000398756,0.001294745,0.00007019643,0.0002323098,0.0003332302,0.000235964,1.109913e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001545477,"about_ca_system_score_gemma":0.0000422923,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001520544,"about_ca_topic_score_gemma":0.00002359706,"domain_scores_codex":[0.9985887,0.0000265573,0.0005414995,0.0002386748,0.0004696351,0.0001349223],"domain_scores_gemma":[0.9981979,0.0006911566,0.0002213516,0.0003763936,0.0004407005,0.00007253759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002321168,0.0006444402,0.409878,0.0003616299,0.003776198,0.000413144,0.0008636586,0.1213612,0.01878678,0.0575623,0.02002904,0.3660915],"study_design_scores_gemma":[0.0003566704,0.0002694874,0.06004811,0.00007693752,0.0001590892,0.0001390584,0.001065674,0.7933449,0.0008330217,0.009327455,0.134238,0.0001416208],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3901258,0.005306226,0.6029665,0.001138213,0.00009039971,0.0002417538,0.00002270219,0.00002390655,0.00008450177],"genre_scores_gemma":[0.9953995,0.0005369141,0.003713516,0.000004334655,0.00003019899,0.000006249237,0.00002882307,0.000003629465,0.0002768532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6719837,"threshold_uncertainty_score":0.5590737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}