{"meta":{"query_hash":"b633b755ce29","filters":{"venue":"Big Data and Information Analytics"},"cohort_total":18,"direct_labels_cover":0,"predictions_cover":18,"exported":18,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/b633b755ce29","api":"https://metacan.xera.ac/api/v1/cohort?venue=Big+Data+and+Information+Analytics"},"results":[{"id":"W2476626105","doi":"10.3934/bdia.2016.1.1","title":"ACO-based solution for computation offloading in mobile cloud computing","year":2015,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Science Foundation of Hunan Province; National Natural Science Foundation of China","keywords":"Mobile cloud computing; Computation offloading; Cloud computing; Computer science; Ant colony optimization algorithms; Distributed computing; Computation; Mobile device; Mobile computing; Computer network; Edge computing; Operating system; Algorithm","score_opus":0.12292265115255017,"score_gpt":0.31653533143521567,"score_spread":0.19361268028266548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2476626105","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011140066,0.0000450256,0.98536694,0.00022955395,0.002565027,0.00022004041,0.0000063316124,0.00007903484,0.00034799345],"genre_scores_gemma":[0.8965744,0.000010258645,0.100508556,0.0008947522,0.0009512819,0.0000046731316,0.0010421124,0.000006614291,0.0000073518418],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99897337,0.000027637305,0.00042247926,0.00016668472,0.00019228151,0.0002175381],"domain_scores_gemma":[0.9991383,0.00010873355,0.00018940277,0.00030439286,0.00017040441,0.00008879851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010229893,0.000101223326,0.00013784303,0.00026602272,0.00013025073,0.0003248793,0.00043133635,0.000057993137,8.973812e-8],"category_scores_gemma":[0.00015303586,0.00010324585,0.00001960069,0.00041429215,0.000022122598,0.002442865,0.0003272895,0.00008130148,0.00001233595],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021783886,0.000047043937,0.0018504469,0.00012443373,0.000013403191,8.917889e-7,0.0029559922,0.029605927,0.000014515635,0.001579008,0.035858396,0.92792815],"study_design_scores_gemma":[0.0007497932,0.000056936147,0.00044388557,0.000032223004,0.0000055844803,0.0000027703409,0.00009787027,0.94462913,0.00002464066,0.00019784916,0.053635333,0.00012398741],"about_ca_topic_score_codex":0.000018766144,"about_ca_topic_score_gemma":0.000002853872,"teacher_disagreement_score":0.9278042,"about_ca_system_score_codex":0.00006872227,"about_ca_system_score_gemma":0.00014184731,"threshold_uncertainty_score":0.42102435},"labels":[],"label_agreement":null},{"id":"W2497857151","doi":"10.3934/bdia.2016.1.31","title":"What's the big deal about big data?","year":2015,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Big data; Variety (cybernetics); Data science; Theme (computing); Novelty; Computer science; Analytics; Scale (ratio); Informatics; Business intelligence; Data analysis; Cloud computing; Knowledge management; World Wide Web; Engineering; Artificial intelligence; Data mining; Psychology","score_opus":0.502372524389615,"score_gpt":0.40834206601971434,"score_spread":0.09403045836990065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2497857151","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030015567,0.0017087549,0.8263881,0.030478006,0.045257237,0.0011391642,0.006604286,0.00034080015,0.058068078],"genre_scores_gemma":[0.9435082,0.0020169239,0.003963918,0.01608481,0.0033590253,0.0000064107016,0.022684589,0.000021747714,0.008354347],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99687576,0.00009149134,0.00079633197,0.00042670147,0.0015762917,0.00023339162],"domain_scores_gemma":[0.9938185,0.00034610723,0.0003494599,0.004943747,0.00034521217,0.00019692589],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.010186119,0.00012563396,0.00016541447,0.0003301578,0.00030528312,0.0061185923,0.0041558295,0.000044692653,0.00001993408],"category_scores_gemma":[0.003467382,0.00007361612,0.000021998123,0.0011417929,0.00016232168,0.008194793,0.0048548263,0.000115960385,0.0008913516],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000044918547,0.000007046402,0.0002289362,0.0000024097585,0.000008755056,4.293942e-7,0.0003486067,0.00007341749,8.9105875e-8,0.00062303647,0.3944362,0.6042666],"study_design_scores_gemma":[0.00020611467,0.000011245771,0.0017832734,0.000009810687,0.000019824305,0.000004506853,0.005329352,0.2525744,9.007411e-7,0.0005330939,0.7394431,0.00008434903],"about_ca_topic_score_codex":0.00009274046,"about_ca_topic_score_gemma":0.00019197063,"teacher_disagreement_score":0.9134927,"about_ca_system_score_codex":0.000017839364,"about_ca_system_score_gemma":0.00019036783,"threshold_uncertainty_score":0.9998866},"labels":[],"label_agreement":null},{"id":"W2527216788","doi":"10.3934/bdia.2016006","title":"Detecting coalition attacks in online advertising: A hybrid data mining approach","year":2016,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Mitacs","keywords":"Computer science; Computer security; Data mining","score_opus":0.12153644611219627,"score_gpt":0.2952623683958516,"score_spread":0.17372592228365535,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527216788","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030658996,0.000029488509,0.96771216,0.00046305588,0.00022308082,0.00007607934,0.0002653972,0.000074204574,0.0004975221],"genre_scores_gemma":[0.9708221,0.0001355753,0.027186206,0.00040357315,0.00011533109,0.0000012103462,0.0013118548,0.000003855722,0.000020315741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989932,0.00003478337,0.00036364325,0.0002442979,0.0002044333,0.00015963225],"domain_scores_gemma":[0.99847746,0.00007987693,0.00015785385,0.0011763768,0.00004960578,0.000058820315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00068939786,0.00009122668,0.000106840795,0.00022531104,0.00009451771,0.00026725885,0.0009750818,0.000043213124,0.0000017597146],"category_scores_gemma":[0.00042482547,0.00007090119,0.000009402682,0.00032775014,0.000024760737,0.008858513,0.0009142093,0.00007809578,0.000009250382],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008727697,0.000025348623,0.0018897183,0.000033395903,0.000009929012,0.0000011646176,0.00036084605,0.000035389632,0.00005646313,0.00034857236,0.0020072635,0.99522316],"study_design_scores_gemma":[0.0004807885,0.000025083353,0.0039588707,0.000067745335,0.000008724511,0.000036181078,0.00019009483,0.9608169,0.000086828484,0.000066877335,0.034122538,0.00013934891],"about_ca_topic_score_codex":0.000047740854,"about_ca_topic_score_gemma":0.000046639478,"teacher_disagreement_score":0.9950838,"about_ca_system_score_codex":0.00003275002,"about_ca_system_score_gemma":0.000048353315,"threshold_uncertainty_score":0.6422208},"labels":[],"label_agreement":null},{"id":"W2552308941","doi":"10.3934/bdia.2016008","title":"Time aware topic based recommender system","year":2016,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Recommender Systems and Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Recommender system; Computer science; Collaborative filtering; Information retrieval; Filter (signal processing); Cold start (automotive); World Wide Web; Topic model","score_opus":0.0647731355806819,"score_gpt":0.2560971786824018,"score_spread":0.19132404310171988,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552308941","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000086129374,0.000012827079,0.9905476,0.0030778334,0.00022336975,0.000096395925,0.00008061836,0.00021762954,0.0056575937],"genre_scores_gemma":[0.98254853,0.00008733571,0.014062966,0.0023790482,0.00014705105,0.000010824129,0.00023644936,0.0000069084367,0.000520909],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992737,0.000030234043,0.0002991748,0.00013018976,0.000143901,0.00012276396],"domain_scores_gemma":[0.998811,0.000047966194,0.00012623474,0.00087987084,0.000067598565,0.0000673024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003490631,0.00008493686,0.00011603019,0.00012713764,0.00007434501,0.00020057459,0.000641672,0.000051953302,0.000011195599],"category_scores_gemma":[0.000022756793,0.000053918422,0.000018126311,0.00013854052,0.000015848384,0.0029568493,0.00031536588,0.000033671204,0.00011536304],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026521006,0.000014300246,0.00051416765,0.00013142104,0.00002831683,0.0000016023262,0.00012812742,0.0000013989497,0.000013937321,0.029915055,0.16043971,0.8088093],"study_design_scores_gemma":[0.00027047392,0.00002604815,0.000241126,0.000080017264,0.0000054275765,0.000010654741,0.00004068967,0.3544524,0.000104181025,0.0000538474,0.64459383,0.00012133039],"about_ca_topic_score_codex":0.000011125014,"about_ca_topic_score_gemma":0.0000019102038,"teacher_disagreement_score":0.9824624,"about_ca_system_score_codex":0.00003595213,"about_ca_system_score_gemma":0.000042410044,"threshold_uncertainty_score":0.21987295},"labels":[],"label_agreement":null},{"id":"W2553369270","doi":"10.3934/bdia.2016009","title":"Manifold data mining helps businesses grow more effectively","year":2016,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Manifold (fluid mechanics); Nonlinear dimensionality reduction; Data mining; Data science; Business; Computer science; Engineering; Artificial intelligence; Mechanical engineering","score_opus":0.08789576314961048,"score_gpt":0.2890048371131446,"score_spread":0.20110907396353414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2553369270","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016853389,0.000037948004,0.9923975,0.0029427367,0.00015647935,0.000094315474,0.0018650922,0.000093386625,0.0007272435],"genre_scores_gemma":[0.5664449,0.0022975681,0.4100223,0.004548784,0.00076698395,0.000031751326,0.015248376,0.000029813951,0.00060956844],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991002,0.000011808052,0.00026004136,0.0002700678,0.00020322303,0.00015467877],"domain_scores_gemma":[0.99748844,0.0001109314,0.000141669,0.0020815595,0.00009887246,0.00007852175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035599858,0.00010644185,0.00010953259,0.00012267614,0.00014415907,0.00041432324,0.0020137634,0.000039266655,0.0000046507303],"category_scores_gemma":[0.00024556453,0.000073412804,0.000008457057,0.00037780395,0.0000423599,0.0100513045,0.002170306,0.000038827224,0.00008436767],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000001582208,0.000015312471,0.00039111177,0.000025116282,0.000019131538,8.9992244e-7,0.00013331865,9.314632e-7,0.000029659697,0.010089088,0.028595733,0.9606981],"study_design_scores_gemma":[0.00040047,0.000022012153,0.012538263,0.00006931057,0.000026569525,0.0000274784,0.00012928761,0.49528298,0.000066530476,0.000116847645,0.49109757,0.00022267253],"about_ca_topic_score_codex":0.000030148713,"about_ca_topic_score_gemma":0.000009031492,"teacher_disagreement_score":0.96047544,"about_ca_system_score_codex":0.000011803791,"about_ca_system_score_gemma":0.0000676648,"threshold_uncertainty_score":0.7286953},"labels":[],"label_agreement":null},{"id":"W2604624992","doi":"10.3934/bdia.2016011","title":"Analyzing opinion dynamics in online social networks","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Opinion Dynamics and Social Influence","field":"Physics and Astronomy","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Skepticism; Empathy; Dynamics (music); Social network (sociolinguistics); Population; Focus (optics); Social media; Psychology; Social psychology; Computer science; Data science; Sociology; World Wide Web; Epistemology","score_opus":0.054415160693912556,"score_gpt":0.32772892051200514,"score_spread":0.2733137598180926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604624992","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32706776,0.00011268736,0.60675234,0.006814815,0.0031651133,0.0006635467,0.008348558,0.0000869564,0.046988223],"genre_scores_gemma":[0.9943534,0.00013047279,0.00017086846,0.00009699406,0.00039201582,9.890496e-7,0.004825674,0.0000036934746,0.000025896874],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937576,0.000010661093,0.00028833054,0.00009727954,0.000083627776,0.00014435803],"domain_scores_gemma":[0.99925613,0.0000131498755,0.00025133122,0.0003822536,0.000053118227,0.00004403522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018895043,0.00008633963,0.0001345894,0.00007213178,0.00040502765,0.00040030084,0.00038402816,0.00005107883,0.000009704704],"category_scores_gemma":[0.000021333157,0.00008790899,0.000024607292,0.00007823961,0.00006765315,0.0019088918,0.00031962208,0.0001426283,0.000004382441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000093675435,0.00005109317,0.38416028,0.000019726815,0.000043928,2.3370475e-7,0.0002774704,0.0007145738,2.6366502e-7,0.19145216,0.0009184944,0.4223524],"study_design_scores_gemma":[0.00028987575,0.000005324434,0.085638344,0.000015648866,0.0000073881624,1.0921893e-7,0.0006978593,0.900956,9.807619e-8,0.0005473996,0.0117318,0.00011015902],"about_ca_topic_score_codex":0.00044541643,"about_ca_topic_score_gemma":0.00017169901,"teacher_disagreement_score":0.90024143,"about_ca_system_score_codex":0.000030251087,"about_ca_system_score_gemma":0.000037104874,"threshold_uncertainty_score":0.386011},"labels":[],"label_agreement":null},{"id":"W2604652933","doi":"10.3934/bdia.2016012","title":"Modeling daily guest count prediction","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Customer churn and segmentation","field":"Business, Management and Accounting","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Lasso (programming language); Computer science; Data mining; Preprocessor; Data pre-processing; Count data; Transaction data; Feature (linguistics); Data modeling; Regression; Artificial intelligence; Predictive modelling; Machine learning; Regression analysis; Poisson distribution; Database transaction; Statistics; Mathematics; Database","score_opus":0.10183468277054568,"score_gpt":0.2750029553143635,"score_spread":0.17316827254381778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604652933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47146773,0.00014615136,0.27766228,0.0064917775,0.009090632,0.0010460896,0.0010286573,0.0005802745,0.2324864],"genre_scores_gemma":[0.99424076,0.00014918909,0.00008647039,0.0014143173,0.0011807698,0.0000018528424,0.0028491819,0.0000047635167,0.00007272019],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934185,0.000001545366,0.00025595483,0.00009903194,0.00019802124,0.00010360256],"domain_scores_gemma":[0.9991132,0.0000037011703,0.00020000212,0.0005453539,0.00012533856,0.000012385922],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00028349823,0.00008147686,0.00008098123,0.0001515912,0.0004994555,0.0015580138,0.00030969278,0.00004084434,0.00001829052],"category_scores_gemma":[0.00012751253,0.00007513939,0.000013733786,0.000064008804,0.00003000779,0.014507307,0.00030179493,0.00005875869,0.00019029723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021370132,0.00017824341,0.11631284,0.001250517,0.0002477625,0.0000059230024,0.0010544576,0.006743057,0.0001719546,0.0530006,0.20884109,0.61197984],"study_design_scores_gemma":[0.00032285962,0.0000022193121,0.0060548787,0.0000146744715,0.00004052926,8.780729e-7,0.0002703155,0.7762857,0.0000016170266,0.00007496397,0.21685676,0.000074587675],"about_ca_topic_score_codex":0.00033473084,"about_ca_topic_score_gemma":0.00008681794,"teacher_disagreement_score":0.76954263,"about_ca_system_score_codex":0.000014072265,"about_ca_system_score_gemma":0.000013997452,"threshold_uncertainty_score":0.99947846},"labels":[],"label_agreement":null},{"id":"W2611392997","doi":"10.3934/bdia.2016013","title":"A testbed to enable comparisons between competing approaches for computational social choice","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Logic, Reasoning, and Knowledge","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Testbed; Computer science; Rank (graph theory); Context (archaeology); Domain (mathematical analysis); Preference; Voting; Action (physics); Social choice theory; Order (exchange); Field (mathematics); Group decision-making; Artificial intelligence; Operations research; Data science; Machine learning; Engineering","score_opus":0.26739060138568005,"score_gpt":0.3367448301259789,"score_spread":0.06935422874029884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611392997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020277502,0.000011730628,0.9875008,0.0018541025,0.00015901627,0.00021764499,0.00023352042,0.000056150817,0.007939269],"genre_scores_gemma":[0.9456339,0.0000028856678,0.052536223,0.00040036242,0.00041136798,0.000008161874,0.0009398001,0.0000038126796,0.000063470325],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991255,0.0000159623,0.0002960878,0.0001791898,0.00017937341,0.00020392632],"domain_scores_gemma":[0.998755,0.00018470048,0.00027303564,0.0005305072,0.00014940658,0.000107392494],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00040456702,0.0001074426,0.00018632354,0.00009900911,0.001072825,0.0011981908,0.0012784259,0.000053749423,0.0000011266044],"category_scores_gemma":[0.00050110917,0.00009878394,0.000028942128,0.00010783675,0.000058146103,0.002730744,0.0008711526,0.00008183596,0.00003200792],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001878556,0.00011805219,0.07115987,0.00023156643,0.00018455536,5.4765303e-7,0.006232519,0.001923486,0.000004120209,0.36936295,0.15334673,0.3974168],"study_design_scores_gemma":[0.00041386436,0.000027211445,0.05347328,0.000007982323,0.000018571911,0.0000011470667,0.00013466245,0.70240366,0.0000060524085,0.00052139146,0.2428528,0.00013939757],"about_ca_topic_score_codex":0.000029616436,"about_ca_topic_score_gemma":0.000029438279,"teacher_disagreement_score":0.94360614,"about_ca_system_score_codex":0.000020455187,"about_ca_system_score_gemma":0.000094507224,"threshold_uncertainty_score":0.99983865},"labels":[],"label_agreement":null},{"id":"W2736357342","doi":"10.3934/bdia.2017001","title":"First steps in the investigation of automated text annotation with pictures","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Computer graphics (images)","score_opus":0.0545208875358242,"score_gpt":0.2972021565263602,"score_spread":0.24268126899053596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736357342","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04637691,0.000020030893,0.9497119,0.0023196382,0.00003333533,0.0002257778,0.000035510766,0.00014134953,0.0011355495],"genre_scores_gemma":[0.98064476,0.000058144007,0.018843364,0.00029439232,0.000008645055,0.0000027998628,0.00014270468,0.0000012950604,0.00000388764],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993725,0.000019019479,0.00024671823,0.000088019115,0.00020587783,0.0000679071],"domain_scores_gemma":[0.99840426,0.00004155015,0.0003787983,0.0010594872,0.00009680167,0.000019114992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003433328,0.000063796746,0.00008865106,0.0001524964,0.00016562246,0.0003230604,0.0010228701,0.000030349438,4.735706e-7],"category_scores_gemma":[0.00014516282,0.000040639123,0.000008035832,0.00022786736,0.000090047026,0.005547599,0.0001976025,0.000055472025,0.0000019229037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006274159,0.00011075445,0.14823961,0.00048231133,0.00017662812,0.000008481132,0.029302575,0.007711764,0.00019104796,0.2216241,0.019471485,0.5726185],"study_design_scores_gemma":[0.00017463637,0.000031515545,0.18842876,0.000030202737,0.000011689412,0.0000028779643,0.00014963966,0.80556655,0.00019140312,0.00085831323,0.0044878176,0.00006661746],"about_ca_topic_score_codex":0.000051498544,"about_ca_topic_score_gemma":0.00020546633,"teacher_disagreement_score":0.9342679,"about_ca_system_score_codex":0.000009519614,"about_ca_system_score_gemma":0.00003155703,"threshold_uncertainty_score":0.40218753},"labels":[],"label_agreement":null},{"id":"W2739232917","doi":"10.3934/bdia.2017003","title":"Rendering website traffic data into interactive taste graph visualizations","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario College of Art and Design","funders":"","keywords":"Rendering (computer graphics); Computer science; Computer graphics (images); Graph; World Wide Web; Multimedia; Theoretical computer science","score_opus":0.11087586483674504,"score_gpt":0.35835827069580023,"score_spread":0.24748240585905518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2739232917","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006255824,0.00004138127,0.9952269,0.0009080001,0.00041546108,0.00009909082,0.00061420916,0.000107103544,0.0019622552],"genre_scores_gemma":[0.96121025,0.0019092017,0.015473465,0.0021362738,0.0002051276,0.0000032204046,0.018793108,0.000015847727,0.0002534777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986678,0.000031539774,0.00047299347,0.00034957816,0.00029882212,0.0001792992],"domain_scores_gemma":[0.995026,0.0000418556,0.00046656825,0.0041526086,0.00016857359,0.00014441808],"candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00041108424,0.00015801923,0.00017316004,0.0002968484,0.00075044326,0.0027011477,0.004094137,0.000059196373,0.000010785444],"category_scores_gemma":[0.0006013257,0.00015067024,0.000021264506,0.00031851497,0.00010759092,0.022386989,0.004153996,0.000115573974,0.00008557516],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014891075,0.00017857908,0.0014170946,0.00023760609,0.00031774497,0.000009040158,0.0053571537,0.0018809417,0.000026814927,0.18225887,0.10544067,0.7028606],"study_design_scores_gemma":[0.00023972896,0.0000123021655,0.00058383314,0.00002980748,0.000026931586,0.000005383925,0.00029268124,0.7575238,0.000008887144,0.00018284506,0.2409404,0.00015343538],"about_ca_topic_score_codex":0.000029285227,"about_ca_topic_score_gemma":0.00009071533,"teacher_disagreement_score":0.97975343,"about_ca_system_score_codex":0.000019360185,"about_ca_system_score_gemma":0.000098621145,"threshold_uncertainty_score":0.99833417},"labels":[],"label_agreement":null},{"id":"W2767704871","doi":"10.3934/bdia.2017015","title":"Identifying electronic gaming machine gambling personae through unsupervised session classification","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Gambling Behavior and Treatments","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Session (web analytics); Outlier; Psychology; Identification (biology); Exploratory research; Applied psychology; Computer science; Artificial intelligence; World Wide Web","score_opus":0.41945866055791536,"score_gpt":0.45244340705503866,"score_spread":0.032984746497123296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767704871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9169989,0.0006840279,0.055136167,0.00092907285,0.0017240809,0.00051093753,0.00052344287,0.00019004173,0.023303334],"genre_scores_gemma":[0.99663305,0.00046443197,0.0003822401,0.00015961482,0.00007761961,0.0000067198057,0.001964049,0.00001005934,0.00030220379],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99894744,0.00002792152,0.00033339352,0.00021809385,0.0002077976,0.00026535016],"domain_scores_gemma":[0.99835587,0.000022548891,0.00031865595,0.0011687953,0.00007323276,0.00006090475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030159397,0.00014357513,0.00014705797,0.00012951365,0.00069106725,0.0005228526,0.00045432735,0.00010409928,0.00008757733],"category_scores_gemma":[0.0000795515,0.00012827589,0.000032621476,0.00008971345,0.00005579784,0.003418623,0.00019363014,0.00017267751,0.00016498826],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013418331,0.0002614416,0.27842486,0.00012981494,0.00030549767,0.0000109287275,0.010294324,0.000005639604,0.00042043024,0.01988838,0.0025994058,0.6875251],"study_design_scores_gemma":[0.003372053,0.00010242756,0.86935043,0.000108870605,0.00041869257,0.00004337704,0.005375742,0.04811048,0.00011380906,0.00027378736,0.07227221,0.00045808853],"about_ca_topic_score_codex":0.00027358142,"about_ca_topic_score_gemma":0.00004762164,"teacher_disagreement_score":0.68706703,"about_ca_system_score_codex":0.00004900801,"about_ca_system_score_gemma":0.00003985856,"threshold_uncertainty_score":0.53152007},"labels":[],"label_agreement":null},{"id":"W2768733040","doi":"10.3934/bdia.2017016","title":"An ontological account of flow-control components in BPMN process models","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Business Process Modeling and Analysis","field":"Business, Management and Accounting","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"TD Bank Group; York University","funders":"","keywords":"Business Process Model and Notation; Petri net; Computer science; XPDL; Programming language; Business process; Process modeling; Business process modeling; Software engineering; Theoretical computer science; Workflow; Database; Work in process; Workflow management system","score_opus":0.14119815110025397,"score_gpt":0.2975243409845658,"score_spread":0.15632618988431185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2768733040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78046006,0.00007402918,0.21142253,0.0015625348,0.0002282895,0.00026064613,0.00020087122,0.00007728307,0.0057137255],"genre_scores_gemma":[0.99829954,0.00005629422,0.00013669072,0.0006669767,0.0001476913,0.0000032015619,0.0006809111,0.000004738871,0.0000039389847],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989414,0.00000430342,0.00046911283,0.00016576852,0.00026091214,0.0001585057],"domain_scores_gemma":[0.99844646,0.0000073309966,0.0005061949,0.0007099114,0.00031321024,0.00001688049],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004463252,0.0001285855,0.00027356012,0.00029404953,0.00021142075,0.00066523306,0.0008014871,0.00008074094,0.000010128575],"category_scores_gemma":[0.00015578345,0.00010550985,0.000024489591,0.00016989658,0.00007532684,0.015109858,0.00019067511,0.00009227364,0.000012739378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053237414,0.00083145825,0.18869884,0.0025849438,0.00023952861,0.000008942938,0.00070834626,0.26638123,0.000088149376,0.019487865,0.00075447746,0.51968384],"study_design_scores_gemma":[0.0007589481,0.0000037191728,0.017940467,0.00004863015,0.00007404563,4.8949425e-7,0.00017750383,0.9779564,0.0000013682126,0.0015067734,0.0013974315,0.00013419242],"about_ca_topic_score_codex":0.00074180093,"about_ca_topic_score_gemma":0.00017802855,"teacher_disagreement_score":0.7115752,"about_ca_system_score_codex":0.000007566118,"about_ca_system_score_gemma":0.000025150388,"threshold_uncertainty_score":0.9986653},"labels":[],"label_agreement":null},{"id":"W2793062537","doi":"10.3934/bdia.2017018","title":"Fuzzy temporal meta-clustering of financial trading volatility patterns","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Stock Market Forecasting Methods","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Volatility (finance); Cluster analysis; Volatility clustering; Fuzzy clustering; Fuzzy logic; Econometrics; Finance; Computer science; Business; Economics; Artificial intelligence; Autoregressive conditional heteroskedasticity","score_opus":0.4454039739101132,"score_gpt":0.428209438481672,"score_spread":0.017194535428441238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793062537","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2872086,0.000038900045,0.68610615,0.00047223805,0.0010931611,0.00024710156,0.0015869027,0.000031100764,0.023215834],"genre_scores_gemma":[0.9900968,0.000011529382,0.009548776,0.00010284682,0.00007046782,0.0000012377578,0.00007652785,0.00000277844,0.00008902831],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803144,0.0000902857,0.00089091767,0.00018785086,0.00065866235,0.00014083982],"domain_scores_gemma":[0.9965747,0.00043545876,0.0009731017,0.0017167649,0.00021813287,0.00008182248],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0059236535,0.0001127401,0.00036349005,0.00021995467,0.00032273782,0.00057700736,0.0013066618,0.0000651371,0.00007082514],"category_scores_gemma":[0.01633373,0.00008197421,0.00007680533,0.0001505546,0.000105454026,0.0041898536,0.00085948803,0.000099434845,0.000006972537],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039271825,0.000012407003,0.15863211,0.00004690899,0.00007370537,7.718324e-7,0.0005276765,0.000023316241,0.000006470656,0.000401651,0.0037400376,0.8364957],"study_design_scores_gemma":[0.0002857875,0.000029225894,0.38135225,0.000016197966,0.00015670674,0.000005612832,0.00016123935,0.5826467,0.000036478767,0.002270102,0.032910544,0.00012909145],"about_ca_topic_score_codex":0.00012132823,"about_ca_topic_score_gemma":0.00014488828,"teacher_disagreement_score":0.8363666,"about_ca_system_score_codex":0.000010905196,"about_ca_system_score_gemma":0.00007023064,"threshold_uncertainty_score":0.9919521},"labels":[],"label_agreement":null},{"id":"W2896525219","doi":"10.3934/bdia.2018002","title":"An application of PART to the Football Manager data for players clusters analyses to inform club team formation","year":2017,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Cluster analysis; Computer science; Club; Space (punctuation); Cluster (spacecraft); Hierarchical clustering; Football team; Artificial intelligence; Data science; Machine learning; Football; Geography","score_opus":0.2353395288865652,"score_gpt":0.35022244469127956,"score_spread":0.11488291580471435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2896525219","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013743483,0.000067147266,0.95888734,0.0041401875,0.00043254675,0.0012494528,0.013300205,0.000027215274,0.00815245],"genre_scores_gemma":[0.98910826,0.0003398073,0.0016403637,0.0019300827,0.00017535897,0.000025321726,0.0066150078,0.000009393283,0.00015642698],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986168,0.0000025014037,0.0008603326,0.00023302475,0.00009467045,0.00019266536],"domain_scores_gemma":[0.9958615,0.000033306143,0.0008396187,0.0030258936,0.000113977105,0.00012571372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011656425,0.00013141058,0.00026187915,0.00029387037,0.0004659612,0.0005002457,0.0017080017,0.00006369897,0.000013580044],"category_scores_gemma":[0.00033360187,0.00011199202,0.00003438431,0.00020444249,0.000043822976,0.0054101236,0.000549491,0.00006139255,0.000079482044],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002859642,0.0002169415,0.046619125,0.00070495746,0.0004306891,2.8134954e-7,0.004468407,0.031350553,0.000019063915,0.09634226,0.30823818,0.5113236],"study_design_scores_gemma":[0.00016107626,0.000045868153,0.008681064,0.0000069291514,0.000021206164,4.7967757e-7,0.0002267364,0.498571,0.000007910372,0.00007255374,0.49210978,0.00009539759],"about_ca_topic_score_codex":0.00023161616,"about_ca_topic_score_gemma":0.000438971,"teacher_disagreement_score":0.97536474,"about_ca_system_score_codex":0.000028969023,"about_ca_system_score_gemma":0.000020839576,"threshold_uncertainty_score":0.4823881},"labels":[],"label_agreement":null},{"id":"W2997468375","doi":"10.3934/bdia.2019001","title":"Statistical modeling on human microbiome sequencing data","year":2019,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Oral microbiology and periodontitis research","field":"Dentistry","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Princess Margaret Cancer Centre; University of Toronto; Public Health Ontario","funders":"","keywords":"Microbiome; Human microbiome; Computational biology; Metagenomics; Human Microbiome Project; Biology; Linkage (software); Statistical model; DNA sequencing; Data science; Computer science; Genetics; Artificial intelligence; Gene","score_opus":0.24333426281341072,"score_gpt":0.3871920293009617,"score_spread":0.14385776648755097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997468375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9388446,0.00006624325,0.032238852,0.00017285047,0.00063728547,0.0002896434,0.020037588,0.00006304225,0.007649862],"genre_scores_gemma":[0.9613244,0.000060597566,0.0006020404,0.0004367513,0.00007033944,4.7167543e-7,0.037053555,0.0000056869694,0.00044619164],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990998,0.0000364853,0.00032456437,0.0002152052,0.00012818775,0.0001957417],"domain_scores_gemma":[0.9985791,0.000041496707,0.000064155174,0.0011897817,0.000060294926,0.000065163666],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00044410012,0.000097779586,0.0001467396,0.00014390943,0.00014045107,0.0002348588,0.00068224804,0.000103028986,0.0004198636],"category_scores_gemma":[0.000108196655,0.00008752852,0.000010121303,0.000115009614,0.0000567031,0.0018075659,0.00079994666,0.00021065232,0.001963272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00071451877,0.000357721,0.08940416,0.0026802323,0.0010619465,0.00015075873,0.0018745617,0.0042517954,0.06988068,0.09513229,0.5266465,0.20784482],"study_design_scores_gemma":[0.00092529773,0.00009710348,0.0027213339,0.00007030403,0.000036192232,0.00007837009,0.00042367913,0.7862104,0.00013930914,0.000099215875,0.20889397,0.00030480084],"about_ca_topic_score_codex":0.00012930704,"about_ca_topic_score_gemma":0.00008139541,"teacher_disagreement_score":0.78195864,"about_ca_system_score_codex":0.000031938114,"about_ca_system_score_gemma":0.00006805985,"threshold_uncertainty_score":0.9988138},"labels":[],"label_agreement":null},{"id":"W3003902258","doi":"10.3934/bdia.2021005","title":"Aggregate loss model with Poisson-Tweedie frequency","year":2021,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Insurance and Financial Risk Management","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Poisson distribution; Percentile; Econometrics; Aggregate (composite); Reinsurance; Compound Poisson distribution; Distribution (mathematics); Zero-inflated model; Sensitivity (control systems); Statistics; Poisson regression; Mathematics; Computer science; Economics; Population; Actuarial science; Engineering","score_opus":0.06624022060634314,"score_gpt":0.2292257438401906,"score_spread":0.16298552323384746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003902258","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08930373,0.00253165,0.63256174,0.004837004,0.000717553,0.00036506503,0.005376481,0.000103280676,0.26420352],"genre_scores_gemma":[0.9833993,0.006448109,0.0047737393,0.0022931334,0.000116613905,0.0000052426053,0.0017801677,0.000011326301,0.0011723986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916345,0.000002680051,0.00042823105,0.00017862151,0.000052874042,0.00017416835],"domain_scores_gemma":[0.9990928,0.0000067692777,0.00022831716,0.0005393918,0.00007676701,0.000055928787],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022967329,0.000103027414,0.00019506233,0.0001331952,0.00010652435,0.00016966765,0.00020838149,0.000052784635,0.000031943462],"category_scores_gemma":[0.00007089254,0.000103574894,0.000022067194,0.0002808522,0.000041035433,0.0021880225,0.00015487448,0.0000807302,0.00027096504],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002117095,0.000054868065,0.033204976,0.00013497692,0.00010175916,0.000017369955,0.0006570829,0.0010776906,0.0000012285986,0.92114866,0.008858276,0.034721926],"study_design_scores_gemma":[0.0010801186,0.000052220963,0.016889457,0.000045120658,0.000033061984,0.000013776114,0.00025763354,0.34112027,0.000024867435,0.022540439,0.6174865,0.00045653616],"about_ca_topic_score_codex":0.000052226715,"about_ca_topic_score_gemma":0.000053144642,"teacher_disagreement_score":0.8986082,"about_ca_system_score_codex":0.000025736732,"about_ca_system_score_gemma":0.000045533707,"threshold_uncertainty_score":0.42236617},"labels":[],"label_agreement":null},{"id":"W3047104034","doi":"10.3934/bdia.2020001","title":"Modeling portfolio loss by interval distributions","year":2020,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Probabilistic and Robust Engineering Design","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Bank of Canada","funders":"","keywords":"Portfolio; Interval (graph theory); Outcome (game theory); Mathematics; Statistics; Econometrics; Capital allocation line; Regression analysis; Regression; Computer science; Economics; Mathematical economics; Combinatorics","score_opus":0.21734204926902354,"score_gpt":0.3329600770183434,"score_spread":0.11561802774931987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3047104034","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019190593,0.000054959266,0.9939423,0.0017090348,0.00011617905,0.00005398468,0.001319925,0.00003945043,0.0008450602],"genre_scores_gemma":[0.99601835,0.00009750643,0.001506843,0.0008599411,0.00007275646,9.315229e-7,0.0013865576,0.000002681992,0.0000544581],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987812,0.000015499909,0.0005326347,0.00014992057,0.00040109904,0.0001196425],"domain_scores_gemma":[0.9991107,0.00007300024,0.000083673236,0.00041865587,0.00014915472,0.00016482628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005900677,0.00008204372,0.00013842781,0.000068474874,0.000092463975,0.00031439413,0.0005857514,0.000046401296,0.00005129305],"category_scores_gemma":[0.002340639,0.000061520775,0.000024123954,0.00040725782,0.000042111147,0.0019109234,0.0003179163,0.00009241759,0.00014451751],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004169836,0.000041337065,0.0009822545,0.00004969271,0.00006702148,0.0000038230446,0.00092993624,0.09435697,0.00002376044,0.030031426,0.7425995,0.13087262],"study_design_scores_gemma":[0.00010517285,0.000013125311,0.000036904625,0.0000037849513,0.000011919008,0.0000029501136,0.0001888531,0.81846,0.0000040786144,0.00044370862,0.1806597,0.000069799986],"about_ca_topic_score_codex":0.000006744203,"about_ca_topic_score_gemma":6.918811e-7,"teacher_disagreement_score":0.99409926,"about_ca_system_score_codex":0.000011488992,"about_ca_system_score_gemma":0.00004704554,"threshold_uncertainty_score":0.30317098},"labels":[],"label_agreement":null},{"id":"W4408719487","doi":"10.3934/bdia.2025001","title":"Deep neural networks with application in predicting the spread of avian influenza through disease-informed neural networks","year":2025,"lang":"en","type":"article","venue":"Big Data and Information Analytics","topic":"Influenza Virus Research Studies","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Artificial neural network; Influenza A virus subtype H5N1; Deep neural networks; Disease; Computer science; Artificial intelligence; Virology; Biology; Medicine; Pathology; Virus","score_opus":0.07355436373879289,"score_gpt":0.35757403848675934,"score_spread":0.28401967474796647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408719487","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27739978,0.006254086,0.6881592,0.0068100737,0.00053204177,0.0063628415,0.00044962266,0.00027394472,0.0137584135],"genre_scores_gemma":[0.9949519,0.0006122928,0.00016910055,0.0034931898,0.00008465151,0.00003196197,0.0006386065,0.000005967186,0.000012352553],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864334,0.000030325293,0.0006012614,0.0001393135,0.00031236446,0.00027339772],"domain_scores_gemma":[0.99861944,0.0001820948,0.00021931242,0.00069470395,0.00020708055,0.00007739267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031973934,0.0001495917,0.00024273703,0.00016665075,0.00016067288,0.00007396978,0.00027745587,0.000067180765,0.000002254918],"category_scores_gemma":[0.00045165847,0.00009560417,0.000027874772,0.0007708116,0.00022341339,0.0014753083,0.00034183165,0.00030919368,0.000001211473],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010774353,0.000048391754,0.66523427,0.0004861476,0.00018197174,0.000002442704,0.0012184478,0.18397936,7.746857e-7,0.0011030185,0.0008998726,0.14576785],"study_design_scores_gemma":[0.0009762777,0.0000489798,0.16504991,0.000093450355,0.0001043318,0.0000023468249,0.00071582064,0.8255805,0.0000015121477,0.000012143446,0.0073453607,0.000069396294],"about_ca_topic_score_codex":0.00014766923,"about_ca_topic_score_gemma":0.00024157135,"teacher_disagreement_score":0.7175521,"about_ca_system_score_codex":0.00005181988,"about_ca_system_score_gemma":0.00010080613,"threshold_uncertainty_score":0.38986248},"labels":[],"label_agreement":null}]}