{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":41,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":41,"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","author_layer_release":"2026-06-26"},"query_hash":"151acead7183","filters":{"venue":"2022 IEEE International Conference on Big Data (Big Data)"}},"results":[{"id":"W4318185132","doi":"10.1109/bigdata55660.2022.10020719","title":"From Data Warehouse to Lakehouse: A Comparative Review","year":2022,"lang":"en","type":"review","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Data warehouse; Computer science; Big data; Data science; Unstructured data; Data management; Data extraction; Analytics; Strengths and weaknesses; Data transformation; Data virtualization; Database; Data mining; Cloud computing","authors":[{"name":"Ahmed A. Harby","is_ca":true},{"name":"Farhana Zulkernine","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.9445247924110595,"gpt":0.5941263284283097,"spread":0.3503984639827498,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.01202171,0.001083525,0.00336608,0.0009694112,0.0003833817,0.002031271,0.0844325,0.0002023946,0.01805538],"category_scores_gemma":[0.009123594,0.0008831522,0.0002410187,0.001847045,0.0002190458,0.00263279,0.06154928,0.00155858,0.01191348],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003130618,"about_ca_system_score_gemma":0.001485576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00123872,"about_ca_topic_score_gemma":0.004582827,"domain_scores_codex":[0.9797466,0.002583426,0.003333068,0.006373909,0.007298391,0.0006645376],"domain_scores_gemma":[0.9574002,0.004158267,0.00225961,0.03528107,0.0003933385,0.0005075001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002078466,0.0001571821,2.525445e-7,0.0004495791,0.0003278988,0.00006297513,0.00003756451,8.513198e-7,7.606146e-8,0.0007144516,0.5003039,0.4979244],"study_design_scores_gemma":[0.0002660718,0.00007629258,0.000001732904,0.00914134,0.0006437727,0.00001615672,0.0003045546,0.0005753363,1.589689e-7,0.0007503935,0.9872922,0.0009320264],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"review","genre_scores_codex":[2.48294e-7,0.4560863,0.004004519,0.002172947,0.009992622,0.001539545,0.5214807,0.0001009664,0.004622118],"genre_scores_gemma":[0.000002920847,0.6072145,0.0004314948,0.002894839,0.001551814,0.0001746239,0.3853348,0.00005044918,0.00234463],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.4969924,"threshold_uncertainty_score":0.9993619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024021","doi":"10.1109/bigdata55660.2022.10020313","title":"The Analysis and Development of an XAI Process on Feature Contribution Explanation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Consistency (knowledge bases); Computer science; Feature (linguistics); Process (computing); Ranking (information retrieval); Data mining; Feature selection; Artificial intelligence; Information retrieval","authors":[{"name":"Jun Huang","is_ca":true},{"name":"Zerui Wang","is_ca":true},{"name":"Li Ding","is_ca":true},{"name":"Yan Liu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2539979832914212,"gpt":0.3711565148971464,"spread":0.1171585316057251,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.00166766,0.0001908983,0.0002084332,0.0003809528,0.0007296043,0.0004268448,0.006234177,0.00004925815,0.00006033423],"category_scores_gemma":[0.0003087125,0.0001635856,0.0000247359,0.0008142921,0.00008625969,0.001142208,0.001775117,0.0003554256,0.00001751127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001514487,"about_ca_system_score_gemma":0.0003966797,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001019392,"about_ca_topic_score_gemma":0.001605774,"domain_scores_codex":[0.9967165,0.0002261623,0.0004401158,0.0009718127,0.001382412,0.000262992],"domain_scores_gemma":[0.9967681,0.0002245786,0.0003788739,0.002130371,0.0004056574,0.00009238906],"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":[0.0003562506,0.0005700326,0.0006175959,0.00001562569,0.0006535724,0.00003662926,0.001606149,0.001234936,0.0027786,0.08992799,0.004991137,0.8972115],"study_design_scores_gemma":[0.0006147005,0.0004017534,0.005026561,0.00005247209,0.0001004105,0.00002275932,0.003041417,0.866309,0.03197844,0.005367869,0.08639202,0.0006926274],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2616138,0.0001632976,0.6978266,0.01417523,0.007875231,0.001274059,0.01488414,0.0002463814,0.001941262],"genre_scores_gemma":[0.9857733,0.00006843157,0.001209893,0.0002779453,0.0001594196,0.00006967019,0.01229839,0.000008522232,0.0001344811],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8965188,"threshold_uncertainty_score":0.9991426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147647","doi":"10.1109/bigdata55660.2022.10020940","title":"Using CNN-LSTM Model for Weather Forecasting","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Energy Load and Power Forecasting","field":"Engineering","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Deep learning; Generalization; Artificial neural network; Weather forecasting; Artificial intelligence; Feature (linguistics); Data modeling; Big data; Machine learning; Numerical weather prediction; Data mining; Meteorology; Database; Geography","authors":[{"name":"Michael K.H. Fan","is_ca":true},{"name":"Omar Imran","is_ca":true},{"name":"Arka Singh","is_ca":true},{"name":"Samuel A. Ajila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5383621885771043,"gpt":0.3526381344140766,"spread":0.1857240541630277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000578081,0.000275577,0.0002272002,0.0002139711,0.0003169326,0.000168157,0.003011309,0.0000605683,0.0003552554],"category_scores_gemma":[0.0001252989,0.0003104261,0.00005093442,0.0001736511,0.00003644063,0.0005457267,0.001380454,0.0004220056,0.00001418171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696895,"about_ca_system_score_gemma":0.0001382804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007464205,"about_ca_topic_score_gemma":0.0001738303,"domain_scores_codex":[0.9978414,0.00003680524,0.000408328,0.0007032328,0.0006116279,0.0003985861],"domain_scores_gemma":[0.9981785,0.0001250514,0.0001236898,0.001394829,0.00008475692,0.00009318603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001390958,0.0001256133,0.0001210805,0.00006922724,0.0003243291,0.00003612194,0.0003305797,0.7596338,0.0099571,0.008180215,0.04182647,0.1792563],"study_design_scores_gemma":[0.0004334733,0.0000314433,0.000003026957,0.00005995285,0.00002757901,0.00002862301,0.0001127251,0.9443151,0.0002504885,0.0007650549,0.05364449,0.0003280011],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04003178,0.000208154,0.8201762,0.0004318921,0.02177356,0.0006026444,0.08723974,0.0005130515,0.02902291],"genre_scores_gemma":[0.9674579,0.00006227559,0.006783874,0.0002457421,0.001616519,0.00007740056,0.02251542,0.00009760293,0.001143271],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9274261,"threshold_uncertainty_score":0.9999348,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318185064","doi":"10.1109/bigdata55660.2022.10020982","title":"Mixers Detection in bitcoin network: a step towards detecting money laundering in crypto-currencies","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Crime, Illicit Activities, and Governance","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"Innovation Fund","keywords":"Money laundering; Computer science; Proof-of-work system; Anonymity; Database transaction; Computer security; Mixing (physics); Process (computing); Cryptocurrency; Communication source; Digital currency; Pruning; Tree (set theory); Decision tree; Computer network; Data mining; Business; World Wide Web; Operating system; Payment; Database","authors":[{"name":"M. Mazhar Rathore","is_ca":true},{"name":"Sushil S. Chaurasia","is_ca":true},{"name":"Dhirendra Shukla","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3417629011562336,"gpt":0.3747394520079122,"spread":0.03297655085167861,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002346204,0.000241705,0.0002883453,0.0003574794,0.0005978295,0.0002957162,0.003196319,0.00009032535,0.0003641911],"category_scores_gemma":[0.0008340192,0.0002944719,0.00004248886,0.0008105696,0.0001628123,0.001143633,0.001778625,0.0008798298,0.00001757591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008896123,"about_ca_system_score_gemma":0.0006236295,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05198947,"about_ca_topic_score_gemma":0.2966233,"domain_scores_codex":[0.9960296,0.0004415661,0.0005059559,0.0009962355,0.001426109,0.0006006003],"domain_scores_gemma":[0.9981846,0.0002836097,0.0003272218,0.001026354,0.00007979861,0.0000983867],"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":[0.0005135001,0.0003591914,0.005642018,0.00003242492,0.00007473586,0.0001057793,0.00927934,0.001618269,0.001309626,0.005863082,0.006604506,0.9685975],"study_design_scores_gemma":[0.003853661,0.0003945966,0.02191788,0.0006826082,0.00004976428,0.00003344763,0.1066325,0.2207832,0.0009503551,0.004252809,0.6382857,0.002163513],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.92893,0.0003948493,0.009005869,0.002032414,0.02551983,0.001032581,0.009146845,0.0002248342,0.02371273],"genre_scores_gemma":[0.9961196,0.0005807385,0.0001416841,0.0002185469,0.001294883,0.00009319185,0.001191882,0.00002294965,0.0003365513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.966434,"threshold_uncertainty_score":0.9999508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147159","doi":"10.1109/bigdata55660.2022.10020959","title":"Adaptive Content Forwarding Mechanism for Platoon based Vehicular Named Data Networks","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Caching and Content Delivery","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"","keywords":"Platoon; Computer science; Computer network; Overhead (engineering); Scheme (mathematics); Throughput; The Internet; Vehicular ad hoc network; Data exchange; Electronic data interchange; Protocol (science); Distributed computing; Wireless ad hoc network; Telecommunications; Control (management); Wireless; Database; Operating system","authors":[{"name":"Anu Kaushik","is_ca":false},{"name":"Deepanshu Garg","is_ca":false},{"name":"Anushka Nehra","is_ca":false},{"name":"Rasmeet Singh Bali","is_ca":false},{"name":"Mohamed Baza","is_ca":false},{"name":"Gautam Srivastava","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4758896369626464,"gpt":0.3314948332699191,"spread":0.1443948036927272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001888668,0.0003601623,0.0003770338,0.0002840101,0.0006006079,0.0006135579,0.01869106,0.00008362992,0.00008418977],"category_scores_gemma":[0.0003594149,0.0003774168,0.00008896274,0.0002812379,0.00005857875,0.00155903,0.01058918,0.0006877652,0.00002552621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002171686,"about_ca_system_score_gemma":0.0004420109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003926327,"about_ca_topic_score_gemma":0.0002969714,"domain_scores_codex":[0.9950696,0.0002500231,0.0005588413,0.002144256,0.001467798,0.0005094954],"domain_scores_gemma":[0.9922036,0.0004292373,0.0003895379,0.006479049,0.0003298844,0.0001686926],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001455522,0.001037983,0.0001176677,0.00004319388,0.001351591,0.0003981601,0.0001693203,0.01170794,0.007077153,0.3864312,0.2309552,0.3592551],"study_design_scores_gemma":[0.00134404,0.0001987648,0.00001990673,0.00006866574,0.00004984725,0.00002524305,0.0002264229,0.967399,0.0001291759,0.001250068,0.0288578,0.0004310548],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001181243,0.00007758827,0.9434425,0.003467652,0.01086234,0.0005904366,0.03987293,0.0001685626,0.0003367842],"genre_scores_gemma":[0.9244427,0.00007947977,0.003836338,0.002964868,0.0009843201,0.000174935,0.06706505,0.00003715311,0.0004151278],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.955691,"threshold_uncertainty_score":0.9998678,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318185035","doi":"10.1109/bigdata55660.2022.10020256","title":"Neuro-heuristic Pallet Detection for Automated Guided Vehicle Navigation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Manufacturing and Logistics Optimization","field":"Engineering","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Brandon University","funders":"Silesian University of Technology","keywords":"Heuristics; Computer science; Pallet; Focus (optics); Automation; Heuristic; Artificial intelligence; Computer vision; Point (geometry); Robot; Real-time computing; Engineering","authors":[{"name":"Katarzyna Prokop","is_ca":false},{"name":"Dawid Połap","is_ca":false},{"name":"Gautam Srivastava","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2412269997103307,"gpt":0.3397395132856229,"spread":0.0985125135752922,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003039383,0.000205967,0.0001580493,0.0001645994,0.0002668386,0.000129855,0.001614904,0.00005322398,0.0001108517],"category_scores_gemma":[0.0003247882,0.0002429538,0.00002543718,0.0001556848,0.00003324553,0.0003419517,0.00052813,0.0003244682,0.00002835809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696457,"about_ca_system_score_gemma":0.00004868351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004416593,"about_ca_topic_score_gemma":0.00004772153,"domain_scores_codex":[0.9982544,0.00005739128,0.0003611286,0.0006137669,0.0004806456,0.0002326631],"domain_scores_gemma":[0.9983245,0.0001646278,0.0001293589,0.001201037,0.0001159614,0.00006455218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001248142,0.00009329485,0.00001412567,0.00005442328,0.00009505347,0.0000195058,0.00004154792,0.8672553,0.01103502,0.0009241696,0.04789381,0.07244891],"study_design_scores_gemma":[0.0005493046,0.00007433213,0.0001021236,0.00001677016,0.00002415037,0.00001495243,0.00003638716,0.9459896,0.001850154,0.0008023729,0.05029869,0.0002411336],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008869858,0.00002881918,0.9440605,0.0005024527,0.01339612,0.0006043635,0.03000841,0.001375065,0.001154404],"genre_scores_gemma":[0.9418175,0.00008570847,0.001725311,0.000154112,0.0005632547,0.0001277523,0.05533703,0.00004915214,0.0001402143],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9423352,"threshold_uncertainty_score":0.9907369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147587","doi":"10.1109/bigdata55660.2022.10021025","title":"Handwritten Word Recognition using Deep Learning Approach: A Novel Way of Generating Handwritten Words","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Handwritten Text Recognition Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"","keywords":"Computer science; Word (group theory); Artificial intelligence; Word error rate; Bengali; Natural language processing; Process (computing); Speech recognition; Recall rate; Deep learning; Precision and recall; Language model; Pattern recognition (psychology); Mathematics","authors":[{"name":"Mst Shapna Akter","is_ca":false},{"name":"Hossain Shahriar","is_ca":false},{"name":"Alfredo Cuzzocrea","is_ca":false},{"name":"Nova Ahmed","is_ca":false},{"name":"Carson K. Leung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3210273366955822,"gpt":0.3386155405561522,"spread":0.01758820386056997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.002184958,0.0004139354,0.0004785925,0.0007383843,0.0006436945,0.0006165558,0.008187549,0.0001245197,0.0003898194],"category_scores_gemma":[0.0004495487,0.00046137,0.00009369228,0.0008790128,0.0001407304,0.001849486,0.006346155,0.001097085,0.00003311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000224227,"about_ca_system_score_gemma":0.0003142018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003411322,"about_ca_topic_score_gemma":0.0001072685,"domain_scores_codex":[0.9945787,0.0004392822,0.000944462,0.001770491,0.001756982,0.0005101204],"domain_scores_gemma":[0.9957981,0.0002104765,0.000779931,0.00259334,0.0004585033,0.000159685],"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":[0.00008854218,0.0005659429,0.00011499,0.00003905486,0.0001829366,0.0000317223,0.0005101248,0.0005151468,0.03885971,0.001000616,0.002104329,0.9559869],"study_design_scores_gemma":[0.001092605,0.00020652,0.00006872723,0.0001708773,0.0000493118,0.0001825455,0.0007388224,0.9826981,0.004698668,0.0009649312,0.008440451,0.0006884299],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01797709,0.00007724106,0.9692883,0.0004839903,0.00259555,0.0004750934,0.00595841,0.0003254818,0.002818879],"genre_scores_gemma":[0.7828411,0.0002200504,0.1856927,0.0006767326,0.001273522,0.0001982605,0.02870318,0.00007180277,0.0003225667],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.982183,"threshold_uncertainty_score":0.9997838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024165","doi":"10.1109/bigdata55660.2022.10020320","title":"Preserving Privacy Integration and Mining for Big Temporal Co-occurrence Patterns","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Transparency (behavior); Big data; Information privacy; Computer science; Internet privacy; Data integration; Privacy law; Hierarchy; Open data; Computer security; Data science; Privacy policy; Data mining; World Wide Web; Political science","authors":[{"name":"Anifat M. Olawoyin","is_ca":true},{"name":"Carson K. Leung","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.386741268485755,"gpt":0.384995275204468,"spread":0.001745993281286995,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001716541,0.0003871524,0.0003379281,0.0005039863,0.0005485744,0.0009713388,0.07500989,0.0001062144,0.0001090425],"category_scores_gemma":[0.009435008,0.0004088182,0.00004215353,0.0004319305,0.0001437398,0.002413565,0.1526715,0.0007318861,0.00001243848],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001854369,"about_ca_system_score_gemma":0.0003843823,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002963268,"about_ca_topic_score_gemma":0.0003320345,"domain_scores_codex":[0.9951479,0.000212628,0.0006534471,0.002151284,0.001311525,0.0005231714],"domain_scores_gemma":[0.9834281,0.0005496902,0.0005129602,0.01516448,0.0002125332,0.0001322868],"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":[0.0000864143,0.0001981388,0.00379708,0.00004688948,0.00009788869,0.00003595776,0.0001751233,0.00001067922,0.0009334297,0.003209083,0.5282995,0.4631099],"study_design_scores_gemma":[0.001191943,0.0003507817,0.001144459,0.0002064527,0.00002723805,0.00007179662,0.0005490216,0.8085216,0.001084171,0.01899059,0.167034,0.0008279249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02747599,0.00009751681,0.7545375,0.02708799,0.01334431,0.001030053,0.1750064,0.0006858466,0.0007343965],"genre_scores_gemma":[0.8573691,0.0003293323,0.0424503,0.0007177923,0.0008604653,0.0003356466,0.09775686,0.00003641898,0.0001440298],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8298932,"threshold_uncertainty_score":0.9998364,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318187137","doi":"10.1109/bigdata55660.2022.10020293","title":"Entity Matching with AUC-Based Fairness","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Computer science; Matching (statistics); Statistics; Mathematics","authors":[{"name":"Soudeh Nilforoushan","is_ca":true},{"name":"Qianfan Wu","is_ca":true},{"name":"Mostafa Milani","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6664563814827509,"gpt":0.4557380255016488,"spread":0.2107183559811021,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.006350874,0.0002867569,0.0003435746,0.0005316997,0.0005833614,0.001351768,0.01682367,0.00004258657,0.006070213],"category_scores_gemma":[0.0008768787,0.0002424697,0.00005007774,0.0007240304,0.000174298,0.001740458,0.0084126,0.0005727002,0.0007007702],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000151647,"about_ca_system_score_gemma":0.0005706901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00118039,"about_ca_topic_score_gemma":0.003087913,"domain_scores_codex":[0.9911465,0.0006054767,0.0007664596,0.001907813,0.005200207,0.0003735556],"domain_scores_gemma":[0.9922483,0.0006265891,0.000530135,0.0061527,0.0002854757,0.0001568198],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007920436,0.00102725,0.001314471,0.00002488884,0.0002543556,0.0002565026,0.000217452,0.001640319,0.0003933101,0.09533767,0.5560572,0.3426845],"study_design_scores_gemma":[0.001159996,0.0001769364,0.001318211,0.00004421529,0.00003428354,0.00001526433,0.002329668,0.03620015,0.00009883745,0.01239902,0.9457222,0.0005011918],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03767144,0.00005120442,0.58079,0.02968436,0.02680365,0.001251427,0.2732681,0.0003333516,0.05014645],"genre_scores_gemma":[0.9421769,0.00002733572,0.0008851946,0.003000821,0.0005505584,0.00007188579,0.04975439,0.00002443166,0.003508525],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9045054,"threshold_uncertainty_score":0.9996849,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147167","doi":"10.1109/bigdata55660.2022.10020867","title":"Emergence of an Autonomous Vehicle Secondary Data Market for Breakthrough Applications","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Human Mobility and Location-Based Analysis","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Data science; Cloud computing; Variety (cybernetics); Architecture; Data collection; Key (lock); Telecommunications; Systems engineering; Artificial intelligence; Engineering; Computer security; Geography","authors":[{"name":"Kevin Dick","is_ca":true},{"name":"James R. Green","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3288503865665113,"gpt":0.4098341532725872,"spread":0.08098376670607593,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003000716,0.000170404,0.0002477839,0.0001831933,0.001017204,0.0001608357,0.01061071,0.00006404257,0.01173459],"category_scores_gemma":[0.0004078787,0.0002016068,0.00004758112,0.0004540755,0.0003394316,0.001158606,0.002201926,0.0003233613,0.00003449031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001004498,"about_ca_system_score_gemma":0.001541866,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.008235564,"about_ca_topic_score_gemma":0.03286694,"domain_scores_codex":[0.9964315,0.0003956484,0.0005662617,0.001276815,0.001042249,0.000287554],"domain_scores_gemma":[0.9942868,0.0003520852,0.0003636292,0.00454926,0.000308872,0.000139407],"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":[0.00018471,0.001140142,0.0003492754,0.00004671112,0.0002899245,0.000004239989,0.001094193,0.0001600127,0.0006651166,0.02743535,0.1966378,0.7719926],"study_design_scores_gemma":[0.0004323911,0.00009572615,0.0004440402,0.00001390526,0.00009179275,0.000001483805,0.006467714,0.1713104,0.00006359342,0.003461242,0.8173012,0.0003165392],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.01212628,0.0002690576,0.1271326,0.01623726,0.006944743,0.003064519,0.7705986,0.0002949914,0.06333195],"genre_scores_gemma":[0.8494418,0.0002119051,0.0008106812,0.0005258239,0.001168295,0.0003189979,0.1455466,0.00002075382,0.001955043],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.8373156,"threshold_uncertainty_score":0.9983687,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147794","doi":"10.1109/bigdata55660.2022.10020299","title":"Temporal Graph Representation Learning via Maximal Cliques","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Clique; Computer science; Graph; Node (physics); Theoretical computer science; Embedding; Representation (politics); Graph embedding; Feature learning; Artificial intelligence; Mathematics; Combinatorics","authors":[{"name":"Shima Khoshraftar","is_ca":true},{"name":"Aijun An","is_ca":true},{"name":"Nastaran Babanejad","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.304841879149363,"gpt":0.3731440942115506,"spread":0.06830221506218759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0008250314,0.0002987366,0.0002605509,0.0004104453,0.0005251564,0.0004362739,0.01049551,0.0000609007,0.0002660603],"category_scores_gemma":[0.0001821376,0.0003266711,0.00006343421,0.0007853389,0.0001135658,0.002337157,0.007543416,0.001075525,0.00006935865],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001058924,"about_ca_system_score_gemma":0.0001509437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002501253,"about_ca_topic_score_gemma":0.0001769658,"domain_scores_codex":[0.995315,0.0004268783,0.0005414111,0.001767437,0.001528473,0.0004208479],"domain_scores_gemma":[0.9956364,0.0002036682,0.0004471705,0.003398478,0.0001751003,0.0001392023],"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":[0.0003616462,0.0004428941,0.006417328,0.00001422713,0.000221227,0.0004506286,0.0002577544,0.005960971,0.004549197,0.05777858,0.06865,0.8548955],"study_design_scores_gemma":[0.0009909078,0.0004403842,0.001908886,0.00004522875,0.00002202583,0.000170424,0.0002166865,0.8289555,0.0006088278,0.02588478,0.1399221,0.0008342757],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007484924,0.00009302594,0.9647464,0.005363283,0.01323283,0.0004665821,0.003843309,0.0005421861,0.004227418],"genre_scores_gemma":[0.9654011,0.0002495935,0.007581398,0.001037485,0.0009790782,0.00007939543,0.02382435,0.00003410158,0.0008135544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9579161,"threshold_uncertainty_score":0.9999185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318186065","doi":"10.1109/bigdata55660.2022.10020878","title":"Cough Classification with Deep Derived Features using Audio Spectrogram Transformer","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Respiratory and Cough-Related Research","field":"Medicine","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa; Carleton University; National Research Council Canada","funders":"National Research Council","keywords":"Spectrogram; Transformer; Computer science; Artificial intelligence; Feature engineering; Feature selection; Machine learning; Nonlinear system; Feature extraction; Deep learning; Data mining; Pattern recognition (psychology); Engineering","authors":[{"name":"Julio J. Valdés","is_ca":true},{"name":"Karim Habashy","is_ca":true},{"name":"Pengcheng Xi","is_ca":true},{"name":"Madison Cohen-McFarlane","is_ca":true},{"name":"Bruce Wallace","is_ca":true},{"name":"Rafik Goubran","is_ca":true},{"name":"Frank Knoefel","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4486312601254973,"gpt":0.407795632811187,"spread":0.04083562731431023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006814381,0.0002695174,0.0002954217,0.0003046652,0.0004258117,0.0001861042,0.002285618,0.000097414,0.001657514],"category_scores_gemma":[0.0000987049,0.0002317741,0.00004981194,0.0004568741,0.0001967525,0.0005025389,0.0004345354,0.001214537,0.00006097463],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002785333,"about_ca_system_score_gemma":0.0008159592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001838978,"about_ca_topic_score_gemma":0.0004684998,"domain_scores_codex":[0.9961476,0.0001902227,0.0003808044,0.001042272,0.00184046,0.0003986181],"domain_scores_gemma":[0.9972209,0.00008047247,0.0001806126,0.002075772,0.0002605452,0.0001817274],"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":[0.01030275,0.002437305,0.003669587,0.0001461762,0.002284266,0.001298711,0.000645292,0.0006093645,0.3325211,0.01039753,0.0503976,0.5852903],"study_design_scores_gemma":[0.01467444,0.005178474,0.03289337,0.0007158867,0.001056075,0.002352156,0.007268642,0.2607358,0.0196456,0.0009714478,0.6521698,0.002338336],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.803276,0.001169853,0.06040262,0.0232731,0.009932373,0.004045504,0.03213302,0.00053327,0.06523424],"genre_scores_gemma":[0.971005,0.0003406804,0.0004588048,0.000721988,0.0008488037,0.00007832232,0.0255502,0.00004304179,0.0009531935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6017721,"threshold_uncertainty_score":0.9992551,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318186088","doi":"10.1109/bigdata55660.2022.10020426","title":"A Convergence Theory for Federated Average: Beyond Smoothness","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Privacy-Preserving Technologies in Data","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of British Columbia Hospital","funders":"","keywords":"Smoothness; Computer science; Lipschitz continuity; Convergence (economics); Bounded function; Function (biology); Gradient descent; Mathematical optimization; Scheme (mathematics); Stochastic gradient descent; Applied mathematics; Mathematics; Artificial intelligence; Artificial neural network; Mathematical analysis","authors":[{"name":"Xiaoxiao Li","is_ca":true},{"name":"Zhao Song","is_ca":false},{"name":"Runzhou Tao","is_ca":false},{"name":"Guangyi Zhang","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2782544865332073,"gpt":0.3560469689397069,"spread":0.07779248240649961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002421409,0.0003839014,0.0003398061,0.000384959,0.00074579,0.0008213733,0.1165975,0.0001144715,0.0007594126],"category_scores_gemma":[0.009589282,0.0004096291,0.00005508044,0.0006642034,0.0002100728,0.002019586,0.1851463,0.0008215796,0.0001187527],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002380419,"about_ca_system_score_gemma":0.0006305305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001081644,"about_ca_topic_score_gemma":0.00008944605,"domain_scores_codex":[0.9947531,0.0003273642,0.0005915338,0.002288251,0.001457949,0.0005817885],"domain_scores_gemma":[0.9786849,0.0006681751,0.0004067071,0.01979848,0.000315014,0.0001267046],"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":[0.0001935906,0.0002739127,0.00008656712,0.00002170952,0.0001767002,0.0000841457,0.00004979159,0.00003736495,0.001950822,0.09356381,0.7021781,0.2013835],"study_design_scores_gemma":[0.0009881699,0.000176847,0.00008381361,0.00003645567,0.00001868574,0.00005539127,0.0001513798,0.6100502,0.001586391,0.1970095,0.1892258,0.0006173671],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001406194,0.00009474752,0.8855934,0.0267104,0.0173078,0.0006973483,0.06485911,0.0006826976,0.002648367],"genre_scores_gemma":[0.8927077,0.0003316758,0.03300059,0.003693576,0.0009231156,0.0005995614,0.06695841,0.00007751535,0.001707818],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8913015,"threshold_uncertainty_score":0.9998356,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318185157","doi":"10.1109/bigdata55660.2022.10020564","title":"A Novel Rigorous Measurement Model for Big Data Quality Characteristics","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Big Data and Business Intelligence","field":"Business, Management and Accounting","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Big data; Computer science; Data modeling; Quality (philosophy); Data mining; Database; Physics","authors":[{"name":"Haochen Zou","is_ca":true},{"name":"Kun Xiang","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7505477363862263,"gpt":0.4080711581157322,"spread":0.3424765782704941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.003808621,0.0005230819,0.0005241804,0.0004306049,0.0006925223,0.001165245,0.01558162,0.0001077835,0.0006162717],"category_scores_gemma":[0.001687976,0.0005366653,0.00006724057,0.0005040185,0.0001508142,0.003019417,0.01423682,0.0006236541,0.00021407],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002138077,"about_ca_system_score_gemma":0.0005341115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001791008,"about_ca_topic_score_gemma":0.002560489,"domain_scores_codex":[0.9933088,0.00005003914,0.001074828,0.002262869,0.002695192,0.0006082271],"domain_scores_gemma":[0.9908994,0.0001312753,0.0009334378,0.007001189,0.0009757305,0.00005893692],"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":[0.001191419,0.002063079,0.0006978903,0.0003821337,0.0004788555,0.00002837353,0.00005136909,0.0003042303,0.007977203,0.03119813,0.4345047,0.5211226],"study_design_scores_gemma":[0.0007286242,0.00001880804,0.0005257921,0.00007358225,0.0001081833,0.000008436114,0.0001184559,0.5060958,0.00002868474,0.001105564,0.4906168,0.0005712986],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002940909,0.00008346818,0.6129281,0.007544855,0.03040891,0.001241568,0.3410549,0.0002534418,0.003543884],"genre_scores_gemma":[0.6710271,0.0001511794,0.0009029489,0.003928367,0.009516309,0.0001935718,0.3133636,0.00008316475,0.0008338011],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6680862,"threshold_uncertainty_score":0.9998716,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147859","doi":"10.1109/bigdata55660.2022.10020507","title":"Discovering Limitations of Image Quality Assessments with Noised Deep Learning Image Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Image and Video Quality Assessment","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institute for Advanced Research; Google","keywords":"MNIST database; Computer science; Artificial intelligence; Pixel; Image quality; Image (mathematics); Image processing; Computer vision; Noise (video); Image resolution; Image restoration; Pattern recognition (psychology); Deep learning","authors":[{"name":"Wei Dai","is_ca":false},{"name":"Daniel Berleant","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4654309621175568,"gpt":0.4333924151649992,"spread":0.03203854695255764,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.001708834,0.0002800979,0.0003340147,0.0002663892,0.0004244745,0.0006616238,0.007555006,0.00003599521,0.0001943694],"category_scores_gemma":[0.0003773488,0.0002802954,0.00005151549,0.0004631789,0.0001328138,0.00318961,0.00565855,0.000684987,0.00004011433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001868744,"about_ca_system_score_gemma":0.0005191971,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005126414,"about_ca_topic_score_gemma":0.0004609226,"domain_scores_codex":[0.9951586,0.0006270029,0.0006757426,0.001240265,0.001939431,0.0003589812],"domain_scores_gemma":[0.9953462,0.000490205,0.0006270287,0.003095068,0.0003276853,0.0001138167],"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":[0.0007710004,0.003498412,0.003557518,0.0002267424,0.001278912,0.000470557,0.003147541,0.002604074,0.09501731,0.1025117,0.01520099,0.7717152],"study_design_scores_gemma":[0.004741988,0.001411669,0.0197345,0.0002592205,0.0001337163,0.00008530421,0.007551903,0.9013361,0.00573751,0.002996583,0.05407296,0.001938549],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02227743,0.00002083648,0.9558966,0.002665506,0.002346364,0.0003727822,0.008451953,0.0001286014,0.007839932],"genre_scores_gemma":[0.9541134,0.000116059,0.02909539,0.0004225354,0.0001828301,0.00007570186,0.0155695,0.0000263162,0.0003982989],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9318359,"threshold_uncertainty_score":0.9999649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147653","doi":"10.1109/bigdata55660.2022.10020557","title":"Multimodal Deep Homography Estimation Using a Domain Adaptation Generative Adversarial Network","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Image and Video Retrieval Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Defence Research and Development Canada; National Research Council Canada; Thales (Canada)","funders":"","keywords":"Artificial intelligence; Computer science; Homography; Computer vision; Parallax; Deep learning; Feature (linguistics); Generative grammar; Modalities; Domain (mathematical analysis); Adversarial system; Pattern recognition (psychology); Mathematics; Projective test","authors":[{"name":"T. Pouplin","is_ca":true},{"name":"Hughes Perreault","is_ca":true},{"name":"Benoît Debaque","is_ca":true},{"name":"M-A. Drouin","is_ca":true},{"name":"N. Duclos-Hindie","is_ca":true},{"name":"Sébastien Roy","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2705887029607451,"gpt":0.3671188911458947,"spread":0.09653018818514963,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0009362872,0.0002883886,0.0002476647,0.000336225,0.0006213601,0.0004278646,0.005876778,0.00006523317,0.0001066679],"category_scores_gemma":[0.0001795141,0.0003150704,0.00005858633,0.000793525,0.00009654916,0.002590727,0.003781629,0.0005144311,0.00001783188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002150429,"about_ca_system_score_gemma":0.0003146691,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001956709,"about_ca_topic_score_gemma":0.0001400056,"domain_scores_codex":[0.9963098,0.0003271356,0.0004867217,0.001271449,0.001238429,0.0003664536],"domain_scores_gemma":[0.9967909,0.0001549825,0.0004117142,0.002313011,0.0002247933,0.0001045632],"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":[0.0004089845,0.0003987917,0.0001557954,0.00001213008,0.0002430157,0.0001395768,0.0007027267,0.05683004,0.004982248,0.05073051,0.01053227,0.8748639],"study_design_scores_gemma":[0.000622443,0.0001624437,0.00009858951,0.00002881258,0.00001796677,0.00003033876,0.0001569397,0.9691442,0.0004933913,0.01532918,0.01356382,0.0003519133],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001038429,0.00006987926,0.9884655,0.0005926071,0.005157764,0.0003948599,0.003621511,0.0001986222,0.0004608419],"genre_scores_gemma":[0.4493974,0.0001518451,0.5291451,0.0008609174,0.00182246,0.00009066663,0.01843664,0.00003317239,0.00006183884],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9123141,"threshold_uncertainty_score":0.9999301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318148360","doi":"10.1109/bigdata55660.2022.10020874","title":"LSTM-based Pulmonary Air Leak Forecasting for Chest Tube Management","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"COVID-19 diagnosis using AI","field":"Medicine","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ottawa Hospital","funders":"","keywords":"Context (archaeology); Empyema; Chest tube; Computer science; Leak; Autoregressive model; Medicine; Intensive care medicine; Surgery; Engineering","authors":[{"name":"Roberto Corizzo","is_ca":false},{"name":"Rodrigo Yepez-Lopez","is_ca":false},{"name":"Sébastien Gilbert","is_ca":true},{"name":"Nathalie Japkowicz","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4472536916586746,"gpt":0.3922616421471449,"spread":0.05499204951152969,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001171864,0.0003419855,0.0003709635,0.0004935606,0.0003795669,0.0001203434,0.003478993,0.00006626761,0.0008852045],"category_scores_gemma":[0.0005578842,0.0003723426,0.00009135504,0.0003522899,0.000100492,0.0003460326,0.002848443,0.0005384409,0.00007107279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005271088,"about_ca_system_score_gemma":0.0005571554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000232575,"about_ca_topic_score_gemma":0.0002355795,"domain_scores_codex":[0.9959137,0.00009921122,0.000566471,0.001516833,0.001449682,0.0004540719],"domain_scores_gemma":[0.9957911,0.0005103537,0.0002828419,0.00302429,0.0002169853,0.0001744587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001812289,0.002082064,0.001410761,0.0005348293,0.0006062154,0.0009036731,0.00006622465,0.001274479,0.002201401,0.003331555,0.5246468,0.4611297],"study_design_scores_gemma":[0.001841159,0.0002730964,0.001133835,0.0002650867,0.0001626421,0.00005667863,0.0002209454,0.2828609,0.0003453369,0.0002296333,0.7122698,0.0003408601],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04110725,0.0004634128,0.1022484,0.4614002,0.05101498,0.01065337,0.3004737,0.001479835,0.03115878],"genre_scores_gemma":[0.8478464,0.00009672275,0.002401144,0.02358443,0.001815149,0.000640746,0.1213851,0.00009114327,0.002139157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8067392,"threshold_uncertainty_score":0.9998729,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024352","doi":"10.1109/bigdata55660.2022.10020258","title":"Review of Publically Available Health Big Data Sets","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Health informatics; Public health informatics; Computer science; Informatics; Usability; Data science; Dashboard; Data mining; Information retrieval; World Wide Web; Public health; Medicine; Health policy; International health; Engineering","authors":[{"name":"Dillon Chrimes","is_ca":true},{"name":"Chanhee Kim","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.8077064389291911,"gpt":0.5061207953285485,"spread":0.3015856436006427,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.02283281,0.0003446123,0.0007724446,0.0006014536,0.0004136508,0.0007487819,0.03879162,0.00005472701,0.01333064],"category_scores_gemma":[0.007644592,0.0003099359,0.00007111667,0.00131025,0.0002171208,0.002426151,0.03510995,0.0006791715,0.001720524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001647721,"about_ca_system_score_gemma":0.001615119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001394118,"about_ca_topic_score_gemma":0.001752737,"domain_scores_codex":[0.9871895,0.001328427,0.002143914,0.002861492,0.005934084,0.0005425894],"domain_scores_gemma":[0.9789383,0.0009062659,0.001566848,0.01765819,0.0006188772,0.0003115143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004630001,0.0002833316,0.00003851975,0.0001514346,0.00007721219,0.00001125277,0.00001722076,0.000002242099,0.000018643,0.006074741,0.6461211,0.347158],"study_design_scores_gemma":[0.0004644484,0.0001475755,0.0001167916,0.0005437565,0.00002954715,0.0000162624,0.0003093175,0.006916731,0.000007550864,0.001921572,0.9892234,0.0003030168],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0001490502,0.005669428,0.0188944,0.1130892,0.02354572,0.0015442,0.7918164,0.0001433642,0.04514833],"genre_scores_gemma":[0.02511134,0.0704499,0.002573376,0.07330798,0.002118886,0.0001657913,0.8058515,0.000081982,0.0203393],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.346855,"threshold_uncertainty_score":0.9999353,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318148204","doi":"10.1109/bigdata55660.2022.10020871","title":"Predicting Deduplication Performance: An Analytical Model and Empirical Evaluation","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Advanced Data Storage Technologies","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":"University of Alberta","funders":"","keywords":"Data deduplication; Computer science; Data mining; Software versioning; Kernel (algebra); Database; Software; Operating system","authors":[{"name":"Owen Randall","is_ca":true},{"name":"Paul Lu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5054255254777182,"gpt":0.4297697773039301,"spread":0.07565574817378812,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001701643,0.0002260543,0.0001927063,0.0003354184,0.0004392889,0.0003348427,0.00850097,0.00007319442,0.00006331935],"category_scores_gemma":[0.0005306479,0.0002375211,0.00001628743,0.0004312034,0.0001412007,0.003315632,0.008200962,0.0006094473,0.00002077238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002641534,"about_ca_system_score_gemma":0.0004423017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002880252,"about_ca_topic_score_gemma":0.00006522831,"domain_scores_codex":[0.995834,0.0001565052,0.0004190122,0.00159077,0.001700327,0.000299365],"domain_scores_gemma":[0.9949324,0.0001099511,0.0002466704,0.004366409,0.0002314242,0.0001131842],"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":[0.0000743058,0.0002797578,0.002411202,0.00001040052,0.00005540471,0.00001106999,0.0001712653,0.009577411,0.0008338721,0.02291452,0.009909265,0.9537515],"study_design_scores_gemma":[0.000391696,0.0001534506,0.0013,0.00001283484,0.00002237058,0.00004157196,0.0001525655,0.9886321,0.00008094605,0.004092254,0.004870388,0.0002498038],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2489682,0.00006396672,0.7290938,0.005338928,0.002642121,0.0006339412,0.01083588,0.0005967025,0.001826397],"genre_scores_gemma":[0.9688495,0.0001761601,0.01224546,0.0005520443,0.0002654276,0.0001213418,0.01771075,0.00001650101,0.00006279691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9790547,"threshold_uncertainty_score":0.9998205,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024124","doi":"10.1109/bigdata55660.2022.10020422","title":"Dynamic Graph Summarization: Optimal and Scalable","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Graph Theory and Algorithms","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":"University of Victoria","funders":"","keywords":"Automatic summarization; Computer science; Scalability; Lossless compression; Graph; Theoretical computer science; Algorithm; Artificial intelligence; Data compression","authors":[{"name":"Mahdi Hajiabadi","is_ca":true},{"name":"Venkatesh Srinivasan","is_ca":true},{"name":"Alex Thomo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.158207502154851,"gpt":0.3135448753019634,"spread":0.1553373731471124,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0009428939,0.0002251869,0.0001911905,0.0003333503,0.0005054172,0.000546813,0.008319966,0.00004426768,0.0003776515],"category_scores_gemma":[0.00008134788,0.0002388949,0.00003008136,0.0005438657,0.0001368893,0.001423851,0.006648605,0.0004345763,0.00005050478],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005206601,"about_ca_system_score_gemma":0.0001816669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005410695,"about_ca_topic_score_gemma":0.00005576893,"domain_scores_codex":[0.9969995,0.0001952443,0.0003231668,0.001260124,0.0009213287,0.000300639],"domain_scores_gemma":[0.9967743,0.0001167366,0.0001726773,0.002699526,0.0001096603,0.0001271326],"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":[0.0001501122,0.0005800648,0.0005643301,0.0000241277,0.0002654797,0.0002095167,0.0002991545,0.001046153,0.002230699,0.4530905,0.03444255,0.5070974],"study_design_scores_gemma":[0.000756553,0.0001811652,0.0005770667,0.00002971366,0.00001876725,0.0001135561,0.0001915017,0.9121439,0.0001177813,0.01921738,0.06617222,0.0004804143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01512603,0.000223947,0.9249254,0.006785614,0.01688935,0.000470875,0.02884995,0.0003235827,0.006405284],"genre_scores_gemma":[0.9604231,0.0004219676,0.01008471,0.001250414,0.0003907443,0.00006652655,0.02536394,0.00002913041,0.001969503],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9452971,"threshold_uncertainty_score":0.9970455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147168","doi":"10.1109/bigdata55660.2022.10020831","title":"A Real-time, Scalable Monitoring and User Analytics Solution for Microservices-based Software Applications","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Software System Performance and Reliability","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Microservices; Computer science; Scalability; Analytics; Big data; Database transaction; Transaction log; Software; Distributed computing; Database; Cloud computing; Data mining; Operating system","authors":[{"name":"Cathy H Zhang","is_ca":true},{"name":"M. Omair Shafiq","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.1826437870504777,"gpt":0.3440523884764013,"spread":0.1614086014259236,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001048227,0.0002121187,0.0002258621,0.0002144384,0.0006165061,0.000385234,0.005228559,0.00006594109,0.00004778585],"category_scores_gemma":[0.00009616561,0.0002174368,0.00003985497,0.0004039415,0.00006690933,0.0009094949,0.00262824,0.0002512415,0.00004241518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001887763,"about_ca_system_score_gemma":0.0004159941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003163077,"about_ca_topic_score_gemma":0.00005648427,"domain_scores_codex":[0.9972787,0.00008763587,0.0004200866,0.001175961,0.0007299976,0.0003075518],"domain_scores_gemma":[0.9961019,0.0002637698,0.000259772,0.002971787,0.000294894,0.0001079076],"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":[0.0006390563,0.00198129,0.04798531,0.0008185004,0.0006529777,0.00002880457,0.0004288689,0.003668496,0.03737635,0.00716438,0.125798,0.7734579],"study_design_scores_gemma":[0.001104344,0.0001681103,0.002688063,0.00009044419,0.00004484898,0.00001724579,0.00007668295,0.8536895,0.001063099,0.0006482534,0.1399122,0.0004972435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01136085,0.00007588638,0.9616096,0.001949318,0.004439701,0.001089673,0.01889784,0.0003221995,0.0002549448],"genre_scores_gemma":[0.7960157,0.0005844889,0.1493467,0.0007803363,0.003038225,0.001878039,0.04628352,0.0000919365,0.001981044],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.850021,"threshold_uncertainty_score":0.9716051,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318148225","doi":"10.1109/bigdata55660.2022.10020386","title":"Adaptive Method for Machine Learning Model Selection in Data Science Projects","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Software Engineering Research","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Selection (genetic algorithm); Machine learning; Process (computing); Heuristics; Feature selection; Model selection; Artificial intelligence; Data mining","authors":[{"name":"Cristina Tavares","is_ca":true},{"name":"Nathalia Nascimento","is_ca":true},{"name":"Paulo Alencar","is_ca":true},{"name":"Donald Cowan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4726800557815008,"gpt":0.4217361885031067,"spread":0.05094386727839412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.005531415,0.00023625,0.0002271603,0.0009363489,0.0004663224,0.0005056286,0.02152296,0.00004454443,0.00004310672],"category_scores_gemma":[0.003437208,0.0002587308,0.00002022214,0.001512878,0.00009423188,0.003106384,0.0162759,0.001017962,0.00001570304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004532275,"about_ca_system_score_gemma":0.001708324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005706761,"about_ca_topic_score_gemma":0.0005372976,"domain_scores_codex":[0.9946086,0.0002236878,0.0003755367,0.002258941,0.001987331,0.0005459514],"domain_scores_gemma":[0.9952162,0.0008247124,0.0001763452,0.00335621,0.000303188,0.0001233606],"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":[0.0005551873,0.0008490575,0.00192063,0.00006556102,0.0001888419,0.00007926275,0.0008684627,0.1977151,0.01901194,0.05619213,0.02628268,0.6962711],"study_design_scores_gemma":[0.0005226916,0.000149414,0.0002182224,0.00002679622,0.000005490677,0.000028235,0.00006513614,0.9884093,0.0003301831,0.0007008202,0.009274444,0.0002692922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008434698,0.00003000243,0.9849275,0.001071936,0.00197954,0.0005302154,0.01016896,0.0001747133,0.0002736131],"genre_scores_gemma":[0.7386898,0.00009132178,0.2425025,0.0002646273,0.0004967786,0.0003035716,0.01685787,0.00004804716,0.0007454802],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7906941,"threshold_uncertainty_score":0.9999865,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318187680","doi":"10.1109/bigdata55660.2022.10020691","title":"Air Pollution Surveillance System: A Big Data Approach to Monitoring Adverse Health Outcomes for Public Health Interventions","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Air Quality and Health Impacts","field":"Environmental 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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Big data; Harm; Air pollution; Public health; Psychological intervention; Environmental health; Environmental planning; Business; Risk analysis (engineering); Computer science; Environmental science; Medicine; Political science; Data mining","authors":[{"name":"Shahan Salim","is_ca":true},{"name":"Irfhana Zakir Hussain","is_ca":true},{"name":"Jasleen Kaur","is_ca":true},{"name":"Plinio Pelegrini Morita","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6416240419164759,"gpt":0.4430536513876135,"spread":0.1985703905288624,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.007118542,0.0003477214,0.0005651927,0.0003006907,0.00118842,0.0001733874,0.007673989,0.00006661446,0.0002551307],"category_scores_gemma":[0.000750949,0.0003627701,0.00008117536,0.0005786031,0.0001171603,0.001226628,0.007615218,0.0005505866,0.0001667304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002025352,"about_ca_system_score_gemma":0.0008740486,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006564627,"about_ca_topic_score_gemma":0.004918199,"domain_scores_codex":[0.9936911,0.0007715561,0.001159277,0.001831161,0.001644909,0.0009020031],"domain_scores_gemma":[0.9938653,0.0001802863,0.0007821018,0.004429485,0.00005958672,0.0006832809],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003086247,0.002015105,0.01698569,0.0009541257,0.0002658121,0.000007675963,0.000990159,0.001815475,0.00003333642,0.00678435,0.5147369,0.4551027],"study_design_scores_gemma":[0.001941386,0.0007588537,0.08956577,0.0003773195,0.0000226512,0.00004390975,0.005674037,0.06447575,0.00000335047,0.0001257508,0.8361799,0.0008313115],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.006015258,0.0002600123,0.351172,0.197287,0.02737913,0.004408914,0.4097319,0.0004408915,0.003304973],"genre_scores_gemma":[0.9038478,0.0002219946,0.00395778,0.008348281,0.001168734,0.0003106577,0.08126599,0.00004849856,0.0008302974],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8978325,"threshold_uncertainty_score":0.9998824,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024183","doi":"10.1109/bigdata55660.2022.10020511","title":"Dynamic Ensemble Size Adjustment for Memory Constrained Mondrian Forest","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Stream Mining 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":"Concordia University","funders":"","keywords":"Mondrian; Overfitting; Computer science; Machine learning; Ensemble learning; Tree (set theory); Data stream mining; Artificial intelligence; Memory model; Data mining; Shared memory; Parallel computing; Mathematics; Artificial neural network","authors":[{"name":"Martin Khannouz","is_ca":true},{"name":"Tristan Glatard","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2162287159834481,"gpt":0.3500891358264674,"spread":0.1338604198430194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001104554,0.0003629104,0.0003348027,0.0002935242,0.000354318,0.0004384728,0.01665491,0.00007283949,0.0003061126],"category_scores_gemma":[0.0004513334,0.0003953897,0.00006487243,0.0003132719,0.0001396113,0.001256034,0.008948982,0.0004483721,0.00005597885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002919731,"about_ca_system_score_gemma":0.0006375826,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002150081,"about_ca_topic_score_gemma":0.0007148937,"domain_scores_codex":[0.9957039,0.0001601081,0.0005779085,0.001809565,0.001251207,0.0004973239],"domain_scores_gemma":[0.9930424,0.0005188845,0.0003809723,0.005703775,0.0001917166,0.0001622677],"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":[0.0002322014,0.0005641511,0.0000526066,0.00002909042,0.0002432512,0.0001082436,0.0001664618,0.00009098757,0.004775104,0.09421953,0.27284,0.6266783],"study_design_scores_gemma":[0.002184832,0.0009827001,0.0004354224,0.0001033891,0.00006230748,0.0001750359,0.000423076,0.7270855,0.001188846,0.01414893,0.2521634,0.001046545],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002743004,0.00008416266,0.8068509,0.008618482,0.01637206,0.001592661,0.152112,0.0008211672,0.0108055],"genre_scores_gemma":[0.827562,0.000179109,0.08799274,0.002025427,0.0006845673,0.000689582,0.07883611,0.00006373208,0.00196673],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.824819,"threshold_uncertainty_score":0.9998498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024064","doi":"10.1109/bigdata55660.2022.10020783","title":"Imbalanced Multi-layer Cloud Classification with Advanced Baseline Imager (ABI) and CloudSat/CALIPSO Data","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Remote Sensing in Agriculture","field":"Environmental 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":"National Research Council Canada","funders":"National Security Agency; National Science Foundation","keywords":"Cloud computing; Random forest; Lidar; Computer science; Classifier (UML); Perceptron; Baseline (sea); Deep learning; Resampling; Remote sensing; Cloud cover; Cloud fraction; Artificial intelligence; Environmental science; Artificial neural network; Geography; Geology","authors":[{"name":"Lei Ding","is_ca":false},{"name":"Roberto Corizzo","is_ca":false},{"name":"Colin Bellinger","is_ca":true},{"name":"N. Ching","is_ca":false},{"name":"Spencer Login","is_ca":false},{"name":"Rodrigo Yepez-Lopez","is_ca":false},{"name":"Jie Gong","is_ca":false},{"name":"Dong L. Wu","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2510556575753,"gpt":0.3345477456942415,"spread":0.08349208811894149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001023325,0.0003634642,0.000285813,0.0000807305,0.000386055,0.0002403119,0.005884828,0.00007726631,0.001630018],"category_scores_gemma":[0.0003197511,0.0003111062,0.0000208913,0.0003673344,0.0003135993,0.001188331,0.006849079,0.0007114765,0.0002349307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002586385,"about_ca_system_score_gemma":0.00009198984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00037581,"about_ca_topic_score_gemma":0.0009358696,"domain_scores_codex":[0.9952173,0.0002936213,0.0004745035,0.002134704,0.001490973,0.0003889027],"domain_scores_gemma":[0.9945236,0.0001486847,0.000375948,0.004703711,0.00006908653,0.0001790078],"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":[0.0008039586,0.0009977078,0.004080283,0.00002378332,0.0002153714,0.0001409969,0.0002246881,0.002010349,0.1437413,0.0004690842,0.3838893,0.4634032],"study_design_scores_gemma":[0.002082696,0.0001798272,0.02434222,0.00006680762,0.00007126615,0.0001360999,0.0006513781,0.6166309,0.0005859152,0.0001034144,0.354338,0.0008115086],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4317868,0.0004708806,0.1182691,0.0502676,0.03556304,0.005425327,0.3291708,0.001086615,0.0279598],"genre_scores_gemma":[0.862228,0.0003771927,0.01564335,0.001414975,0.0009426644,0.00002193179,0.1175138,0.00005646468,0.001801677],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6146205,"threshold_uncertainty_score":0.9999341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318185484","doi":"10.1109/bigdata55660.2022.10020371","title":"Understanding Levels of Automation in Human-Machine Collaboration","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Human-Automation Interaction and Safety","field":"Psychology","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":"Automation; Variety (cybernetics); Computer science; Autonomy; Process (computing); Task (project management); Data science; Risk analysis (engineering); Knowledge management; Systems engineering; Artificial intelligence; Engineering","authors":[{"name":"Glaucia Melo","is_ca":true},{"name":"Nathalia Nascimento","is_ca":true},{"name":"Paulo Alencar","is_ca":true},{"name":"Donald Cowan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6250192258128631,"gpt":0.46840426658817,"spread":0.1566149592246931,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001244284,0.0001992462,0.0002596816,0.0007198633,0.0002669414,0.0001180167,0.002263458,0.00007600211,0.0219004],"category_scores_gemma":[0.0001774576,0.0002295577,0.00003241589,0.0005181344,0.00007515107,0.0007216249,0.0007905795,0.0004972906,0.0001375625],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005292599,"about_ca_system_score_gemma":0.0002057328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003446746,"about_ca_topic_score_gemma":0.00203333,"domain_scores_codex":[0.9967946,0.0004589228,0.0008294196,0.000769691,0.0009329778,0.000214437],"domain_scores_gemma":[0.9973664,0.0001959632,0.0005585425,0.001659512,0.000159758,0.00005978644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008842895,0.001906772,0.002748869,0.00005407105,0.0005294778,0.00009482686,0.00503396,0.00155265,0.01882929,0.6637772,0.255333,0.04925561],"study_design_scores_gemma":[0.01252387,0.001173886,0.05313288,0.0004013618,0.000143314,0.0001444567,0.04086688,0.5011687,0.001418971,0.01891319,0.3679589,0.002153564],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.130518,0.0001263704,0.1542723,0.02001101,0.07257748,0.002622449,0.2311854,0.0007153659,0.3879717],"genre_scores_gemma":[0.9702075,0.00001530275,0.00008186066,0.0004076214,0.000321975,0.0000632993,0.02709601,0.00002264619,0.001783758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8396896,"threshold_uncertainty_score":0.9789937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318148398","doi":"10.1109/bigdata55660.2022.10020567","title":"Heterogeneity in feature importance and prediction performance for sales at the market and store levels: the case of branded yogurt products in Quebec","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Consumer Attitudes and Food Labeling","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal; McGill University","funders":"HORIZON EUROPE Health","keywords":"Gradient boosting; Random forest; Aggregate (composite); Python (programming language); Loyalty; Computer science; Loyalty business model; Product (mathematics); Aggregate data; Marketing; Machine learning; Business; Statistics","authors":[{"name":"Cameron McRae","is_ca":true},{"name":"Jian‐Yun Nie","is_ca":true},{"name":"Laurette Dubé","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.248189087809298,"gpt":0.3494119663719226,"spread":0.1012228785626246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001064181,0.0001294043,0.0001810431,0.00009172887,0.0001633295,0.00004012779,0.0005658304,0.00003539943,0.00005320907],"category_scores_gemma":[0.0002104289,0.00009004824,0.00001316274,0.0001405921,0.0001268515,0.0002100432,0.0008689622,0.0003259619,3.278086e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009904528,"about_ca_system_score_gemma":0.0001784372,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001322951,"about_ca_topic_score_gemma":0.09188995,"domain_scores_codex":[0.9986869,0.00008422211,0.0002702101,0.0005314934,0.0002876961,0.0001395432],"domain_scores_gemma":[0.9986576,0.0001441077,0.0001403199,0.0009438277,0.00008107361,0.00003304441],"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":[0.006892523,0.0006747873,0.4275461,0.0007580493,0.00079449,0.0004251819,0.001818134,0.00007258656,0.01401569,0.0008486409,0.04084745,0.5053064],"study_design_scores_gemma":[0.008035734,0.0007050196,0.7154686,0.0006596338,0.0003474172,0.002535142,0.002432665,0.173434,0.001739582,0.00009364564,0.09400117,0.0005474105],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9745566,0.00139658,0.00002480122,0.006058007,0.0006286052,0.0006499553,0.01660305,0.000007997057,0.00007443343],"genre_scores_gemma":[0.9939407,0.0005468069,0.00006690968,0.0002159065,0.0001309686,0.00008082292,0.004592783,0.00001042394,0.0004147457],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.504759,"threshold_uncertainty_score":0.9246807,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024230","doi":"10.1109/bigdata55660.2022.10020333","title":"Thick Data Techniques for Identifying Abnormality in Video Frames for Wireless Capsule Endoscopy","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Gastrointestinal Bleeding Diagnosis and Treatment","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"NOSM University; Lakehead University","funders":"","keywords":"Computer science; Artificial intelligence; Capsule endoscopy; Abnormality; Modality (human–computer interaction); Filter (signal processing); Decision tree; Deep learning; Computer vision; Feature (linguistics); Feature extraction; Pattern recognition (psychology); Medicine; Radiology","authors":[{"name":"Jinan Fiaidhi","is_ca":true},{"name":"Sabah Mohammed","is_ca":true},{"name":"Petros Zezos","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4424567085698399,"gpt":0.4287686708050186,"spread":0.0136880377648213,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001714527,0.0002989245,0.0004468106,0.0002980354,0.0002518823,0.0001977911,0.003915959,0.00006644527,0.0002508978],"category_scores_gemma":[0.0008990389,0.0002943993,0.00005965432,0.0001920002,0.00008748336,0.0006661935,0.003164067,0.0005088277,0.00001302047],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002848113,"about_ca_system_score_gemma":0.0004242978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001156732,"about_ca_topic_score_gemma":0.0008101901,"domain_scores_codex":[0.9965592,0.0000851325,0.0006282393,0.001439749,0.0008784895,0.0004091581],"domain_scores_gemma":[0.9956951,0.0004496597,0.0003129491,0.003170766,0.0002441242,0.0001274465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.004288979,0.006742912,0.04956658,0.0008929188,0.001424159,0.0005881166,0.0003850787,0.00002823066,0.03366287,0.02043199,0.575272,0.3067161],"study_design_scores_gemma":[0.02287601,0.006643583,0.02547004,0.004736107,0.001552121,0.0009977712,0.004140732,0.2736922,0.044635,0.009816465,0.6026727,0.002767289],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1998496,0.0005296601,0.09106721,0.03218737,0.01389392,0.008903537,0.6502448,0.0005801612,0.002743797],"genre_scores_gemma":[0.8304764,0.0002729098,0.01144685,0.0008483864,0.0008695051,0.0009010861,0.154889,0.00004498287,0.0002508442],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6306269,"threshold_uncertainty_score":0.9999508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024146","doi":"10.1109/bigdata55660.2022.10020239","title":"A Stylized Presence Detection System in the Era of Blockchain and Big Data","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Bluetooth and Wireless Communication Technologies","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":"McGill University","funders":"","keywords":"Stylized fact; Big data; Computer science; Blockchain; Popularity; Beacon; Identification (biology); Internet of Things; Bluetooth; Data science; Computer security; Telecommunications; Data mining; Wireless","authors":[{"name":"Anastasios Alexandridis","is_ca":true},{"name":"Ghassan Al-Sumaidaee","is_ca":true},{"name":"Rami Alkhudary","is_ca":false},{"name":"Željko Žilić","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2687715235562875,"gpt":0.3297032818409691,"spread":0.06093175828468167,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.002129636,0.0001905769,0.0002407682,0.000302969,0.0002746756,0.000297204,0.02616455,0.0000648416,0.00001745812],"category_scores_gemma":[0.0004833328,0.0001643912,0.00001795921,0.0006912286,0.0001765518,0.0006522228,0.01665941,0.0007994567,0.000006376441],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006970309,"about_ca_system_score_gemma":0.0002336255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009804952,"about_ca_topic_score_gemma":0.001467973,"domain_scores_codex":[0.9966937,0.0004951597,0.0005116986,0.00102875,0.001035476,0.0002352619],"domain_scores_gemma":[0.9900169,0.0004626565,0.0003741921,0.00899102,0.0001114312,0.00004376747],"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":[0.0001017052,0.0002617859,0.0003141294,0.00004585882,0.00006856353,0.00002901587,0.0003533336,0.00008818295,0.002695394,0.03640323,0.005917411,0.9537214],"study_design_scores_gemma":[0.001137688,0.0001907299,0.001274325,0.0001664161,0.00001921098,0.0001098048,0.002882739,0.9425863,0.001479426,0.001234001,0.04853343,0.0003859237],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2278501,0.002388002,0.6112442,0.04017305,0.02030997,0.003492009,0.08807025,0.001302081,0.005170377],"genre_scores_gemma":[0.9946967,0.0005077266,0.001214906,0.00020277,0.0001365956,0.00009016684,0.003109959,0.000009206451,0.00003193718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9533355,"threshold_uncertainty_score":0.9912937,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024115","doi":"10.1109/bigdata55660.2022.10020387","title":"An Intelligent Class: The Development Of A Novel Context Capturing Method For The Functional Auto Classification Of Records","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Digital and Traditional Archives Management","field":"Arts and Humanities","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Context (archaeology); Machine learning; Process (computing); Statistical classification; Set (abstract data type); One-class classification; Task (project management); Data mining; Engineering","authors":[{"name":"Nathaniel Payne","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5787873684648848,"gpt":0.3602816516620805,"spread":0.2185057168028043,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009805611,0.0001476706,0.0001510431,0.0001292102,0.0004838148,0.0001643489,0.002704693,0.00001023414,0.0006031023],"category_scores_gemma":[0.00006505298,0.0001008287,0.00005147526,0.00005249211,0.0001916291,0.0003843572,0.0008501663,0.0001896358,0.000008144265],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006755489,"about_ca_system_score_gemma":0.0002375292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001957462,"about_ca_topic_score_gemma":0.001658904,"domain_scores_codex":[0.9980396,0.00007432543,0.0005296582,0.0004647051,0.0007547849,0.0001369394],"domain_scores_gemma":[0.9979466,0.0004741135,0.0003649566,0.0009881631,0.0001917176,0.0000344433],"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":[0.0002112812,0.0004911661,0.000008286247,0.00001911842,0.000285483,2.887093e-7,0.001763687,0.0002202545,0.0004283527,0.6388353,0.009474627,0.3482622],"study_design_scores_gemma":[0.0004351096,0.000153279,0.002018672,0.00003892078,0.00005568569,0.00000279432,0.009738395,0.1695213,0.0001737542,0.005483991,0.812203,0.000175108],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01059146,0.00005865236,0.7591844,0.01200454,0.01532042,0.001870435,0.1278014,0.00007811449,0.07309054],"genre_scores_gemma":[0.9728423,0.00001639604,0.001241818,0.000415139,0.0006748652,0.0002441333,0.02281921,0.00001462828,0.001731522],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622508,"threshold_uncertainty_score":0.6603547,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4317781640","doi":"10.1109/bigdata55660.2022.10020852","title":"The Lannion report on Big Data and Security Monitoring Research","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Network Security and Intrusion Detection","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":"Bell (Canada)","funders":"Engineering and Physical Sciences Research Council; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"Big data; Computer science; Data science; Analytics; Data management; Computer security; Computation; Data mining","authors":[{"name":"Laurent d’Orazio","is_ca":false},{"name":"Jalil Boukhobza","is_ca":false},{"name":"Omer Rana","is_ca":false},{"name":"Juba Agoun","is_ca":false},{"name":"Le Gruenwald","is_ca":false},{"name":"Herve Rannou","is_ca":false},{"name":"Elisa Bertino","is_ca":false},{"name":"Mohand-Saïd Hacid","is_ca":false},{"name":"Taofik Saidi","is_ca":false},{"name":"Georges Bossert","is_ca":false},{"name":"Van Long Nguyen Huu","is_ca":true},{"name":"Dimitri Tombroff","is_ca":false},{"name":"Makoto Onizuka","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4622280971601727,"gpt":0.414755484398714,"spread":0.0474726127614587,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.006323639,0.0002257379,0.0001910974,0.0003004352,0.001626937,0.001174352,0.01452562,0.00007633848,0.00006749957],"category_scores_gemma":[0.0008471241,0.0001981631,0.00002343361,0.0006375522,0.0001815482,0.001289463,0.02098801,0.001513417,0.00006459544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001625718,"about_ca_system_score_gemma":0.0003432218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005850984,"about_ca_topic_score_gemma":0.0005129561,"domain_scores_codex":[0.9939569,0.0006606187,0.0005108489,0.001872155,0.002542232,0.0004571989],"domain_scores_gemma":[0.9909055,0.0006305561,0.0002767557,0.007760413,0.0002791932,0.0001476327],"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":[0.000231484,0.0002663766,0.0004857028,0.00001286551,0.00009857707,0.0003303636,0.000265541,0.00003231722,0.0005937731,0.01908787,0.1940445,0.7845506],"study_design_scores_gemma":[0.0003458173,0.0002315394,0.000653927,0.00007188039,0.000007645434,0.0001960701,0.0002702376,0.1952924,0.0003590492,0.00557441,0.7967233,0.0002737304],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"editorial","genre_gemma":"empirical","genre_scores_codex":[0.3060119,0.002794597,0.1062693,0.1100787,0.3350344,0.004638353,0.08207164,0.001601193,0.05149991],"genre_scores_gemma":[0.9832289,0.001971796,0.0002174133,0.0002532153,0.004444456,0.00005744135,0.009040474,0.00002121113,0.0007650642],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7842768,"threshold_uncertainty_score":0.9998626,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024117","doi":"10.1109/bigdata55660.2022.10021046","title":"A novel self-adaptive method for improving patient monitoring with composite early-warning scores","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Healthcare Technology and Patient Monitoring","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":"University of Waterloo","funders":"","keywords":"Computer science; Wearable computer; Remote patient monitoring; Real-time computing; Pruning; Wearable technology; Transmission (telecommunications); Adaptive sampling; Machine learning; Artificial intelligence; Data mining; Embedded system; Medicine; Telecommunications","authors":[{"name":"Antonio Iyda Paganelli","is_ca":false},{"name":"Pedro Elkind Velmovitsky","is_ca":true},{"name":"Adriano Branco","is_ca":false},{"name":"Markus Endler","is_ca":false},{"name":"Plinio Pelegrini Morita","is_ca":true},{"name":"Paulo Alencar","is_ca":true},{"name":"Donald Cowan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.3307912242688666,"gpt":0.395012270814312,"spread":0.06422104654544541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000784617,0.0002794141,0.0003476862,0.0003594611,0.0005055499,0.00007533772,0.001668679,0.00009769273,0.00003130625],"category_scores_gemma":[0.0002178901,0.0002670078,0.00003909138,0.0002634457,0.00005547838,0.0003676005,0.001650416,0.001000073,0.000008090386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003327187,"about_ca_system_score_gemma":0.0004683886,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009752652,"about_ca_topic_score_gemma":0.00007557623,"domain_scores_codex":[0.9969487,0.0001137192,0.0004549931,0.00111483,0.0009578957,0.0004098355],"domain_scores_gemma":[0.9971967,0.0003094784,0.0003717291,0.001657847,0.0003153883,0.0001488518],"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":[0.004171872,0.00108129,0.04155746,0.0002003927,0.0008892547,0.0001851748,0.00142089,0.00017519,0.04620422,0.001989633,0.001014455,0.9011102],"study_design_scores_gemma":[0.02460382,0.02658037,0.05584634,0.003843421,0.001657963,0.001546921,0.014576,0.7000486,0.06673801,0.0006586957,0.09956502,0.004334873],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7064985,0.0001462286,0.2521032,0.002458558,0.01288454,0.002234347,0.0224092,0.0005863353,0.0006790644],"genre_scores_gemma":[0.9260787,0.00002654323,0.06593563,0.0002005297,0.001039618,0.0002762541,0.00632337,0.00004570705,0.00007360848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8967753,"threshold_uncertainty_score":0.9999782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318186095","doi":"10.1109/bigdata55660.2022.10020676","title":"DelphAI: A human-centered approach to time-series forecasting","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Forecasting Techniques and Applications","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph; Vector Institute","funders":"","keywords":"Series (stratigraphy); Time series; Computer science; Machine learning; Geology","authors":[{"name":"Kristina L. Kupferschmidt","is_ca":true},{"name":"Joshua G. Skorburg","is_ca":true},{"name":"Graham W. Taylor","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.762746653460341,"gpt":0.4577294211491272,"spread":0.3050172323112137,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.003153242,0.0002907436,0.0003417305,0.0005292398,0.0008441776,0.0008039199,0.01390524,0.00005803184,0.001784262],"category_scores_gemma":[0.001473265,0.0002715789,0.00006727108,0.0009186195,0.0001318095,0.0008078087,0.008966708,0.0005031244,0.0004598073],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001389728,"about_ca_system_score_gemma":0.000199038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001832291,"about_ca_topic_score_gemma":0.000148956,"domain_scores_codex":[0.9940524,0.0002193669,0.000897464,0.001826772,0.002600476,0.0004035804],"domain_scores_gemma":[0.9940458,0.0003172264,0.0004653183,0.004602142,0.0003756303,0.0001939114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001818464,0.0005756721,0.0002242488,0.000005533592,0.00007147033,0.00002025051,0.0002032352,0.0002434057,0.003857547,0.03845256,0.7675487,0.1886155],"study_design_scores_gemma":[0.000531631,0.0002959195,0.0002086661,0.00004441595,0.00002413092,0.0001265,0.0007713403,0.237068,0.00035284,0.02021951,0.7397473,0.0006097516],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04502962,0.0000679587,0.3969702,0.02071814,0.01075856,0.003562386,0.2211894,0.001154732,0.3005491],"genre_scores_gemma":[0.9366099,0.00001192531,0.01781269,0.001211875,0.001141766,0.0004142558,0.03297188,0.00005423248,0.009771528],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8915802,"threshold_uncertainty_score":0.9999737,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147664","doi":"10.1109/bigdata55660.2022.10021035","title":"Analysis of Airfare during Pandemic: A Multi-Agent Based Modeling Approach","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Aviation Industry Analysis and Trends","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Pandemic; Coronavirus disease 2019 (COVID-19); Air travel; Computer science; 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Aviation; Business; Risk analysis (engineering); Operations research; Engineering; Aerospace engineering; Infectious disease (medical specialty)","authors":[{"name":"Abdul Mutakabbir","is_ca":true},{"name":"Chung–Horng Lung","is_ca":true},{"name":"Samuel A. Ajila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5808910784080009,"gpt":0.3499821377569418,"spread":0.2309089406510591,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001046469,0.0002174926,0.0005494365,0.001170319,0.0002611984,0.0001147398,0.0030815,0.00007971544,0.002740691],"category_scores_gemma":[0.0001389254,0.000259064,0.0001616261,0.001073116,0.00004230458,0.0003936583,0.001287143,0.0004572174,0.00003979107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001950845,"about_ca_system_score_gemma":0.00009098103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000648751,"about_ca_topic_score_gemma":0.0002193735,"domain_scores_codex":[0.9971802,0.00007012166,0.0009817684,0.0011808,0.0003456498,0.0002414282],"domain_scores_gemma":[0.9968229,0.00004574241,0.0007278241,0.002211212,0.0001032307,0.00008909771],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002489206,0.002001665,0.2289888,0.0000557394,0.006536653,0.00002586348,0.000331167,0.7233828,0.0002463778,0.01946663,0.002376601,0.01633884],"study_design_scores_gemma":[0.0006956338,0.00002063014,0.005638995,0.000008382227,0.0001789713,0.000001696167,0.0003065174,0.9881675,0.00001245937,0.0001003481,0.00460632,0.0002625363],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2426676,0.0003365726,0.4804563,0.001195283,0.003210128,0.0003527333,0.2627497,0.0001081361,0.008923583],"genre_scores_gemma":[0.9484544,0.00009828261,0.0005296575,0.0001470984,0.0001882397,0.00004772185,0.04987683,0.0000188988,0.0006388735],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7057868,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226052253","doi":"10.1109/bigdata55660.2022.10020281","title":"PMFL: Partial Meta-Federated Learning for heterogeneous tasks and its applications on real-world medical records","year":2022,"lang":"en","type":"preprint","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Privacy-Preserving Technologies in Data","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":"Mila - Quebec Artificial Intelligence Institute","funders":"Fundamental Research Funds for the Central Universities","keywords":"Computer science; Federated learning; Transfer of learning; Meta learning (computer science); Task (project management); Machine learning; Generalization; Artificial intelligence; Homogeneous; Exploit","authors":[{"name":"Tianyi Zhang","is_ca":false},{"name":"Shirui Zhang","is_ca":false},{"name":"Ziwei Chen","is_ca":false}],"retraction":null,"screen_n_in":null,"score":{"opus":0.4329335683524456,"gpt":0.4114458854522562,"spread":0.02148768290018938,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":["open_science"],"category_scores_codex":[0.002504131,0.0007011896,0.0008315202,0.0006864081,0.0006055008,0.001255837,0.08308052,0.0004295491,0.0007729074],"category_scores_gemma":[0.01507158,0.0007070379,0.000130428,0.0004628963,0.0001912,0.0007545505,0.2444771,0.002771372,0.00007193889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002977555,"about_ca_system_score_gemma":0.001023349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004883046,"about_ca_topic_score_gemma":0.001358257,"domain_scores_codex":[0.9916825,0.0004581204,0.001036816,0.003916204,0.002275268,0.0006311298],"domain_scores_gemma":[0.9792249,0.001226931,0.0008762106,0.01802609,0.0003604615,0.0002854438],"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":[0.0002919798,0.0006743768,0.00008125772,0.0002029983,0.003281213,0.0002094513,0.00003901794,0.0005821218,0.0002592883,0.03450948,0.4382997,0.5215691],"study_design_scores_gemma":[0.0004549671,0.0001539357,0.00001907096,0.0001111534,0.0001789297,0.00002856636,0.00001405976,0.7012509,0.0004478582,0.01736148,0.2793345,0.000644593],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001261898,0.0004890282,0.7868885,0.07368369,0.01640765,0.003272413,0.1115433,0.002013405,0.004440113],"genre_scores_gemma":[0.5046873,0.01378231,0.05478113,0.003450612,0.004952565,0.008360964,0.4071056,0.0003034734,0.002576056],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7321073,"threshold_uncertainty_score":0.999781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147681","doi":"10.1109/bigdata55660.2022.10020382","title":"A Framework for the Design, Development, Testing and Deployment of Reliable Big Data Platforms","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Distributed systems and fault tolerance","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":"Ontario Tech University","funders":"","keywords":"Software deployment; Computer science; Scalability; Big data; Distributed computing; Reliability (semiconductor); Fault tolerance; Process (computing); Pipeline (software); Data science; Systems engineering; Software engineering; Database; Engineering; Data mining","authors":[{"name":"Carolyn McGregor","is_ca":true},{"name":"Catherine Inibhunu","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.5304000793599303,"gpt":0.3686517544763004,"spread":0.1617483248836298,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00223691,0.0002355049,0.0002649536,0.0001216388,0.0005336915,0.0004252514,0.01344898,0.00005479304,0.00002567656],"category_scores_gemma":[0.0008820324,0.0001878765,0.00001833532,0.0004265895,0.00008015796,0.0008957609,0.009114257,0.0003746318,0.000009023655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007946143,"about_ca_system_score_gemma":0.0006364522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000209651,"about_ca_topic_score_gemma":0.00007343812,"domain_scores_codex":[0.9967368,0.00005719756,0.0006089243,0.001225864,0.00103344,0.000337761],"domain_scores_gemma":[0.9936808,0.001060703,0.0004698619,0.004479778,0.000217199,0.00009168874],"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":[0.0002030606,0.0004004607,0.001026997,0.00008749274,0.0004081832,0.00003417974,0.0004117929,0.0009185487,0.001319943,0.04191235,0.08913579,0.8641412],"study_design_scores_gemma":[0.0008026563,0.000167219,0.0006854865,0.0002873116,0.00002845905,0.00004762505,0.0002963016,0.6729468,0.0006618038,0.005519288,0.3181215,0.0004355767],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008341111,0.0002116085,0.974892,0.0008892864,0.004748727,0.0005542625,0.01762435,0.00005791936,0.0001877867],"genre_scores_gemma":[0.8159575,0.0001985613,0.1640815,0.0009568996,0.001075232,0.0003626232,0.0169262,0.00004489477,0.0003965797],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8637056,"threshold_uncertainty_score":0.9988998,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318148079","doi":"10.1109/bigdata55660.2022.10020681","title":"Don’t Blindly Use Data: Towards a Data Statement for Computational Financial Research","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning and Data Classification","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":"Dalhousie University","funders":"","keywords":"Computer science; Statement (logic); Data science; Data quality; Context (archaeology); Problem statement; Focus (optics); Quality (philosophy); Work (physics); Management science","authors":[{"name":"Stacey Taylor","is_ca":true},{"name":"Vlado Kešelj","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.7268565196499841,"gpt":0.4798004812067899,"spread":0.2470560384431942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007859824,0.0003204349,0.0003086058,0.0005789054,0.001000998,0.001740532,0.03841855,0.0000776883,0.0003180532],"category_scores_gemma":[0.003013388,0.0003376369,0.00002993699,0.0007330783,0.0001659673,0.00485014,0.03782948,0.001138848,0.000122343],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002645286,"about_ca_system_score_gemma":0.002472907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001405975,"about_ca_topic_score_gemma":0.001092074,"domain_scores_codex":[0.9912679,0.0007454842,0.00084484,0.003263452,0.003270721,0.0006075887],"domain_scores_gemma":[0.9841397,0.0009281028,0.0004524404,0.01364921,0.0006305694,0.0001999977],"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":[0.0002197829,0.000507305,0.000176139,0.00002340631,0.00009250003,0.00002819058,0.00008689985,0.0007853724,0.0001057044,0.04686062,0.6117989,0.3393151],"study_design_scores_gemma":[0.0006289837,0.0001229807,0.001008608,0.00001901942,0.00001104276,0.00001190551,0.00005829606,0.5085685,0.000005508988,0.001371167,0.4879778,0.0002162476],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"dataset","genre_scores_codex":[0.0007385315,0.00004600239,0.6619424,0.01674653,0.005959207,0.0007169757,0.313174,0.0001356504,0.0005407151],"genre_scores_gemma":[0.1855578,0.0002053567,0.03264333,0.001170495,0.001720918,0.0001784737,0.777316,0.00003922691,0.001168373],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.6292991,"threshold_uncertainty_score":0.9999076,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147813","doi":"10.1109/bigdata55660.2022.10021073","title":"Systematic Analysis of Public Transit Data Availability in Canada","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Traffic Prediction and Management Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Carleton University","funders":"","keywords":"Public transport; Computer science; Transit (satellite); Transport engineering; Data science; Engineering","authors":[{"name":"Kevin Dick","is_ca":true},{"name":"Azizul Hasan","is_ca":true},{"name":"Jamil Dergham","is_ca":true},{"name":"A. J. Clarke","is_ca":true},{"name":"Hoda Khalil","is_ca":true},{"name":"Gabriel Wainer","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2616339857047169,"gpt":0.3015119091661445,"spread":0.0398779234614276,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001427778,0.0001750187,0.000408987,0.0006249642,0.00005286673,0.0000731319,0.006644564,0.00002875797,0.0006091002],"category_scores_gemma":[0.0001870274,0.0001918845,0.00002928183,0.0008616234,0.00003283557,0.000567126,0.00178242,0.0003253357,0.000005477295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004874406,"about_ca_system_score_gemma":0.0004181443,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1152518,"about_ca_topic_score_gemma":0.7952311,"domain_scores_codex":[0.9972154,0.0001775456,0.0007042271,0.0006910281,0.001002942,0.0002087978],"domain_scores_gemma":[0.9954698,0.0001228169,0.0001408295,0.004133263,0.00006147486,0.00007181847],"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":[0.0001136696,0.0008846768,0.007565919,0.00407005,0.009586339,0.0001712657,0.0002847977,0.02784564,0.001182362,0.009257176,0.8237459,0.1152922],"study_design_scores_gemma":[0.0002306109,0.00001416797,0.002196222,0.0001126068,0.0002408723,0.000002211818,0.0004411613,0.9811985,0.0000215716,0.00001619055,0.01533025,0.000195669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.05708959,0.0005162911,0.270536,0.003638291,0.01836656,0.002599537,0.6277262,0.002052311,0.01747524],"genre_scores_gemma":[0.9372232,0.0002110317,0.00009382267,0.0001068096,0.00005233167,0.00005531345,0.06219732,0.00001401938,0.0000461264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9533528,"threshold_uncertainty_score":0.9987299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4320024084","doi":"10.1109/bigdata55660.2022.10020739","title":"The Dimensional Analysis of Data Flow Programs That Include Multidimensional and User-Defined Functions","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"University of Victoria","keywords":"Computer science; Dimension (graph theory); Curse of dimensionality; Multidimensional analysis; Data mining; Flow (mathematics); Rank (graph theory); Theoretical computer science; Data flow diagram; Raw data; Artificial intelligence; Database; Programming language; Mathematics; Statistics","authors":[{"name":"Abdulmonem I. Shennat","is_ca":true},{"name":"William W. Wadge","is_ca":true},{"name":"Alex Kuo","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.6122670306410279,"gpt":0.4310872843677545,"spread":0.1811797462732734,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","open_science","insufficient_payload"],"consensus_categories":["open_science"],"category_scores_codex":[0.009355021,0.0002719839,0.0004221731,0.0008680695,0.0013382,0.0009508677,0.01477543,0.00004387726,0.001048849],"category_scores_gemma":[0.002336142,0.0001967127,0.00008127001,0.002049841,0.000400673,0.001131832,0.03453492,0.0004263976,0.00008796015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006848728,"about_ca_system_score_gemma":0.0003167267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005612059,"about_ca_topic_score_gemma":0.002894643,"domain_scores_codex":[0.9901613,0.0005362791,0.0009935346,0.002593312,0.005350038,0.000365512],"domain_scores_gemma":[0.9856824,0.002322393,0.000685914,0.01069602,0.000448034,0.0001652038],"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":[0.000267434,0.0005229602,0.004274483,0.00000314002,0.00116424,0.00002059857,0.00007242993,0.002280628,0.0002234827,0.004515918,0.4314239,0.5552308],"study_design_scores_gemma":[0.0003465817,0.00005014424,0.005646142,0.00001092626,0.0001881141,0.000007175557,0.0006474024,0.5892569,0.000005081983,0.0003610839,0.4033126,0.000167926],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.192576,0.0006116975,0.1140181,0.03004499,0.05211749,0.001997547,0.604129,0.0003037322,0.004201384],"genre_scores_gemma":[0.802406,0.00009249244,0.003430693,0.0004849265,0.0003747916,0.00004104285,0.1888428,0.00002025518,0.00430704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.60983,"threshold_uncertainty_score":0.9999619,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318147483","doi":"10.1109/bigdata55660.2022.10020802","title":"A Graph-based Analysis Approach to Cluster Lifetime Dynamics","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Data Management and Algorithms","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":"Computer science; Cluster analysis; Cluster (spacecraft); Graph; Data mining; Outlier; Power graph analysis; Theoretical computer science; Visualization; Data visualization; Artificial intelligence","authors":[{"name":"Ivens Portugal","is_ca":true},{"name":"Paulo Alencar","is_ca":true},{"name":"Donald Cowan","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2103282896521805,"gpt":0.3246473363864822,"spread":0.1143190467343017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001415496,0.0003269168,0.0003446902,0.001321944,0.0003466252,0.001057417,0.02118593,0.00004510137,0.0002931906],"category_scores_gemma":[0.0001060892,0.0003417372,0.0001005125,0.002341622,0.00006490536,0.001405242,0.01304293,0.0004524055,0.0001783007],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000180883,"about_ca_system_score_gemma":0.0002039831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002913174,"about_ca_topic_score_gemma":0.0003638107,"domain_scores_codex":[0.9948825,0.0002336765,0.0004965543,0.002043647,0.001905696,0.0004379258],"domain_scores_gemma":[0.9929588,0.0001076034,0.0002471617,0.00634312,0.0001403771,0.0002028955],"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":[0.0002246947,0.002002978,0.0009651868,0.00003502286,0.002237647,0.0001149869,0.0001788352,0.01662306,0.0000765644,0.1264928,0.4143861,0.4366621],"study_design_scores_gemma":[0.0004826835,0.00008182899,0.0003726372,0.000008063977,0.0001074933,0.000003952503,0.00008181405,0.9087697,0.000007672517,0.0004760986,0.08921655,0.0003914547],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003097974,0.000009977057,0.9414078,0.006262717,0.003728731,0.0003717999,0.03725804,0.0001587136,0.01049242],"genre_scores_gemma":[0.5332628,0.00006379114,0.06993852,0.01212674,0.001339633,0.0003622449,0.3774649,0.00006759883,0.005373806],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8921467,"threshold_uncertainty_score":0.9999796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4318187617","doi":"10.1109/bigdata55660.2022.10020838","title":"A Semisupervised Approach to Predicting a Twitch Streamer’s Growth based on the Game Streamed","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Consumer Market Behavior and Pricing","field":"Business, Management and Accounting","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Entertainment; Computer science; Meaning (existential); Set (abstract data type); Order (exchange); Approximation error; Work (physics); Artificial intelligence; Simulation; Algorithm; Economics; Engineering","authors":[{"name":"Andrew Dybka","is_ca":true},{"name":"Dominic Kocjan","is_ca":true},{"name":"Samuel A. Ajila","is_ca":true}],"retraction":null,"screen_n_in":null,"score":{"opus":0.2948102546880593,"gpt":0.3133429269993256,"spread":0.01853267231126632,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00155432,0.0003649397,0.0002746768,0.0004963955,0.0005044445,0.0008307067,0.005895653,0.00005006502,0.001985089],"category_scores_gemma":[0.0006912812,0.0003130079,0.00006384016,0.000754796,0.00006174979,0.000771691,0.00378121,0.0007245895,0.0001295324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001034108,"about_ca_system_score_gemma":0.0001898553,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002107749,"about_ca_topic_score_gemma":0.0003142856,"domain_scores_codex":[0.996147,0.0001195127,0.0004573491,0.001264174,0.001587748,0.0004242077],"domain_scores_gemma":[0.9965535,0.0003323307,0.0002823648,0.002561943,0.0002187683,0.00005108244],"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":[0.00265482,0.003644244,0.08715586,0.0003149495,0.0006070958,0.0001715624,0.0005303037,0.001231825,0.00449306,0.01960974,0.3635896,0.5159969],"study_design_scores_gemma":[0.001799857,0.00008212047,0.009161007,0.0002004587,0.0002129369,0.00001002182,0.00223652,0.8319919,0.00007401001,0.0003696473,0.152963,0.0008985682],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6218552,0.00005255296,0.01137799,0.03449977,0.01628015,0.003926497,0.04222712,0.0009076263,0.2688731],"genre_scores_gemma":[0.9706571,0.00001067223,0.00008974996,0.005723732,0.001540577,0.0002302744,0.02135908,0.00004808642,0.0003407609],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.83076,"threshold_uncertainty_score":0.9999322,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}