{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":18,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":18,"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":"b633b755ce29","filters":{"venue":"Big Data and Information Analytics"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.502372524389615,"gpt":0.4083420660197143,"spread":0.09403045836990065,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01018612,0.000125634,0.0001654145,0.0003301578,0.0003052831,0.006118592,0.00415583,0.00004469265,0.00001993408],"category_scores_gemma":[0.003467382,0.00007361612,0.00002199812,0.001141793,0.0001623217,0.008194793,0.004854826,0.0001159604,0.0008913516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001783936,"about_ca_system_score_gemma":0.0001903678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009274046,"about_ca_topic_score_gemma":0.0001919706,"domain_scores_codex":[0.9968758,0.00009149134,0.000796332,0.0004267015,0.001576292,0.0002333916],"domain_scores_gemma":[0.9938185,0.0003461072,0.0003494599,0.004943747,0.0003452122,0.0001969259],"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":[0.000004491855,0.000007046402,0.0002289362,0.000002409759,0.000008755056,4.293942e-7,0.0003486067,0.00007341749,8.910587e-8,0.0006230365,0.3944362,0.6042666],"study_design_scores_gemma":[0.0002061147,0.00001124577,0.001783273,0.000009810687,0.00001982431,0.000004506853,0.005329352,0.2525744,9.007411e-7,0.0005330939,0.7394431,0.00008434903],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03001557,0.001708755,0.8263881,0.03047801,0.04525724,0.001139164,0.006604286,0.0003408002,0.05806808],"genre_scores_gemma":[0.9435082,0.002016924,0.003963918,0.01608481,0.003359025,0.000006410702,0.02268459,0.00002174771,0.008354347],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9134927,"threshold_uncertainty_score":0.9998866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1229226511525502,"gpt":0.3165353314352157,"spread":0.1936126802826655,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001022989,0.0001012233,0.000137843,0.0002660227,0.0001302507,0.0003248793,0.0004313363,0.00005799314,8.973812e-8],"category_scores_gemma":[0.0001530359,0.0001032459,0.00001960069,0.0004142922,0.0000221226,0.002442865,0.0003272895,0.00008130148,0.00001233595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006872227,"about_ca_system_score_gemma":0.0001418473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001876614,"about_ca_topic_score_gemma":0.000002853872,"domain_scores_codex":[0.9989734,0.0000276373,0.0004224793,0.0001666847,0.0001922815,0.0002175381],"domain_scores_gemma":[0.9991383,0.0001087335,0.0001894028,0.0003043929,0.0001704044,0.00008879851],"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":[0.00002178389,0.00004704394,0.001850447,0.0001244337,0.00001340319,8.917889e-7,0.002955992,0.02960593,0.00001451563,0.001579008,0.0358584,0.9279281],"study_design_scores_gemma":[0.0007497932,0.00005693615,0.0004438856,0.000032223,0.00000558448,0.000002770341,0.00009787027,0.9446291,0.00002464066,0.0001978492,0.05363533,0.0001239874],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01114007,0.0000450256,0.9853669,0.0002295539,0.002565027,0.0002200404,0.000006331612,0.00007903484,0.0003479935],"genre_scores_gemma":[0.8965744,0.00001025864,0.1005086,0.0008947522,0.0009512819,0.000004673132,0.001042112,0.000006614291,0.000007351842],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9278042,"threshold_uncertainty_score":0.4210244,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2353395288865652,"gpt":0.3502224446912796,"spread":0.1148829158047144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001165643,0.0001314106,0.0002618791,0.0002938704,0.0004659612,0.0005002457,0.001708002,0.00006369897,0.00001358004],"category_scores_gemma":[0.0003336019,0.000111992,0.00003438431,0.0002044425,0.00004382298,0.005410124,0.000549491,0.00006139255,0.00007948204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002896902,"about_ca_system_score_gemma":0.00002083958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002316162,"about_ca_topic_score_gemma":0.000438971,"domain_scores_codex":[0.9986168,0.000002501404,0.0008603326,0.0002330248,0.00009467045,0.0001926654],"domain_scores_gemma":[0.9958615,0.00003330614,0.0008396187,0.003025894,0.0001139771,0.0001257137],"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":[0.0002859642,0.0002169415,0.04661912,0.0007049575,0.0004306891,2.813495e-7,0.004468407,0.03135055,0.00001906391,0.09634226,0.3082382,0.5113236],"study_design_scores_gemma":[0.0001610763,0.00004586815,0.008681064,0.000006929151,0.00002120616,4.796776e-7,0.0002267364,0.498571,0.000007910372,0.00007255374,0.4921098,0.00009539759],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01374348,0.00006714727,0.9588873,0.004140188,0.0004325467,0.001249453,0.0133002,0.00002721527,0.00815245],"genre_scores_gemma":[0.9891083,0.0003398073,0.001640364,0.001930083,0.000175359,0.00002532173,0.006615008,0.000009393283,0.000156427],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9753647,"threshold_uncertainty_score":0.4823881,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4194586605579154,"gpt":0.4524434070550387,"spread":0.0329847464971233,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000301594,0.0001435751,0.000147058,0.0001295136,0.0006910673,0.0005228526,0.0004543274,0.0001040993,0.00008757733],"category_scores_gemma":[0.0000795515,0.0001282759,0.00003262148,0.00008971345,0.00005579784,0.003418623,0.0001936301,0.0001726775,0.0001649883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004900801,"about_ca_system_score_gemma":0.00003985856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002735814,"about_ca_topic_score_gemma":0.00004762164,"domain_scores_codex":[0.9989474,0.00002792152,0.0003333935,0.0002180938,0.0002077976,0.0002653502],"domain_scores_gemma":[0.9983559,0.00002254889,0.0003186559,0.001168795,0.00007323276,0.00006090475],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001341833,0.0002614416,0.2784249,0.0001298149,0.0003054977,0.00001092873,0.01029432,0.000005639604,0.0004204302,0.01988838,0.002599406,0.6875251],"study_design_scores_gemma":[0.003372053,0.0001024276,0.8693504,0.0001088706,0.0004186926,0.00004337704,0.005375742,0.04811048,0.0001138091,0.0002737874,0.07227221,0.0004580885],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9169989,0.0006840279,0.05513617,0.0009290728,0.001724081,0.0005109375,0.0005234429,0.0001900417,0.02330333],"genre_scores_gemma":[0.9966331,0.000464432,0.0003822401,0.0001596148,0.00007761961,0.000006719806,0.001964049,0.00001005934,0.0003022038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.687067,"threshold_uncertainty_score":0.5315201,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0647731355806819,"gpt":0.2560971786824018,"spread":0.1913240431017199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003490631,0.00008493686,0.0001160302,0.0001271376,0.00007434501,0.0002005746,0.000641672,0.0000519533,0.0000111956],"category_scores_gemma":[0.00002275679,0.00005391842,0.00001812631,0.0001385405,0.00001584838,0.002956849,0.0003153659,0.0000336712,0.000115363],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003595213,"about_ca_system_score_gemma":0.00004241004,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001112501,"about_ca_topic_score_gemma":0.000001910204,"domain_scores_codex":[0.9992737,0.00003023404,0.0002991748,0.0001301898,0.000143901,0.000122764],"domain_scores_gemma":[0.998811,0.00004796619,0.0001262347,0.0008798708,0.00006759856,0.0000673024],"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":[0.000002652101,0.00001430025,0.0005141677,0.000131421,0.00002831683,0.000001602326,0.0001281274,0.00000139895,0.00001393732,0.02991506,0.1604397,0.8088093],"study_design_scores_gemma":[0.0002704739,0.00002604815,0.000241126,0.00008001726,0.000005427577,0.00001065474,0.00004068967,0.3544524,0.000104181,0.0000538474,0.6445938,0.0001213304],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008612937,0.00001282708,0.9905476,0.003077833,0.0002233697,0.00009639592,0.00008061836,0.0002176295,0.005657594],"genre_scores_gemma":[0.9825485,0.00008733571,0.01406297,0.002379048,0.000147051,0.00001082413,0.0002364494,0.000006908437,0.000520909],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9824624,"threshold_uncertainty_score":0.219873,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Trent University","funders":"Mitacs","keywords":"Computer science; Computer security; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.1215364461121963,"gpt":0.2952623683958516,"spread":0.1737259222836554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006893979,0.00009122668,0.0001068408,0.000225311,0.00009451771,0.0002672588,0.0009750818,0.00004321312,0.000001759715],"category_scores_gemma":[0.0004248255,0.00007090119,0.000009402682,0.0003277501,0.00002476074,0.008858513,0.0009142093,0.00007809578,0.000009250382],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003275002,"about_ca_system_score_gemma":0.00004835331,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004774085,"about_ca_topic_score_gemma":0.00004663948,"domain_scores_codex":[0.9989932,0.00003478337,0.0003636433,0.0002442979,0.0002044333,0.0001596323],"domain_scores_gemma":[0.9984775,0.00007987693,0.0001578539,0.001176377,0.00004960578,0.00005882031],"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":[0.000008727697,0.00002534862,0.001889718,0.0000333959,0.000009929012,0.000001164618,0.0003608461,0.00003538963,0.00005646313,0.0003485724,0.002007263,0.9952232],"study_design_scores_gemma":[0.0004807885,0.00002508335,0.003958871,0.00006774534,0.000008724511,0.00003618108,0.0001900948,0.9608169,0.00008682848,0.00006687734,0.03412254,0.0001393489],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.030659,0.00002948851,0.9677122,0.0004630559,0.0002230808,0.00007607934,0.0002653972,0.00007420457,0.0004975221],"genre_scores_gemma":[0.9708221,0.0001355753,0.02718621,0.0004035732,0.0001153311,0.000001210346,0.001311855,0.000003855722,0.00002031574],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9950838,"threshold_uncertainty_score":0.6422208,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.141198151100254,"gpt":0.2975243409845658,"spread":0.1563261898843119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004463252,0.0001285855,0.0002735601,0.0002940495,0.0002114207,0.0006652331,0.0008014871,0.00008074094,0.00001012858],"category_scores_gemma":[0.0001557834,0.0001055098,0.00002448959,0.0001698966,0.00007532684,0.01510986,0.0001906751,0.00009227364,0.00001273938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007566118,"about_ca_system_score_gemma":0.00002515039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007418009,"about_ca_topic_score_gemma":0.0001780286,"domain_scores_codex":[0.9989414,0.00000430342,0.0004691128,0.0001657685,0.0002609121,0.0001585057],"domain_scores_gemma":[0.9984465,0.000007330997,0.0005061949,0.0007099114,0.0003132102,0.00001688049],"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":[0.0005323741,0.0008314583,0.1886988,0.002584944,0.0002395286,0.000008942938,0.0007083463,0.2663812,0.00008814938,0.01948787,0.0007544775,0.5196838],"study_design_scores_gemma":[0.0007589481,0.000003719173,0.01794047,0.00004863015,0.00007404563,4.894943e-7,0.0001775038,0.9779564,0.000001368213,0.001506773,0.001397431,0.0001341924],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7804601,0.00007402918,0.2114225,0.001562535,0.0002282895,0.0002606461,0.0002008712,0.00007728307,0.005713725],"genre_scores_gemma":[0.9982995,0.00005629422,0.0001366907,0.0006669767,0.0001476913,0.000003201562,0.0006809111,0.000004738871,0.000003938985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7115752,"threshold_uncertainty_score":0.9986653,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Annotation; Computer science; Natural language processing; Artificial intelligence; Information retrieval; Computer graphics (images)","retraction":null,"screen_n_in":null,"score":{"opus":0.0545208875358242,"gpt":0.2972021565263602,"spread":0.242681268990536,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003433328,0.00006379675,0.00008865106,0.0001524964,0.0001656225,0.0003230604,0.00102287,0.00003034944,4.735706e-7],"category_scores_gemma":[0.0001451628,0.00004063912,0.000008035832,0.0002278674,0.00009004703,0.005547599,0.0001976025,0.00005547202,0.000001922904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009519614,"about_ca_system_score_gemma":0.00003155703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005149854,"about_ca_topic_score_gemma":0.0002054663,"domain_scores_codex":[0.9993725,0.00001901948,0.0002467182,0.00008801911,0.0002058778,0.0000679071],"domain_scores_gemma":[0.9984043,0.00004155015,0.0003787983,0.001059487,0.00009680167,0.00001911499],"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":[0.00006274159,0.0001107545,0.1482396,0.0004823113,0.0001766281,0.000008481132,0.02930257,0.007711764,0.000191048,0.2216241,0.01947149,0.5726185],"study_design_scores_gemma":[0.0001746364,0.00003151554,0.1884288,0.00003020274,0.00001168941,0.000002877964,0.0001496397,0.8055665,0.0001914031,0.0008583132,0.004487818,0.00006661746],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04637691,0.00002003089,0.9497119,0.002319638,0.00003333533,0.0002257778,0.00003551077,0.0001413495,0.00113555],"genre_scores_gemma":[0.9806448,0.00005814401,0.01884336,0.0002943923,0.000008645055,0.000002799863,0.0001427047,0.00000129506,0.00000388764],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9342679,"threshold_uncertainty_score":0.4021875,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05441516069391256,"gpt":0.3277289205120051,"spread":0.2733137598180926,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001889504,0.00008633963,0.0001345894,0.00007213178,0.0004050276,0.0004003008,0.0003840282,0.00005107883,0.000009704704],"category_scores_gemma":[0.00002133316,0.00008790899,0.00002460729,0.00007823961,0.00006765315,0.001908892,0.0003196221,0.0001426283,0.000004382441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003025109,"about_ca_system_score_gemma":0.00003710487,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004454164,"about_ca_topic_score_gemma":0.000171699,"domain_scores_codex":[0.9993758,0.00001066109,0.0002883305,0.00009727954,0.00008362778,0.000144358],"domain_scores_gemma":[0.9992561,0.00001314988,0.0002513312,0.0003822536,0.00005311823,0.00004403522],"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":[0.000009367543,0.00005109317,0.3841603,0.00001972681,0.000043928,2.337048e-7,0.0002774704,0.0007145738,2.63665e-7,0.1914522,0.0009184944,0.4223524],"study_design_scores_gemma":[0.0002898758,0.000005324434,0.08563834,0.00001564887,0.000007388162,1.092189e-7,0.0006978593,0.900956,9.807619e-8,0.0005473996,0.0117318,0.000110159],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3270678,0.0001126874,0.6067523,0.006814815,0.003165113,0.0006635467,0.008348558,0.0000869564,0.04698822],"genre_scores_gemma":[0.9943534,0.0001304728,0.0001708685,0.00009699406,0.0003920158,9.890496e-7,0.004825674,0.000003693475,0.00002589687],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9002414,"threshold_uncertainty_score":0.386011,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.07355436373879289,"gpt":0.3575740384867593,"spread":0.2840196747479665,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003197393,0.0001495917,0.000242737,0.0001666507,0.0001606729,0.00007396978,0.0002774559,0.00006718076,0.000002254918],"category_scores_gemma":[0.0004516585,0.00009560417,0.00002787477,0.0007708116,0.0002234134,0.001475308,0.0003418316,0.0003091937,0.000001211473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005181988,"about_ca_system_score_gemma":0.0001008061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001476692,"about_ca_topic_score_gemma":0.0002415714,"domain_scores_codex":[0.9986433,0.00003032529,0.0006012614,0.0001393135,0.0003123645,0.0002733977],"domain_scores_gemma":[0.9986194,0.0001820948,0.0002193124,0.000694704,0.0002070805,0.00007739267],"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":[0.001077435,0.00004839175,0.6652343,0.0004861476,0.0001819717,0.000002442704,0.001218448,0.1839794,7.746857e-7,0.001103019,0.0008998726,0.1457679],"study_design_scores_gemma":[0.0009762777,0.0000489798,0.1650499,0.00009345036,0.0001043318,0.000002346825,0.0007158206,0.8255805,0.000001512148,0.00001214345,0.007345361,0.00006939629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2773998,0.006254086,0.6881592,0.006810074,0.0005320418,0.006362841,0.0004496227,0.0002739447,0.01375841],"genre_scores_gemma":[0.9949519,0.0006122928,0.0001691005,0.00349319,0.00008465151,0.00003196197,0.0006386065,0.000005967186,0.00001235255],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7175521,"threshold_uncertainty_score":0.3898625,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1018346827705457,"gpt":0.2750029553143635,"spread":0.1731682725438178,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0002834982,0.00008147686,0.00008098123,0.0001515912,0.0004994555,0.001558014,0.0003096928,0.00004084434,0.00001829052],"category_scores_gemma":[0.0001275125,0.00007513939,0.00001373379,0.0000640088,0.00003000779,0.01450731,0.0003017949,0.00005875869,0.0001902972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001407227,"about_ca_system_score_gemma":0.00001399745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003347308,"about_ca_topic_score_gemma":0.00008681794,"domain_scores_codex":[0.9993418,0.000001545366,0.0002559548,0.00009903194,0.0001980212,0.0001036026],"domain_scores_gemma":[0.9991132,0.00000370117,0.0002000021,0.0005453539,0.0001253386,0.00001238592],"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":[0.0002137013,0.0001782434,0.1163128,0.001250517,0.0002477625,0.000005923002,0.001054458,0.006743057,0.0001719546,0.0530006,0.2088411,0.6119798],"study_design_scores_gemma":[0.0003228596,0.000002219312,0.006054879,0.00001467447,0.00004052926,8.780729e-7,0.0002703155,0.7762857,0.000001617027,0.00007496397,0.2168568,0.00007458768],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4714677,0.0001461514,0.2776623,0.006491777,0.009090632,0.00104609,0.001028657,0.0005802745,0.2324864],"genre_scores_gemma":[0.9942408,0.0001491891,0.00008647039,0.001414317,0.00118077,0.000001852842,0.002849182,0.000004763517,0.00007272019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7695426,"threshold_uncertainty_score":0.9994785,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2433342628134107,"gpt":0.3871920293009617,"spread":0.143857766487551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004441001,0.00009777959,0.0001467396,0.0001439094,0.0001404511,0.0002348588,0.000682248,0.000103029,0.0004198636],"category_scores_gemma":[0.0001081967,0.00008752852,0.0000101213,0.0001150096,0.0000567031,0.001807566,0.0007999467,0.0002106523,0.001963272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003193811,"about_ca_system_score_gemma":0.00006805985,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000129307,"about_ca_topic_score_gemma":0.00008139541,"domain_scores_codex":[0.9990998,0.0000364853,0.0003245644,0.0002152052,0.0001281877,0.0001957417],"domain_scores_gemma":[0.9985791,0.00004149671,0.00006415517,0.001189782,0.00006029493,0.00006516367],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007145188,0.000357721,0.08940416,0.002680232,0.001061947,0.0001507587,0.001874562,0.004251795,0.06988068,0.09513229,0.5266465,0.2078448],"study_design_scores_gemma":[0.0009252977,0.00009710348,0.002721334,0.00007030403,0.00003619223,0.00007837009,0.0004236791,0.7862104,0.0001393091,0.00009921587,0.208894,0.0003048008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9388446,0.00006624325,0.03223885,0.0001728505,0.0006372855,0.0002896434,0.02003759,0.00006304225,0.007649862],"genre_scores_gemma":[0.9613244,0.00006059757,0.0006020404,0.0004367513,0.00007033944,4.716754e-7,0.03705356,0.000005686969,0.0004461916],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7819586,"threshold_uncertainty_score":0.9988138,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.110875864836745,"gpt":0.3583582706958002,"spread":0.2474824058590552,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.0004110842,0.0001580192,0.00017316,0.0002968484,0.0007504433,0.002701148,0.004094137,0.00005919637,0.00001078544],"category_scores_gemma":[0.0006013257,0.0001506702,0.00002126451,0.000318515,0.0001075909,0.02238699,0.004153996,0.000115574,0.00008557516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001936018,"about_ca_system_score_gemma":0.00009862115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002928523,"about_ca_topic_score_gemma":0.00009071533,"domain_scores_codex":[0.9986678,0.00003153977,0.0004729935,0.0003495782,0.0002988221,0.0001792992],"domain_scores_gemma":[0.995026,0.0000418556,0.0004665682,0.004152609,0.0001685736,0.0001444181],"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":[0.00001489107,0.0001785791,0.001417095,0.0002376061,0.000317745,0.000009040158,0.005357154,0.001880942,0.00002681493,0.1822589,0.1054407,0.7028606],"study_design_scores_gemma":[0.000239729,0.00001230217,0.0005838331,0.00002980748,0.00002693159,0.000005383925,0.0002926812,0.7575238,0.000008887144,0.0001828451,0.2409404,0.0001534354],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006255824,0.00004138127,0.9952269,0.0009080001,0.0004154611,0.00009909082,0.0006142092,0.0001071035,0.001962255],"genre_scores_gemma":[0.9612103,0.001909202,0.01547347,0.002136274,0.0002051276,0.000003220405,0.01879311,0.00001584773,0.0002534777],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9797534,"threshold_uncertainty_score":0.9983342,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.2173420492690235,"gpt":0.3329600770183434,"spread":0.1156180277493199,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005900677,0.00008204372,0.0001384278,0.00006847487,0.00009246398,0.0003143941,0.0005857514,0.0000464013,0.00005129305],"category_scores_gemma":[0.002340639,0.00006152078,0.00002412395,0.0004072578,0.00004211115,0.001910923,0.0003179163,0.00009241759,0.0001445175],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001148899,"about_ca_system_score_gemma":0.00004704554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006744203,"about_ca_topic_score_gemma":6.918811e-7,"domain_scores_codex":[0.9987812,0.00001549991,0.0005326347,0.0001499206,0.000401099,0.0001196425],"domain_scores_gemma":[0.9991107,0.00007300024,0.00008367324,0.0004186559,0.0001491547,0.0001648263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004169836,0.00004133707,0.0009822545,0.00004969271,0.00006702148,0.000003823045,0.0009299362,0.09435697,0.00002376044,0.03003143,0.7425995,0.1308726],"study_design_scores_gemma":[0.0001051728,0.00001312531,0.00003690462,0.000003784951,0.00001191901,0.000002950114,0.0001888531,0.81846,0.000004078614,0.0004437086,0.1806597,0.00006979999],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001919059,0.00005495927,0.9939423,0.001709035,0.000116179,0.00005398468,0.001319925,0.00003945043,0.0008450602],"genre_scores_gemma":[0.9960184,0.00009750643,0.001506843,0.0008599411,0.00007275646,9.315229e-7,0.001386558,0.000002681992,0.0000544581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9940993,"threshold_uncertainty_score":0.303171,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06624022060634314,"gpt":0.2292257438401906,"spread":0.1629855232338475,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002296733,0.0001030274,0.0001950623,0.0001331952,0.0001065243,0.0001696676,0.0002083815,0.00005278464,0.00003194346],"category_scores_gemma":[0.00007089254,0.0001035749,0.00002206719,0.0002808522,0.00004103543,0.002188022,0.0001548745,0.0000807302,0.000270965],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002573673,"about_ca_system_score_gemma":0.00004553371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005222671,"about_ca_topic_score_gemma":0.00005314464,"domain_scores_codex":[0.9991634,0.000002680051,0.0004282311,0.0001786215,0.00005287404,0.0001741684],"domain_scores_gemma":[0.9990928,0.000006769278,0.0002283172,0.0005393918,0.00007676701,0.00005592879],"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":[0.00002117095,0.00005486807,0.03320498,0.0001349769,0.0001017592,0.00001736996,0.0006570829,0.001077691,0.000001228599,0.9211487,0.008858276,0.03472193],"study_design_scores_gemma":[0.001080119,0.00005222096,0.01688946,0.00004512066,0.00003306198,0.00001377611,0.0002576335,0.3411203,0.00002486744,0.02254044,0.6174865,0.0004565362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08930373,0.00253165,0.6325617,0.004837004,0.000717553,0.000365065,0.005376481,0.0001032807,0.2642035],"genre_scores_gemma":[0.9833993,0.006448109,0.004773739,0.002293133,0.0001166139,0.000005242605,0.001780168,0.0000113263,0.001172399],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8986082,"threshold_uncertainty_score":0.4223662,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.26739060138568,"gpt":0.3367448301259789,"spread":0.06935422874029884,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.000404567,0.0001074426,0.0001863235,0.00009900911,0.001072825,0.001198191,0.001278426,0.00005374942,0.000001126604],"category_scores_gemma":[0.0005011092,0.00009878394,0.00002894213,0.0001078367,0.0000581461,0.002730744,0.0008711526,0.00008183596,0.00003200792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002045519,"about_ca_system_score_gemma":0.00009450722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002961644,"about_ca_topic_score_gemma":0.00002943828,"domain_scores_codex":[0.9991255,0.0000159623,0.0002960878,0.0001791898,0.0001793734,0.0002039263],"domain_scores_gemma":[0.998755,0.0001847005,0.0002730356,0.0005305072,0.0001494066,0.0001073925],"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":[0.00001878556,0.0001180522,0.07115987,0.0002315664,0.0001845554,5.47653e-7,0.006232519,0.001923486,0.000004120209,0.369363,0.1533467,0.3974168],"study_design_scores_gemma":[0.0004138644,0.00002721144,0.05347328,0.000007982323,0.00001857191,0.000001147067,0.0001346624,0.7024037,0.000006052408,0.0005213915,0.2428528,0.0001393976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00202775,0.00001173063,0.9875008,0.001854102,0.0001590163,0.000217645,0.0002335204,0.00005615082,0.007939269],"genre_scores_gemma":[0.9456339,0.000002885668,0.05253622,0.0004003624,0.000411368,0.000008161874,0.0009398001,0.00000381268,0.00006347032],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9436061,"threshold_uncertainty_score":0.9998387,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08789576314961048,"gpt":0.2890048371131446,"spread":0.2011090739635341,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003559986,0.0001064418,0.0001095326,0.0001226761,0.0001441591,0.0004143232,0.002013763,0.00003926666,0.00000465073],"category_scores_gemma":[0.0002455645,0.0000734128,0.000008457057,0.000377804,0.0000423599,0.0100513,0.002170306,0.00003882722,0.00008436767],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001180379,"about_ca_system_score_gemma":0.0000676648,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003014871,"about_ca_topic_score_gemma":0.000009031492,"domain_scores_codex":[0.9991002,0.00001180805,0.0002600414,0.0002700678,0.000203223,0.0001546788],"domain_scores_gemma":[0.9974884,0.0001109314,0.000141669,0.00208156,0.00009887246,0.00007852175],"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":[0.000001582208,0.00001531247,0.0003911118,0.00002511628,0.00001913154,8.999224e-7,0.0001333187,9.314632e-7,0.0000296597,0.01008909,0.02859573,0.9606981],"study_design_scores_gemma":[0.00040047,0.00002201215,0.01253826,0.00006931057,0.00002656953,0.0000274784,0.0001292876,0.495283,0.00006653048,0.0001168476,0.4910976,0.0002226725],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001685339,0.000037948,0.9923975,0.002942737,0.0001564793,0.00009431547,0.001865092,0.00009338662,0.0007272435],"genre_scores_gemma":[0.5664449,0.002297568,0.4100223,0.004548784,0.000766984,0.00003175133,0.01524838,0.00002981395,0.0006095684],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9604754,"threshold_uncertainty_score":0.7286953,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.4454039739101132,"gpt":0.428209438481672,"spread":0.01719453542844124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005923653,0.0001127401,0.00036349,0.0002199547,0.0003227378,0.0005770074,0.001306662,0.0000651371,0.00007082514],"category_scores_gemma":[0.01633373,0.00008197421,0.00007680533,0.0001505546,0.000105454,0.004189854,0.000859488,0.00009943484,0.000006972537],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000109052,"about_ca_system_score_gemma":0.00007023064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001213282,"about_ca_topic_score_gemma":0.0001448883,"domain_scores_codex":[0.9980314,0.0000902857,0.0008909177,0.0001878509,0.0006586623,0.0001408398],"domain_scores_gemma":[0.9965747,0.0004354588,0.0009731017,0.001716765,0.0002181329,0.00008182248],"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":[0.00003927182,0.000012407,0.1586321,0.00004690899,0.00007370537,7.718324e-7,0.0005276765,0.00002331624,0.000006470656,0.000401651,0.003740038,0.8364957],"study_design_scores_gemma":[0.0002857875,0.00002922589,0.3813522,0.00001619797,0.0001567067,0.000005612832,0.0001612394,0.5826467,0.00003647877,0.002270102,0.03291054,0.0001290915],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2872086,0.00003890005,0.6861061,0.0004722381,0.001093161,0.0002471016,0.001586903,0.00003110076,0.02321583],"genre_scores_gemma":[0.9900968,0.00001152938,0.009548776,0.0001028468,0.00007046782,0.000001237758,0.00007652785,0.00000277844,0.00008902831],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8363666,"threshold_uncertainty_score":0.9919521,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}